diff --git a/logistic_regression/OpenLID-v2/bow_maxabs_lr_char_ngram_3_5/classification_report.txt b/logistic_regression/OpenLID-v2/bow_maxabs_lr_char_ngram_3_5/classification_report.txt new file mode 100644 index 0000000000000000000000000000000000000000..19d65cd0f4ede1479fe3cf52ec88413861e1e490 --- /dev/null +++ b/logistic_regression/OpenLID-v2/bow_maxabs_lr_char_ngram_3_5/classification_report.txt @@ -0,0 +1,30 @@ + precision recall f1-score support + + ca 1.00 0.99 0.99 7223 + da 0.98 0.98 0.98 20007 + de 1.00 1.00 1.00 19996 + el 1.00 1.00 1.00 20025 + en 0.99 1.00 0.99 19981 + es 1.00 1.00 1.00 20062 + fi 0.99 0.99 0.99 19949 + fr 1.00 1.00 1.00 20039 + hr 0.98 0.98 0.98 19986 + it 1.00 1.00 1.00 19953 + ja 0.97 0.80 0.88 19983 + ko 0.83 0.99 0.90 19990 + lt 0.99 0.99 0.99 19939 + mk 1.00 1.00 1.00 20014 + nb 0.99 0.99 0.99 19962 + nl 0.98 0.98 0.98 19987 + pl 0.98 0.99 0.99 20033 + pt 0.99 0.99 0.99 20037 + ro 1.00 0.99 1.00 19961 + ru 1.00 0.99 1.00 20029 + sl 0.97 0.97 0.97 19959 + sv 0.98 0.98 0.98 19922 + uk 1.00 1.00 1.00 20037 + zh 0.00 0.00 0.00 0 + + accuracy 0.98 447074 + macro avg 0.94 0.94 0.94 447074 +weighted avg 0.98 0.98 0.98 447074 diff --git a/logistic_regression/OpenLID-v2/bow_maxabs_lr_char_ngram_3_5/cv_results.csv b/logistic_regression/OpenLID-v2/bow_maxabs_lr_char_ngram_3_5/cv_results.csv new file mode 100644 index 0000000000000000000000000000000000000000..8551fad91902c320e508f54dc8af4f098594ae56 --- /dev/null +++ b/logistic_regression/OpenLID-v2/bow_maxabs_lr_char_ngram_3_5/cv_results.csv @@ -0,0 +1,11 @@ +mean_fit_time,std_fit_time,mean_score_time,std_score_time,param_clf__C,param_clf__penalty,param_vectorizer__max_features,param_vectorizer__min_df,params,split0_test_score,split1_test_score,split2_test_score,mean_test_score,std_test_score,rank_test_score +1041.1416900157928,35.084471980497625,282.708448489507,26.858883835512284,0.09915644566638392,l2,50000,1,"{'clf__C': 0.09915644566638392, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1}",0.9802134882665875,0.9800990677001699,0.9800526645605366,0.9801217401757647,6.758499325136823e-05,5 +939.3910819689432,20.5468658244182,317.05882239341736,18.283980434928182,0.0029341230215132346,l2,50000,5,"{'clf__C': 0.0029341230215132346, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9614627159159564,0.9628094259777792,0.962487886482808,0.9622533427921812,0.0005742618768258299,7 +1015.3143272399902,17.818277752531323,288.7444857756297,29.35005618395361,6.155564318973006,l2,50000,3,"{'clf__C': 6.155564318973006, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.9813014757359649,0.9813868293760803,0.98128974141665,0.9813260155095652,4.3267912150893565e-05,3 +1045.292368332545,26.252137003322023,304.16649746894836,20.372170331450015,0.3686905640846153,l2,50000,3,"{'clf__C': 0.3686905640846153, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.980860187060233,0.9810350589942068,0.9808662250888074,0.9809204903810823,8.104973692001813e-05,4 +1026.5849002997081,50.62719086675843,274.11564381917316,40.45962602434597,0.00029152036385288323,l2,50000,5,"{'clf__C': 0.00029152036385288323, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9261539554418532,0.9223667914857019,0.9276794328098825,0.9254000599124792,0.0022334290992038095,8 +1096.3341462612152,28.168015469641972,286.9407886664073,22.380286434472303,0.0467378670778782,l2,50000,5,"{'clf__C': 0.0467378670778782, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9787622075249414,0.9786802276214641,0.978916716747495,0.9787863839646335,9.804812376194722e-05,6 +1029.094319343567,18.805606989775928,317.5117747783661,36.04870680504547,46.19347374377369,l2,50000,2,"{'clf__C': 46.19347374377369, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2}",0.9813171969002967,0.9814151465206824,0.9813114953576457,0.9813479462595417,4.757473573366747e-05,2 +1000.5285371939341,77.87680351101064,364.13514431317645,22.861414563982052,0.00028267840503514715,l2,50000,5,"{'clf__C': 0.00028267840503514715, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9250467702719952,0.9214567568400774,0.9270901041175275,0.9245312104098667,0.0023285191096011877,9 +1054.4045932292938,35.90226742096984,327.0744074185689,28.62473167816423,456.60548734461145,l2,50000,2,"{'clf__C': 456.60548734461145, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2}",0.9813264357061897,0.981413553626723,0.9813146467257367,0.981351545352883,4.410982153278905e-05,1 +1146.8312856356304,55.61288203329003,357.35789163907367,44.32726586582983,0.00010144487859320231,l2,50000,5,"{'clf__C': 0.00010144487859320231, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.8890696284528324,0.8926661728325486,0.8935091752315354,0.8917483255056388,0.001925136650857023,10 diff --git a/logistic_regression/OpenLID-v2/bow_maxabs_lr_char_ngram_3_5/run_metadata.json b/logistic_regression/OpenLID-v2/bow_maxabs_lr_char_ngram_3_5/run_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..056403facaadcddbcf0fd204d46933bde58b7631 --- /dev/null +++ b/logistic_regression/OpenLID-v2/bow_maxabs_lr_char_ngram_3_5/run_metadata.json @@ -0,0 +1,25 @@ +{ + "run_name": "bow_maxabs_lr_char_ngram_3_5", + "tags": { + "feature_type": "bow", + "scaler": "MaxAbsScaler", + "n_gram_range": "(3,5)", + "dataset_version": "OpenLID-v2", + "vectorizer_class": "CountVectorizer" + }, + "params": { + "clf__C": "456.60548734461145", + "clf__penalty": "l2", + "vectorizer__max_features": "50000", + "vectorizer__min_df": "2" + }, + "metrics": { + "accuracy": 0.9814102363367139, + "f1_macro": 0.9816951437188624, + "precision_macro": 0.983095730666879, + "recall_macro": 0.9816585186171294, + "inference_time_total_s": 257.3287, + "inference_time_ms_per_sample": 0.575584, + "throughput_samples_per_sec": 1737.37 + } +} \ No newline at end of file diff --git a/logistic_regression/OpenLID-v2/tfidf_lr_char_ngram_3_5/classification_report.txt b/logistic_regression/OpenLID-v2/tfidf_lr_char_ngram_3_5/classification_report.txt new file mode 100644 index 0000000000000000000000000000000000000000..8ca0f69c35d00fa241cc8aca0077516dbfdf96e4 --- /dev/null +++ b/logistic_regression/OpenLID-v2/tfidf_lr_char_ngram_3_5/classification_report.txt @@ -0,0 +1,30 @@ + precision recall f1-score support + + ca 1.00 0.99 1.00 7223 + da 0.98 0.98 0.98 20007 + de 1.00 1.00 1.00 19996 + el 1.00 1.00 1.00 20025 + en 0.99 1.00 0.99 19981 + es 1.00 1.00 1.00 20062 + fi 0.99 0.99 0.99 19949 + fr 1.00 1.00 1.00 20039 + hr 0.98 0.98 0.98 19986 + it 1.00 1.00 1.00 19953 + ja 0.84 0.98 0.91 19983 + ko 0.98 0.82 0.89 19990 + lt 0.99 0.99 0.99 19939 + mk 1.00 1.00 1.00 20014 + nb 0.99 0.99 0.99 19962 + nl 0.99 0.99 0.99 19987 + pl 0.99 0.99 0.99 20033 + pt 1.00 1.00 1.00 20037 + ro 1.00 1.00 1.00 19961 + ru 1.00 1.00 1.00 20029 + sl 0.97 0.98 0.97 19959 + sv 0.97 0.99 0.98 19922 + uk 1.00 1.00 1.00 20037 + zh 0.00 0.00 0.00 0 + + accuracy 0.98 447074 + macro avg 0.94 0.94 0.94 447074 +weighted avg 0.98 0.98 0.98 447074 diff --git a/logistic_regression/OpenLID-v2/tfidf_lr_char_ngram_3_5/cv_results.csv b/logistic_regression/OpenLID-v2/tfidf_lr_char_ngram_3_5/cv_results.csv new file mode 100644 index 0000000000000000000000000000000000000000..f1cd8e64b345113f150be6344551a6627ca30014 --- /dev/null +++ b/logistic_regression/OpenLID-v2/tfidf_lr_char_ngram_3_5/cv_results.csv @@ -0,0 +1,11 @@ +mean_fit_time,std_fit_time,mean_score_time,std_score_time,param_clf__C,param_clf__penalty,param_vectorizer__max_features,param_vectorizer__min_df,param_vectorizer__sublinear_tf,params,split0_test_score,split1_test_score,split2_test_score,mean_test_score,std_test_score,rank_test_score +1177.1960979302723,64.96314842995189,407.4506374200185,22.257658847090692,0.09915644566638392,l2,50000,1,True,"{'clf__C': 0.09915644566638392, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9767745965576218,0.9780597223864775,0.9776228208283391,0.9774857132574795,0.000533532856525455,5 +1115.4476176897685,22.72887433843238,503.8296180566152,3.286561121103191,71.77141927992008,l2,50000,1,True,"{'clf__C': 71.77141927992008, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9829905714200443,0.9829022509948367,0.9827327668540775,0.9828751964229863,0.00010697277208662466,2 +1405.8827237288158,93.36829860279127,407.3532235622406,35.56408136522917,0.0017707168643537816,l2,50000,3,True,"{'clf__C': 0.0017707168643537816, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': True}",0.9119458869118672,0.9123948637816973,0.9126505763698679,0.9123304423544775,0.00029127237913234214,8 +1566.9878056049347,143.2470977187642,405.675767103831,37.325007308101526,0.00029152036385288323,l2,50000,5,True,"{'clf__C': 0.00029152036385288323, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.9042959539753,0.9043219443164305,0.8945926448030828,0.9010701810316045,0.0045803220824389085,10 +1225.2683494091034,71.00485253663666,404.9212706883748,34.14379754490904,6.440507553993708,l2,50000,5,True,"{'clf__C': 6.440507553993708, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.9835441321616867,0.9832011618100668,0.9834958843964662,0.9834137261227399,0.00015159079123049942,1 +1583.2893005212147,169.70222837266766,306.29970502853394,33.645833048831065,0.00014610865886287189,l2,50000,2,False,"{'clf__C': 0.00014610865886287189, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.9018519904046731,0.9015713091002491,0.9025068921663808,0.901976730557101,0.00039200254899588734,9 +1040.0020178953807,22.92054196428311,307.93366201718646,17.313707081885063,456.60548734461145,l2,50000,2,False,"{'clf__C': 456.60548734461145, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.9827716691434817,0.982855002014398,0.9826782338723861,0.9827683016767553,7.220456532983022e-05,3 +1260.0860554377239,98.08504339455561,311.4735604921977,44.80802938613155,0.0028483918709108036,l2,50000,1,True,"{'clf__C': 0.0028483918709108036, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9335510859068542,0.9336379793862851,0.9334658263678486,0.9335516305536626,7.028223065760043e-05,7 +1072.8258341948192,22.952734504253225,300.4805498123169,13.750253295733005,0.027160511446548484,l2,50000,2,True,"{'clf__C': 0.027160511446548484, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': True}",0.9712729908696486,0.9736375441788574,0.9729763227553202,0.9726289526012755,0.0009960848712043994,6 +949.5436635812124,42.612229722788996,303.22136847178143,25.983376233642552,0.28546978577971793,l2,50000,1,True,"{'clf__C': 0.28546978577971793, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.980137586107902,0.9806820754005156,0.9804126248521482,0.9804107621201886,0.00022229072520831727,4 diff --git a/logistic_regression/OpenLID-v2/tfidf_lr_char_ngram_3_5/run_metadata.json b/logistic_regression/OpenLID-v2/tfidf_lr_char_ngram_3_5/run_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..680b3b1a8baf36b2bb426b74b9b4ebb745cb1a7e --- /dev/null +++ b/logistic_regression/OpenLID-v2/tfidf_lr_char_ngram_3_5/run_metadata.json @@ -0,0 +1,26 @@ +{ + "run_name": "tfidf_lr_char_ngram_3_5", + "tags": { + "feature_type": "tfidf", + "scaler": "none", + "n_gram_range": "(3,5)", + "dataset_version": "OpenLID-v2", + "vectorizer_class": "TfidfVectorizer" + }, + "params": { + "clf__C": "6.440507553993708", + "clf__penalty": "l2", + "vectorizer__max_features": "50000", + "vectorizer__min_df": "5", + "vectorizer__sublinear_tf": "True" + }, + "metrics": { + "accuracy": 0.9835284539024859, + "f1_macro": 0.9837905549610888, + "precision_macro": 0.9849400616925207, + "recall_macro": 0.9837720372524135, + "inference_time_total_s": 240.6572, + "inference_time_ms_per_sample": 0.538294, + "throughput_samples_per_sec": 1857.72 + } +} \ No newline at end of file diff --git a/logistic_regression/flores_plus/tfidf_lr_char_ngram_3_5/run_metadata.json b/logistic_regression/flores_plus/tfidf_lr_char_ngram_3_5/run_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..267ef26315ad652dccb04e45230b089d8be5d240 --- /dev/null +++ b/logistic_regression/flores_plus/tfidf_lr_char_ngram_3_5/run_metadata.json @@ -0,0 +1,26 @@ +{ + "run_name": "tfidf_lr_char_ngram_3_5", + "tags": { + "feature_type": "tfidf", + "scaler": "none", + "n_gram_range": "(3,5)", + "dataset_version": "flores_plus", + "vectorizer_class": "TfidfVectorizer" + }, + "params": { + "clf__C": "6.440507553993708", + "clf__penalty": "l2", + "vectorizer__max_features": "50000", + "vectorizer__min_df": "5", + "vectorizer__sublinear_tf": "True" + }, + "metrics": { + "accuracy": 0.984225621414914, + "f1_macro": 0.9859709060910451, + "precision_macro": 0.9872362994654668, + "recall_macro": 0.985541963917231, + "inference_time_total_s": 0.6405, + "inference_time_ms_per_sample": 0.30617, + "throughput_samples_per_sec": 3266.16 + } +} \ No newline at end of file diff --git a/logistic_regression/language-identification/bow_maxabs_lr_char_ngram_3_5/classification_report.txt b/logistic_regression/language-identification/bow_maxabs_lr_char_ngram_3_5/classification_report.txt new file mode 100644 index 0000000000000000000000000000000000000000..8f7b4a2f9c6229764fcd1acec112da69fba46f04 --- /dev/null +++ b/logistic_regression/language-identification/bow_maxabs_lr_char_ngram_3_5/classification_report.txt @@ -0,0 +1,30 @@ + precision recall f1-score support + + ca 0.00 0.00 0.00 0 + da 0.00 0.00 0.00 0 + de 1.00 1.00 1.00 433 + el 1.00 0.99 1.00 418 + en 1.00 1.00 1.00 441 + es 1.00 1.00 1.00 436 + fi 0.00 0.00 0.00 0 + fr 1.00 1.00 1.00 417 + hr 0.00 0.00 0.00 0 + it 0.99 1.00 0.99 428 + ja 1.00 0.87 0.93 449 + ko 0.00 0.00 0.00 0 + lt 0.00 0.00 0.00 0 + mk 0.00 0.00 0.00 0 + nb 0.00 0.00 0.00 0 + nl 0.99 0.99 0.99 399 + pl 1.00 0.98 0.99 392 + pt 1.00 1.00 1.00 423 + ro 0.00 0.00 0.00 0 + ru 1.00 1.00 1.00 425 + sl 0.00 0.00 0.00 0 + sv 0.00 0.00 0.00 0 + uk 0.00 0.00 0.00 0 + zh 0.86 1.00 0.93 452 + + accuracy 0.98 5113 + macro avg 0.49 0.49 0.49 5113 +weighted avg 0.99 0.98 0.98 5113 diff --git a/logistic_regression/language-identification/bow_maxabs_lr_char_ngram_3_5/cv_results.csv b/logistic_regression/language-identification/bow_maxabs_lr_char_ngram_3_5/cv_results.csv new file mode 100644 index 0000000000000000000000000000000000000000..4b1868307cf62f6c2321b136af55bbb616de89a2 --- /dev/null +++ b/logistic_regression/language-identification/bow_maxabs_lr_char_ngram_3_5/cv_results.csv @@ -0,0 +1,11 @@ +mean_fit_time,std_fit_time,mean_score_time,std_score_time,param_clf__C,param_clf__penalty,param_vectorizer__max_features,param_vectorizer__min_df,params,split0_test_score,split1_test_score,split2_test_score,mean_test_score,std_test_score,rank_test_score +19.384628613789875,3.8331015399707047,4.308941682179769,1.712907469276069,0.09915644566638392,l2,50000,1,"{'clf__C': 0.09915644566638392, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1}",0.9809062399697316,0.9777824340426097,0.9812220853968348,0.979970253136392,0.0015523860932543819,5 +21.579487403233845,3.835541701693018,5.787985722223918,0.7496542187761066,0.0029341230215132346,l2,50000,5,"{'clf__C': 0.0029341230215132346, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9663949590024239,0.9623920442901414,0.9653338066779228,0.9647069366568294,0.001693232818400207,7 +25.824681997299194,8.342065368857105,3.821570078531901,0.45336299425181253,6.155564318973006,l2,50000,3,"{'clf__C': 6.155564318973006, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.9850077313197844,0.9820763019847915,0.9852936339773072,0.9841258890939609,0.0014539694107167755,3 +24.18393127123515,2.277633235290609,3.90667716662089,1.8438042331418356,0.3686905640846153,l2,50000,3,"{'clf__C': 0.3686905640846153, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.9841817675979536,0.9804763945916357,0.9843422902946145,0.9830001508280679,0.0017857680027994977,4 +27.190136273701984,5.4925571086319955,6.402633984883626,2.5053355911824977,0.00029152036385288323,l2,50000,5,"{'clf__C': 0.00029152036385288323, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9577989225040214,0.9545303188343118,0.9571315496631287,0.9564869303338206,0.0014101047354004037,8 +20.16955812772115,8.033087065958464,4.754613558451335,2.2203947955627217,0.0467378670778782,l2,50000,5,"{'clf__C': 0.0467378670778782, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9781771047408362,0.9759891429181439,0.978336182401398,0.977500810020126,0.001070881100133207,6 +21.257368246714275,3.1234232990216553,4.408258597056071,1.0393339616415767,46.19347374377369,l2,50000,2,"{'clf__C': 46.19347374377369, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2}",0.9857186384335314,0.9823439632088586,0.9850189556796329,0.9843605191073409,0.0014542494645701043,1 +20.534382104873657,5.828078239173822,3.253084103266398,1.6859592587246428,0.00028267840503514715,l2,50000,5,"{'clf__C': 0.00028267840503514715, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9559121018642457,0.9532025736570295,0.9545571144729276,0.9545572633314009,0.0011061602635676635,9 +18.108100096384685,4.147995813634339,5.95265777905782,1.1191833050241058,456.60548734461145,l2,50000,2,"{'clf__C': 456.60548734461145, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2}",0.9857186384335314,0.9823439632088586,0.9850189556796329,0.9843605191073409,0.0014542494645701043,1 +22.98309310277303,2.101787814648165,2.8774582544962564,1.2359151172601692,0.00010144487859320231,l2,50000,5,"{'clf__C': 0.00010144487859320231, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.8442227223985483,0.8457379621801148,0.8496728941564529,0.8465445262450387,0.0022969548306086946,10 diff --git a/logistic_regression/language-identification/bow_maxabs_lr_char_ngram_3_5/run_metadata.json b/logistic_regression/language-identification/bow_maxabs_lr_char_ngram_3_5/run_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..404e09f56103cdf0eed5526c4d409b456bd59727 --- /dev/null +++ b/logistic_regression/language-identification/bow_maxabs_lr_char_ngram_3_5/run_metadata.json @@ -0,0 +1,25 @@ +{ + "run_name": "bow_maxabs_lr_char_ngram_3_5", + "tags": { + "feature_type": "bow", + "scaler": "MaxAbsScaler", + "n_gram_range": "(3,5)", + "dataset_version": "language-identification", + "vectorizer_class": "CountVectorizer" + }, + "params": { + "clf__C": "46.19347374377369", + "clf__penalty": "l2", + "vectorizer__max_features": "50000", + "vectorizer__min_df": "2" + }, + "metrics": { + "accuracy": 0.9837668687658908, + "f1_macro": 0.9844389961384462, + "precision_macro": 0.9863210921743177, + "recall_macro": 0.9841261942624783, + "inference_time_total_s": 3.4034, + "inference_time_ms_per_sample": 0.665643, + "throughput_samples_per_sec": 1502.31 + } +} \ No newline at end of file diff --git a/logistic_regression/language-identification/tfidf_lr_char_ngram_3_5/classification_report.txt b/logistic_regression/language-identification/tfidf_lr_char_ngram_3_5/classification_report.txt new file mode 100644 index 0000000000000000000000000000000000000000..9a869d08a199f89e15553440d2bbd935b2dc49cd --- /dev/null +++ b/logistic_regression/language-identification/tfidf_lr_char_ngram_3_5/classification_report.txt @@ -0,0 +1,30 @@ + precision recall f1-score support + + ca 0.00 0.00 0.00 0 + da 0.00 0.00 0.00 0 + de 1.00 1.00 1.00 433 + el 1.00 1.00 1.00 418 + en 0.99 1.00 1.00 441 + es 1.00 1.00 1.00 436 + fi 0.00 0.00 0.00 0 + fr 1.00 1.00 1.00 417 + hr 0.00 0.00 0.00 0 + it 1.00 1.00 1.00 428 + ja 1.00 0.96 0.98 449 + ko 0.00 0.00 0.00 0 + lt 0.00 0.00 0.00 0 + mk 0.00 0.00 0.00 0 + nb 0.00 0.00 0.00 0 + nl 1.00 1.00 1.00 399 + pl 1.00 0.98 0.99 392 + pt 0.99 1.00 0.99 423 + ro 0.00 0.00 0.00 0 + ru 1.00 1.00 1.00 425 + sl 0.00 0.00 0.00 0 + sv 0.00 0.00 0.00 0 + uk 0.00 0.00 0.00 0 + zh 0.95 1.00 0.97 452 + + accuracy 0.99 5113 + macro avg 0.50 0.50 0.50 5113 +weighted avg 0.99 0.99 0.99 5113 diff --git a/logistic_regression/language-identification/tfidf_lr_char_ngram_3_5/cv_results.csv b/logistic_regression/language-identification/tfidf_lr_char_ngram_3_5/cv_results.csv new file mode 100644 index 0000000000000000000000000000000000000000..e61749e8bc15dfbcde5aba437866afe63c43f9b9 --- /dev/null +++ b/logistic_regression/language-identification/tfidf_lr_char_ngram_3_5/cv_results.csv @@ -0,0 +1,11 @@ +mean_fit_time,std_fit_time,mean_score_time,std_score_time,param_clf__C,param_clf__penalty,param_vectorizer__max_features,param_vectorizer__min_df,param_vectorizer__sublinear_tf,params,split0_test_score,split1_test_score,split2_test_score,mean_test_score,std_test_score,rank_test_score +24.066272258758545,3.0391953849440956,3.621941884358724,2.263294500771926,0.09915644566638392,l2,50000,1,True,"{'clf__C': 0.09915644566638392, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.99336354741965,0.9924559086646587,0.9946730722573522,0.9934975094472204,0.0009100963201092047,5 +25.41511861483256,2.690370502531163,8.407360871632894,1.3489772727463232,71.77141927992008,l2,50000,1,True,"{'clf__C': 71.77141927992008, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9942439327297804,0.9937703879265899,0.9927321751759624,0.9935821652774441,0.0006313601981014462,3 +26.703498204549152,7.959151535802446,4.880916992823283,3.5688900413443685,0.0017707168643537816,l2,50000,3,True,"{'clf__C': 0.0017707168643537816, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': True}",0.6538676278213051,0.4378628766170832,0.6546825298353354,0.5821376780912412,0.10201823291820244,8 +28.760569095611572,12.150343299108188,5.237223068873088,4.139852282823081,0.00029152036385288323,l2,50000,5,True,"{'clf__C': 0.00029152036385288323, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.08352215580360571,0.07613279856629844,0.08020485967731297,0.07995327134907237,0.0030219334440405874,9 +22.985459327697754,2.718322957008903,5.419108311335246,3.4793378202761756,6.440507553993708,l2,50000,5,True,"{'clf__C': 6.440507553993708, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.9950884907577199,0.9938057481504633,0.9943166404642939,0.9944036264574924,0.0005272773282801592,1 +31.711488644282024,3.727225812530605,5.710396846135457,1.9609189795634325,0.00014610865886287189,l2,50000,2,False,"{'clf__C': 0.00014610865886287189, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.012985256323549304,0.012881248872044759,0.05075443007662835,0.02554031175740747,0.01782912460646427,10 +21.026910384496052,8.837167900408234,3.331766049067179,1.3283306292448738,456.60548734461145,l2,50000,2,False,"{'clf__C': 456.60548734461145, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.9941113746512653,0.9941844849320045,0.9924423515739108,0.9935794037190603,0.0008045710923131994,4 +28.85173026720683,1.2566208938046495,4.797921975453694,2.233529341191331,0.0028483918709108036,l2,50000,1,True,"{'clf__C': 0.0028483918709108036, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.7777764179387172,0.6694205069966505,0.780275838418925,0.7424909211180976,0.05167865994517823,7 +31.233232895533245,5.221077561469457,4.673653205235799,1.1545385754722695,0.027160511446548484,l2,50000,2,True,"{'clf__C': 0.027160511446548484, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': True}",0.9898770663311244,0.9892655798114894,0.9917822383250359,0.9903082948225498,0.001071715455804161,6 +24.232994715372723,3.301897471422535,3.1286118030548096,1.2692860024427923,0.28546978577971793,l2,50000,1,True,"{'clf__C': 0.28546978577971793, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9946288669234727,0.993511461693859,0.9944209117261901,0.9941870801145072,0.000485219214210579,2 diff --git a/logistic_regression/language-identification/tfidf_lr_char_ngram_3_5/run_metadata.json b/logistic_regression/language-identification/tfidf_lr_char_ngram_3_5/run_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..ebcb959dcd02d40a9abdd342b5c2c395590170d8 --- /dev/null +++ b/logistic_regression/language-identification/tfidf_lr_char_ngram_3_5/run_metadata.json @@ -0,0 +1,26 @@ +{ + "run_name": "tfidf_lr_char_ngram_3_5", + "tags": { + "feature_type": "tfidf", + "scaler": "none", + "n_gram_range": "(3,5)", + "dataset_version": "language-identification", + "vectorizer_class": "TfidfVectorizer" + }, + "params": { + "clf__C": "6.440507553993708", + "clf__penalty": "l2", + "vectorizer__max_features": "50000", + "vectorizer__min_df": "5", + "vectorizer__sublinear_tf": "True" + }, + "metrics": { + "accuracy": 0.99315470369646, + "f1_macro": 0.993344498787548, + "precision_macro": 0.9936685194721587, + "recall_macro": 0.9932338860235449, + "inference_time_total_s": 1.7974, + "inference_time_ms_per_sample": 0.351533, + "throughput_samples_per_sec": 2844.68 + } +} \ No newline at end of file diff --git a/logistic_regression/massive/bow_maxabs_lr_char_ngram_3_5/classification_report.txt b/logistic_regression/massive/bow_maxabs_lr_char_ngram_3_5/classification_report.txt new file mode 100644 index 0000000000000000000000000000000000000000..80ab21f84179a414fb53e03a8e671562f6e28ccb --- /dev/null +++ b/logistic_regression/massive/bow_maxabs_lr_char_ngram_3_5/classification_report.txt @@ -0,0 +1,30 @@ + precision recall f1-score support + + ca 0.00 0.00 0.00 0 + da 1.00 1.00 1.00 957 + de 1.00 1.00 1.00 1142 + el 1.00 1.00 1.00 1141 + en 0.99 1.00 1.00 963 + es 1.00 0.99 0.99 1097 + fi 1.00 1.00 1.00 1044 + fr 1.00 1.00 1.00 1221 + hr 0.00 0.00 0.00 0 + it 1.00 1.00 1.00 1093 + ja 1.00 0.92 0.96 1337 + ko 1.00 0.93 0.96 1324 + lt 0.00 0.00 0.00 0 + mk 0.00 0.00 0.00 0 + nb 0.00 0.00 0.00 0 + nl 1.00 1.00 1.00 1129 + pl 1.00 1.00 1.00 1002 + pt 0.99 0.99 0.99 1070 + ro 1.00 1.00 1.00 1010 + ru 1.00 0.99 1.00 1023 + sl 1.00 1.00 1.00 998 + sv 1.00 0.99 1.00 957 + uk 0.00 0.00 0.00 0 + zh 0.80 1.00 0.89 874 + + accuracy 0.99 19382 + macro avg 0.74 0.74 0.74 19382 +weighted avg 0.99 0.99 0.99 19382 diff --git a/logistic_regression/massive/bow_maxabs_lr_char_ngram_3_5/cv_results.csv b/logistic_regression/massive/bow_maxabs_lr_char_ngram_3_5/cv_results.csv new file mode 100644 index 0000000000000000000000000000000000000000..fab95b3501f80b57614bef159b68102d0bf211fc --- /dev/null +++ b/logistic_regression/massive/bow_maxabs_lr_char_ngram_3_5/cv_results.csv @@ -0,0 +1,11 @@ +mean_fit_time,std_fit_time,mean_score_time,std_score_time,param_clf__C,param_clf__penalty,param_vectorizer__max_features,param_vectorizer__min_df,params,split0_test_score,split1_test_score,split2_test_score,mean_test_score,std_test_score,rank_test_score +8.806038777033487,0.1752176687282589,1.8943706353505452,0.03727540730953514,0.09915644566638392,l2,50000,1,"{'clf__C': 0.09915644566638392, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1}",0.9869506520087205,0.9852729163102816,0.9865066022921292,0.9862433902037105,0.0007097697847759615,4 +8.512574275334677,0.5397481553457544,1.9069794019063313,0.05429025459154519,0.0029341230215132346,l2,50000,5,"{'clf__C': 0.0029341230215132346, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9475948789202777,0.9508172187995846,0.9444343815222648,0.947615493080709,0.00260582317574742,7 +8.828056812286377,0.16389161555023937,1.863707462946574,0.04273698349252348,6.155564318973006,l2,50000,3,"{'clf__C': 6.155564318973006, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.9871552320784241,0.985144863081794,0.986231310151279,0.9861771351038323,0.0008216232216278756,6 +8.692294359207153,0.16293045207679602,1.9106624126434326,0.016190018826483594,0.3686905640846153,l2,50000,3,"{'clf__C': 0.3686905640846153, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.9871550126544126,0.9851893415400785,0.9863800587405667,0.9862414709783526,0.0008084432193248496,5 +9.043086131413778,0.32208519903394495,1.9802601337432861,0.15603986443881065,0.00029152036385288323,l2,50000,5,"{'clf__C': 0.00029152036385288323, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.8859559228005294,0.8900094519507787,0.8920350863679657,0.8893334870397579,0.002527416842101805,8 +7.779061317443848,0.12415004559575947,2.1071348190307617,0.032728674331174136,0.0467378670778782,l2,50000,5,"{'clf__C': 0.0467378670778782, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9874498749465922,0.9854895372668911,0.9863503679111729,0.9864299267082188,0.0008022793180492943,1 +8.55941637357076,0.06689128208385134,1.8991725444793701,0.01354718381536146,46.19347374377369,l2,50000,2,"{'clf__C': 46.19347374377369, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2}",0.987296221658316,0.9853964094505956,0.9864077689635226,0.9863668000241447,0.0007761359187866395,2 +9.052494287490845,0.3775782794355721,1.8512430985768635,0.014670465614623337,0.00028267840503514715,l2,50000,5,"{'clf__C': 0.00028267840503514715, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.8793390381001349,0.8873376386415608,0.8904146698241728,0.8856971155219563,0.004668039674288462,9 +8.631972710291544,0.20340224630571552,1.8465713659922283,0.036144672920940556,456.60548734461145,l2,50000,2,"{'clf__C': 456.60548734461145, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2}",0.987296221658316,0.9853561509992572,0.9864077689635226,0.9863533805403653,0.0007929636880989923,3 +10.089497725168863,0.26447080603423045,1.4514545599619548,0.06531349435891155,0.00010144487859320231,l2,50000,5,"{'clf__C': 0.00010144487859320231, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.6869670009150837,0.6792802390547998,0.6901147121276733,0.6854539840325189,0.004550704469778963,10 diff --git a/logistic_regression/massive/bow_maxabs_lr_char_ngram_3_5/run_metadata.json b/logistic_regression/massive/bow_maxabs_lr_char_ngram_3_5/run_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..8e9d61ad8352341fde14be302dfabb688f379ebd --- /dev/null +++ b/logistic_regression/massive/bow_maxabs_lr_char_ngram_3_5/run_metadata.json @@ -0,0 +1,25 @@ +{ + "run_name": "bow_maxabs_lr_char_ngram_3_5", + "tags": { + "feature_type": "bow", + "scaler": "MaxAbsScaler", + "n_gram_range": "(3,5)", + "dataset_version": "massive", + "vectorizer_class": "CountVectorizer" + }, + "params": { + "clf__C": "0.0467378670778782", + "clf__penalty": "l2", + "vectorizer__max_features": "50000", + "vectorizer__min_df": "5" + }, + "metrics": { + "accuracy": 0.9869466515323496, + "f1_macro": 0.987175281526507, + "precision_macro": 0.987050282253769, + "recall_macro": 0.9888379051984971, + "inference_time_total_s": 0.9894, + "inference_time_ms_per_sample": 0.051048, + "throughput_samples_per_sec": 19589.47 + } +} \ No newline at end of file diff --git a/logistic_regression/massive/tfidf_lr_char_ngram_3_5/classification_report.txt b/logistic_regression/massive/tfidf_lr_char_ngram_3_5/classification_report.txt new file mode 100644 index 0000000000000000000000000000000000000000..85f7ef0d17b0934b90a10d4b1802f7a186143313 --- /dev/null +++ b/logistic_regression/massive/tfidf_lr_char_ngram_3_5/classification_report.txt @@ -0,0 +1,30 @@ + precision recall f1-score support + + ca 0.00 0.00 0.00 0 + da 0.99 1.00 1.00 957 + de 1.00 1.00 1.00 1142 + el 1.00 1.00 1.00 1141 + en 1.00 1.00 1.00 963 + es 1.00 1.00 1.00 1097 + fi 1.00 1.00 1.00 1044 + fr 1.00 1.00 1.00 1221 + hr 0.00 0.00 0.00 0 + it 1.00 1.00 1.00 1093 + ja 1.00 0.93 0.96 1337 + ko 1.00 0.97 0.98 1324 + lt 0.00 0.00 0.00 0 + mk 0.00 0.00 0.00 0 + nb 0.00 0.00 0.00 0 + nl 1.00 1.00 1.00 1129 + pl 1.00 1.00 1.00 1002 + pt 0.99 1.00 0.99 1070 + ro 1.00 1.00 1.00 1010 + ru 1.00 1.00 1.00 1023 + sl 1.00 1.00 1.00 998 + sv 1.00 1.00 1.00 957 + uk 0.00 0.00 0.00 0 + zh 0.87 1.00 0.93 874 + + accuracy 0.99 19382 + macro avg 0.74 0.74 0.74 19382 +weighted avg 0.99 0.99 0.99 19382 diff --git a/logistic_regression/massive/tfidf_lr_char_ngram_3_5/cv_results.csv b/logistic_regression/massive/tfidf_lr_char_ngram_3_5/cv_results.csv new file mode 100644 index 0000000000000000000000000000000000000000..6f8d3c8bfa13dfe1f1fc8fe48a4a2b9bf5f3eed2 --- /dev/null +++ b/logistic_regression/massive/tfidf_lr_char_ngram_3_5/cv_results.csv @@ -0,0 +1,11 @@ +mean_fit_time,std_fit_time,mean_score_time,std_score_time,param_clf__C,param_clf__penalty,param_vectorizer__max_features,param_vectorizer__min_df,param_vectorizer__sublinear_tf,params,split0_test_score,split1_test_score,split2_test_score,mean_test_score,std_test_score,rank_test_score +8.41204277674357,0.03800403238490002,2.130410114924113,0.08880732514408764,0.09915644566638392,l2,50000,1,True,"{'clf__C': 0.09915644566638392, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9729910424797432,0.9733399852969846,0.9738694150122245,0.9734001475963175,0.00036110866614740374,5 +7.746164083480835,0.24946507299764603,2.1380454699198403,0.058062556097476244,71.77141927992008,l2,50000,1,True,"{'clf__C': 71.77141927992008, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.989913260043953,0.9894861630512239,0.9884300658341301,0.989276496309769,0.0006233973440577038,3 +9.926965634028116,0.24857141234102267,1.9099247455596924,0.11720351930324341,0.0017707168643537816,l2,50000,3,True,"{'clf__C': 0.0017707168643537816, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': True}",0.28948538807893903,0.2891538687960144,0.2880832375410509,0.2889074981386681,0.0005983479524635098,8 +10.602810462315878,0.472668710982073,1.9435614744822185,0.11176598364492388,0.00029152036385288323,l2,50000,5,True,"{'clf__C': 0.00029152036385288323, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.06072823370136157,0.061920327623000766,0.0579689410422329,0.06020583412219841,0.0016548997890910644,9 +9.06920305887858,0.5940014475948462,2.001631021499634,0.13090904898254052,6.440507553993708,l2,50000,5,True,"{'clf__C': 6.440507553993708, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.9906162773916051,0.9900120609761767,0.9899847503626515,0.9902043629101444,0.0002914808426300923,1 +11.624321222305298,0.2825827874130309,1.7265090942382812,0.11564576970282385,0.00014610865886287189,l2,50000,2,False,"{'clf__C': 0.00014610865886287189, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.02403926940150334,0.03542528702201226,0.03300912599136062,0.03082456080495874,0.004898271334791776,10 +7.584720770517985,0.19078849380875443,2.027594725290934,0.014661266984491505,456.60548734461145,l2,50000,2,False,"{'clf__C': 456.60548734461145, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.989827648631286,0.9892548125214762,0.9886183646504715,0.9892336086010779,0.0004939157426416381,4 +9.725672086079916,0.11306594801186873,1.7257123788197835,0.08169984862783343,0.0028483918709108036,l2,50000,1,True,"{'clf__C': 0.0028483918709108036, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.5252265628707862,0.5276941666920951,0.5261065185506385,0.5263424160378399,0.0010211114444844223,7 +8.481626510620117,0.4627061651280554,1.7441190878550212,0.10620556747677802,0.027160511446548484,l2,50000,2,True,"{'clf__C': 0.027160511446548484, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': True}",0.9653768773786644,0.9647228220063488,0.9679398938158121,0.9660131977336084,0.0013883000281874598,6 +8.094027280807495,0.20726157673706772,1.7728882630666096,0.050696983855423185,0.28546978577971793,l2,50000,1,True,"{'clf__C': 0.28546978577971793, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9902870355876624,0.9897382107350143,0.9894092506684539,0.9898114989970436,0.0003620819134863722,2 diff --git a/logistic_regression/massive/tfidf_lr_char_ngram_3_5/run_metadata.json b/logistic_regression/massive/tfidf_lr_char_ngram_3_5/run_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..27f785fcc35b80f223c74dd8c9f727b60eb13fa3 --- /dev/null +++ b/logistic_regression/massive/tfidf_lr_char_ngram_3_5/run_metadata.json @@ -0,0 +1,26 @@ +{ + "run_name": "tfidf_lr_char_ngram_3_5", + "tags": { + "feature_type": "tfidf", + "scaler": "none", + "n_gram_range": "(3,5)", + "dataset_version": "massive", + "vectorizer_class": "TfidfVectorizer" + }, + "params": { + "clf__C": "6.440507553993708", + "clf__penalty": "l2", + "vectorizer__max_features": "50000", + "vectorizer__min_df": "5", + "vectorizer__sublinear_tf": "True" + }, + "metrics": { + "accuracy": 0.9916933237024043, + "f1_macro": 0.9917252601889304, + "precision_macro": 0.9911473317774038, + "recall_macro": 0.9929328394176677, + "inference_time_total_s": 0.9903, + "inference_time_ms_per_sample": 0.051093, + "throughput_samples_per_sec": 19572.3 + } +} \ No newline at end of file diff --git a/logistic_regression/mmarco/bow_maxabs_lr_char_ngram_3_5/classification_report.txt b/logistic_regression/mmarco/bow_maxabs_lr_char_ngram_3_5/classification_report.txt new file mode 100644 index 0000000000000000000000000000000000000000..19eac98481c5c846c6d9dee1eadaa38abbef7985 --- /dev/null +++ b/logistic_regression/mmarco/bow_maxabs_lr_char_ngram_3_5/classification_report.txt @@ -0,0 +1,30 @@ + precision recall f1-score support + + ca 0.00 0.00 0.00 0 + da 0.00 0.00 0.00 0 + de 1.00 1.00 1.00 20033 + el 0.00 0.00 0.00 0 + en 0.99 1.00 0.99 20044 + es 0.99 0.99 0.99 20016 + fi 0.00 0.00 0.00 0 + fr 1.00 1.00 1.00 19956 + hr 0.00 0.00 0.00 0 + it 1.00 1.00 1.00 19992 + ja 1.00 0.87 0.93 19935 + ko 0.00 0.00 0.00 0 + lt 0.00 0.00 0.00 0 + mk 0.00 0.00 0.00 0 + nb 0.00 0.00 0.00 0 + nl 1.00 1.00 1.00 19942 + pl 0.00 0.00 0.00 0 + pt 0.99 0.99 0.99 20036 + ro 0.00 0.00 0.00 0 + ru 1.00 1.00 1.00 20086 + sl 0.00 0.00 0.00 0 + sv 0.00 0.00 0.00 0 + uk 0.00 0.00 0.00 0 + zh 0.88 1.00 0.94 20005 + + accuracy 0.98 200045 + macro avg 0.41 0.41 0.41 200045 +weighted avg 0.99 0.98 0.98 200045 diff --git a/logistic_regression/mmarco/bow_maxabs_lr_char_ngram_3_5/cv_results.csv b/logistic_regression/mmarco/bow_maxabs_lr_char_ngram_3_5/cv_results.csv new file mode 100644 index 0000000000000000000000000000000000000000..9a59e35a478bd3fd954f30ff1f00eef95c2944a7 --- /dev/null +++ b/logistic_regression/mmarco/bow_maxabs_lr_char_ngram_3_5/cv_results.csv @@ -0,0 +1,11 @@ +mean_fit_time,std_fit_time,mean_score_time,std_score_time,param_clf__C,param_clf__penalty,param_vectorizer__max_features,param_vectorizer__min_df,params,split0_test_score,split1_test_score,split2_test_score,mean_test_score,std_test_score,rank_test_score +66.5223552385966,3.442939478354831,19.303172906239826,0.6179726425335146,0.09915644566638392,l2,50000,1,"{'clf__C': 0.09915644566638392, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1}",0.9816077153766996,0.9811656247847337,0.9814521436439888,0.9814084946018072,0.00018310279815575867,6 +64.78002214431763,2.3454436585317855,19.040038267771404,1.0511100641461475,0.0029341230215132346,l2,50000,5,"{'clf__C': 0.0029341230215132346, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9667275514753921,0.9667991298401912,0.9668098111214853,0.9667788308123563,3.652122891442162e-05,7 +70.61315234502156,3.9931379788581687,18.763609727223713,0.5701110154356371,6.155564318973006,l2,50000,3,"{'clf__C': 6.155564318973006, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.9839623927384455,0.9843367748597099,0.9837529461180112,0.9840173712387221,0.0002414966894567856,3 +69.23730270067851,4.66706506108104,18.664097627003986,0.6371831089310802,0.3686905640846153,l2,50000,3,"{'clf__C': 0.3686905640846153, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.9827264987172839,0.9838144848495279,0.9832643913175347,0.983268458294782,0.0004441777881410264,4 +65.5788471698761,1.4394848907851474,17.97521750132243,0.10428279780608445,0.00029152036385288323,l2,50000,5,"{'clf__C': 0.00029152036385288323, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9428079552865585,0.9466900015549994,0.9428883510689122,0.94412876930349,0.0018113620759130098,8 +71.44474705060323,3.347553457202775,18.226688226064045,0.4661330272129226,0.0467378670778782,l2,50000,5,"{'clf__C': 0.0467378670778782, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.981402609170039,0.9812462487454214,0.9817275641254124,0.9814588073469576,0.00020047410484598003,5 +65.06078600883484,0.21780367153264815,17.72416130701701,0.16610170198210247,46.19347374377369,l2,50000,2,"{'clf__C': 46.19347374377369, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2}",0.9839584446752623,0.9843887118316094,0.9837791994795599,0.9840421186621437,0.00025576985603689326,1 +64.34969687461853,1.327372786682874,17.40241042772929,0.18591026765558533,0.00028267840503514715,l2,50000,5,"{'clf__C': 0.00028267840503514715, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9426543210488647,0.9465419867199142,0.9426799998349568,0.9439587692012452,0.0018266407075252437,9 +65.24408038457234,0.8699221487258816,16.950232187906902,0.061915212666849136,456.60548734461145,l2,50000,2,"{'clf__C': 456.60548734461145, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2}",0.9839546992390027,0.9843887118316094,0.9837791994795599,0.9840408701833908,0.0002561840491622399,2 +64.38435085614522,0.7162908714508494,16.607149759928387,0.344745535331013,0.00010144487859320231,l2,50000,5,"{'clf__C': 0.00010144487859320231, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.939047143828233,0.9409774619794792,0.9378003040687191,0.9392749699588103,0.0013070352346198934,10 diff --git a/logistic_regression/mmarco/bow_maxabs_lr_char_ngram_3_5/run_metadata.json b/logistic_regression/mmarco/bow_maxabs_lr_char_ngram_3_5/run_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..c00068aec894d6094c633bc942b0ff68e164e1f3 --- /dev/null +++ b/logistic_regression/mmarco/bow_maxabs_lr_char_ngram_3_5/run_metadata.json @@ -0,0 +1,25 @@ +{ + "run_name": "bow_maxabs_lr_char_ngram_3_5", + "tags": { + "feature_type": "bow", + "scaler": "MaxAbsScaler", + "n_gram_range": "(3,5)", + "dataset_version": "mmarco", + "vectorizer_class": "CountVectorizer" + }, + "params": { + "clf__C": "46.19347374377369", + "clf__penalty": "l2", + "vectorizer__max_features": "50000", + "vectorizer__min_df": "2" + }, + "metrics": { + "accuracy": 0.9837136644255042, + "f1_macro": 0.9836626999127922, + "precision_macro": 0.985201679742007, + "recall_macro": 0.9836709364057225, + "inference_time_total_s": 10.377, + "inference_time_ms_per_sample": 0.051874, + "throughput_samples_per_sec": 19277.64 + } +} \ No newline at end of file diff --git a/logistic_regression/mmarco/tfidf_lr_char_ngram_3_5/classification_report.txt b/logistic_regression/mmarco/tfidf_lr_char_ngram_3_5/classification_report.txt new file mode 100644 index 0000000000000000000000000000000000000000..67ee4dde16ac03375fc5bda545d808cb79f3d593 --- /dev/null +++ b/logistic_regression/mmarco/tfidf_lr_char_ngram_3_5/classification_report.txt @@ -0,0 +1,30 @@ + precision recall f1-score support + + ca 0.00 0.00 0.00 0 + da 0.00 0.00 0.00 0 + de 1.00 1.00 1.00 20033 + el 0.00 0.00 0.00 0 + en 0.99 1.00 1.00 20044 + es 0.99 0.99 0.99 20016 + fi 0.00 0.00 0.00 0 + fr 1.00 1.00 1.00 19956 + hr 0.00 0.00 0.00 0 + it 1.00 1.00 1.00 19992 + ja 1.00 0.90 0.95 19935 + ko 0.00 0.00 0.00 0 + lt 0.00 0.00 0.00 0 + mk 0.00 0.00 0.00 0 + nb 0.00 0.00 0.00 0 + nl 1.00 1.00 1.00 19942 + pl 0.00 0.00 0.00 0 + pt 0.99 1.00 0.99 20036 + ro 0.00 0.00 0.00 0 + ru 1.00 1.00 1.00 20086 + sl 0.00 0.00 0.00 0 + sv 0.00 0.00 0.00 0 + uk 0.00 0.00 0.00 0 + zh 0.91 0.99 0.95 20005 + + accuracy 0.99 200045 + macro avg 0.41 0.41 0.41 200045 +weighted avg 0.99 0.99 0.99 200045 diff --git a/logistic_regression/mmarco/tfidf_lr_char_ngram_3_5/cv_results.csv b/logistic_regression/mmarco/tfidf_lr_char_ngram_3_5/cv_results.csv new file mode 100644 index 0000000000000000000000000000000000000000..efbccddc27a83ae5f9c1b3ca423d4f88b062bd03 --- /dev/null +++ b/logistic_regression/mmarco/tfidf_lr_char_ngram_3_5/cv_results.csv @@ -0,0 +1,11 @@ +mean_fit_time,std_fit_time,mean_score_time,std_score_time,param_clf__C,param_clf__penalty,param_vectorizer__max_features,param_vectorizer__min_df,param_vectorizer__sublinear_tf,params,split0_test_score,split1_test_score,split2_test_score,mean_test_score,std_test_score,rank_test_score +59.6538671652476,2.074384059881507,20.118187030156452,1.2479418357581145,0.09915644566638392,l2,50000,1,True,"{'clf__C': 0.09915644566638392, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9833258053335129,0.9838468317706035,0.9833805034256725,0.9835177135099297,0.00023379063632977408,5 +60.61395804087321,2.305601307861205,19.585657835006714,1.1408303303992218,71.77141927992008,l2,50000,1,True,"{'clf__C': 71.77141927992008, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9855790450750206,0.9865762503924931,0.9864237736487402,0.9861930230387513,0.0004385878812025037,2 +70.79162931442261,2.646390432395221,18.570846160252888,0.5584507400917724,0.0017707168643537816,l2,50000,3,True,"{'clf__C': 0.0017707168643537816, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': True}",0.9619645279896675,0.9746191346656217,0.9676746803269509,0.9680861143274133,0.005174406631574839,8 +75.09138417243958,5.40426609528691,19.9089670976003,1.7869296876622531,0.00029152036385288323,l2,50000,5,True,"{'clf__C': 0.00029152036385288323, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.928443540007254,0.9739812908058056,0.9710815108508912,0.957835447221317,0.02081690560108609,10 +71.04249183336894,5.58215604555665,18.799468994140625,0.7432630586734928,6.440507553993708,l2,50000,5,True,"{'clf__C': 6.440507553993708, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.9861762802254667,0.9868189262341623,0.9873751997927988,0.986790135417476,0.0004898800639456188,1 +76.76116863886516,4.259923992078333,17.62615132331848,0.6644368377752696,0.00014610865886287189,l2,50000,2,False,"{'clf__C': 0.00014610865886287189, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.9645103144613729,0.9415430800750798,0.9695522231577154,0.958535205898056,0.01219028208077935,9 +60.52088395754496,2.249377028691026,18.770265181859333,0.4240722708301269,456.60548734461145,l2,50000,2,False,"{'clf__C': 456.60548734461145, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.9854502990107626,0.9864001389352858,0.9862143327972349,0.986021590247761,0.0004110241179766901,3 +65.97150150934856,1.731910808777453,16.917045036951702,0.44875397436509445,0.0028483918709108036,l2,50000,1,True,"{'clf__C': 0.0028483918709108036, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9659258485440183,0.9734511205583004,0.9749578985871136,0.9714449558964774,0.003950780891841069,7 +61.16194780667623,1.9453262427812146,16.694405635197956,0.7564741669941186,0.027160511446548484,l2,50000,2,True,"{'clf__C': 0.027160511446548484, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': True}",0.9799072878065406,0.9807516459238188,0.9821819197889194,0.9809469511730929,0.000938827555734894,6 +59.47458577156067,0.5901416153251525,16.188791116078693,0.24599274884352676,0.28546978577971793,l2,50000,1,True,"{'clf__C': 0.28546978577971793, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9848508053302464,0.9855014124805159,0.9857010838976163,0.9853511005694596,0.0003630322882667097,4 diff --git a/logistic_regression/mmarco/tfidf_lr_char_ngram_3_5/run_metadata.json b/logistic_regression/mmarco/tfidf_lr_char_ngram_3_5/run_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..cb08c192eb66f9bbdc862fbed6b9f52be6b77c92 --- /dev/null +++ b/logistic_regression/mmarco/tfidf_lr_char_ngram_3_5/run_metadata.json @@ -0,0 +1,26 @@ +{ + "run_name": "tfidf_lr_char_ngram_3_5", + "tags": { + "feature_type": "tfidf", + "scaler": "none", + "n_gram_range": "(3,5)", + "dataset_version": "mmarco", + "vectorizer_class": "TfidfVectorizer" + }, + "params": { + "clf__C": "6.440507553993708", + "clf__penalty": "l2", + "vectorizer__max_features": "50000", + "vectorizer__min_df": "5", + "vectorizer__sublinear_tf": "True" + }, + "metrics": { + "accuracy": 0.9872028793521458, + "f1_macro": 0.9871717798405111, + "precision_macro": 0.9879831577726538, + "recall_macro": 0.9871698822374911, + "inference_time_total_s": 10.3763, + "inference_time_ms_per_sample": 0.05187, + "throughput_samples_per_sec": 19278.98 + } +} \ No newline at end of file diff --git a/logistic_regression/multi_eurlex/bow_maxabs_lr_char_ngram_3_5/classification_report.txt b/logistic_regression/multi_eurlex/bow_maxabs_lr_char_ngram_3_5/classification_report.txt new file mode 100644 index 0000000000000000000000000000000000000000..91321ea5b6846fcc74990658fd6b40bf17eafb47 --- /dev/null +++ b/logistic_regression/multi_eurlex/bow_maxabs_lr_char_ngram_3_5/classification_report.txt @@ -0,0 +1,30 @@ + precision recall f1-score support + + ca 0.00 0.00 0.00 0 + da 1.00 1.00 1.00 6478 + de 1.00 1.00 1.00 6514 + el 1.00 1.00 1.00 6499 + en 1.00 1.00 1.00 6537 + es 1.00 1.00 1.00 6263 + fi 1.00 1.00 1.00 5230 + fr 1.00 1.00 1.00 6508 + hr 1.00 1.00 1.00 1557 + it 1.00 1.00 1.00 6499 + ja 0.00 0.00 0.00 0 + ko 0.00 0.00 0.00 0 + lt 1.00 1.00 1.00 3330 + mk 0.00 0.00 0.00 0 + nb 0.00 0.00 0.00 0 + nl 1.00 1.00 1.00 6529 + pl 1.00 1.00 1.00 3317 + pt 1.00 1.00 1.00 6233 + ro 1.00 1.00 1.00 2600 + ru 0.00 0.00 0.00 0 + sl 1.00 1.00 1.00 3313 + sv 1.00 1.00 1.00 5257 + uk 0.00 0.00 0.00 0 + zh 0.00 0.00 0.00 0 + + accuracy 1.00 82664 + macro avg 0.67 0.67 0.67 82664 +weighted avg 1.00 1.00 1.00 82664 diff --git a/logistic_regression/multi_eurlex/bow_maxabs_lr_char_ngram_3_5/cv_results.csv b/logistic_regression/multi_eurlex/bow_maxabs_lr_char_ngram_3_5/cv_results.csv new file mode 100644 index 0000000000000000000000000000000000000000..dfd0a9b8b261957fe833e72b40bf551fc58a95e0 --- /dev/null +++ b/logistic_regression/multi_eurlex/bow_maxabs_lr_char_ngram_3_5/cv_results.csv @@ -0,0 +1,11 @@ +mean_fit_time,std_fit_time,mean_score_time,std_score_time,param_clf__C,param_clf__penalty,param_vectorizer__max_features,param_vectorizer__min_df,params,split0_test_score,split1_test_score,split2_test_score,mean_test_score,std_test_score,rank_test_score +58.11060563723246,0.379962077274111,21.211435317993164,0.9448053631930966,0.09915644566638392,l2,50000,1,"{'clf__C': 0.09915644566638392, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1}",0.9998117390231491,0.9998332454583383,0.9998188856607799,0.9998212900474224,8.943060437438874e-06,2 +59.3550066947937,0.13962543586908094,20.462625741958618,0.9450047828624563,0.0029341230215132346,l2,50000,5,"{'clf__C': 0.0029341230215132346, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9997595056959798,0.9997149870024714,0.9997521675168728,0.9997422200717746,1.94883258372628e-05,7 +59.568419535954796,0.664639820264726,20.143352508544922,0.8190291119801871,6.155564318973006,l2,50000,3,"{'clf__C': 6.155564318973006, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.9998043903179885,0.9998332652846516,0.9998188856607799,0.9998188470878068,1.1788187331777226e-05,3 +59.52647336324056,0.8705879774657466,20.153676827748615,0.9539645421872754,0.3686905640846153,l2,50000,3,"{'clf__C': 0.3686905640846153, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.9998043903179885,0.9998332652846516,0.9998188856607799,0.9998188470878068,1.1788187331777226e-05,3 +58.92317684491476,0.5066054578998324,20.894578059514362,0.9530331901121322,0.00029152036385288323,l2,50000,5,"{'clf__C': 0.00029152036385288323, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9995934475075559,0.9993940553133949,0.9995556513181287,0.9995143847130264,8.647354622689244e-05,8 +68.48207505544026,3.2884036089716475,19.520317633946735,1.0031714327124717,0.0467378670778782,l2,50000,5,"{'clf__C': 0.0467378670778782, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9998264176705822,0.9998332437631596,0.9998335879365807,0.9998310831234409,3.301964225332328e-06,1 +58.04341173171997,0.6357297993833433,19.429731369018555,0.04803814652826426,46.19347374377369,l2,50000,2,"{'clf__C': 46.19347374377369, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2}",0.9998043903179885,0.9998332652846516,0.9998188856607799,0.9998188470878068,1.1788187331777226e-05,3 +57.63342340787252,0.13569377155713697,19.285069227218628,0.1991914375848924,0.00028267840503514715,l2,50000,5,"{'clf__C': 0.00028267840503514715, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9995934475075559,0.9993940553133949,0.9995556513181287,0.9995143847130264,8.647354622689244e-05,8 +57.47682205835978,0.3791579637148409,19.386224110921223,0.13647914233662936,456.60548734461145,l2,50000,2,"{'clf__C': 456.60548734461145, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2}",0.9998043903179885,0.9998332652846516,0.9998188856607799,0.9998188470878068,1.1788187331777226e-05,3 +59.77876329421997,1.6395823468633917,19.146162192026775,0.6610139274757174,0.00010144487859320231,l2,50000,5,"{'clf__C': 0.00010144487859320231, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9991479032074926,0.9993074342715771,0.999465369882376,0.9993069024538151,0.00012960577286006444,10 diff --git a/logistic_regression/multi_eurlex/bow_maxabs_lr_char_ngram_3_5/run_metadata.json b/logistic_regression/multi_eurlex/bow_maxabs_lr_char_ngram_3_5/run_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..aa15d306551f1b0e9c07273b0edd777698751111 --- /dev/null +++ b/logistic_regression/multi_eurlex/bow_maxabs_lr_char_ngram_3_5/run_metadata.json @@ -0,0 +1,25 @@ +{ + "run_name": "bow_maxabs_lr_char_ngram_3_5", + "tags": { + "feature_type": "bow", + "scaler": "MaxAbsScaler", + "n_gram_range": "(3,5)", + "dataset_version": "multi_eurlex", + "vectorizer_class": "CountVectorizer" + }, + "params": { + "clf__C": "0.0467378670778782", + "clf__penalty": "l2", + "vectorizer__max_features": "50000", + "vectorizer__min_df": "5" + }, + "metrics": { + "accuracy": 0.9997822510403561, + "f1_macro": 0.9998217192528284, + "precision_macro": 0.9998226084060367, + "recall_macro": 0.9998208431704974, + "inference_time_total_s": 11.5672, + "inference_time_ms_per_sample": 0.13993, + "throughput_samples_per_sec": 7146.44 + } +} \ No newline at end of file diff --git a/logistic_regression/multi_eurlex/tfidf_lr_char_ngram_3_5/classification_report.txt b/logistic_regression/multi_eurlex/tfidf_lr_char_ngram_3_5/classification_report.txt new file mode 100644 index 0000000000000000000000000000000000000000..91321ea5b6846fcc74990658fd6b40bf17eafb47 --- /dev/null +++ b/logistic_regression/multi_eurlex/tfidf_lr_char_ngram_3_5/classification_report.txt @@ -0,0 +1,30 @@ + precision recall f1-score support + + ca 0.00 0.00 0.00 0 + da 1.00 1.00 1.00 6478 + de 1.00 1.00 1.00 6514 + el 1.00 1.00 1.00 6499 + en 1.00 1.00 1.00 6537 + es 1.00 1.00 1.00 6263 + fi 1.00 1.00 1.00 5230 + fr 1.00 1.00 1.00 6508 + hr 1.00 1.00 1.00 1557 + it 1.00 1.00 1.00 6499 + ja 0.00 0.00 0.00 0 + ko 0.00 0.00 0.00 0 + lt 1.00 1.00 1.00 3330 + mk 0.00 0.00 0.00 0 + nb 0.00 0.00 0.00 0 + nl 1.00 1.00 1.00 6529 + pl 1.00 1.00 1.00 3317 + pt 1.00 1.00 1.00 6233 + ro 1.00 1.00 1.00 2600 + ru 0.00 0.00 0.00 0 + sl 1.00 1.00 1.00 3313 + sv 1.00 1.00 1.00 5257 + uk 0.00 0.00 0.00 0 + zh 0.00 0.00 0.00 0 + + accuracy 1.00 82664 + macro avg 0.67 0.67 0.67 82664 +weighted avg 1.00 1.00 1.00 82664 diff --git a/logistic_regression/multi_eurlex/tfidf_lr_char_ngram_3_5/cv_results.csv b/logistic_regression/multi_eurlex/tfidf_lr_char_ngram_3_5/cv_results.csv new file mode 100644 index 0000000000000000000000000000000000000000..7309a8d884314a91b305f93da34c87b2e2cd20dc --- /dev/null +++ b/logistic_regression/multi_eurlex/tfidf_lr_char_ngram_3_5/cv_results.csv @@ -0,0 +1,11 @@ +mean_fit_time,std_fit_time,mean_score_time,std_score_time,param_clf__C,param_clf__penalty,param_vectorizer__max_features,param_vectorizer__min_df,param_vectorizer__sublinear_tf,params,split0_test_score,split1_test_score,split2_test_score,mean_test_score,std_test_score,rank_test_score +51.2232453028361,1.3142174686092774,21.26999632517497,1.6978969320646964,0.09915644566638392,l2,50000,1,True,"{'clf__C': 0.09915644566638392, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9996923440006453,0.999572573925271,0.999775889330342,0.9996802690854194,8.344116157741288e-05,5 +50.95029719670614,1.5331219888959293,19.845767895380657,0.22058695426570238,71.77141927992008,l2,50000,1,True,"{'clf__C': 71.77141927992008, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.999848279199895,0.9998155603678858,0.9998449055564081,0.9998362483747297,1.469332247368876e-05,1 +56.47531700134277,2.0276314353741824,20.515960216522217,1.5188026332487372,0.0017707168643537816,l2,50000,3,True,"{'clf__C': 0.0017707168643537816, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': True}",0.9866035290502679,0.9877420796794085,0.9874921338758486,0.987279247535175,0.0004885794574158426,8 +73.0179849465688,1.3606154757052669,20.774610837300617,0.29146226969339684,0.00029152036385288323,l2,50000,5,True,"{'clf__C': 0.00029152036385288323, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.6496726295709538,0.6463484848305601,0.6449876533201166,0.6470029225738768,0.001967818959768285,9 +54.08846044540405,3.811135046304561,21.75122380256653,1.5871673584552195,6.440507553993708,l2,50000,5,True,"{'clf__C': 6.440507553993708, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.9998411050554616,0.9998085160514245,0.9998449055564081,0.9998315088877647,1.6332255285955568e-05,2 +67.77160255114238,3.4047254460362333,18.902366558710735,1.2611757935868972,0.00014610865886287189,l2,50000,2,False,"{'clf__C': 0.00014610865886287189, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.5994429376198614,0.5972865826053974,0.6216152761654814,0.6061149321302467,0.010995695086262238,10 +51.30253863334656,2.7206037266488687,20.6509002049764,0.46571918980480437,456.60548734461145,l2,50000,2,False,"{'clf__C': 456.60548734461145, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.9998556269244205,0.9998010153763707,0.999830207929822,0.999828950076871,2.2312805600302612e-05,3 +51.64417084058126,2.1085992095917288,20.048081477483112,0.6197062548115148,0.0028483918709108036,l2,50000,1,True,"{'clf__C': 0.0028483918709108036, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9887654249446605,0.991687090672797,0.9900873697759416,0.9901799617977997,0.0011945606217701348,7 +49.21649479866028,0.5427624612301145,19.9834201335907,0.4216165302661986,0.027160511446548484,l2,50000,2,True,"{'clf__C': 0.027160511446548484, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': True}",0.9995719670993201,0.9994570946027668,0.9995363490447238,0.9995218035822702,4.801111312038349e-05,6 +48.79159132639567,0.6494571625348741,18.51280887921651,0.6551590521276021,0.28546978577971793,l2,50000,1,True,"{'clf__C': 0.28546978577971793, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9997864891955355,0.9997170527525259,0.9997752511743214,0.9997595977074609,3.0431652085957768e-05,4 diff --git a/logistic_regression/multi_eurlex/tfidf_lr_char_ngram_3_5/run_metadata.json b/logistic_regression/multi_eurlex/tfidf_lr_char_ngram_3_5/run_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..848606d174549edeb69281dc5519a80dd0ea0d91 --- /dev/null +++ b/logistic_regression/multi_eurlex/tfidf_lr_char_ngram_3_5/run_metadata.json @@ -0,0 +1,26 @@ +{ + "run_name": "tfidf_lr_char_ngram_3_5", + "tags": { + "feature_type": "tfidf", + "scaler": "none", + "n_gram_range": "(3,5)", + "dataset_version": "multi_eurlex", + "vectorizer_class": "TfidfVectorizer" + }, + "params": { + "clf__C": "71.77141927992008", + "clf__penalty": "l2", + "vectorizer__max_features": "50000", + "vectorizer__min_df": "1", + "vectorizer__sublinear_tf": "True" + }, + "metrics": { + "accuracy": 0.9997943482047807, + "f1_macro": 0.9998310955808424, + "precision_macro": 0.9998300253353787, + "recall_macro": 0.9998322719298366, + "inference_time_total_s": 11.4756, + "inference_time_ms_per_sample": 0.138822, + "throughput_samples_per_sec": 7203.47 + } +} \ No newline at end of file diff --git a/logistic_regression/multilingual_cc_news/bow_maxabs_lr_char_ngram_3_5/classification_report.txt b/logistic_regression/multilingual_cc_news/bow_maxabs_lr_char_ngram_3_5/classification_report.txt new file mode 100644 index 0000000000000000000000000000000000000000..461174802856ab3321a9154ada82086e6edda0f7 --- /dev/null +++ b/logistic_regression/multilingual_cc_news/bow_maxabs_lr_char_ngram_3_5/classification_report.txt @@ -0,0 +1,30 @@ + precision recall f1-score support + + ca 1.00 1.00 1.00 20015 + da 0.99 0.99 0.99 20013 + de 1.00 1.00 1.00 20008 + el 1.00 1.00 1.00 20050 + en 0.98 1.00 0.99 20005 + es 0.00 0.00 0.00 0 + fi 1.00 1.00 1.00 20084 + fr 0.00 0.00 0.00 0 + hr 1.00 1.00 1.00 19914 + it 0.00 0.00 0.00 0 + ja 0.71 0.98 0.82 20022 + ko 0.99 0.83 0.90 20000 + lt 1.00 0.99 1.00 4950 + mk 1.00 1.00 1.00 18680 + nb 0.99 0.99 0.99 19959 + nl 1.00 1.00 1.00 20009 + pl 1.00 1.00 1.00 20033 + pt 1.00 1.00 1.00 19949 + ro 1.00 1.00 1.00 20113 + ru 1.00 1.00 1.00 20065 + sl 1.00 1.00 1.00 19951 + sv 1.00 1.00 1.00 20044 + uk 1.00 0.99 1.00 20033 + zh 0.97 0.76 0.85 19979 + + accuracy 0.98 403876 + macro avg 0.86 0.85 0.85 403876 +weighted avg 0.98 0.98 0.98 403876 diff --git a/logistic_regression/multilingual_cc_news/bow_maxabs_lr_char_ngram_3_5/cv_results.csv b/logistic_regression/multilingual_cc_news/bow_maxabs_lr_char_ngram_3_5/cv_results.csv new file mode 100644 index 0000000000000000000000000000000000000000..e335d8bed1f868e81d270ba8644dab5ac0bcefec --- /dev/null +++ b/logistic_regression/multilingual_cc_news/bow_maxabs_lr_char_ngram_3_5/cv_results.csv @@ -0,0 +1,11 @@ +mean_fit_time,std_fit_time,mean_score_time,std_score_time,param_clf__C,param_clf__penalty,param_vectorizer__max_features,param_vectorizer__min_df,params,split0_test_score,split1_test_score,split2_test_score,mean_test_score,std_test_score,rank_test_score +402.9399371147156,8.154657269017594,95.20252974828084,2.0797345240090186,0.09915644566638392,l2,50000,1,"{'clf__C': 0.09915644566638392, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1}",0.9752277520546296,0.974338503210626,0.9750254403671778,0.9748638985441445,0.00038058086927060075,5 +380.97084434827167,2.096794290577095,90.9351966381073,0.8475863264935782,0.0029341230215132346,l2,50000,5,"{'clf__C': 0.0029341230215132346, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9656756294108784,0.9646967887735727,0.9656415967419004,0.9653380049754504,0.00045362114795086784,7 +403.4427442550659,11.427001607226778,93.5841719309489,2.2056415233593736,6.155564318973006,l2,50000,3,"{'clf__C': 6.155564318973006, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.9764374935614732,0.9756131467393677,0.9761156109011319,0.9760554170673243,0.0003392190973399652,3 +402.5956726074219,13.617858289354421,97.36782177289327,5.511217277327732,0.3686905640846153,l2,50000,3,"{'clf__C': 0.3686905640846153, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.9759331912035696,0.9753399557527218,0.9757030313980376,0.9756587261181097,0.000244205232550765,4 +393.6945722103119,24.312571724344345,95.80627179145813,2.3690566482175197,0.00029152036385288323,l2,50000,5,"{'clf__C': 0.00029152036385288323, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9522448367266754,0.951290233113672,0.9525833370485026,0.95203946896295,0.0005475164444116591,8 +387.80599387486774,22.64524855130065,93.43839979171753,3.9156075612376933,0.0467378670778782,l2,50000,5,"{'clf__C': 0.0467378670778782, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9744132497491936,0.9738388423746759,0.974262851645611,0.9741716479231601,0.00024320710956817393,6 +386.3445611000061,7.549293275136315,90.40917595227559,3.72332399859066,46.19347374377369,l2,50000,2,"{'clf__C': 46.19347374377369, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2}",0.9764455705928385,0.9756172821037771,0.9761210137533212,0.9760612888166457,0.00034077436946226695,2 +361.68538037935895,13.157352840529368,91.73455119132996,2.695762613364933,0.00028267840503514715,l2,50000,5,"{'clf__C': 0.00028267840503514715, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9519740282093876,0.9510311614518805,0.952325945638046,0.9517770450997713,0.0005466371625930101,9 +394.5825621287028,4.753316303726586,88.7125723361969,3.3864155009464953,456.60548734461145,l2,50000,2,"{'clf__C': 456.60548734461145, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2}",0.9764473401367928,0.9756170092230521,0.9761480404733097,0.9760707966110514,0.00034335338187820946,1 +387.46650465329486,6.832365252854412,87.48951387405396,3.2864414083328612,0.00010144487859320231,l2,50000,5,"{'clf__C': 0.00010144487859320231, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.8945935376189939,0.905198488874407,0.9093624319141937,0.9030514861358648,0.006217570546184826,10 diff --git a/logistic_regression/multilingual_cc_news/bow_maxabs_lr_char_ngram_3_5/run_metadata.json b/logistic_regression/multilingual_cc_news/bow_maxabs_lr_char_ngram_3_5/run_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..edc5d89db116babaa430d65b308bfbd1d78a248a --- /dev/null +++ b/logistic_regression/multilingual_cc_news/bow_maxabs_lr_char_ngram_3_5/run_metadata.json @@ -0,0 +1,25 @@ +{ + "run_name": "bow_maxabs_lr_char_ngram_3_5", + "tags": { + "feature_type": "bow", + "scaler": "MaxAbsScaler", + "n_gram_range": "(3,5)", + "dataset_version": "multilingual_cc_news", + "vectorizer_class": "CountVectorizer" + }, + "params": { + "clf__C": "456.60548734461145", + "clf__penalty": "l2", + "vectorizer__max_features": "50000", + "vectorizer__min_df": "2" + }, + "metrics": { + "accuracy": 0.9757425546454852, + "f1_macro": 0.9769901432987629, + "precision_macro": 0.9815579981555338, + "recall_macro": 0.9763925161914471, + "inference_time_total_s": 54.8261, + "inference_time_ms_per_sample": 0.13575, + "throughput_samples_per_sec": 7366.5 + } +} \ No newline at end of file diff --git a/logistic_regression/multilingual_cc_news/tfidf_lr_char_ngram_3_5/classification_report.txt b/logistic_regression/multilingual_cc_news/tfidf_lr_char_ngram_3_5/classification_report.txt new file mode 100644 index 0000000000000000000000000000000000000000..ae080096c17e792a5465811fc6c88e95bd936c0b --- /dev/null +++ b/logistic_regression/multilingual_cc_news/tfidf_lr_char_ngram_3_5/classification_report.txt @@ -0,0 +1,30 @@ + precision recall f1-score support + + ca 1.00 1.00 1.00 20015 + da 0.99 0.99 0.99 20013 + de 1.00 1.00 1.00 20008 + el 1.00 1.00 1.00 20050 + en 0.98 1.00 0.99 20005 + es 0.00 0.00 0.00 0 + fi 1.00 1.00 1.00 20084 + fr 0.00 0.00 0.00 0 + hr 1.00 1.00 1.00 19914 + it 0.00 0.00 0.00 0 + ja 0.76 0.96 0.85 20022 + ko 0.98 0.87 0.92 20000 + lt 1.00 0.99 1.00 4950 + mk 1.00 1.00 1.00 18680 + nb 0.99 0.99 0.99 19959 + nl 1.00 1.00 1.00 20009 + pl 1.00 1.00 1.00 20033 + pt 1.00 1.00 1.00 19949 + ro 1.00 1.00 1.00 20113 + ru 1.00 1.00 1.00 20065 + sl 1.00 1.00 1.00 19951 + sv 1.00 1.00 1.00 20044 + uk 1.00 0.99 1.00 20033 + zh 0.95 0.81 0.87 19979 + + accuracy 0.98 403876 + macro avg 0.86 0.86 0.86 403876 +weighted avg 0.98 0.98 0.98 403876 diff --git a/logistic_regression/multilingual_cc_news/tfidf_lr_char_ngram_3_5/cv_results.csv b/logistic_regression/multilingual_cc_news/tfidf_lr_char_ngram_3_5/cv_results.csv new file mode 100644 index 0000000000000000000000000000000000000000..cfcb4728de26dcda05251d5f58d7ffcb99d611b9 --- /dev/null +++ b/logistic_regression/multilingual_cc_news/tfidf_lr_char_ngram_3_5/cv_results.csv @@ -0,0 +1,11 @@ +mean_fit_time,std_fit_time,mean_score_time,std_score_time,param_clf__C,param_clf__penalty,param_vectorizer__max_features,param_vectorizer__min_df,param_vectorizer__sublinear_tf,params,split0_test_score,split1_test_score,split2_test_score,mean_test_score,std_test_score,rank_test_score +387.14908870061237,10.42996720885376,103.22419436772664,4.436658127357272,0.09915644566638392,l2,50000,1,True,"{'clf__C': 0.09915644566638392, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9768182861408593,0.9767568931960271,0.9765458863566485,0.976707021897845,0.0001166641058660818,5 +391.8255871136983,15.368568481786543,100.51205062866211,3.220759423950863,71.77141927992008,l2,50000,1,True,"{'clf__C': 71.77141927992008, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9797900944731284,0.9794235244038101,0.9794082901409027,0.9795406363392803,0.00017650314652298794,2 +446.27149240175885,29.054544895738466,95.0022524992625,2.608151464896373,0.0017707168643537816,l2,50000,3,True,"{'clf__C': 0.0017707168643537816, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': True}",0.9190900623481623,0.9173214284053496,0.9409196894876505,0.9257770600803874,0.01073177324677203,8 +452.4179784456889,29.159745115837524,93.67036859194438,2.7291077562187,0.00029152036385288323,l2,50000,5,True,"{'clf__C': 0.00029152036385288323, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.9120915218384804,0.9121332298416716,0.8050393995954123,0.8764213837585214,0.05047468792828181,10 +424.96267716089886,7.284722268470122,98.61706328392029,4.555820736147861,6.440507553993708,l2,50000,5,True,"{'clf__C': 6.440507553993708, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.9800145518273617,0.9797307989053394,0.9797799799488286,0.9798417768938433,0.00012380919997832622,1 +463.7910005251567,26.796591656182194,89.84521587689717,4.76783496832902,0.00014610865886287189,l2,50000,2,False,"{'clf__C': 0.00014610865886287189, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.9106661762467955,0.9106675015295603,0.9107332030472706,0.910688960274542,3.128904278526697e-05,9 +373.6284962495168,14.232401492412562,96.45695861180623,5.697114629543932,456.60548734461145,l2,50000,2,False,"{'clf__C': 456.60548734461145, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.9796566744404435,0.9792835403796589,0.9792844693383306,0.979408228052811,0.0001756785348048597,3 +393.46992659568787,23.09630129683921,87.79749663670857,1.0754166944404593,0.0028483918709108036,l2,50000,1,True,"{'clf__C': 0.0028483918709108036, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9586044191820471,0.9580164952150932,0.9589165200264395,0.9585124781411932,0.0003731407522679695,7 +380.7316460609436,6.8812991032022515,88.0167322953542,1.2114695598564937,0.027160511446548484,l2,50000,2,True,"{'clf__C': 0.027160511446548484, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': True}",0.9742560600989444,0.9742945797824765,0.9739362286516305,0.9741622895110171,0.00016062082806993106,6 +392.1845534642537,15.298243699958181,84.93731991449992,8.203447659422412,0.28546978577971793,l2,50000,1,True,"{'clf__C': 0.28546978577971793, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9784690777439445,0.9782639037336438,0.9780913210054424,0.9782747674943435,0.00015440974568412197,4 diff --git a/logistic_regression/multilingual_cc_news/tfidf_lr_char_ngram_3_5/run_metadata.json b/logistic_regression/multilingual_cc_news/tfidf_lr_char_ngram_3_5/run_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..4a496b24436547a5ba74717a9815fc6fb98f6ff2 --- /dev/null +++ b/logistic_regression/multilingual_cc_news/tfidf_lr_char_ngram_3_5/run_metadata.json @@ -0,0 +1,26 @@ +{ + "run_name": "tfidf_lr_char_ngram_3_5", + "tags": { + "feature_type": "tfidf", + "scaler": "none", + "n_gram_range": "(3,5)", + "dataset_version": "multilingual_cc_news", + "vectorizer_class": "TfidfVectorizer" + }, + "params": { + "clf__C": "6.440507553993708", + "clf__penalty": "l2", + "vectorizer__max_features": "50000", + "vectorizer__min_df": "5", + "vectorizer__sublinear_tf": "True" + }, + "metrics": { + "accuracy": 0.9795209420713288, + "f1_macro": 0.9804527733547908, + "precision_macro": 0.9827989401352565, + "recall_macro": 0.9800439981432557, + "inference_time_total_s": 55.1468, + "inference_time_ms_per_sample": 0.136544, + "throughput_samples_per_sec": 7323.66 + } +} \ No newline at end of file diff --git a/logistic_regression/multilingual_toxicity_dataset/bow_maxabs_lr_char_ngram_3_5/classification_report.txt b/logistic_regression/multilingual_toxicity_dataset/bow_maxabs_lr_char_ngram_3_5/classification_report.txt new file mode 100644 index 0000000000000000000000000000000000000000..b24ed005d09ef416cf4fcd2a32b1f943e07663b4 --- /dev/null +++ b/logistic_regression/multilingual_toxicity_dataset/bow_maxabs_lr_char_ngram_3_5/classification_report.txt @@ -0,0 +1,30 @@ + precision recall f1-score support + + ca 0.00 0.00 0.00 0 + da 0.00 0.00 0.00 0 + de 1.00 1.00 1.00 506 + el 0.00 0.00 0.00 0 + en 0.99 1.00 0.99 478 + es 1.00 0.99 0.99 495 + fi 0.00 0.00 0.00 0 + fr 1.00 0.99 0.99 472 + hr 0.00 0.00 0.00 0 + it 1.00 1.00 1.00 478 + ja 1.00 0.79 0.88 493 + ko 0.00 0.00 0.00 0 + lt 0.00 0.00 0.00 0 + mk 0.00 0.00 0.00 0 + nb 0.00 0.00 0.00 0 + nl 0.00 0.00 0.00 0 + pl 0.00 0.00 0.00 0 + pt 0.00 0.00 0.00 0 + ro 0.00 0.00 0.00 0 + ru 1.00 0.99 0.99 492 + sl 0.00 0.00 0.00 0 + sv 0.00 0.00 0.00 0 + uk 0.99 0.99 0.99 455 + zh 0.79 1.00 0.89 455 + + accuracy 0.97 4324 + macro avg 0.37 0.36 0.36 4324 +weighted avg 0.98 0.97 0.97 4324 diff --git a/logistic_regression/multilingual_toxicity_dataset/bow_maxabs_lr_char_ngram_3_5/cv_results.csv b/logistic_regression/multilingual_toxicity_dataset/bow_maxabs_lr_char_ngram_3_5/cv_results.csv new file mode 100644 index 0000000000000000000000000000000000000000..df61360c0ecf98c7e5e88eec484b06a5bb333718 --- /dev/null +++ b/logistic_regression/multilingual_toxicity_dataset/bow_maxabs_lr_char_ngram_3_5/cv_results.csv @@ -0,0 +1,11 @@ +mean_fit_time,std_fit_time,mean_score_time,std_score_time,param_clf__C,param_clf__penalty,param_vectorizer__max_features,param_vectorizer__min_df,params,split0_test_score,split1_test_score,split2_test_score,mean_test_score,std_test_score,rank_test_score +4.040556033452352,0.2035284762584747,0.6972482204437256,0.02066138439134423,0.09915644566638392,l2,50000,1,"{'clf__C': 0.09915644566638392, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1}",0.9653392188400132,0.963977108186834,0.9597028752035628,0.96300640074347,0.002401221508939484,5 +4.047645092010498,0.08398335122140148,0.7023676236470541,0.014108892106838362,0.0029341230215132346,l2,50000,5,"{'clf__C': 0.0029341230215132346, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.8537109050099432,0.8494223545046622,0.8865347645938498,0.8632226747028184,0.01657685269031758,7 +4.27047594388326,0.045011945531176406,0.7021175225575765,0.021968218840048216,6.155564318973006,l2,50000,3,"{'clf__C': 6.155564318973006, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.9682132389520426,0.9675306246864641,0.9632948604605684,0.9663462413663583,0.002175574197471764,1 +4.047166268030803,0.06535130427514227,0.7372770309448242,0.036618304507032066,0.3686905640846153,l2,50000,3,"{'clf__C': 0.3686905640846153, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.9674354523313442,0.9664781486266119,0.9619639468590014,0.9652925159389859,0.0023858802269385725,4 +4.356929937998454,0.10613291928686613,0.7481387456258138,0.02214152640693379,0.00029152036385288323,l2,50000,5,"{'clf__C': 0.00029152036385288323, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.8166368388753926,0.819233045626842,0.8179227976649744,0.8179308940557363,0.001059912429629702,8 +3.876397450764974,0.13087851195357808,0.726686159769694,0.03464620132678077,0.0467378670778782,l2,50000,5,"{'clf__C': 0.0467378670778782, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9644260968851864,0.9626887984958667,0.9568466707398555,0.9613205220403028,0.003242022055988025,6 +3.8898606300354004,0.03739246875719135,0.6777958075205485,0.0030575897224061487,46.19347374377369,l2,50000,2,"{'clf__C': 46.19347374377369, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2}",0.9683916700693344,0.9683831894580818,0.9618557690445331,0.966210209523983,0.0030790563377974894,2 +4.0603954792022705,0.06339875502603774,0.6255292892456055,0.004404361708554165,0.00028267840503514715,l2,50000,5,"{'clf__C': 0.00028267840503514715, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.815543995896894,0.81805974836216,0.8154345079182215,0.8163460840590918,0.001212567774621574,9 +3.878629207611084,0.0632108031301941,0.6451913515726725,0.008300134344414923,456.60548734461145,l2,50000,2,"{'clf__C': 456.60548734461145, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2}",0.9683916700693344,0.9683831894580818,0.9618557690445331,0.966210209523983,0.0030790563377974894,2 +4.218158880869548,0.241054313075401,0.5932675202687582,0.02689271267763404,0.00010144487859320231,l2,50000,5,"{'clf__C': 0.00010144487859320231, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.7313444062530139,0.7376569517327378,0.7344403744996182,0.7344805774951233,0.0025772426892619747,10 diff --git a/logistic_regression/multilingual_toxicity_dataset/bow_maxabs_lr_char_ngram_3_5/run_metadata.json b/logistic_regression/multilingual_toxicity_dataset/bow_maxabs_lr_char_ngram_3_5/run_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..279f360bcbd939464c17e439a2c4796d4373c120 --- /dev/null +++ b/logistic_regression/multilingual_toxicity_dataset/bow_maxabs_lr_char_ngram_3_5/run_metadata.json @@ -0,0 +1,25 @@ +{ + "run_name": "bow_maxabs_lr_char_ngram_3_5", + "tags": { + "feature_type": "bow", + "scaler": "MaxAbsScaler", + "n_gram_range": "(3,5)", + "dataset_version": "multilingual_toxicity_dataset", + "vectorizer_class": "CountVectorizer" + }, + "params": { + "clf__C": "6.155564318973006", + "clf__penalty": "l2", + "vectorizer__max_features": "50000", + "vectorizer__min_df": "3" + }, + "metrics": { + "accuracy": 0.9699352451433858, + "f1_macro": 0.9697068633400848, + "precision_macro": 0.9742811759448592, + "recall_macro": 0.9705447736079997, + "inference_time_total_s": 0.3653, + "inference_time_ms_per_sample": 0.084493, + "throughput_samples_per_sec": 11835.32 + } +} \ No newline at end of file diff --git a/logistic_regression/multilingual_toxicity_dataset/tfidf_lr_char_ngram_3_5/classification_report.txt b/logistic_regression/multilingual_toxicity_dataset/tfidf_lr_char_ngram_3_5/classification_report.txt new file mode 100644 index 0000000000000000000000000000000000000000..d9aa34155fb6b080d3219896cc7b762cf51de67c --- /dev/null +++ b/logistic_regression/multilingual_toxicity_dataset/tfidf_lr_char_ngram_3_5/classification_report.txt @@ -0,0 +1,30 @@ + precision recall f1-score support + + ca 0.00 0.00 0.00 0 + da 0.00 0.00 0.00 0 + de 1.00 1.00 1.00 506 + el 0.00 0.00 0.00 0 + en 1.00 1.00 1.00 478 + es 1.00 0.99 0.99 495 + fi 0.00 0.00 0.00 0 + fr 1.00 0.99 0.99 472 + hr 0.00 0.00 0.00 0 + it 0.99 1.00 1.00 478 + ja 1.00 0.92 0.96 493 + ko 0.00 0.00 0.00 0 + lt 0.00 0.00 0.00 0 + mk 0.00 0.00 0.00 0 + nb 0.00 0.00 0.00 0 + nl 0.00 0.00 0.00 0 + pl 0.00 0.00 0.00 0 + pt 0.00 0.00 0.00 0 + ro 0.00 0.00 0.00 0 + ru 0.99 0.99 0.99 492 + sl 0.00 0.00 0.00 0 + sv 0.00 0.00 0.00 0 + uk 1.00 0.99 0.99 455 + zh 0.90 1.00 0.95 455 + + accuracy 0.99 4324 + macro avg 0.37 0.37 0.37 4324 +weighted avg 0.99 0.99 0.99 4324 diff --git a/logistic_regression/multilingual_toxicity_dataset/tfidf_lr_char_ngram_3_5/cv_results.csv b/logistic_regression/multilingual_toxicity_dataset/tfidf_lr_char_ngram_3_5/cv_results.csv new file mode 100644 index 0000000000000000000000000000000000000000..c711327394291c07753b1a9c4f0e2b1c7197566d --- /dev/null +++ b/logistic_regression/multilingual_toxicity_dataset/tfidf_lr_char_ngram_3_5/cv_results.csv @@ -0,0 +1,11 @@ +mean_fit_time,std_fit_time,mean_score_time,std_score_time,param_clf__C,param_clf__penalty,param_vectorizer__max_features,param_vectorizer__min_df,param_vectorizer__sublinear_tf,params,split0_test_score,split1_test_score,split2_test_score,mean_test_score,std_test_score,rank_test_score +3.9588398138682046,0.20348158738211433,0.7723536491394043,0.0025173423011794578,0.09915644566638392,l2,50000,1,True,"{'clf__C': 0.09915644566638392, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9845364014625712,0.9854455679898189,0.985105666152761,0.9850292118683837,0.0003750821125803859,1 +3.9503840605417886,0.024054342345522246,0.7935018539428711,0.01792406073588315,71.77141927992008,l2,50000,1,True,"{'clf__C': 71.77141927992008, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9831628738697789,0.9842119286232374,0.9819523383582642,0.9831090469504268,0.0009232587374171034,2 +4.3404280344645185,0.08676557819811387,0.7395785649617513,0.021064106308070252,0.0017707168643537816,l2,50000,3,True,"{'clf__C': 0.0017707168643537816, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': True}",0.5139475473905333,0.5726503036729831,0.5758080595813414,0.554135303548286,0.028446261199443323,8 +4.639631907145183,0.04971859206642914,0.7199817498524984,0.028834425139493622,0.00029152036385288323,l2,50000,5,True,"{'clf__C': 0.00029152036385288323, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.034302515583123375,0.025982239501097307,0.023295542786146917,0.027860099290122533,0.004685661147143366,9 +4.061478853225708,0.06215993517270243,0.7521119117736816,0.02351433838498911,6.440507553993708,l2,50000,5,True,"{'clf__C': 6.440507553993708, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.9836907160449173,0.9838789936753068,0.9802041985999305,0.9825913027733848,0.0016896867298839486,4 +4.818209648132324,0.29378475505492335,0.6650259494781494,0.049656153306557205,0.00014610865886287189,l2,50000,2,False,"{'clf__C': 0.00014610865886287189, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.02329192546583851,0.02329192546583851,0.023295542786146917,0.023293131239274647,1.7052211465316545e-06,10 +3.685816685358683,0.05627530678108159,0.7520771821339926,0.018130198468875022,456.60548734461145,l2,50000,2,False,"{'clf__C': 456.60548734461145, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.9821249321526742,0.9826325484874301,0.980029413093332,0.9815956312444788,0.0011267055393384378,5 +4.131646076838176,0.05632133127822176,0.6499122778574625,0.005002638936394404,0.0028483918709108036,l2,50000,1,True,"{'clf__C': 0.0028483918709108036, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.6541855665753074,0.6745892232208965,0.6813744904102502,0.6700497600688181,0.011554636561640236,7 +4.031825304031372,0.01084199153967617,0.6525913874308268,0.008953133516846668,0.027160511446548484,l2,50000,2,True,"{'clf__C': 0.027160511446548484, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': True}",0.8896291380999679,0.9752940758171058,0.890161144270522,0.9183614527291986,0.04025802972818929,6 +3.832550843556722,0.04273312072344384,0.6429457664489746,0.0124096852756637,0.28546978577971793,l2,50000,1,True,"{'clf__C': 0.28546978577971793, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9835010930237785,0.983022193578694,0.9812775009095039,0.9826002625039921,0.0009555486544442522,3 diff --git a/logistic_regression/multilingual_toxicity_dataset/tfidf_lr_char_ngram_3_5/run_metadata.json b/logistic_regression/multilingual_toxicity_dataset/tfidf_lr_char_ngram_3_5/run_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..8b299c2fb5f3a5708b7615fd450211a72ff94442 --- /dev/null +++ b/logistic_regression/multilingual_toxicity_dataset/tfidf_lr_char_ngram_3_5/run_metadata.json @@ -0,0 +1,26 @@ +{ + "run_name": "tfidf_lr_char_ngram_3_5", + "tags": { + "feature_type": "tfidf", + "scaler": "none", + "n_gram_range": "(3,5)", + "dataset_version": "multilingual_toxicity_dataset", + "vectorizer_class": "TfidfVectorizer" + }, + "params": { + "clf__C": "0.09915644566638392", + "clf__penalty": "l2", + "vectorizer__max_features": "50000", + "vectorizer__min_df": "1", + "vectorizer__sublinear_tf": "True" + }, + "metrics": { + "accuracy": 0.9854301572617946, + "f1_macro": 0.9853149526463483, + "precision_macro": 0.9859826911878914, + "recall_macro": 0.9856368834317932, + "inference_time_total_s": 0.3755, + "inference_time_ms_per_sample": 0.086836, + "throughput_samples_per_sec": 11515.93 + } +} \ No newline at end of file diff --git a/logistic_regression/stsb_multi_mt/bow_maxabs_lr_char_ngram_3_5/classification_report.txt b/logistic_regression/stsb_multi_mt/bow_maxabs_lr_char_ngram_3_5/classification_report.txt new file mode 100644 index 0000000000000000000000000000000000000000..7d885906592aaaacfd419ec1743888681e631472 --- /dev/null +++ b/logistic_regression/stsb_multi_mt/bow_maxabs_lr_char_ngram_3_5/classification_report.txt @@ -0,0 +1,30 @@ + precision recall f1-score support + + ca 0.00 0.00 0.00 0 + da 0.00 0.00 0.00 0 + de 0.99 0.99 0.99 783 + el 0.00 0.00 0.00 0 + en 0.98 0.99 0.99 738 + es 0.99 0.99 0.99 818 + fi 0.00 0.00 0.00 0 + fr 1.00 0.99 1.00 784 + hr 0.00 0.00 0.00 0 + it 1.00 0.99 0.99 820 + ja 0.00 0.00 0.00 0 + ko 0.00 0.00 0.00 0 + lt 0.00 0.00 0.00 0 + mk 0.00 0.00 0.00 0 + nb 0.00 0.00 0.00 0 + nl 1.00 0.99 0.99 766 + pl 1.00 0.99 1.00 733 + pt 0.99 0.99 0.99 801 + ro 0.00 0.00 0.00 0 + ru 1.00 1.00 1.00 721 + sl 0.00 0.00 0.00 0 + sv 0.00 0.00 0.00 0 + uk 0.00 0.00 0.00 0 + zh 0.98 1.00 0.99 737 + + accuracy 0.99 7701 + macro avg 0.41 0.41 0.41 7701 +weighted avg 0.99 0.99 0.99 7701 diff --git a/logistic_regression/stsb_multi_mt/bow_maxabs_lr_char_ngram_3_5/cv_results.csv b/logistic_regression/stsb_multi_mt/bow_maxabs_lr_char_ngram_3_5/cv_results.csv new file mode 100644 index 0000000000000000000000000000000000000000..ecbc03d9490861b4c3ceefc0719ba6d05705f3ff --- /dev/null +++ b/logistic_regression/stsb_multi_mt/bow_maxabs_lr_char_ngram_3_5/cv_results.csv @@ -0,0 +1,11 @@ +mean_fit_time,std_fit_time,mean_score_time,std_score_time,param_clf__C,param_clf__penalty,param_vectorizer__max_features,param_vectorizer__min_df,params,split0_test_score,split1_test_score,split2_test_score,mean_test_score,std_test_score,rank_test_score +4.716332038243611,0.033669166650861865,1.0893371105194092,0.009346588189355357,0.09915644566638392,l2,50000,1,"{'clf__C': 0.09915644566638392, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1}",0.9882940669177043,0.990650339156544,0.9866336101764543,0.9885260054169009,0.0016480037470487697,5 +4.699404398600261,0.06490197621995386,1.092738151550293,0.012109625807892047,0.0029341230215132346,l2,50000,5,"{'clf__C': 0.0029341230215132346, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9778427787834453,0.9795172556595476,0.9773029116942148,0.9782209820457358,0.0009427293991055687,9 +4.706962903340657,0.09118766077772919,1.083038568496704,0.0012596301500125313,6.155564318973006,l2,50000,3,"{'clf__C': 6.155564318973006, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.988717093239116,0.9922552399519413,0.9880805642187355,0.9896842991365976,0.001836408597497985,3 +4.756442864735921,0.03578817266607296,1.0879961649576824,0.016369438873409463,0.3686905640846153,l2,50000,3,"{'clf__C': 0.3686905640846153, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.9886118944412576,0.9919450286841016,0.9874996325705132,0.9893521852319574,0.0018888108239088757,4 +5.062972068786621,0.04263837250513081,1.0298703511555989,0.009960285119840344,0.00029152036385288323,l2,50000,5,"{'clf__C': 0.00029152036385288323, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9889564112322283,0.989344903242418,0.9864171821882393,0.9882394988876285,0.0012982963516727144,6 +4.678500413894653,0.04341698209804257,1.0894962151845295,0.016198095062798727,0.0467378670778782,l2,50000,5,"{'clf__C': 0.0467378670778782, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9869287782343079,0.9900604230513592,0.9859301073479683,0.9876397695445451,0.0017595469937541882,8 +4.742682456970215,0.15976416248502323,1.0770845413208008,0.04140823436453012,46.19347374377369,l2,50000,2,"{'clf__C': 46.19347374377369, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2}",0.988815118320473,0.9922625845079416,0.9882871806297044,0.9897882944860396,0.0017628126929608897,2 +5.043879667917888,0.06514892994177782,1.0084983507792156,0.012649626871591263,0.00028267840503514715,l2,50000,5,"{'clf__C': 0.00028267840503514715, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9889582984604631,0.9890544746568818,0.9864308199381103,0.9881478643518183,0.0012147684564486633,7 +4.5661946932474775,0.16129829207674537,1.0662109057108562,0.018104495066729287,456.60548734461145,l2,50000,2,"{'clf__C': 456.60548734461145, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2}",0.988815118320473,0.9922625845079416,0.9882906569719075,0.989789453266774,0.001761826425155435,1 +5.152834971745809,0.087561310196268,0.9657223224639893,0.024119761852694342,0.00010144487859320231,l2,50000,5,"{'clf__C': 0.00010144487859320231, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.8462281697436292,0.8400275040062753,0.8400185952794761,0.8420914230097937,0.0029251239285744733,10 diff --git a/logistic_regression/stsb_multi_mt/bow_maxabs_lr_char_ngram_3_5/run_metadata.json b/logistic_regression/stsb_multi_mt/bow_maxabs_lr_char_ngram_3_5/run_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..138d0eb7e984f3367e078836e50e82106dff36fa --- /dev/null +++ b/logistic_regression/stsb_multi_mt/bow_maxabs_lr_char_ngram_3_5/run_metadata.json @@ -0,0 +1,25 @@ +{ + "run_name": "bow_maxabs_lr_char_ngram_3_5", + "tags": { + "feature_type": "bow", + "scaler": "MaxAbsScaler", + "n_gram_range": "(3,5)", + "dataset_version": "stsb_multi_mt", + "vectorizer_class": "CountVectorizer" + }, + "params": { + "clf__C": "456.60548734461145", + "clf__penalty": "l2", + "vectorizer__max_features": "50000", + "vectorizer__min_df": "2" + }, + "metrics": { + "accuracy": 0.9920789507856123, + "f1_macro": 0.9921168431288381, + "precision_macro": 0.9921252329617325, + "recall_macro": 0.9921589905758508, + "inference_time_total_s": 0.5729, + "inference_time_ms_per_sample": 0.074399, + "throughput_samples_per_sec": 13440.99 + } +} \ No newline at end of file diff --git a/logistic_regression/stsb_multi_mt/tfidf_lr_char_ngram_3_5/classification_report.txt b/logistic_regression/stsb_multi_mt/tfidf_lr_char_ngram_3_5/classification_report.txt new file mode 100644 index 0000000000000000000000000000000000000000..8d0aadd944f69920fc7ed4825ff95db5989c8105 --- /dev/null +++ b/logistic_regression/stsb_multi_mt/tfidf_lr_char_ngram_3_5/classification_report.txt @@ -0,0 +1,30 @@ + precision recall f1-score support + + ca 0.00 0.00 0.00 0 + da 0.00 0.00 0.00 0 + de 1.00 0.99 1.00 783 + el 0.00 0.00 0.00 0 + en 0.98 1.00 0.99 738 + es 1.00 0.99 1.00 818 + fi 0.00 0.00 0.00 0 + fr 1.00 0.99 1.00 784 + hr 0.00 0.00 0.00 0 + it 1.00 1.00 1.00 820 + ja 0.00 0.00 0.00 0 + ko 0.00 0.00 0.00 0 + lt 0.00 0.00 0.00 0 + mk 0.00 0.00 0.00 0 + nb 0.00 0.00 0.00 0 + nl 1.00 0.99 0.99 766 + pl 1.00 0.99 1.00 733 + pt 1.00 1.00 1.00 801 + ro 0.00 0.00 0.00 0 + ru 1.00 1.00 1.00 721 + sl 0.00 0.00 0.00 0 + sv 0.00 0.00 0.00 0 + uk 0.00 0.00 0.00 0 + zh 0.99 1.00 1.00 737 + + accuracy 1.00 7701 + macro avg 0.41 0.41 0.41 7701 +weighted avg 1.00 1.00 1.00 7701 diff --git a/logistic_regression/stsb_multi_mt/tfidf_lr_char_ngram_3_5/cv_results.csv b/logistic_regression/stsb_multi_mt/tfidf_lr_char_ngram_3_5/cv_results.csv new file mode 100644 index 0000000000000000000000000000000000000000..99188c2f9edda9332f6ecc0d80005563d8cf71bb --- /dev/null +++ b/logistic_regression/stsb_multi_mt/tfidf_lr_char_ngram_3_5/cv_results.csv @@ -0,0 +1,11 @@ +mean_fit_time,std_fit_time,mean_score_time,std_score_time,param_clf__C,param_clf__penalty,param_vectorizer__max_features,param_vectorizer__min_df,param_vectorizer__sublinear_tf,params,split0_test_score,split1_test_score,split2_test_score,mean_test_score,std_test_score,rank_test_score +4.862948735555013,0.02713757947858657,1.2074730396270752,0.01175361660279572,0.09915644566638392,l2,50000,1,True,"{'clf__C': 0.09915644566638392, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9909309928718406,0.9894025958880288,0.9735626007590467,0.984632063172972,0.007852122767549808,6 +4.342029333114624,0.08301768099923795,1.1870969136555989,0.0027877095213319826,71.77141927992008,l2,50000,1,True,"{'clf__C': 71.77141927992008, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9909543932315676,0.992202978478064,0.9902507982659593,0.9911360566585303,0.0008072600141446394,2 +5.297547499338786,0.10167505193669585,1.123515526453654,0.024829901913426686,0.0017707168643537816,l2,50000,3,True,"{'clf__C': 0.0017707168643537816, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': True}",0.6285875158014022,0.573677130341143,0.5828085546993258,0.5950244002806236,0.024023707322811297,8 +5.70340100924174,0.060631748756073245,1.1091025670369465,0.04083488103544944,0.00029152036385288323,l2,50000,5,True,"{'clf__C': 0.00029152036385288323, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.08293930192624308,0.09495161159647861,0.10702171359856576,0.09497087570709582,0.009831612832025554,10 +4.595508098602295,0.18645010041184368,1.192524512608846,0.008980676345992374,6.440507553993708,l2,50000,5,True,"{'clf__C': 6.440507553993708, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.9924952584968227,0.9931932200866154,0.9901439770111983,0.9919441518648787,0.0013044180626047331,1 +5.940989335378011,0.2829331074385385,1.0091668764750164,0.021744272414171324,0.00014610865886287189,l2,50000,2,False,"{'clf__C': 0.00014610865886287189, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.08253890703815472,0.10650197930984706,0.10001139294506578,0.09635075976435585,0.010119531762467188,9 +4.284287134806315,0.06012390558164843,1.2297604878743489,0.06559458291513869,456.60548734461145,l2,50000,2,False,"{'clf__C': 456.60548734461145, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.9903579756129239,0.9919081615067021,0.9900604843956573,0.9907755405050945,0.0008100403307036753,4 +4.994303385416667,0.06684144663787477,0.9738579591115316,0.010950182012580892,0.0028483918709108036,l2,50000,1,True,"{'clf__C': 0.0028483918709108036, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.8306698932575582,0.8029874551025236,0.8079964911188853,0.8138846131596557,0.012043859609142046,7 +4.858863830566406,0.14325703620079885,1.0002411206563313,0.03757748280223919,0.027160511446548484,l2,50000,2,True,"{'clf__C': 0.027160511446548484, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': True}",0.9892428099338192,0.9889992440808235,0.9889280148588308,0.9890566896244911,0.00013478124912785408,5 +4.592370271682739,0.03903599807242429,0.9755910237630209,0.02206236451445047,0.28546978577971793,l2,50000,1,True,"{'clf__C': 0.28546978577971793, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9909267746319264,0.992690185367391,0.9897731482356809,0.9911300360783327,0.0011995173525604025,3 diff --git a/logistic_regression/stsb_multi_mt/tfidf_lr_char_ngram_3_5/run_metadata.json b/logistic_regression/stsb_multi_mt/tfidf_lr_char_ngram_3_5/run_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..9f25fddbea45aa11f11b5d1341f6c93aa2322c23 --- /dev/null +++ b/logistic_regression/stsb_multi_mt/tfidf_lr_char_ngram_3_5/run_metadata.json @@ -0,0 +1,26 @@ +{ + "run_name": "tfidf_lr_char_ngram_3_5", + "tags": { + "feature_type": "tfidf", + "scaler": "none", + "n_gram_range": "(3,5)", + "dataset_version": "stsb_multi_mt", + "vectorizer_class": "TfidfVectorizer" + }, + "params": { + "clf__C": "6.440507553993708", + "clf__penalty": "l2", + "vectorizer__max_features": "50000", + "vectorizer__min_df": "5", + "vectorizer__sublinear_tf": "True" + }, + "metrics": { + "accuracy": 0.9954551356966628, + "f1_macro": 0.9954399626268631, + "precision_macro": 0.9954229026821475, + "recall_macro": 0.9954906190072986, + "inference_time_total_s": 0.5699, + "inference_time_ms_per_sample": 0.073998, + "throughput_samples_per_sec": 13513.92 + } +} \ No newline at end of file diff --git a/logistic_regression/tweet_sentiment_multilingual/bow_maxabs_lr_char_ngram_3_5/classification_report.txt b/logistic_regression/tweet_sentiment_multilingual/bow_maxabs_lr_char_ngram_3_5/classification_report.txt new file mode 100644 index 0000000000000000000000000000000000000000..4dfa8a9a4b9e6258f181491274e438afb2cd18b0 --- /dev/null +++ b/logistic_regression/tweet_sentiment_multilingual/bow_maxabs_lr_char_ngram_3_5/classification_report.txt @@ -0,0 +1,30 @@ + precision recall f1-score support + + ca 0.00 0.00 0.00 0 + da 0.00 0.00 0.00 0 + de 0.99 0.99 0.99 271 + el 0.00 0.00 0.00 0 + en 0.99 1.00 0.99 292 + es 1.00 0.99 0.99 288 + fi 0.00 0.00 0.00 0 + fr 0.99 1.00 1.00 299 + hr 0.00 0.00 0.00 0 + it 1.00 1.00 1.00 288 + ja 0.00 0.00 0.00 0 + ko 0.00 0.00 0.00 0 + lt 0.00 0.00 0.00 0 + mk 0.00 0.00 0.00 0 + nb 0.00 0.00 0.00 0 + nl 0.00 0.00 0.00 0 + pl 0.00 0.00 0.00 0 + pt 1.00 1.00 1.00 291 + ro 0.00 0.00 0.00 0 + ru 0.00 0.00 0.00 0 + sl 0.00 0.00 0.00 0 + sv 0.00 0.00 0.00 0 + uk 0.00 0.00 0.00 0 + zh 0.00 0.00 0.00 0 + + accuracy 1.00 1729 + macro avg 0.25 0.25 0.25 1729 +weighted avg 1.00 1.00 1.00 1729 diff --git a/logistic_regression/tweet_sentiment_multilingual/bow_maxabs_lr_char_ngram_3_5/cv_results.csv b/logistic_regression/tweet_sentiment_multilingual/bow_maxabs_lr_char_ngram_3_5/cv_results.csv new file mode 100644 index 0000000000000000000000000000000000000000..de439d948ca589f9293303a3364186a64bf8cf7e --- /dev/null +++ b/logistic_regression/tweet_sentiment_multilingual/bow_maxabs_lr_char_ngram_3_5/cv_results.csv @@ -0,0 +1,11 @@ +mean_fit_time,std_fit_time,mean_score_time,std_score_time,param_clf__C,param_clf__penalty,param_vectorizer__max_features,param_vectorizer__min_df,params,split0_test_score,split1_test_score,split2_test_score,mean_test_score,std_test_score,rank_test_score +3.132206916809082,0.17980842915072937,0.7805747191111246,0.14065412380618045,0.09915644566638392,l2,50000,1,"{'clf__C': 0.09915644566638392, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1}",0.9943101787549694,0.9964637191186366,0.9951383715652904,0.9953040898129655,0.0008869539363068628,1 +3.6618231932322183,0.863848821795047,0.7989474932352701,0.024638108101125364,0.0029341230215132346,l2,50000,5,"{'clf__C': 0.0029341230215132346, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9903454205448687,0.9938076131001597,0.9917054075785273,0.9919528137411854,0.001424219477343988,7 +3.843501170476278,1.0053584705313299,0.725118080774943,0.07116299679158118,6.155564318973006,l2,50000,3,"{'clf__C': 6.155564318973006, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.9938658850434474,0.9964637191186366,0.9951253429064763,0.9951516490228535,0.0010607244315003718,2 +4.721199989318848,0.4732529175819291,0.7023828824361166,0.05102901365918078,0.3686905640846153,l2,50000,3,"{'clf__C': 0.3686905640846153, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.9938658850434474,0.9964637191186366,0.9946935581701991,0.9950077207774277,0.0010835771248936092,4 +4.104452451070149,0.4967359087139507,0.6848850250244141,0.06253956622019795,0.00029152036385288323,l2,50000,5,"{'clf__C': 0.00029152036385288323, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9779909540572612,0.9650924873633081,0.9757605550133156,0.972947998811295,0.005628822556325491,8 +3.517397960027059,0.6844769053060321,0.7546558380126953,0.0447647624005384,0.0467378670778782,l2,50000,5,"{'clf__C': 0.0467378670778782, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9938830430523802,0.9964637191186366,0.9942715039456843,0.9948727553722336,0.0011361043667383662,6 +3.4813626607259116,0.31281533291032926,0.7975250879923502,0.006089254983568467,46.19347374377369,l2,50000,2,"{'clf__C': 46.19347374377369, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2}",0.9938658850434474,0.9964637191186366,0.9946935581701991,0.9950077207774277,0.0010835771248936092,4 +3.1521048545837402,0.1886143124128306,0.6545911629994711,0.08518475309149323,0.00028267840503514715,l2,50000,5,"{'clf__C': 0.00028267840503514715, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9779909540572612,0.9637044185586112,0.9748541366004905,0.9721831697387877,0.006130623792121139,9 +2.9137818018595376,0.2190170516866214,0.6934545040130615,0.08496440763762707,456.60548734461145,l2,50000,2,"{'clf__C': 456.60548734461145, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2}",0.9938658850434474,0.9964637191186366,0.9951253429064763,0.9951516490228535,0.0010607244315003718,2 +2.8767886956532798,0.07546028763752802,0.6268069744110107,0.05518153819660347,0.00010144487859320231,l2,50000,5,"{'clf__C': 0.00010144487859320231, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.8865181530008138,0.8778566052300766,0.88288959744817,0.8824214518930201,0.003551522926088257,10 diff --git a/logistic_regression/tweet_sentiment_multilingual/bow_maxabs_lr_char_ngram_3_5/run_metadata.json b/logistic_regression/tweet_sentiment_multilingual/bow_maxabs_lr_char_ngram_3_5/run_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..5daf572404053c12c02a6a9eb38762d648e451c1 --- /dev/null +++ b/logistic_regression/tweet_sentiment_multilingual/bow_maxabs_lr_char_ngram_3_5/run_metadata.json @@ -0,0 +1,25 @@ +{ + "run_name": "bow_maxabs_lr_char_ngram_3_5", + "tags": { + "feature_type": "bow", + "scaler": "MaxAbsScaler", + "n_gram_range": "(3,5)", + "dataset_version": "tweet_sentiment_multilingual", + "vectorizer_class": "CountVectorizer" + }, + "params": { + "clf__C": "0.09915644566638392", + "clf__penalty": "l2", + "vectorizer__max_features": "50000", + "vectorizer__min_df": "1" + }, + "metrics": { + "accuracy": 0.995373048004627, + "f1_macro": 0.9952934210868153, + "precision_macro": 0.9953312017062821, + "recall_macro": 0.995269390479293, + "inference_time_total_s": 0.293, + "inference_time_ms_per_sample": 0.169468, + "throughput_samples_per_sec": 5900.83 + } +} \ No newline at end of file diff --git a/logistic_regression/tweet_sentiment_multilingual/tfidf_lr_char_ngram_3_5/classification_report.txt b/logistic_regression/tweet_sentiment_multilingual/tfidf_lr_char_ngram_3_5/classification_report.txt new file mode 100644 index 0000000000000000000000000000000000000000..ca0b73c4be95802753cc616560424b8a4754ed7e --- /dev/null +++ b/logistic_regression/tweet_sentiment_multilingual/tfidf_lr_char_ngram_3_5/classification_report.txt @@ -0,0 +1,30 @@ + precision recall f1-score support + + ca 0.00 0.00 0.00 0 + da 0.00 0.00 0.00 0 + de 0.99 0.99 0.99 271 + el 0.00 0.00 0.00 0 + en 0.99 1.00 0.99 292 + es 1.00 1.00 1.00 288 + fi 0.00 0.00 0.00 0 + fr 1.00 1.00 1.00 299 + hr 0.00 0.00 0.00 0 + it 1.00 0.99 0.99 288 + ja 0.00 0.00 0.00 0 + ko 0.00 0.00 0.00 0 + lt 0.00 0.00 0.00 0 + mk 0.00 0.00 0.00 0 + nb 0.00 0.00 0.00 0 + nl 0.00 0.00 0.00 0 + pl 0.00 0.00 0.00 0 + pt 1.00 1.00 1.00 291 + ro 0.00 0.00 0.00 0 + ru 0.00 0.00 0.00 0 + sl 0.00 0.00 0.00 0 + sv 0.00 0.00 0.00 0 + uk 0.00 0.00 0.00 0 + zh 0.00 0.00 0.00 0 + + accuracy 1.00 1729 + macro avg 0.25 0.25 0.25 1729 +weighted avg 1.00 1.00 1.00 1729 diff --git a/logistic_regression/tweet_sentiment_multilingual/tfidf_lr_char_ngram_3_5/cv_results.csv b/logistic_regression/tweet_sentiment_multilingual/tfidf_lr_char_ngram_3_5/cv_results.csv new file mode 100644 index 0000000000000000000000000000000000000000..25fc0d0d003f8811ec947df1532384ef2bffd27a --- /dev/null +++ b/logistic_regression/tweet_sentiment_multilingual/tfidf_lr_char_ngram_3_5/cv_results.csv @@ -0,0 +1,11 @@ +mean_fit_time,std_fit_time,mean_score_time,std_score_time,param_clf__C,param_clf__penalty,param_vectorizer__max_features,param_vectorizer__min_df,param_vectorizer__sublinear_tf,params,split0_test_score,split1_test_score,split2_test_score,mean_test_score,std_test_score,rank_test_score +7.661678791046143,1.5085110638443473,1.4203418890635173,0.5797132755989518,0.09915644566638392,l2,50000,1,True,"{'clf__C': 0.09915644566638392, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9843211111902582,0.9942771816519538,0.9946995073486601,0.9910992667302908,0.004795979854154191,5 +6.2613124052683515,0.9853394063177716,2.440807263056437,1.6394842270716417,71.77141927992008,l2,50000,1,True,"{'clf__C': 71.77141927992008, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.995215778980565,0.9902215812545857,0.996508726174581,0.9939820288032438,0.002710922651827294,3 +10.691745201746622,3.5424583563330976,1.9876818656921387,0.8856017239272747,0.0017707168643537816,l2,50000,3,True,"{'clf__C': 0.0017707168643537816, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': True}",0.38694542612572386,0.4310451790599293,0.5507062461786815,0.4562322837881115,0.06918667612358903,8 +13.079137881596884,3.5073249734631644,1.737606684366862,0.8093629860092527,0.00029152036385288323,l2,50000,5,True,"{'clf__C': 0.00029152036385288323, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.07301240486351858,0.04908126772721667,0.04908126772721667,0.057058313439317304,0.011281246233722864,9 +12.446452458699545,2.5519844556260884,2.072986364364624,1.1790060544205487,6.440507553993708,l2,50000,5,True,"{'clf__C': 6.440507553993708, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.9938677704160018,0.9924508565907068,0.9960657877283118,0.9941281382450068,0.001487229042479595,2 +8.5853377978007,4.386959030826828,2.5167163213094077,1.3441538860656856,0.00014610865886287189,l2,50000,2,False,"{'clf__C': 0.00014610865886287189, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.04768983029852595,0.04908126772721667,0.04908126772721667,0.04861745525098643,0.0006559298942826529,10 +5.051501035690308,0.6933533906882532,1.7173677285512288,0.5529893673204233,456.60548734461145,l2,50000,2,False,"{'clf__C': 456.60548734461145, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.994761192689756,0.9893831949949236,0.9964966012985804,0.9935469963277533,0.003028293459398298,4 +5.647335926691691,1.2737858404786981,2.085089365641276,1.1034002066261162,0.0028483918709108036,l2,50000,1,True,"{'clf__C': 0.0028483918709108036, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.7037730546808829,0.379763890518993,0.7081829274538286,0.5972399575512348,0.153789339776478,7 +5.469881137212117,1.2933915379379468,1.4652889569600422,0.6352703092034861,0.027160511446548484,l2,50000,2,True,"{'clf__C': 0.027160511446548484, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': True}",0.986386590512145,0.989791160784157,0.9813772642575557,0.9858516718512859,0.003455721552284924,6 +6.034270604451497,2.552467045778939,1.6812629699707031,1.056523117716238,0.28546978577971793,l2,50000,1,True,"{'clf__C': 0.28546978577971793, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9929946806804074,0.9964659189083602,0.9956096036216842,0.9950234010701506,0.0014765046071422833,1 diff --git a/logistic_regression/tweet_sentiment_multilingual/tfidf_lr_char_ngram_3_5/run_metadata.json b/logistic_regression/tweet_sentiment_multilingual/tfidf_lr_char_ngram_3_5/run_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..f382b32f798f60f07b37fee1f001a6270e51cd13 --- /dev/null +++ b/logistic_regression/tweet_sentiment_multilingual/tfidf_lr_char_ngram_3_5/run_metadata.json @@ -0,0 +1,26 @@ +{ + "run_name": "tfidf_lr_char_ngram_3_5", + "tags": { + "feature_type": "tfidf", + "scaler": "none", + "n_gram_range": "(3,5)", + "dataset_version": "tweet_sentiment_multilingual", + "vectorizer_class": "TfidfVectorizer" + }, + "params": { + "clf__C": "0.28546978577971793", + "clf__penalty": "l2", + "vectorizer__max_features": "50000", + "vectorizer__min_df": "1", + "vectorizer__sublinear_tf": "True" + }, + "metrics": { + "accuracy": 0.9965297860034702, + "f1_macro": 0.9964738532787099, + "precision_macro": 0.9964985311720604, + "recall_macro": 0.9964631003330581, + "inference_time_total_s": 0.9529, + "inference_time_ms_per_sample": 0.55114, + "throughput_samples_per_sec": 1814.42 + } +} \ No newline at end of file diff --git a/logistic_regression/tydiqa/bow_maxabs_lr_char_ngram_3_5/classification_report.txt b/logistic_regression/tydiqa/bow_maxabs_lr_char_ngram_3_5/classification_report.txt new file mode 100644 index 0000000000000000000000000000000000000000..06b7df386633849839428dc5efdb6b0e07982d15 --- /dev/null +++ b/logistic_regression/tydiqa/bow_maxabs_lr_char_ngram_3_5/classification_report.txt @@ -0,0 +1,30 @@ + precision recall f1-score support + + ca 0.00 0.00 0.00 0 + da 0.00 0.00 0.00 0 + de 0.00 0.00 0.00 0 + el 0.00 0.00 0.00 0 + en 1.00 1.00 1.00 855 + es 0.00 0.00 0.00 0 + fi 1.00 1.00 1.00 1296 + fr 0.00 0.00 0.00 0 + hr 0.00 0.00 0.00 0 + it 0.00 0.00 0.00 0 + ja 0.98 1.00 0.99 1751 + ko 1.00 0.98 0.99 1259 + lt 0.00 0.00 0.00 0 + mk 0.00 0.00 0.00 0 + nb 0.00 0.00 0.00 0 + nl 0.00 0.00 0.00 0 + pl 0.00 0.00 0.00 0 + pt 0.00 0.00 0.00 0 + ro 0.00 0.00 0.00 0 + ru 1.00 1.00 1.00 1282 + sl 0.00 0.00 0.00 0 + sv 0.00 0.00 0.00 0 + uk 0.00 0.00 0.00 0 + zh 0.00 0.00 0.00 0 + + accuracy 1.00 6443 + macro avg 0.21 0.21 0.21 6443 +weighted avg 1.00 1.00 1.00 6443 diff --git a/logistic_regression/tydiqa/bow_maxabs_lr_char_ngram_3_5/cv_results.csv b/logistic_regression/tydiqa/bow_maxabs_lr_char_ngram_3_5/cv_results.csv new file mode 100644 index 0000000000000000000000000000000000000000..46c4df88f71d03ccff8d1392e9c83c8ec8178d03 --- /dev/null +++ b/logistic_regression/tydiqa/bow_maxabs_lr_char_ngram_3_5/cv_results.csv @@ -0,0 +1,11 @@ +mean_fit_time,std_fit_time,mean_score_time,std_score_time,param_clf__C,param_clf__penalty,param_vectorizer__max_features,param_vectorizer__min_df,params,split0_test_score,split1_test_score,split2_test_score,mean_test_score,std_test_score,rank_test_score +2.69244384765625,0.1860757750180955,0.4973321755727132,0.009063866779179449,0.09915644566638392,l2,50000,1,"{'clf__C': 0.09915644566638392, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1}",0.9964600557144314,0.9949857397900299,0.9972786489064008,0.9962414814702875,0.000948749731361076,5 +2.6520512898763022,0.060287315152256174,0.5084742705027262,0.01820844647155785,0.0029341230215132346,l2,50000,5,"{'clf__C': 0.0029341230215132346, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9838876931090835,0.9813821474621893,0.9835051354962652,0.9829249920225127,0.0011020782140334785,7 +2.6068837642669678,0.024703535377908134,0.48021364212036133,0.009571331982657413,6.155564318973006,l2,50000,3,"{'clf__C': 6.155564318973006, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.9971296494117015,0.9956571269678681,0.9977428888445747,0.9968432217413815,0.0008752642493648762,1 +2.63995091120402,0.0195177830285907,0.502833366394043,0.018134733713990457,0.3686905640846153,l2,50000,3,"{'clf__C': 0.3686905640846153, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.9971572510422109,0.9952470478796179,0.9974089415704036,0.9966044134974107,0.0009652868643638715,4 +2.7074273427327475,0.08009498717995711,0.5041439533233643,0.00579033397488205,0.00029152036385288323,l2,50000,5,"{'clf__C': 0.00029152036385288323, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.8840298824543595,0.8813117756193595,0.8797163642048702,0.8816860074261964,0.0017807577050431293,8 +2.6060731410980225,0.1044574939786179,0.48953890800476074,0.01565751282805374,0.0467378670778782,l2,50000,5,"{'clf__C': 0.0467378670778782, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9959937317820324,0.9946494921169725,0.9971777554848718,0.9959403264612923,0.0010328497827460444,6 +2.602447748184204,0.012873189549770098,0.46695176760355633,0.0016544835345968908,46.19347374377369,l2,50000,2,"{'clf__C': 46.19347374377369, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2}",0.9971296494117015,0.9956571269678681,0.9977428888445747,0.9968432217413815,0.0008752642493648762,1 +2.6049590905507407,0.016700833391592115,0.4646066029866536,0.008957744996266519,0.00028267840503514715,l2,50000,5,"{'clf__C': 0.00028267840503514715, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.8802283591659122,0.8774439195341716,0.8750901900836707,0.8775874895945849,0.0021001039103039584,9 +2.605396032333374,0.11647155609633335,0.4754358132680257,0.005240875438586652,456.60548734461145,l2,50000,2,"{'clf__C': 456.60548734461145, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2}",0.9971296494117015,0.9956571269678681,0.9977428888445747,0.9968432217413815,0.0008752642493648762,1 +2.5730525652567544,0.020753676440607847,0.4632052580515544,0.007935163534048148,0.00010144487859320231,l2,50000,5,"{'clf__C': 0.00010144487859320231, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.6779022837979833,0.6503433128939591,0.6484120348736008,0.6588858771885144,0.013469725286742621,10 diff --git a/logistic_regression/tydiqa/bow_maxabs_lr_char_ngram_3_5/run_metadata.json b/logistic_regression/tydiqa/bow_maxabs_lr_char_ngram_3_5/run_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..8d8ca2c751f7261cd4930f43053ab8fe5677dcc3 --- /dev/null +++ b/logistic_regression/tydiqa/bow_maxabs_lr_char_ngram_3_5/run_metadata.json @@ -0,0 +1,25 @@ +{ + "run_name": "bow_maxabs_lr_char_ngram_3_5", + "tags": { + "feature_type": "bow", + "scaler": "MaxAbsScaler", + "n_gram_range": "(3,5)", + "dataset_version": "tydiqa", + "vectorizer_class": "CountVectorizer" + }, + "params": { + "clf__C": "6.155564318973006", + "clf__penalty": "l2", + "vectorizer__max_features": "50000", + "vectorizer__min_df": "3" + }, + "metrics": { + "accuracy": 0.9953437839515753, + "f1_macro": 0.9958198372189087, + "precision_macro": 0.9963818768143969, + "recall_macro": 0.9953264345209358, + "inference_time_total_s": 0.2622, + "inference_time_ms_per_sample": 0.040689, + "throughput_samples_per_sec": 24576.67 + } +} \ No newline at end of file diff --git a/logistic_regression/tydiqa/tfidf_lr_char_ngram_3_5/classification_report.txt b/logistic_regression/tydiqa/tfidf_lr_char_ngram_3_5/classification_report.txt new file mode 100644 index 0000000000000000000000000000000000000000..53874816873caa3bd7e149d032843ea78b497f91 --- /dev/null +++ b/logistic_regression/tydiqa/tfidf_lr_char_ngram_3_5/classification_report.txt @@ -0,0 +1,30 @@ + precision recall f1-score support + + ca 0.00 0.00 0.00 0 + da 0.00 0.00 0.00 0 + de 0.00 0.00 0.00 0 + el 0.00 0.00 0.00 0 + en 0.99 1.00 1.00 855 + es 0.00 0.00 0.00 0 + fi 1.00 1.00 1.00 1296 + fr 0.00 0.00 0.00 0 + hr 0.00 0.00 0.00 0 + it 0.00 0.00 0.00 0 + ja 0.99 1.00 1.00 1751 + ko 1.00 0.99 1.00 1259 + lt 0.00 0.00 0.00 0 + mk 0.00 0.00 0.00 0 + nb 0.00 0.00 0.00 0 + nl 0.00 0.00 0.00 0 + pl 0.00 0.00 0.00 0 + pt 0.00 0.00 0.00 0 + ro 0.00 0.00 0.00 0 + ru 1.00 1.00 1.00 1282 + sl 0.00 0.00 0.00 0 + sv 0.00 0.00 0.00 0 + uk 0.00 0.00 0.00 0 + zh 0.00 0.00 0.00 0 + + accuracy 1.00 6443 + macro avg 0.21 0.21 0.21 6443 +weighted avg 1.00 1.00 1.00 6443 diff --git a/logistic_regression/tydiqa/tfidf_lr_char_ngram_3_5/cv_results.csv b/logistic_regression/tydiqa/tfidf_lr_char_ngram_3_5/cv_results.csv new file mode 100644 index 0000000000000000000000000000000000000000..8a46bc6d02b86d309f4831ccae81ea7ba3363301 --- /dev/null +++ b/logistic_regression/tydiqa/tfidf_lr_char_ngram_3_5/cv_results.csv @@ -0,0 +1,11 @@ +mean_fit_time,std_fit_time,mean_score_time,std_score_time,param_clf__C,param_clf__penalty,param_vectorizer__max_features,param_vectorizer__min_df,param_vectorizer__sublinear_tf,params,split0_test_score,split1_test_score,split2_test_score,mean_test_score,std_test_score,rank_test_score +2.4985291163126626,0.04801144291833253,0.5187452634175619,0.025383576774209975,0.09915644566638392,l2,50000,1,True,"{'clf__C': 0.09915644566638392, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9940492654516218,0.9933022538738061,0.9888576353340472,0.9920697182198251,0.0022916680857950882,5 +2.418835401535034,0.038914320798141916,0.48714343706766766,0.006791692493479492,71.77141927992008,l2,50000,1,True,"{'clf__C': 71.77141927992008, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9980972754830126,0.9967934147772304,0.9986236507047905,0.9978381136550111,0.0007693350061157946,1 +2.862689654032389,0.16851450438282764,0.5438613891601562,0.03368540577794753,0.0017707168643537816,l2,50000,3,True,"{'clf__C': 0.0017707168643537816, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': True}",0.12833207527174245,0.13511457509524755,0.12464665108286228,0.1293644338166174,0.00433541089218775,8 +2.97040057182312,0.03350154707046651,0.5084307193756104,0.02057523539445862,0.00029152036385288323,l2,50000,5,True,"{'clf__C': 0.00029152036385288323, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.0854553775743707,0.0854553775743707,0.085463200292933,0.0854579851472248,3.687664895142984e-06,9 +2.600637435913086,0.03195665548973055,0.5328783194224039,0.0055192795514229865,6.440507553993708,l2,50000,5,True,"{'clf__C': 6.440507553993708, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.9981999689147681,0.9965876503585054,0.9986236507047905,0.9978037566593546,0.0008771402267304721,3 +3.091437578201294,0.19442638342892168,0.47189998626708984,0.02891531657862816,0.00014610865886287189,l2,50000,2,False,"{'clf__C': 0.00014610865886287189, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.0854553775743707,0.0854553775743707,0.085463200292933,0.0854579851472248,3.687664895142984e-06,9 +2.4194442431131997,0.013480416003105343,0.4956240653991699,0.0013100333143581584,456.60548734461145,l2,50000,2,False,"{'clf__C': 456.60548734461145, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.9981999689147681,0.9966905416939504,0.9986236507047905,0.9978380537711699,0.0008296443174928243,2 +2.7732835610707602,0.16635348978604275,0.4507712523142497,0.02577976236130321,0.0028483918709108036,l2,50000,1,True,"{'clf__C': 0.0028483918709108036, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.27325538890199613,0.2527706385905508,0.249424560414251,0.258483529302266,0.010534227920326582,7 +2.5077298482259116,0.051738639396126655,0.4663976828257243,0.0025997349201078465,0.027160511446548484,l2,50000,2,True,"{'clf__C': 0.027160511446548484, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': True}",0.9712606009423499,0.9751998278627895,0.9772605403250291,0.9745736563767228,0.0024891613308406155,6 +2.4644325574239097,0.01566743962373616,0.44145385424296063,0.012786810155577524,0.28546978577971793,l2,50000,1,True,"{'clf__C': 0.28546978577971793, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9967253076378503,0.9960185748464241,0.9965525902211112,0.9964321575684618,0.00030082755579388236,4 diff --git a/logistic_regression/tydiqa/tfidf_lr_char_ngram_3_5/run_metadata.json b/logistic_regression/tydiqa/tfidf_lr_char_ngram_3_5/run_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..e2e8e8e2e34ca155275e3f91c17119a1f617d832 --- /dev/null +++ b/logistic_regression/tydiqa/tfidf_lr_char_ngram_3_5/run_metadata.json @@ -0,0 +1,26 @@ +{ + "run_name": "tfidf_lr_char_ngram_3_5", + "tags": { + "feature_type": "tfidf", + "scaler": "none", + "n_gram_range": "(3,5)", + "dataset_version": "tydiqa", + "vectorizer_class": "TfidfVectorizer" + }, + "params": { + "clf__C": "71.77141927992008", + "clf__penalty": "l2", + "vectorizer__max_features": "50000", + "vectorizer__min_df": "1", + "vectorizer__sublinear_tf": "True" + }, + "metrics": { + "accuracy": 0.9973614775725593, + "f1_macro": 0.9974902710855368, + "precision_macro": 0.9974720215890149, + "recall_macro": 0.9975226229514146, + "inference_time_total_s": 0.2625, + "inference_time_ms_per_sample": 0.040747, + "throughput_samples_per_sec": 24541.64 + } +} \ No newline at end of file diff --git a/logistic_regression/wikipedia/bow_maxabs_lr_char_ngram_3_5/classification_report.txt b/logistic_regression/wikipedia/bow_maxabs_lr_char_ngram_3_5/classification_report.txt new file mode 100644 index 0000000000000000000000000000000000000000..f507211e73d609a39c47fa4f2bab87ff723dde59 --- /dev/null +++ b/logistic_regression/wikipedia/bow_maxabs_lr_char_ngram_3_5/classification_report.txt @@ -0,0 +1,30 @@ + precision recall f1-score support + + ca 1.00 1.00 1.00 19973 + da 0.98 0.97 0.97 20005 + de 1.00 1.00 1.00 19980 + el 1.00 1.00 1.00 20014 + en 1.00 1.00 1.00 20017 + es 0.99 0.99 0.99 20094 + fi 1.00 1.00 1.00 19991 + fr 1.00 1.00 1.00 20081 + hr 1.00 0.99 0.99 19953 + it 1.00 1.00 1.00 19945 + ja 0.96 0.85 0.90 19959 + ko 0.99 0.93 0.96 20024 + lt 1.00 1.00 1.00 20038 + mk 1.00 1.00 1.00 13831 + nb 0.97 0.97 0.97 20031 + nl 1.00 1.00 1.00 20015 + pl 1.00 1.00 1.00 19968 + pt 1.00 1.00 1.00 19977 + ro 1.00 1.00 1.00 20048 + ru 1.00 1.00 1.00 19982 + sl 1.00 0.99 1.00 18280 + sv 1.00 1.00 1.00 20091 + uk 1.00 1.00 1.00 19970 + zh 0.82 0.99 0.89 19988 + + accuracy 0.98 472255 + macro avg 0.99 0.98 0.98 472255 +weighted avg 0.99 0.98 0.98 472255 diff --git a/logistic_regression/wikipedia/bow_maxabs_lr_char_ngram_3_5/cv_results.csv b/logistic_regression/wikipedia/bow_maxabs_lr_char_ngram_3_5/cv_results.csv new file mode 100644 index 0000000000000000000000000000000000000000..e890a670a556fcc5ebe2d5d1ee85aa142c3a9a89 --- /dev/null +++ b/logistic_regression/wikipedia/bow_maxabs_lr_char_ngram_3_5/cv_results.csv @@ -0,0 +1,11 @@ +mean_fit_time,std_fit_time,mean_score_time,std_score_time,param_clf__C,param_clf__penalty,param_vectorizer__max_features,param_vectorizer__min_df,params,split0_test_score,split1_test_score,split2_test_score,mean_test_score,std_test_score,rank_test_score +1538.382477760315,98.48742510660021,494.0919283231099,38.489036264369254,0.09915644566638392,l2,50000,1,"{'clf__C': 0.09915644566638392, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1}",0.9824344978985139,0.9819173151200857,0.9830829919930343,0.9824782683372114,0.0004768909948891892,5 +1511.755676428477,56.713394082776674,532.1114799976349,26.16969295778033,0.0029341230215132346,l2,50000,5,"{'clf__C': 0.0029341230215132346, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9708230716304552,0.9719705190737651,0.97069997614495,0.9711645222830567,0.0005721370725109121,7 +1482.908682902654,75.93312610419315,518.9716056982676,26.294552698723948,6.155564318973006,l2,50000,3,"{'clf__C': 6.155564318973006, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.9839092472544136,0.9838838272944649,0.9847421420171365,0.984178405522005,0.00039875696069017824,3 +1495.2877122561138,33.50248910818956,485.71584391593933,34.8522668754007,0.3686905640846153,l2,50000,3,"{'clf__C': 0.3686905640846153, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.9831602538592294,0.9830671299428433,0.9842757292182481,0.9835010376734403,0.0005491073107923098,4 +1486.0165418783824,41.427440580233025,495.02436923980713,44.698227122700175,0.00029152036385288323,l2,50000,5,"{'clf__C': 0.00029152036385288323, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9597724472881987,0.9602473168909801,0.9572487694717964,0.9590895112169916,0.001315959197515892,8 +1667.6116446654003,52.67289051457016,537.4241658051809,27.883225406886435,0.0467378670778782,l2,50000,5,"{'clf__C': 0.0467378670778782, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9812352112139925,0.9809113408594964,0.9815039906190547,0.9812168475641813,0.00024229644666802066,6 +1474.3520761330922,57.61584913938245,518.7145636081696,27.665575333732875,46.19347374377369,l2,50000,2,"{'clf__C': 46.19347374377369, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2}",0.9839249640269845,0.9839045308034078,0.9847732665577681,0.9842009204627201,0.0004047957662360362,2 +1478.0126144886017,53.01905251423626,553.7112891674042,27.78165802925531,0.00028267840503514715,l2,50000,5,"{'clf__C': 0.00028267840503514715, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9596348133954381,0.9601112903416039,0.9570515950607043,0.9589325662659154,0.0013441966810904947,9 +1535.9585206508636,72.6636653453837,532.109429359436,38.141303992178194,456.60548734461145,l2,50000,2,"{'clf__C': 456.60548734461145, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2}",0.9839277405150507,0.9839027211207796,0.9847776388883706,0.9842027001747335,0.000406671354495898,1 +1606.7658222516377,126.21949616728591,481.8166387081146,52.83506159707213,0.00010144487859320231,l2,50000,5,"{'clf__C': 0.00010144487859320231, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9532850045725318,0.9528285739773007,0.9498617650965349,0.9519917812154558,0.0015176316466154398,10 diff --git a/logistic_regression/wikipedia/bow_maxabs_lr_char_ngram_3_5/run_metadata.json b/logistic_regression/wikipedia/bow_maxabs_lr_char_ngram_3_5/run_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..62c444236bc91cd9659bca8ab26ef9317edc8e0d --- /dev/null +++ b/logistic_regression/wikipedia/bow_maxabs_lr_char_ngram_3_5/run_metadata.json @@ -0,0 +1,25 @@ +{ + "run_name": "bow_maxabs_lr_char_ngram_3_5", + "tags": { + "feature_type": "bow", + "scaler": "MaxAbsScaler", + "n_gram_range": "(3,5)", + "dataset_version": "wikipedia", + "vectorizer_class": "CountVectorizer" + }, + "params": { + "clf__C": "456.60548734461145", + "clf__penalty": "l2", + "vectorizer__max_features": "50000", + "vectorizer__min_df": "2" + }, + "metrics": { + "accuracy": 0.984607891922796, + "f1_macro": 0.9849831975239757, + "precision_macro": 0.9861888977674544, + "recall_macro": 0.984798742914819, + "inference_time_total_s": 318.0443, + "inference_time_ms_per_sample": 0.673459, + "throughput_samples_per_sec": 1484.87 + } +} \ No newline at end of file diff --git a/logistic_regression/wikipedia/tfidf_lr_char_ngram_3_5/classification_report.txt b/logistic_regression/wikipedia/tfidf_lr_char_ngram_3_5/classification_report.txt new file mode 100644 index 0000000000000000000000000000000000000000..77e751df3cb4a4bf2729900045fd722dbda7b286 --- /dev/null +++ b/logistic_regression/wikipedia/tfidf_lr_char_ngram_3_5/classification_report.txt @@ -0,0 +1,30 @@ + precision recall f1-score support + + ca 1.00 1.00 1.00 19973 + da 0.94 0.98 0.96 20005 + de 1.00 1.00 1.00 19980 + el 1.00 1.00 1.00 20014 + en 0.99 1.00 0.99 20017 + es 0.99 0.99 0.99 20094 + fi 1.00 1.00 1.00 19991 + fr 1.00 1.00 1.00 20081 + hr 1.00 0.99 0.99 19953 + it 1.00 1.00 1.00 19945 + ja 0.95 0.87 0.91 19959 + ko 0.99 0.94 0.96 20024 + lt 1.00 1.00 1.00 20038 + mk 1.00 1.00 1.00 13831 + nb 0.98 0.94 0.96 20031 + nl 1.00 1.00 1.00 20015 + pl 1.00 1.00 1.00 19968 + pt 1.00 1.00 1.00 19977 + ro 1.00 1.00 1.00 20048 + ru 1.00 1.00 1.00 19982 + sl 0.99 1.00 0.99 18280 + sv 1.00 0.99 1.00 20091 + uk 1.00 1.00 1.00 19970 + zh 0.84 0.98 0.91 19988 + + accuracy 0.98 472255 + macro avg 0.99 0.98 0.99 472255 +weighted avg 0.99 0.98 0.98 472255 diff --git a/logistic_regression/wikipedia/tfidf_lr_char_ngram_3_5/cv_results.csv b/logistic_regression/wikipedia/tfidf_lr_char_ngram_3_5/cv_results.csv new file mode 100644 index 0000000000000000000000000000000000000000..54b3cce3980345c7fcd71364c50786fcff107568 --- /dev/null +++ b/logistic_regression/wikipedia/tfidf_lr_char_ngram_3_5/cv_results.csv @@ -0,0 +1,11 @@ +mean_fit_time,std_fit_time,mean_score_time,std_score_time,param_clf__C,param_clf__penalty,param_vectorizer__max_features,param_vectorizer__min_df,param_vectorizer__sublinear_tf,params,split0_test_score,split1_test_score,split2_test_score,mean_test_score,std_test_score,rank_test_score +1113.527126789093,15.230484445197119,376.44224349657696,30.449007303447388,0.09915644566638392,l2,50000,1,True,"{'clf__C': 0.09915644566638392, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9829269193387401,0.982435068586709,0.9814544671373432,0.9822721516875975,0.00061206497931824,5 +1083.273272196452,1.6926558960075675,376.8987678686778,12.775631693801406,71.77141927992008,l2,50000,1,True,"{'clf__C': 71.77141927992008, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9864001240767225,0.9861563239178056,0.976492885287528,0.983016444427352,0.004613926564757212,3 +1289.961486895879,155.1012356758295,362.26485053698224,10.278077916471696,0.0017707168643537816,l2,50000,3,True,"{'clf__C': 0.0017707168643537816, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': True}",0.9649419243355357,0.9512507850868192,0.9698915416217009,0.9620280836813518,0.007884047250267031,8 +1337.1360432306926,112.74842099678037,324.0336847305298,19.84004476495641,0.00029152036385288323,l2,50000,5,True,"{'clf__C': 0.00029152036385288323, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.9422417512543472,0.9455147934165717,0.9432260397805173,0.9436608614838121,0.0013711318157315713,9 +1104.81085729599,38.60611049344202,370.4905370076497,23.287014367461357,6.440507553993708,l2,50000,5,True,"{'clf__C': 6.440507553993708, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.9866043693994552,0.9863754123912667,0.9773469818938118,0.9834422545615112,0.004311022075107996,2 +1365.8868075211842,83.88831920427847,343.0337341626485,3.69816320654081,0.00014610865886287189,l2,50000,2,False,"{'clf__C': 0.00014610865886287189, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.8869266846448859,0.8990904700958934,0.8983893666556441,0.8948021737988078,0.005576162573469221,10 +1046.3613208134968,26.32422418734595,350.1467502117157,4.0135138643524,456.60548734461145,l2,50000,2,False,"{'clf__C': 456.60548734461145, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.9859712501657025,0.9856949226608845,0.9760716645359038,0.9825792791208303,0.004602960997151066,4 +1151.3613557815552,40.0196180221234,355.20848774909973,18.327054433579367,0.0028483918709108036,l2,50000,1,True,"{'clf__C': 0.0028483918709108036, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9721823501689627,0.9649555349696062,0.9707174051944932,0.9692850967776874,0.0031193316626111135,7 +1076.8108280499775,1.9714314852812078,344.4764777024587,14.409039590721083,0.027160511446548484,l2,50000,2,True,"{'clf__C': 0.027160511446548484, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': True}",0.9788748600031152,0.9788099009104293,0.9786870582973544,0.978790606403633,7.78741663028878e-05,6 +1104.1239247322083,37.82102120391642,325.4378352165222,19.682031537323777,0.28546978577971793,l2,50000,1,True,"{'clf__C': 0.28546978577971793, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.985102346393879,0.9846950794370439,0.9831827901187058,0.9843267386498762,0.000825804769102096,1 diff --git a/logistic_regression/wikipedia/tfidf_lr_char_ngram_3_5/run_metadata.json b/logistic_regression/wikipedia/tfidf_lr_char_ngram_3_5/run_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..79b80a9603848fd8871c4f2a5e4cae423901ea8e --- /dev/null +++ b/logistic_regression/wikipedia/tfidf_lr_char_ngram_3_5/run_metadata.json @@ -0,0 +1,26 @@ +{ + "run_name": "tfidf_lr_char_ngram_3_5", + "tags": { + "feature_type": "tfidf", + "scaler": "none", + "n_gram_range": "(3,5)", + "dataset_version": "wikipedia", + "vectorizer_class": "TfidfVectorizer" + }, + "params": { + "clf__C": "0.28546978577971793", + "clf__penalty": "l2", + "vectorizer__max_features": "50000", + "vectorizer__min_df": "1", + "vectorizer__sublinear_tf": "True" + }, + "metrics": { + "accuracy": 0.9846989444262104, + "f1_macro": 0.9850074045573489, + "precision_macro": 0.9857898881724209, + "recall_macro": 0.9849035592480576, + "inference_time_total_s": 159.7656, + "inference_time_ms_per_sample": 0.338304, + "throughput_samples_per_sec": 2955.92 + } +} \ No newline at end of file diff --git a/logistic_regression/xlsum/bow_maxabs_lr_char_ngram_3_5/classification_report.txt b/logistic_regression/xlsum/bow_maxabs_lr_char_ngram_3_5/classification_report.txt new file mode 100644 index 0000000000000000000000000000000000000000..466fe0ac2236fa87f186de9a0cdc8834fa1bf6f5 --- /dev/null +++ b/logistic_regression/xlsum/bow_maxabs_lr_char_ngram_3_5/classification_report.txt @@ -0,0 +1,30 @@ + precision recall f1-score support + + ca 0.00 0.00 0.00 0 + da 0.00 0.00 0.00 0 + de 0.00 0.00 0.00 0 + el 0.00 0.00 0.00 0 + en 1.00 1.00 1.00 20034 + es 1.00 1.00 1.00 4729 + fi 0.00 0.00 0.00 0 + fr 1.00 1.00 1.00 1118 + hr 0.00 0.00 0.00 0 + it 0.00 0.00 0.00 0 + ja 0.99 0.44 0.61 892 + ko 0.99 0.33 0.49 561 + lt 0.00 0.00 0.00 0 + mk 0.00 0.00 0.00 0 + nb 0.00 0.00 0.00 0 + nl 0.00 0.00 0.00 0 + pl 0.00 0.00 0.00 0 + pt 1.00 1.00 1.00 7177 + ro 0.00 0.00 0.00 0 + ru 1.00 1.00 1.00 7833 + sl 0.00 0.00 0.00 0 + sv 0.00 0.00 0.00 0 + uk 1.00 1.00 1.00 5410 + zh 0.84 1.00 0.91 4646 + + accuracy 0.98 52400 + macro avg 0.37 0.32 0.33 52400 +weighted avg 0.99 0.98 0.98 52400 diff --git a/logistic_regression/xlsum/bow_maxabs_lr_char_ngram_3_5/cv_results.csv b/logistic_regression/xlsum/bow_maxabs_lr_char_ngram_3_5/cv_results.csv new file mode 100644 index 0000000000000000000000000000000000000000..b80a3d8dc73f9104d683786c95ef319a561c5168 --- /dev/null +++ b/logistic_regression/xlsum/bow_maxabs_lr_char_ngram_3_5/cv_results.csv @@ -0,0 +1,11 @@ +mean_fit_time,std_fit_time,mean_score_time,std_score_time,param_clf__C,param_clf__penalty,param_vectorizer__max_features,param_vectorizer__min_df,params,split0_test_score,split1_test_score,split2_test_score,mean_test_score,std_test_score,rank_test_score +50.65066456794739,2.171123336220882,13.311866919199625,0.886540692062067,0.09915644566638392,l2,50000,1,"{'clf__C': 0.09915644566638392, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1}",0.8695141811280039,0.862794690810266,0.8597495621687684,0.8640194780356795,0.004079380971456118,5 +48.85404642422994,0.7390842544132619,12.940193970998129,0.5598455662582479,0.0029341230215132346,l2,50000,5,"{'clf__C': 0.0029341230215132346, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.7708539620505563,0.7720991676184336,0.770789547951142,0.7712475592067106,0.000602751999437463,7 +52.81276981035868,2.121230617575625,13.187618573506674,0.6747214663868855,6.155564318973006,l2,50000,3,"{'clf__C': 6.155564318973006, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.8865139895285922,0.882924641424995,0.8769671485674976,0.8821352598403616,0.0039372482394626155,3 +52.28092885017395,1.80565013926761,13.09062933921814,0.5818940789125605,0.3686905640846153,l2,50000,3,"{'clf__C': 0.3686905640846153, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.8858381582973441,0.8827133908559733,0.8765177450387077,0.8816897647306751,0.0038732745544509876,4 +46.78173637390137,0.7623383023946643,12.844029903411865,0.5834352188961769,0.00029152036385288323,l2,50000,5,"{'clf__C': 0.00029152036385288323, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.6753825721489537,0.6805686022446141,0.6639352426927787,0.6732954723621155,0.006949059966898338,8 +48.48345899581909,1.6129810427013478,12.91046659151713,0.3507773223900545,0.0467378670778782,l2,50000,5,"{'clf__C': 0.0467378670778782, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.8482208381823644,0.8505660367048203,0.8454529868635664,0.8480799539169169,0.002089769676619045,6 +50.079533100128174,0.16824579046750973,12.165010134379068,0.10518197950972073,46.19347374377369,l2,50000,2,"{'clf__C': 46.19347374377369, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2}",0.8865139895285922,0.882924641424995,0.8784015772738241,0.8826134027424705,0.0033191826590244266,1 +47.47882843017578,0.9901151168928742,12.443775494893393,0.2637068209083512,0.00028267840503514715,l2,50000,5,"{'clf__C': 0.00028267840503514715, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.669721045810826,0.6751435594487172,0.6593261173857274,0.6680635742150902,0.0065629402669846355,9 +50.41160297393799,1.8369966649153493,11.84638524055481,0.013210458283587821,456.60548734461145,l2,50000,2,"{'clf__C': 456.60548734461145, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2}",0.8865139895285922,0.8829136586100573,0.8784015772738241,0.8826097418041577,0.003318843394568762,2 +46.077698389689125,0.9338136921702557,12.009599685668945,0.17708033181534458,0.00010144487859320231,l2,50000,5,"{'clf__C': 0.00010144487859320231, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.5426222804539297,0.6356096469952842,0.5329637001176224,0.5703985425222787,0.04627949980621476,10 diff --git a/logistic_regression/xlsum/bow_maxabs_lr_char_ngram_3_5/run_metadata.json b/logistic_regression/xlsum/bow_maxabs_lr_char_ngram_3_5/run_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..07265304edb576988712f22702593f434f19f52a --- /dev/null +++ b/logistic_regression/xlsum/bow_maxabs_lr_char_ngram_3_5/run_metadata.json @@ -0,0 +1,25 @@ +{ + "run_name": "bow_maxabs_lr_char_ngram_3_5", + "tags": { + "feature_type": "bow", + "scaler": "MaxAbsScaler", + "n_gram_range": "(3,5)", + "dataset_version": "xlsum", + "vectorizer_class": "CountVectorizer" + }, + "params": { + "clf__C": "46.19347374377369", + "clf__penalty": "l2", + "vectorizer__max_features": "50000", + "vectorizer__min_df": "2" + }, + "metrics": { + "accuracy": 0.9826717557251908, + "f1_macro": 0.890519896553416, + "precision_macro": 0.9809297503434329, + "recall_macro": 0.8624972464042675, + "inference_time_total_s": 7.1097, + "inference_time_ms_per_sample": 0.135681, + "throughput_samples_per_sec": 7370.21 + } +} \ No newline at end of file diff --git a/logistic_regression/xlsum/tfidf_lr_char_ngram_3_5/classification_report.txt b/logistic_regression/xlsum/tfidf_lr_char_ngram_3_5/classification_report.txt new file mode 100644 index 0000000000000000000000000000000000000000..ecd14bccf5ee50a8cc6fa7a00c557eaeb12b4252 --- /dev/null +++ b/logistic_regression/xlsum/tfidf_lr_char_ngram_3_5/classification_report.txt @@ -0,0 +1,30 @@ + precision recall f1-score support + + ca 0.00 0.00 0.00 0 + da 0.00 0.00 0.00 0 + de 0.00 0.00 0.00 0 + el 0.00 0.00 0.00 0 + en 1.00 1.00 1.00 20034 + es 1.00 1.00 1.00 4729 + fi 0.00 0.00 0.00 0 + fr 1.00 1.00 1.00 1118 + hr 0.00 0.00 0.00 0 + it 0.00 0.00 0.00 0 + ja 0.98 0.44 0.61 892 + ko 0.88 0.46 0.61 561 + lt 0.00 0.00 0.00 0 + mk 0.00 0.00 0.00 0 + nb 0.00 0.00 0.00 0 + nl 0.00 0.00 0.00 0 + pl 0.00 0.00 0.00 0 + pt 1.00 1.00 1.00 7177 + ro 0.00 0.00 0.00 0 + ru 1.00 1.00 1.00 7833 + sl 0.00 0.00 0.00 0 + sv 0.00 0.00 0.00 0 + uk 1.00 1.00 1.00 5410 + zh 0.85 0.99 0.92 4646 + + accuracy 0.98 52400 + macro avg 0.36 0.33 0.34 52400 +weighted avg 0.98 0.98 0.98 52400 diff --git a/logistic_regression/xlsum/tfidf_lr_char_ngram_3_5/cv_results.csv b/logistic_regression/xlsum/tfidf_lr_char_ngram_3_5/cv_results.csv new file mode 100644 index 0000000000000000000000000000000000000000..1cad8c54b0f60ad9a7cebb193779b38527bb13c3 --- /dev/null +++ b/logistic_regression/xlsum/tfidf_lr_char_ngram_3_5/cv_results.csv @@ -0,0 +1,11 @@ +mean_fit_time,std_fit_time,mean_score_time,std_score_time,param_clf__C,param_clf__penalty,param_vectorizer__max_features,param_vectorizer__min_df,param_vectorizer__sublinear_tf,params,split0_test_score,split1_test_score,split2_test_score,mean_test_score,std_test_score,rank_test_score +48.34804089864095,0.7433248416671462,13.002125898996988,0.6609699087900938,0.09915644566638392,l2,50000,1,True,"{'clf__C': 0.09915644566638392, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.8875511685236659,0.8829860505031544,0.8806809630952068,0.8837393940406756,0.0028548876827236658,5 +47.334686279296875,0.9140599346992135,13.011134624481201,0.4830339772618724,71.77141927992008,l2,50000,1,True,"{'clf__C': 71.77141927992008, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9031316165819406,0.9022822398273416,0.8975758650915915,0.9009965738336246,0.002443535204190771,2 +50.02394620577494,3.0403525934729787,12.564153830210367,0.3813556700344916,0.0017707168643537816,l2,50000,3,True,"{'clf__C': 0.0017707168643537816, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': True}",0.39468709867130075,0.37377507006896177,0.3846905295232416,0.38438423275450134,0.008540046773844059,8 +50.87543908754984,2.088926204753681,12.925036112467447,0.3301417941802551,0.00029152036385288323,l2,50000,5,True,"{'clf__C': 0.00029152036385288323, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.061462636805102555,0.06146160864157903,0.06146160864157903,0.061461951362753536,4.846809331036258e-07,9 +50.161128282547,0.4213276718930488,12.92906085650126,0.2728729134283714,6.440507553993708,l2,50000,5,True,"{'clf__C': 6.440507553993708, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.9028617865292637,0.9007277515532652,0.8984707992865588,0.9006867791230292,0.0017928471391298125,3 +49.69461051623026,1.0708657621841466,12.245248715082804,0.4981555794212479,0.00014610865886287189,l2,50000,2,False,"{'clf__C': 0.00014610865886287189, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.061462636805102555,0.06146160864157903,0.06146160864157903,0.061461951362753536,4.846809331036258e-07,9 +46.07549182573954,0.6665414305459753,12.248729626337687,0.05681863948756149,456.60548734461145,l2,50000,2,False,"{'clf__C': 456.60548734461145, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.9029478701832543,0.9024794500883916,0.8975663478353112,0.9009978893689857,0.00243399018339812,1 +48.53781819343567,1.2639178670867608,11.891687552134195,0.20090139864450876,0.0028483918709108036,l2,50000,1,True,"{'clf__C': 0.0028483918709108036, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.5310542914373614,0.5392717290220244,0.526067395892273,0.5321311387838863,0.005444159164104249,7 +47.872745990753174,0.4255111828928017,11.957315047581991,0.25931141778036126,0.027160511446548484,l2,50000,2,True,"{'clf__C': 0.027160511446548484, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': True}",0.8614355313700615,0.8471569944220442,0.8569706159655304,0.855187713919212,0.005963958926979536,6 +45.48766899108887,1.4686889297118892,12.011037111282349,0.32681370888241973,0.28546978577971793,l2,50000,1,True,"{'clf__C': 0.28546978577971793, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.896228519866887,0.8900289917305678,0.8865567919452947,0.8909381011809164,0.004000453327800246,4 diff --git a/logistic_regression/xlsum/tfidf_lr_char_ngram_3_5/run_metadata.json b/logistic_regression/xlsum/tfidf_lr_char_ngram_3_5/run_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..84db2e800c86def37d2e9080b8367abb354339a4 --- /dev/null +++ b/logistic_regression/xlsum/tfidf_lr_char_ngram_3_5/run_metadata.json @@ -0,0 +1,26 @@ +{ + "run_name": "tfidf_lr_char_ngram_3_5", + "tags": { + "feature_type": "tfidf", + "scaler": "none", + "n_gram_range": "(3,5)", + "dataset_version": "xlsum", + "vectorizer_class": "TfidfVectorizer" + }, + "params": { + "clf__C": "456.60548734461145", + "clf__penalty": "l2", + "vectorizer__max_features": "50000", + "vectorizer__min_df": "2", + "vectorizer__sublinear_tf": "False" + }, + "metrics": { + "accuracy": 0.9834351145038168, + "f1_macro": 0.9033173230908127, + "precision_macro": 0.9682374303516086, + "recall_macro": 0.8767026687922722, + "inference_time_total_s": 6.9378, + "inference_time_ms_per_sample": 0.132401, + "throughput_samples_per_sec": 7552.81 + } +} \ No newline at end of file diff --git a/logistic_regression/xnli/bow_maxabs_lr_char_ngram_3_5/classification_report.txt b/logistic_regression/xnli/bow_maxabs_lr_char_ngram_3_5/classification_report.txt new file mode 100644 index 0000000000000000000000000000000000000000..2730d627e20494b93790d9e7d97f785683b647a1 --- /dev/null +++ b/logistic_regression/xnli/bow_maxabs_lr_char_ngram_3_5/classification_report.txt @@ -0,0 +1,30 @@ + precision recall f1-score support + + ca 0.00 0.00 0.00 0 + da 0.00 0.00 0.00 0 + de 1.00 1.00 1.00 19945 + el 1.00 1.00 1.00 20008 + en 1.00 1.00 1.00 19929 + es 1.00 1.00 1.00 19996 + fi 0.00 0.00 0.00 0 + fr 1.00 1.00 1.00 20042 + hr 0.00 0.00 0.00 0 + it 0.00 0.00 0.00 0 + ja 0.00 0.00 0.00 0 + ko 0.00 0.00 0.00 0 + lt 0.00 0.00 0.00 0 + mk 0.00 0.00 0.00 0 + nb 0.00 0.00 0.00 0 + nl 0.00 0.00 0.00 0 + pl 0.00 0.00 0.00 0 + pt 0.00 0.00 0.00 0 + ro 0.00 0.00 0.00 0 + ru 1.00 1.00 1.00 19959 + sl 0.00 0.00 0.00 0 + sv 0.00 0.00 0.00 0 + uk 0.00 0.00 0.00 0 + zh 1.00 1.00 1.00 19966 + + accuracy 1.00 139845 + macro avg 0.29 0.29 0.29 139845 +weighted avg 1.00 1.00 1.00 139845 diff --git a/logistic_regression/xnli/bow_maxabs_lr_char_ngram_3_5/cv_results.csv b/logistic_regression/xnli/bow_maxabs_lr_char_ngram_3_5/cv_results.csv new file mode 100644 index 0000000000000000000000000000000000000000..841ec1c497840cc2160169ce46ca74f32a8d0128 --- /dev/null +++ b/logistic_regression/xnli/bow_maxabs_lr_char_ngram_3_5/cv_results.csv @@ -0,0 +1,11 @@ +mean_fit_time,std_fit_time,mean_score_time,std_score_time,param_clf__C,param_clf__penalty,param_vectorizer__max_features,param_vectorizer__min_df,params,split0_test_score,split1_test_score,split2_test_score,mean_test_score,std_test_score,rank_test_score +87.34255862236023,3.3109250442316482,28.22480885187785,1.3480048908135271,0.09915644566638392,l2,50000,1,"{'clf__C': 0.09915644566638392, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1}",0.9989916060760556,0.9989059754043127,0.9990023975940998,0.9989666596914893,4.3135841617161704e-05,5 +83.72481560707092,0.4088530121396404,26.368838389714558,0.030108705380989805,0.0029341230215132346,l2,50000,5,"{'clf__C': 0.0029341230215132346, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.995181652452264,0.9952500526006373,0.9952503076251592,0.9952273375593536,3.2304416795140286e-05,7 +88.69010814030965,4.908445443426352,27.238407532374065,0.8673042324720848,6.155564318973006,l2,50000,3,"{'clf__C': 6.155564318973006, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.9991792345842404,0.9990935839298066,0.9991684940016906,0.9991471041719125,3.809770128397477e-05,1 +88.1647515296936,3.7210939421547318,27.011999368667603,0.823662345345073,0.3686905640846153,l2,50000,3,"{'clf__C': 0.3686905640846153, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.9991470709380259,0.9990185321477425,0.9991255669627401,0.9990970566828361,5.6214957659752206e-05,4 +93.28012561798096,0.38712961509607896,28.396002928415935,0.5438995650873883,0.00029152036385288323,l2,50000,5,"{'clf__C': 0.00029152036385288323, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9715627467037432,0.975699052539363,0.976299532888322,0.9745204440438093,0.0021057262134392025,8 +87.51347430547078,4.667172352899189,26.482512553532917,1.3978448827778964,0.0467378670778782,l2,50000,5,"{'clf__C': 0.0467378670778782, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9988096404250858,0.9987560361772321,0.9988364824233079,0.9988007196752086,3.344233305958462e-05,6 +83.96201658248901,2.5245314415136684,26.34202305475871,0.6105586825602364,46.19347374377369,l2,50000,2,"{'clf__C': 46.19347374377369, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2}",0.9991685231870951,0.9990882230747032,0.9991684940016906,0.9991417467544963,3.7846958811261964e-05,2 +84.40061791737874,0.7621515333482356,25.417482376098633,0.07817566004791614,0.00028267840503514715,l2,50000,5,"{'clf__C': 0.00028267840503514715, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9711389122061391,0.9752713329954846,0.9759518454367917,0.9741206968794719,0.002126664708612171,9 +83.2713418006897,0.4168549683061458,26.005138397216797,0.8299234934294729,456.60548734461145,l2,50000,2,"{'clf__C': 456.60548734461145, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2}",0.9991685231870951,0.9990882230747032,0.9991684940016906,0.9991417467544963,3.7846958811261964e-05,2 +85.11561719576518,0.8764270933395886,24.558207273483276,0.48338978098757107,0.00010144487859320231,l2,50000,5,"{'clf__C': 0.00010144487859320231, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9632163697085536,0.9647079433176907,0.9603754649783788,0.9627665926682077,0.0017970933345578788,10 diff --git a/logistic_regression/xnli/bow_maxabs_lr_char_ngram_3_5/run_metadata.json b/logistic_regression/xnli/bow_maxabs_lr_char_ngram_3_5/run_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..99da40a2cd657137aa61ba892f62259723385ebb --- /dev/null +++ b/logistic_regression/xnli/bow_maxabs_lr_char_ngram_3_5/run_metadata.json @@ -0,0 +1,25 @@ +{ + "run_name": "bow_maxabs_lr_char_ngram_3_5", + "tags": { + "feature_type": "bow", + "scaler": "MaxAbsScaler", + "n_gram_range": "(3,5)", + "dataset_version": "xnli", + "vectorizer_class": "CountVectorizer" + }, + "params": { + "clf__C": "6.155564318973006", + "clf__penalty": "l2", + "vectorizer__max_features": "50000", + "vectorizer__min_df": "3" + }, + "metrics": { + "accuracy": 0.9992563194965856, + "f1_macro": 0.999256107795498, + "precision_macro": 0.9992562768963936, + "recall_macro": 0.9992561015664958, + "inference_time_total_s": 15.1893, + "inference_time_ms_per_sample": 0.108616, + "throughput_samples_per_sec": 9206.78 + } +} \ No newline at end of file diff --git a/logistic_regression/xnli/tfidf_lr_char_ngram_3_5/classification_report.txt b/logistic_regression/xnli/tfidf_lr_char_ngram_3_5/classification_report.txt new file mode 100644 index 0000000000000000000000000000000000000000..2730d627e20494b93790d9e7d97f785683b647a1 --- /dev/null +++ b/logistic_regression/xnli/tfidf_lr_char_ngram_3_5/classification_report.txt @@ -0,0 +1,30 @@ + precision recall f1-score support + + ca 0.00 0.00 0.00 0 + da 0.00 0.00 0.00 0 + de 1.00 1.00 1.00 19945 + el 1.00 1.00 1.00 20008 + en 1.00 1.00 1.00 19929 + es 1.00 1.00 1.00 19996 + fi 0.00 0.00 0.00 0 + fr 1.00 1.00 1.00 20042 + hr 0.00 0.00 0.00 0 + it 0.00 0.00 0.00 0 + ja 0.00 0.00 0.00 0 + ko 0.00 0.00 0.00 0 + lt 0.00 0.00 0.00 0 + mk 0.00 0.00 0.00 0 + nb 0.00 0.00 0.00 0 + nl 0.00 0.00 0.00 0 + pl 0.00 0.00 0.00 0 + pt 0.00 0.00 0.00 0 + ro 0.00 0.00 0.00 0 + ru 1.00 1.00 1.00 19959 + sl 0.00 0.00 0.00 0 + sv 0.00 0.00 0.00 0 + uk 0.00 0.00 0.00 0 + zh 1.00 1.00 1.00 19966 + + accuracy 1.00 139845 + macro avg 0.29 0.29 0.29 139845 +weighted avg 1.00 1.00 1.00 139845 diff --git a/logistic_regression/xnli/tfidf_lr_char_ngram_3_5/cv_results.csv b/logistic_regression/xnli/tfidf_lr_char_ngram_3_5/cv_results.csv new file mode 100644 index 0000000000000000000000000000000000000000..d473aff7b72230a32670521e5e7e01271fa1b7e4 --- /dev/null +++ b/logistic_regression/xnli/tfidf_lr_char_ngram_3_5/cv_results.csv @@ -0,0 +1,11 @@ +mean_fit_time,std_fit_time,mean_score_time,std_score_time,param_clf__C,param_clf__penalty,param_vectorizer__max_features,param_vectorizer__min_df,param_vectorizer__sublinear_tf,params,split0_test_score,split1_test_score,split2_test_score,mean_test_score,std_test_score,rank_test_score +79.29134209950765,2.4806448195280657,29.061942895253498,1.7220033958492245,0.09915644566638392,l2,50000,1,True,"{'clf__C': 0.09915644566638392, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.998932391578817,0.9988358840297951,0.9989431044059717,0.9989037933381946,4.8217885975268325e-05,5 +77.006285349528,1.2537343569700086,26.476049343744915,0.28546054927455655,71.77141927992008,l2,50000,1,True,"{'clf__C': 71.77141927992008, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9993454798061505,0.9992118141054063,0.9994312633003819,0.9993295190706463,9.029782611721175e-05,2 +77.67111666997273,0.5651728352763914,26.3211768468221,0.30841258520929676,0.0017707168643537816,l2,50000,3,True,"{'clf__C': 0.0017707168643537816, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': True}",0.9952969254900552,0.9979894206805723,0.9981499200247674,0.9971454220651316,0.0013087257672824938,8 +93.59193579355876,2.9353339002337133,28.429138978322346,0.21525235349741267,0.00029152036385288323,l2,50000,5,True,"{'clf__C': 0.00029152036385288323, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.9924507181742668,0.9963931215464729,0.8963680543044406,0.9617372980083934,0.04625104793700988,10 +81.76140983899434,3.1458203785311443,27.98693339029948,0.8137845004629547,6.440507553993708,l2,50000,5,True,"{'clf__C': 6.440507553993708, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.9993776339839834,0.9992868065782771,0.9994526845591308,0.9993723750404637,6.782142482646464e-05,1 +88.37728214263916,5.799360772875435,26.588401794433594,1.4521535590364305,0.00014610865886287189,l2,50000,2,False,"{'clf__C': 0.00014610865886287189, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.9955998399440229,0.996404301170814,0.9549979947644193,0.9823340452930854,0.01933229652413621,9 +76.13864072163899,2.059589188578694,25.61633062362671,0.08961600077730335,456.60548734461145,l2,50000,2,False,"{'clf__C': 456.60548734461145, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.9993293804232734,0.9991743423705053,0.9993776383385836,0.9992937870441208,8.67274625435028e-05,3 +75.90602008501689,1.4158125704822835,25.857337872187298,0.4841413270874376,0.0028483918709108036,l2,50000,1,True,"{'clf__C': 0.0028483918709108036, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9984440725815246,0.998230109202966,0.9983319383183263,0.9983353733676057,8.738394785358598e-05,7 +75.73678922653198,0.5805460714070964,25.58175532023112,0.4810786859014024,0.027160511446548484,l2,50000,2,True,"{'clf__C': 0.027160511446548484, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': True}",0.9987821297285386,0.9985141271985968,0.9987339408288032,0.998676732585313,0.00011665026462677336,6 +74.6045712629954,0.7405565692146896,24.709354241689045,1.0862678140701465,0.28546978577971793,l2,50000,1,True,"{'clf__C': 0.28546978577971793, 'clf__penalty': 'l2', 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9992006090336735,0.9991148880137868,0.9991951984459841,0.9991702318311481,3.919627707559956e-05,4 diff --git a/logistic_regression/xnli/tfidf_lr_char_ngram_3_5/run_metadata.json b/logistic_regression/xnli/tfidf_lr_char_ngram_3_5/run_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..ff4139d6cd6d1b516d31ac05da39dac8c473dc27 --- /dev/null +++ b/logistic_regression/xnli/tfidf_lr_char_ngram_3_5/run_metadata.json @@ -0,0 +1,26 @@ +{ + "run_name": "tfidf_lr_char_ngram_3_5", + "tags": { + "feature_type": "tfidf", + "scaler": "none", + "n_gram_range": "(3,5)", + "dataset_version": "xnli", + "vectorizer_class": "TfidfVectorizer" + }, + "params": { + "clf__C": "6.440507553993708", + "clf__penalty": "l2", + "vectorizer__max_features": "50000", + "vectorizer__min_df": "5", + "vectorizer__sublinear_tf": "True" + }, + "metrics": { + "accuracy": 0.9994708427187243, + "f1_macro": 0.9994706272273028, + "precision_macro": 0.9994707332842333, + "recall_macro": 0.9994705906125597, + "inference_time_total_s": 15.3909, + "inference_time_ms_per_sample": 0.110057, + "throughput_samples_per_sec": 9086.22 + } +} \ No newline at end of file diff --git a/naive_bayes/amazon_reviews_multi/bow_char_ngram_3_5/classification_report.txt b/naive_bayes/amazon_reviews_multi/bow_char_ngram_3_5/classification_report.txt new file mode 100644 index 0000000000000000000000000000000000000000..a782e5c1a9c88c7a821f1d0dff7db71cbfccb5c0 --- /dev/null +++ b/naive_bayes/amazon_reviews_multi/bow_char_ngram_3_5/classification_report.txt @@ -0,0 +1,30 @@ + precision recall f1-score support + + ca 0.00 0.00 0.00 0 + da 0.00 0.00 0.00 0 + de 0.99 1.00 1.00 20022 + el 0.00 0.00 0.00 0 + en 1.00 1.00 1.00 19795 + es 1.00 1.00 1.00 19841 + fi 0.00 0.00 0.00 0 + fr 1.00 1.00 1.00 19900 + hr 0.00 0.00 0.00 0 + it 0.00 0.00 0.00 0 + ja 1.00 1.00 1.00 19990 + ko 0.00 0.00 0.00 0 + lt 0.00 0.00 0.00 0 + mk 0.00 0.00 0.00 0 + nb 0.00 0.00 0.00 0 + nl 0.00 0.00 0.00 0 + pl 0.00 0.00 0.00 0 + pt 0.00 0.00 0.00 0 + ro 0.00 0.00 0.00 0 + ru 0.00 0.00 0.00 0 + sl 0.00 0.00 0.00 0 + sv 0.00 0.00 0.00 0 + uk 0.00 0.00 0.00 0 + zh 1.00 0.99 0.99 19993 + + accuracy 1.00 119541 + macro avg 0.25 0.25 0.25 119541 +weighted avg 1.00 1.00 1.00 119541 diff --git a/naive_bayes/amazon_reviews_multi/bow_char_ngram_3_5/cv_results.csv b/naive_bayes/amazon_reviews_multi/bow_char_ngram_3_5/cv_results.csv new file mode 100644 index 0000000000000000000000000000000000000000..75721b8fe06c16aaff6e7dbeb5cec7aa8d5989b9 --- /dev/null +++ b/naive_bayes/amazon_reviews_multi/bow_char_ngram_3_5/cv_results.csv @@ -0,0 +1,31 @@ +mean_fit_time,std_fit_time,mean_score_time,std_score_time,param_clf__alpha,param_vectorizer__max_features,param_vectorizer__min_df,params,split0_test_score,split1_test_score,split2_test_score,split3_test_score,split4_test_score,mean_test_score,std_test_score,rank_test_score +91.17361197471618,1.2821922178655072,12.6455668926239,0.39794499989672133,0.0314891164795686,50000,3,"{'clf__alpha': 0.0314891164795686, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.9825908449032207,0.9828326245433874,0.9831523202228082,0.9831062331024284,0.9825293436550516,0.9828422732853793,0.00025574916286844995,28 +91.7326434135437,1.4733591352834132,12.730443525314332,0.4251288253395669,0.847180141881997,50000,1,"{'clf__alpha': 0.847180141881997, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1}",0.9825594423660383,0.9828976887274515,0.98309860350468,0.9830640788321512,0.9825198190681016,0.9828279264996844,0.00024532209562213756,29 +94.9606258392334,0.7946344012897376,14.301486921310424,0.15718010535161658,0.004207988669606633,150000,3,"{'clf__alpha': 0.004207988669606633, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 3}",0.9980364453022387,0.9980374025559681,0.9980061393310015,0.9980053742883034,0.9979117800818541,0.9979994283118732,4.598892351256426e-05,3 +89.30396466255188,0.2919458459044766,12.530553722381592,0.05695475735127268,0.0017073967431528124,50000,5,"{'clf__alpha': 0.0017073967431528124, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9826942592374373,0.9828650935247575,0.9830342599550147,0.983096572915705,0.9825600875725183,0.9828500546410865,0.00020163438896902668,25 +90.89500212669373,1.8390059239754912,13.699767827987671,0.6567194756090013,0.0037279259033769856,150000,2,"{'clf__alpha': 0.0037279259033769856, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 2}",0.998057344820161,0.9980478290703116,0.9980166504782755,0.998026310517429,0.9979117800818541,0.9980119829936063,5.217340970108004e-05,1 +94.74207882881164,0.484165492434685,14.106930160522461,0.10477995839894226,0.0016813042706040674,100000,2,"{'clf__alpha': 0.0016813042706040674, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 2}",0.9954152199981774,0.9962017318998918,0.9957413178373691,0.9958860279034791,0.995907169983503,0.9958302935244842,0.0002558067562896042,7 +92.29581327438355,3.8043182682121177,13.100759172439576,0.6151500325357628,0.0010071984838809194,50000,1,"{'clf__alpha': 0.0010071984838809194, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1}",0.982578151511546,0.9828755057909099,0.9831288167876561,0.9831594510877251,0.9825595653704732,0.9828602981096621,0.0002576326615679945,23 +89.84074158668518,0.3180886772528717,13.060451793670655,0.12002961602185046,0.01648044642797896,100000,1,"{'clf__alpha': 0.01648044642797896, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 1}",0.9953733213969,0.996212162204238,0.9957204938481944,0.9958649692231906,0.9959073569252204,0.9958156607195487,0.00027304716068527786,16 +94.28883242607117,0.254365442414126,13.630251216888428,0.1139709398273933,0.05342937261279771,50000,3,"{'clf__alpha': 0.05342937261279771, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.9825804122532786,0.9828216266408817,0.9831523513173254,0.9831172064418574,0.9825514031075686,0.9828445999521824,0.00025507352035676227,26 +93.70098476409912,3.8439991499338246,14.097954368591308,0.5744403219378562,0.28016351587162586,100000,5,"{'clf__alpha': 0.28016351587162586, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 5}",0.9953840805214718,0.9962016878683645,0.9957206768705573,0.9958647339683941,0.9959283887707518,0.995819913599908,0.000268076750535274,12 +90.75906076431275,1.4181470562544067,14.128395557403564,0.489410458750243,0.014742753159914659,150000,2,"{'clf__alpha': 0.014742753159914659, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 2}",0.9980050784713153,0.9980479098494457,0.9980062166609477,0.9980053525554634,0.9979014495690284,0.9979932014212402,4.8722736678177185e-05,4 +94.73770880699158,2.0910889288616383,14.167535734176635,0.19887474007365363,0.0023036990230378648,100000,3,"{'clf__alpha': 0.0023036990230378648, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 3}",0.995425659462577,0.9962015963813357,0.995710014625771,0.9958755918534431,0.995907169983503,0.9958240064613259,0.0002544900162203594,9 +95.39291424751282,3.061115101295491,13.68914155960083,0.3384797214381589,0.033872555658521465,50000,3,"{'clf__alpha': 0.033872555658521465, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.9825908449032207,0.9828326245433874,0.9831523202228082,0.9831172064418574,0.9825293436550516,0.9828444679532652,0.00025804168043877854,27 +91.45093674659729,0.7205126542860341,13.978421783447265,0.07055355317745042,2.752717392942936,150000,1,"{'clf__alpha': 2.752717392942936, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 1}",0.9978692537025466,0.9979850910560234,0.9979332494726026,0.9979216044299116,0.9978597393986183,0.9979137876119406,4.566952211472056e-05,6 +94.55510935783386,1.3437934323602765,14.203328847885132,0.298276707814846,0.06338653441536253,100000,5,"{'clf__alpha': 0.06338653441536253, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 5}",0.9953312666013052,0.9962122446490791,0.9957203465998973,0.9958437659413258,0.9958967049561357,0.9958008657495485,0.0002853996749977711,18 +96.28223457336426,2.3489367424223793,14.280338430404663,0.2059013002265943,5.872283616443713,100000,2,"{'clf__alpha': 5.872283616443713, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 2}",0.995289565639033,0.9961067880699109,0.9956575504733108,0.9956756249696367,0.9958762110718776,0.9957211480447539,0.00027023809715629685,21 +91.80608234405517,0.7489502913493168,13.494134998321533,0.08812980309517107,0.0348069532678527,100000,1,"{'clf__alpha': 0.0348069532678527, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 1}",0.9953628882731266,0.996212162204238,0.9957203862681361,0.9958649692231906,0.9959073569252204,0.9958135525787825,0.00027644559611989325,17 +93.5570421218872,1.000185861643963,14.375846195220948,0.6361152347367245,0.008386394780402555,150000,5,"{'clf__alpha': 0.008386394780402555, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 5}",0.9979946871545131,0.9980478671321186,0.9979957904438527,0.9980158834499958,0.9979014138164602,0.9979911283993881,4.8816395010279364e-05,5 +94.72865319252014,0.8536343778779092,13.586042165756226,0.08914604841573437,0.003077180271250686,50000,5,"{'clf__alpha': 0.003077180271250686, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9827057703688618,0.9828540963790354,0.9830447666461598,0.9830861026774155,0.9825606633083185,0.9828502798759583,0.0001991044032958674,24 +94.21943974494934,3.2745337240882315,14.399637699127197,0.134395632515672,0.0013726318898045872,100000,1,"{'clf__alpha': 0.0013726318898045872, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 1}",0.9954152236467247,0.9961911667440839,0.9957413178373691,0.9958754873709248,0.9958861608335567,0.9958218712865318,0.0002510928618912136,10 +94.09176425933838,1.0126728520557393,14.376621007919312,0.2383479546469516,0.010842262717330157,100000,2,"{'clf__alpha': 0.010842262717330157, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 2}",0.995394187037153,0.99620173290297,0.9957204938481944,0.9959068999423093,0.9959072205318337,0.9958261068524921,0.0002652963308059539,8 +96.80487732887268,1.3705902315063596,14.144288206100464,0.0906278031234406,0.1203017887115466,100000,5,"{'clf__alpha': 0.1203017887115466, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 5}",0.9953628842944123,0.9962227723877466,0.9957206709321289,0.995843739564045,0.9959283887707518,0.995815691189817,0.00028045159712517984,14 +96.1268822669983,0.4027064544777901,14.642817258834839,0.29903908091994985,0.005488047000766045,150000,2,"{'clf__alpha': 0.005488047000766045, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 2}",0.9980260162923823,0.9980373566448845,0.9980166045794343,0.9980367415650909,0.9979117800818541,0.9980056998327292,4.757800866330826e-05,2 +96.06800017356872,0.9367795711449095,14.428577661514282,0.20458999884632365,1.2604664585649445,100000,2,"{'clf__alpha': 1.2604664585649445, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 2}",0.9953635087705344,0.9962121331037471,0.9957313451819662,0.9958440014408575,0.995949924529501,0.9958201826053212,0.0002783769301503976,11 +94.53857817649842,1.0417200309815344,13.50762939453125,0.3107748631735612,3.7958531426706337,100000,3,"{'clf__alpha': 3.7958531426706337, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 3}",0.9953107447962374,0.9961488676281385,0.9956790967456501,0.9956756735500735,0.9959288955408764,0.9957486556521952,0.00028092233433310023,19 +93.3079628944397,1.5153080136280046,13.478167009353637,0.1667338249053869,4.86964094152089,100000,3,"{'clf__alpha': 4.86964094152089, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 3}",0.9953106553699991,0.9961277881487889,0.995657974177731,0.9956757046216338,0.9959289338945374,0.9957402112425381,0.0002761428558691724,20 +91.95050320625305,0.18776399395104632,13.279050922393798,0.07291444994432261,0.12115379992469578,100000,5,"{'clf__alpha': 0.12115379992469578, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 5}",0.9953628842944123,0.9962227723877466,0.9957206709321289,0.995843739564045,0.9959283887707518,0.995815691189817,0.00028045159712517984,14 +91.42744731903076,1.0193748066833461,12.726572561264039,0.5385437365714286,2.3885558178688555,50000,2,"{'clf__alpha': 2.3885558178688555, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2}",0.9825161877718758,0.9828329464282247,0.983001729832672,0.9830735672650196,0.982477606725976,0.9827804076047535,0.00024461681676624976,30 +90.17626023292542,2.5699950382986785,12.000277900695801,0.24652011001570087,0.14413469371110316,100000,1,"{'clf__alpha': 0.14413469371110316, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 1}",0.9953733687804035,0.9962123437814784,0.9957312522100207,0.995843739564045,0.995928631324697,0.9958178671321288,0.0002733608770065399,13 +83.94767465591431,0.5108898281765405,10.560004425048827,0.4839507513868845,0.013296521457299506,50000,1,"{'clf__alpha': 0.013296521457299506, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1}",0.9826216584030999,0.982843088586692,0.9831828361395512,0.983106678660906,0.9825717554406209,0.982865203446174,0.00024702865996107553,22 diff --git a/naive_bayes/amazon_reviews_multi/bow_char_ngram_3_5/run_metadata.json b/naive_bayes/amazon_reviews_multi/bow_char_ngram_3_5/run_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..686e432b93efec1b668e735dd1b4ddd0718dbd6a --- /dev/null +++ b/naive_bayes/amazon_reviews_multi/bow_char_ngram_3_5/run_metadata.json @@ -0,0 +1,23 @@ +{ + "run_name": "bow_char_ngram_3_5", + "tags": { + "feature_type": "bow", + "n_gram_range": "(3,5)", + "dataset_version": "amazon_reviews_multi", + "vectorizer_class": "CountVectorizer" + }, + "params": { + "clf__alpha": "0.0037279259033769856", + "vectorizer__max_features": "150000", + "vectorizer__min_df": "2" + }, + "metrics": { + "accuracy": 0.9980257819492894, + "f1_macro": 0.9980291711244248, + "precision_macro": 0.9980382759926357, + "recall_macro": 0.9980325488068149, + "inference_time_total_s": 12.2041, + "inference_time_ms_per_sample": 0.102091, + "throughput_samples_per_sec": 9795.18 + } +} \ No newline at end of file diff --git a/naive_bayes/amazon_reviews_multi/tfidf_char_ngram_3_5/classification_report.txt b/naive_bayes/amazon_reviews_multi/tfidf_char_ngram_3_5/classification_report.txt new file mode 100644 index 0000000000000000000000000000000000000000..f390d35bb2605665cabb5ecedd6010cf95277481 --- /dev/null +++ b/naive_bayes/amazon_reviews_multi/tfidf_char_ngram_3_5/classification_report.txt @@ -0,0 +1,30 @@ + precision recall f1-score support + + ca 0.00 0.00 0.00 0 + da 0.00 0.00 0.00 0 + de 0.99 1.00 1.00 20022 + el 0.00 0.00 0.00 0 + en 1.00 1.00 1.00 19795 + es 1.00 1.00 1.00 19841 + fi 0.00 0.00 0.00 0 + fr 1.00 1.00 1.00 19900 + hr 0.00 0.00 0.00 0 + it 0.00 0.00 0.00 0 + ja 1.00 1.00 1.00 19990 + ko 0.00 0.00 0.00 0 + lt 0.00 0.00 0.00 0 + mk 0.00 0.00 0.00 0 + nb 0.00 0.00 0.00 0 + nl 0.00 0.00 0.00 0 + pl 0.00 0.00 0.00 0 + pt 0.00 0.00 0.00 0 + ro 0.00 0.00 0.00 0 + ru 0.00 0.00 0.00 0 + sl 0.00 0.00 0.00 0 + sv 0.00 0.00 0.00 0 + uk 0.00 0.00 0.00 0 + zh 1.00 0.99 1.00 19993 + + accuracy 1.00 119541 + macro avg 0.25 0.25 0.25 119541 +weighted avg 1.00 1.00 1.00 119541 diff --git a/naive_bayes/amazon_reviews_multi/tfidf_char_ngram_3_5/cv_results.csv b/naive_bayes/amazon_reviews_multi/tfidf_char_ngram_3_5/cv_results.csv new file mode 100644 index 0000000000000000000000000000000000000000..0b21956b25dcd6a133b5e1db480a7c0726876339 --- /dev/null +++ b/naive_bayes/amazon_reviews_multi/tfidf_char_ngram_3_5/cv_results.csv @@ -0,0 +1,31 @@ +mean_fit_time,std_fit_time,mean_score_time,std_score_time,param_clf__alpha,param_vectorizer__max_features,param_vectorizer__min_df,param_vectorizer__sublinear_tf,params,split0_test_score,split1_test_score,split2_test_score,split3_test_score,split4_test_score,mean_test_score,std_test_score,rank_test_score +95.39929056167603,2.4470200861055265,13.176284122467042,0.15952277648918708,0.0314891164795686,50000,3,True,"{'clf__alpha': 0.0314891164795686, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': True}",0.982607521891485,0.9828190176072481,0.9830840431636996,0.9831469402065539,0.9825815844015194,0.9828478214541013,0.00023440496313385697,22 +95.00100712776184,1.4108984133794786,12.856779861450196,0.0814994622619379,1.3145103232150097,50000,3,False,"{'clf__alpha': 1.3145103232150097, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': False}",0.9826172943629518,0.9828731564287443,0.9830619350872366,0.9830391721103267,0.9825412426635146,0.9828265601305548,0.000213529697077082,27 +95.53102259635925,1.0381711197678631,13.631378269195556,0.39180616418232533,0.004207053950287935,150000,3,False,"{'clf__alpha': 0.004207053950287935, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': False}",0.9980468982363028,0.9980479152961436,0.998048260862919,0.9980994747661772,0.9979432954369081,0.9980371689196901,5.1043951040893626e-05,9 +93.02116985321045,2.09437759316857,13.944597339630127,0.28160964080060724,0.02161894240657442,150000,2,True,"{'clf__alpha': 0.02161894240657442, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': True}",0.9980782924948439,0.9981631666429808,0.9980690520814747,0.9981727931844482,0.9979433645356162,0.9980853337878728,8.267652839911754e-05,2 +92.12363843917846,0.9583497317300282,13.531904935836792,0.2861532825294096,7.579479953347995,100000,2,False,"{'clf__alpha': 7.579479953347995, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.995204321503616,0.9960113419307021,0.9955199770395414,0.9955275311276224,0.9956539965253084,0.9955834336253581,0.0002603699172408775,16 +91.09246916770935,0.6973859146281868,12.805020713806153,0.24670591150191237,0.005337032762603956,50000,1,False,"{'clf__alpha': 0.005337032762603956, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': False}",0.9825432242932169,0.9828185160033911,0.9831025435860852,0.983125013406227,0.9825934677548714,0.9828365530087584,0.0002447112166270715,23 +91.5855556488037,1.5906213582732294,13.146079397201538,0.47831907474726165,0.27964859516062435,50000,5,True,"{'clf__alpha': 0.27964859516062435, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.9827991931190428,0.9828615215380951,0.9830740591034831,0.9830945570440942,0.9826142491699458,0.9828887159949323,0.00017933684909450339,18 +91.50032696723937,0.9951196314608649,13.677931547164917,0.30690302144576054,0.014618962793704957,150000,3,False,"{'clf__alpha': 0.014618962793704957, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': False}",0.9980469002321701,0.9980898361938051,0.9980273234143779,0.9980996048568292,0.9979328517305874,0.998039303285554,5.953657494458374e-05,8 +92.62637028694152,1.0917951288696204,14.031596279144287,0.5307481230031403,0.0015369603110608836,150000,2,False,"{'clf__alpha': 0.0015369603110608836, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.9980993833125744,0.9980582440117486,0.9980796558563517,0.9981518032426867,0.9979223316788901,0.9980622836204504,7.65438552546172e-05,6 +92.81882328987122,1.7335426159804501,14.15103178024292,0.23801509087547282,1.3826232179369846,150000,5,True,"{'clf__alpha': 1.3826232179369846, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.9979947113356653,0.998152722189988,0.9979748785150253,0.9980158142912071,0.9979015585003079,0.9980079369664387,8.19865474078013e-05,11 +90.84592094421387,0.9979131176358633,12.962275552749634,0.3481901344409347,8.568869785188989,50000,3,True,"{'clf__alpha': 8.568869785188989, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': True}",0.9824411526235273,0.9826773491031888,0.9829069490666246,0.982829476918872,0.9823296506668312,0.9826369156758089,0.00022107360082822795,30 +91.9925654888153,0.8503910296268355,12.982452058792115,0.27190009091470113,0.26926469100861766,50000,1,True,"{'clf__alpha': 0.26926469100861766, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9826830880800771,0.9828615215380951,0.9831795825054791,0.9831365836459122,0.9826137191619719,0.9828948989863072,0.00022999834279265781,17 +92.44876399040223,1.142661603246423,13.14770073890686,0.059145334357059764,0.0011299516083106617,50000,5,False,"{'clf__alpha': 0.0011299516083106617, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': False}",0.9826906920432167,0.9828509508576566,0.983007920784115,0.9831367944111805,0.9825719511160974,0.9828516618424532,0.00020487425938971518,21 +90.8487596988678,0.22217569782081742,12.781719541549682,0.15961367986091662,1.7123375973163957,50000,2,True,"{'clf__alpha': 1.7123375973163957, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': True}",0.9827126131654095,0.9829270301635075,0.9830933217304301,0.983069951675715,0.982559531402092,0.9828724896274308,0.0002069956918483514,20 +92.2704071521759,0.7257959377426626,14.118387460708618,0.4748661764168418,0.008386394780402555,150000,5,True,"{'clf__alpha': 0.008386394780402555, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.9980574357814342,0.9981001887027334,0.9980796107841711,0.9981308359920944,0.9979537957539115,0.9980643734028689,6.034523394602614e-05,4 +92.34343361854553,0.6869025287637713,14.090984439849853,0.179515067241329,0.27541439213320285,150000,3,False,"{'clf__alpha': 0.27541439213320285, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': False}",0.998036792269235,0.9981317995136325,0.9980064215698882,0.9980892217961627,0.9979119639825637,0.9980352398262964,7.518997528739879e-05,10 +90.78471102714539,0.23736671756998334,13.399306583404542,0.10765884738503359,0.03666421832063719,100000,5,False,"{'clf__alpha': 0.03666421832063719, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': False}",0.995373138735309,0.9962118800357403,0.9957515525852593,0.9959172237272669,0.9960226408997653,0.9958552871966682,0.00028362999031685394,14 +91.47523527145385,0.8125129512936038,13.560195112228394,0.4486833886954185,0.017654048052495066,100000,2,False,"{'clf__alpha': 0.017654048052495066, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.9953835751753687,0.9962119201074637,0.9957200856619592,0.995917095460113,0.9959806268665857,0.995842660654298,0.00027810496777749133,15 +91.89105272293091,1.2829439490749794,13.119740438461303,0.19858551656526838,0.18655260217376815,50000,3,False,"{'clf__alpha': 0.18655260217376815, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': False}",0.9826203148191323,0.9828081303294214,0.9830852164902842,0.9831157136120535,0.9825508840780749,0.9828360518657933,0.00023192087231063794,24 +92.51878423690796,0.29585722150491706,14.341725730895996,0.4652828139754281,1.2604664585649445,100000,2,False,"{'clf__alpha': 1.2604664585649445, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.9954154486137777,0.9962327386429258,0.9957941021863056,0.9958438736333566,0.9960228335529887,0.9958617993258709,0.0002711682837590445,13 +93.00417537689209,0.6815379875527396,14.837605047225953,0.10633959657365297,5.089035297840705,150000,5,True,"{'clf__alpha': 5.089035297840705, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.9977116409403828,0.9979428814055736,0.9978384798828617,0.9976489303865762,0.9976285864496455,0.9977541038130079,0.00011947841169290727,12 +93.92045693397522,0.592418391938266,14.749903202056885,0.13324408660766995,0.002259279742015694,150000,5,True,"{'clf__alpha': 0.002259279742015694, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.9980784053822204,0.9980791225788668,0.9981005341071745,0.9981203304727115,0.9979432386334524,0.9980643262348851,6.249295332418039e-05,5 +95.50227780342102,1.4097948352571903,13.734148168563843,0.24941404226434513,6.993395623207703,50000,5,True,"{'clf__alpha': 6.993395623207703, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.9826004922546514,0.9827427945273426,0.9828978940762959,0.9828746923355541,0.9824497158636087,0.9827131178114905,0.00016923026001682754,28 +96.25822048187256,0.7028795830830349,13.744584655761718,0.1091675493963046,0.012172958098369959,50000,5,False,"{'clf__alpha': 0.012172958098369959, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': False}",0.9826694167390714,0.9828185301109688,0.9829975280868406,0.9830839739393117,0.9825720060177844,0.9828282909787953,0.00019237112822193878,26 +94.93625874519348,0.4691016477494574,13.850488805770874,0.11035508609493787,7.261414516028823,50000,1,True,"{'clf__alpha': 7.261414516028823, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9824843011753531,0.9827208590990093,0.9829925217581542,0.9829167503683754,0.9824387067122488,0.9827106278226282,0.00022236016518469468,29 +94.85474271774292,0.6189348630359441,13.370518159866332,0.35741091721159773,1.6172900811143125,50000,1,True,"{'clf__alpha': 1.6172900811143125, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9827025678340138,0.9829270301635075,0.9831138970594712,0.9830699481091019,0.9825809544161263,0.982878879516444,0.0002068352543470917,19 +94.41574459075927,0.23764215059279203,12.791761112213134,0.07925111685140078,0.04938623547724713,50000,5,False,"{'clf__alpha': 0.04938623547724713, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': False}",0.9827023885623968,0.9827970254269501,0.9830200184781529,0.9830521572565417,0.9825717037298748,0.9828286586907833,0.00018414170508452923,25 +94.20133323669434,0.1810246028536852,13.733996963500976,0.1638599952982139,0.0010521761868451127,150000,3,True,"{'clf__alpha': 0.0010521761868451127, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': True}",0.998151689780625,0.9980686560234809,0.9981005341071745,0.9981412229825392,0.9979536662035593,0.9980831538194757,7.120183822690969e-05,3 +91.81547503471374,3.3870996454661406,13.010969591140746,0.5881922520552646,0.7004349545230055,150000,1,True,"{'clf__alpha': 0.7004349545230055, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9980785159086686,0.998142187031478,0.9980167911424487,0.998068315629876,0.9979328902354708,0.9980477399895884,6.991288157457678e-05,7 +81.86640620231628,0.8263499624740961,11.545135831832885,0.33804477834305835,0.001977782851246271,150000,2,True,"{'clf__alpha': 0.001977782851246271, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': True}",0.9981202691667956,0.9980895953394574,0.9981109589976698,0.9981830851466976,0.9979536662035593,0.9980915149708359,7.562531149881315e-05,1 diff --git a/naive_bayes/amazon_reviews_multi/tfidf_char_ngram_3_5/run_metadata.json b/naive_bayes/amazon_reviews_multi/tfidf_char_ngram_3_5/run_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..cb9f480a0572581fa4ba577bb5f3945299f62d4e --- /dev/null +++ b/naive_bayes/amazon_reviews_multi/tfidf_char_ngram_3_5/run_metadata.json @@ -0,0 +1,24 @@ +{ + "run_name": "tfidf_char_ngram_3_5", + "tags": { + "feature_type": "tfidf", + "n_gram_range": "(3,5)", + "dataset_version": "amazon_reviews_multi", + "vectorizer_class": "TfidfVectorizer" + }, + "params": { + "clf__alpha": "0.001977782851246271", + "vectorizer__max_features": "150000", + "vectorizer__min_df": "2", + "vectorizer__sublinear_tf": "True" + }, + "metrics": { + "accuracy": 0.9981094352565228, + "f1_macro": 0.9981128948489805, + "precision_macro": 0.9981223934474631, + "recall_macro": 0.9981159054980604, + "inference_time_total_s": 13.997, + "inference_time_ms_per_sample": 0.117089, + "throughput_samples_per_sec": 8540.49 + } +} \ No newline at end of file diff --git a/naive_bayes/europarl/bow_char_ngram_3_5/classification_report.txt b/naive_bayes/europarl/bow_char_ngram_3_5/classification_report.txt new file mode 100644 index 0000000000000000000000000000000000000000..a2b844d7bd7c37c335e30fc564fd2e7ac616dd29 --- /dev/null +++ b/naive_bayes/europarl/bow_char_ngram_3_5/classification_report.txt @@ -0,0 +1,30 @@ + precision recall f1-score support + + ca 0.00 0.00 0.00 0 + da 1.00 1.00 1.00 19996 + de 1.00 1.00 1.00 20016 + el 1.00 1.00 1.00 19956 + en 1.00 1.00 1.00 20082 + es 1.00 1.00 1.00 19992 + fi 1.00 1.00 1.00 19935 + fr 1.00 1.00 1.00 19942 + hr 0.00 0.00 0.00 0 + it 1.00 1.00 1.00 20036 + ja 0.00 0.00 0.00 0 + ko 0.00 0.00 0.00 0 + lt 0.00 0.00 0.00 0 + mk 0.00 0.00 0.00 0 + nb 0.00 0.00 0.00 0 + nl 1.00 1.00 1.00 20086 + pl 1.00 1.00 1.00 20006 + pt 1.00 1.00 1.00 19998 + ro 1.00 1.00 1.00 19916 + ru 0.00 0.00 0.00 0 + sl 0.00 0.00 0.00 0 + sv 1.00 1.00 1.00 19996 + uk 0.00 0.00 0.00 0 + zh 0.00 0.00 0.00 0 + + accuracy 1.00 259957 + macro avg 0.54 0.54 0.54 259957 +weighted avg 1.00 1.00 1.00 259957 diff --git a/naive_bayes/europarl/bow_char_ngram_3_5/cv_results.csv b/naive_bayes/europarl/bow_char_ngram_3_5/cv_results.csv new file mode 100644 index 0000000000000000000000000000000000000000..542527983e20e174a8a95075f2b7e85620fa2e74 --- /dev/null +++ b/naive_bayes/europarl/bow_char_ngram_3_5/cv_results.csv @@ -0,0 +1,31 @@ +mean_fit_time,std_fit_time,mean_score_time,std_score_time,param_clf__alpha,param_vectorizer__max_features,param_vectorizer__min_df,params,split0_test_score,split1_test_score,split2_test_score,split3_test_score,split4_test_score,mean_test_score,std_test_score,rank_test_score +170.31041350364686,5.087712779598807,37.9520779132843,0.4476890497269999,0.0314891164795686,50000,3,"{'clf__alpha': 0.0314891164795686, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.9994951977347001,0.9995817314665284,0.9994809404772889,0.9994519074026516,0.9994229176928561,0.999486538954805,5.369346530912495e-05,24 +175.7716505050659,0.846367535380327,38.3115170955658,0.3211934081680104,0.847180141881997,50000,1,"{'clf__alpha': 0.847180141881997, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1}",0.9994711680928157,0.9995625011429831,0.9994665303552712,0.9994374908608018,0.9994133103895787,0.9994702001682901,5.0675872075273396e-05,29 +173.0431224346161,2.9397406538847157,40.601206350326535,1.0923112755319748,0.004207988669606633,150000,3,"{'clf__alpha': 0.004207988669606633, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 3}",0.9995529199160204,0.9995864938138502,0.9995289760366664,0.9995096301771766,0.999475792263964,0.9995307624415355,3.759899944722545e-05,2 +169.76890840530396,5.154106887290365,38.68131628036499,0.4669250623232191,0.0017073967431528124,50000,5,"{'clf__alpha': 0.0017073967431528124, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9995096269923086,0.9995768888078325,0.9994905489558737,0.9994615078823599,0.9994277204095247,0.9994932586095798,5.014507070810724e-05,20 +179.07751512527466,4.375912902361016,42.03943924903869,0.93543966329963,0.0037279259033769856,150000,2,"{'clf__alpha': 0.0037279259033769856, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 2}",0.9995529199160204,0.9995864938138502,0.9995289760366664,0.9995096301771766,0.999475792263964,0.9995307624415355,3.759899944722545e-05,2 +173.91695699691772,4.057110516267723,39.59831576347351,0.6892177776471097,0.0016813042706040674,100000,2,"{'clf__alpha': 0.0016813042706040674, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 2}",0.9995480858279776,0.999581710511412,0.9995145664909815,0.9995096146278524,0.9994661777810353,0.9995240310478517,3.885862696283397e-05,7 +171.6405846118927,5.151503514111589,38.29736685752869,0.42576060366231516,0.0010071984838809194,50000,1,"{'clf__alpha': 0.0010071984838809194, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1}",0.9995096269923086,0.999576875210905,0.999500151536702,0.9994615078823599,0.9994277204095247,0.99949517640636,5.018395567839514e-05,19 +172.70995302200316,2.433475764579536,39.44672074317932,0.9145911286028926,0.01648044642797896,100000,1,"{'clf__alpha': 0.01648044642797896, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 1}",0.9995336595944563,0.9995865168527721,0.9995097659344333,0.9994951995839239,0.9994613821737339,0.9995173048278639,4.1786607306489185e-05,10 +175.39248061180115,1.3143361744347652,37.986717796325685,0.4493787648173785,0.05342937261279771,50000,3,"{'clf__alpha': 0.05342937261279771, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.9994903922927455,0.9995817314665284,0.9994809404772889,0.9994519074026516,0.9994229176928561,0.999485577866414,5.357274750103346e-05,25 +179.17225737571715,1.4323661288039715,42.35795755386353,2.383629645521087,0.28016351587162586,100000,5,"{'clf__alpha': 0.28016351587162586, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 5}",0.9995240442456466,0.9995768887712664,0.9994857895254918,0.9994759783532327,0.9994517633319595,0.9995028928455195,4.3712513911652075e-05,16 +184.48768444061278,2.603239280127221,45.37235770225525,0.6639843890660319,0.014742753159914659,150000,2,"{'clf__alpha': 0.014742753159914659, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 2}",0.9995577292613713,0.9995865153953984,0.9995193686386423,0.9995048066301919,0.9994709966566628,0.9995278833164534,4.0421841518233634e-05,5 +179.44705724716187,2.5589844632317265,41.32510619163513,0.5389879665232772,0.0023036990230378648,100000,3,"{'clf__alpha': 0.0023036990230378648, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 3}",0.9995480858279776,0.999581710511412,0.9995145664909815,0.9995048190294861,0.9994661777810353,0.9995230719281784,3.925973351547364e-05,8 +177.81438546180726,0.7002074594590629,39.24205422401428,0.29915027015146073,0.033872555658521465,50000,3,"{'clf__alpha': 0.033872555658521465, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.9994951992367512,0.9995817314665284,0.9994809404772889,0.9994519074026516,0.9994229176928561,0.9994865392552151,5.369351375757886e-05,23 +180.76044006347655,2.339319956812444,42.783757829666136,1.0708339819751242,2.752717392942936,150000,1,"{'clf__alpha': 2.752717392942936, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 1}",0.9995192726509875,0.9995577142930977,0.9994857895254918,0.9994759920946639,0.9994421348274855,0.9994961806783452,3.938561643254087e-05,18 +178.96871848106383,1.405193548913817,40.28265800476074,0.42666344727730404,0.06338653441536253,100000,5,"{'clf__alpha': 0.06338653441536253, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 5}",0.9995288381901938,0.9995865071973722,0.9995097659344333,0.9994903903887427,0.9994565723765574,0.9995144148174597,4.324321491421282e-05,12 +178.74380655288695,0.45866278761899104,40.02899346351624,0.170450972146708,5.872283616443713,100000,2,"{'clf__alpha': 5.872283616443713, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 2}",0.9994855892753395,0.9995577060279733,0.9994761759033236,0.9994711622177092,0.9994084876923071,0.9994798242233305,4.748905675586061e-05,28 +175.74962515830993,0.8213932113628382,41.672077655792236,1.209456547640637,0.0348069532678527,100000,1,"{'clf__alpha': 0.0348069532678527, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 1}",0.9995288381901938,0.9995865168527721,0.9995097659344333,0.9994903903887427,0.9994565723765574,0.9995144167485398,4.324643434246215e-05,11 +178.8983054637909,0.9470493337984445,41.67346038818359,0.27794050716155205,0.008386394780402555,150000,5,"{'clf__alpha': 0.008386394780402555, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 5}",0.9995577292613713,0.9995864938138502,0.9995289760366664,0.9995096261358085,0.9994709966566628,0.9995307643808719,3.963604146965771e-05,1 +173.60877265930176,1.3478250575436357,37.60326437950134,0.25491475913594625,0.003077180271250686,50000,5,"{'clf__alpha': 0.003077180271250686, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9995096269923086,0.9995721042886966,0.9994905489558737,0.9994615078823599,0.9994277204095247,0.9994923017057527,4.856066991411996e-05,21 +173.64911165237427,1.219840157353417,41.62301568984985,1.3536884410792072,0.0013726318898045872,100000,1,"{'clf__alpha': 0.0013726318898045872, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 1}",0.9995528951737938,0.999581710511412,0.9995193737526763,0.9995096146278524,0.9994661777810353,0.9995259543693539,3.9288895378395654e-05,6 +177.0690445423126,0.9492421801547933,40.341437292099,0.4175113892046495,0.010842262717330157,100000,2,"{'clf__alpha': 0.010842262717330157, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 2}",0.9995432764820061,0.9995865168527721,0.9995097659344333,0.9994951995839239,0.9994661777810353,0.9995201873268341,4.143124147411463e-05,9 +177.04590473175048,0.5800722683153338,40.06713814735413,0.54462773440075,0.1203017887115466,100000,5,"{'clf__alpha': 0.1203017887115466, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 5}",0.9995240442456466,0.9995768887712664,0.9995049939358202,0.9994855968920986,0.9994565723765574,0.9995096192442778,4.0362623758258455e-05,13 +177.18593492507935,1.5830112893494155,43.42783098220825,1.3972993589476561,0.005488047000766045,150000,2,"{'clf__alpha': 0.005488047000766045, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 2}",0.9995529199160204,0.9995864938138502,0.9995289760366664,0.9995096301771766,0.9994709966566628,0.9995298033200752,3.9023205523092166e-05,4 +176.47586584091187,0.8184609287663077,40.921466970443724,0.345584687824238,1.2604664585649445,100000,2,"{'clf__alpha': 1.2604664585649445, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 2}",0.9995096252765799,0.9995673201800374,0.9994857895254918,0.9994759783532327,0.9994517633319595,0.9994980953334602,3.927408066186985e-05,17 +177.07746114730836,0.6530516324807892,40.22073006629944,0.2714286701613174,3.7958531426706337,100000,3,"{'clf__alpha': 3.7958531426706337, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 3}",0.9994951945232858,0.9995577060279733,0.9994809887372533,0.9994711622177092,0.9994084748568733,0.9994827052726191,4.7806773407178865e-05,27 +175.7255223751068,1.3249365914371367,42.36342396736145,2.3710441934299773,4.86964094152089,100000,3,"{'clf__alpha': 4.86964094152089, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 3}",0.9994951945232858,0.9995577060279733,0.9994809887372533,0.9994711622177092,0.9994084876923071,0.9994827078397057,4.7802787556090066e-05,26 +176.17652411460875,1.2038693409823167,43.48093004226685,1.1557836351601654,0.12115379992469578,100000,5,"{'clf__alpha': 0.12115379992469578, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 5}",0.9995240442456466,0.9995768887712664,0.9995049939358202,0.9994855968920986,0.9994565723765574,0.9995096192442778,4.0362623758258455e-05,13 +175.6295262336731,0.7569930083659034,40.51132340431214,0.30551011118805455,2.3885558178688555,50000,2,"{'clf__alpha': 2.3885558178688555, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2}",0.9994615596613857,0.9995577076728532,0.9994473224804062,0.9994278860881519,0.9993796821121446,0.9994548316029883,5.8410009735450576e-05,30 +175.5863435268402,4.926049765439458,41.28920769691467,1.6127408382243726,0.14413469371110316,100000,1,"{'clf__alpha': 0.14413469371110316, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 1}",0.9995240442456466,0.9995768887712664,0.9995049939358202,0.9994855968920986,0.9994517633319595,0.9995086574353582,4.165193396830315e-05,15 +163.60998554229735,4.0456643748937635,35.29822406768799,1.298317022143155,0.013296521457299506,50000,1,"{'clf__alpha': 0.013296521457299506, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1}",0.9995000013842914,0.9995721186324468,0.999485748167922,0.9994519074026516,0.9994277344485204,0.9994875020071664,4.931210924614461e-05,22 diff --git a/naive_bayes/europarl/bow_char_ngram_3_5/run_metadata.json b/naive_bayes/europarl/bow_char_ngram_3_5/run_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..27d993e5dc3f705456a8c1662117829a09421df2 --- /dev/null +++ b/naive_bayes/europarl/bow_char_ngram_3_5/run_metadata.json @@ -0,0 +1,23 @@ +{ + "run_name": "bow_char_ngram_3_5", + "tags": { + "feature_type": "bow", + "n_gram_range": "(3,5)", + "dataset_version": "europarl", + "vectorizer_class": "CountVectorizer" + }, + "params": { + "clf__alpha": "0.008386394780402555", + "vectorizer__max_features": "150000", + "vectorizer__min_df": "5" + }, + "metrics": { + "accuracy": 0.9994960705039679, + "f1_macro": 0.9994961140566423, + "precision_macro": 0.999497045763873, + "recall_macro": 0.9994955769375848, + "inference_time_total_s": 38.6198, + "inference_time_ms_per_sample": 0.148562, + "throughput_samples_per_sec": 6731.18 + } +} \ No newline at end of file diff --git a/naive_bayes/europarl/tfidf_char_ngram_3_5/classification_report.txt b/naive_bayes/europarl/tfidf_char_ngram_3_5/classification_report.txt new file mode 100644 index 0000000000000000000000000000000000000000..a2b844d7bd7c37c335e30fc564fd2e7ac616dd29 --- /dev/null +++ b/naive_bayes/europarl/tfidf_char_ngram_3_5/classification_report.txt @@ -0,0 +1,30 @@ + precision recall f1-score support + + ca 0.00 0.00 0.00 0 + da 1.00 1.00 1.00 19996 + de 1.00 1.00 1.00 20016 + el 1.00 1.00 1.00 19956 + en 1.00 1.00 1.00 20082 + es 1.00 1.00 1.00 19992 + fi 1.00 1.00 1.00 19935 + fr 1.00 1.00 1.00 19942 + hr 0.00 0.00 0.00 0 + it 1.00 1.00 1.00 20036 + ja 0.00 0.00 0.00 0 + ko 0.00 0.00 0.00 0 + lt 0.00 0.00 0.00 0 + mk 0.00 0.00 0.00 0 + nb 0.00 0.00 0.00 0 + nl 1.00 1.00 1.00 20086 + pl 1.00 1.00 1.00 20006 + pt 1.00 1.00 1.00 19998 + ro 1.00 1.00 1.00 19916 + ru 0.00 0.00 0.00 0 + sl 0.00 0.00 0.00 0 + sv 1.00 1.00 1.00 19996 + uk 0.00 0.00 0.00 0 + zh 0.00 0.00 0.00 0 + + accuracy 1.00 259957 + macro avg 0.54 0.54 0.54 259957 +weighted avg 1.00 1.00 1.00 259957 diff --git a/naive_bayes/europarl/tfidf_char_ngram_3_5/cv_results.csv b/naive_bayes/europarl/tfidf_char_ngram_3_5/cv_results.csv new file mode 100644 index 0000000000000000000000000000000000000000..8240b8fd8f8ee9ad849f7d46dc057f595a47e9c6 --- /dev/null +++ b/naive_bayes/europarl/tfidf_char_ngram_3_5/cv_results.csv @@ -0,0 +1,31 @@ +mean_fit_time,std_fit_time,mean_score_time,std_score_time,param_clf__alpha,param_vectorizer__max_features,param_vectorizer__min_df,param_vectorizer__sublinear_tf,params,split0_test_score,split1_test_score,split2_test_score,split3_test_score,split4_test_score,mean_test_score,std_test_score,rank_test_score +172.68633251190187,2.4435147491662654,38.64220757484436,0.23726859926332172,0.0314891164795686,50000,3,True,"{'clf__alpha': 0.0314891164795686, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': True}",0.9995096126817736,0.9995769165044626,0.9994761615921453,0.9994519289430447,0.999418114813403,0.9994865469069658,5.419945338942279e-05,18 +175.92822556495668,0.7986069078227678,38.576344919204715,0.8559110053774972,1.3145103232150097,50000,3,False,"{'clf__alpha': 1.3145103232150097, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': False}",0.9994615420592343,0.999548115102108,0.9994377486682763,0.9994327309786926,0.9993748400758187,0.9994509953768258,5.630660164982033e-05,26 +181.18212156295778,1.3576997209008952,42.594406318664554,0.34762184906886495,0.004207053950287935,150000,3,False,"{'clf__alpha': 0.004207053950287935, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': False}",0.9995529357006474,0.9995769110602208,0.9995193763168806,0.999504812551507,0.9994806013087218,0.9995269273875955,3.425489776628249e-05,5 +179.682395029068,1.5402380773365136,42.811794900894164,0.29543802590695106,0.02161894240657442,150000,2,True,"{'clf__alpha': 0.02161894240657442, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': True}",0.9995529162180643,0.9995721012457014,0.9995241736873763,0.9995000132085482,0.9994709966566628,0.9995240402032707,3.615140428815334e-05,7 +177.75569343566895,1.101394126082097,41.59377641677857,0.44347578164890494,7.579479953347995,100000,2,False,"{'clf__alpha': 7.579479953347995, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.9994711740104338,0.9995528815771901,0.9994473614547548,0.9994471543418194,0.9993940612685953,0.9994625265305587,5.175439916847641e-05,24 +174.80374732017518,1.0459358407890764,38.3756824016571,0.22404004522564466,0.005337032762603956,50000,1,False,"{'clf__alpha': 0.005337032762603956, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': False}",0.99951444091937,0.999576930882976,0.9994905758549967,0.9994615406743422,0.9994229293128029,0.9994932835288977,5.1786428823571164e-05,15 +175.7810384273529,1.6030650278025542,38.62010569572449,0.6355294729750465,0.27964859516062435,50000,5,True,"{'clf__alpha': 0.27964859516062435, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.9994855764600447,0.9995625180197272,0.9994617493867075,0.9994519402836922,0.9993940749328813,0.9994711718166105,5.4688547431263856e-05,22 +177.35724511146546,2.3140161308962672,42.34589800834656,0.8455600792469573,0.014618962793704957,150000,3,False,"{'clf__alpha': 0.014618962793704957, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': False}",0.999543312058705,0.9995721213086564,0.9995241736873763,0.9995000132085482,0.9994709966566628,0.9995221233839897,3.480160414793586e-05,8 +179.8381941318512,1.2410775041774995,42.76184105873108,0.6511088422432374,0.0015369603110608836,150000,2,False,"{'clf__alpha': 0.0015369603110608836, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.9995577442930268,0.9995769110602208,0.9995241799999822,0.9995096281795388,0.9994806013087218,0.9995298129682981,3.4232536077294304e-05,4 +183.99252805709838,3.065763715394212,44.534779977798465,1.5063952076538607,1.3826232179369846,150000,5,True,"{'clf__alpha': 1.3826232179369846, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.9995192624537386,0.9995624971606295,0.9994857905935859,0.9994759853410635,0.999442136392516,0.9994971343883068,4.0896666623174904e-05,13 +183.61917119026185,3.339894809069559,41.53588457107544,0.4335716273942116,8.568869785188989,50000,3,True,"{'clf__alpha': 8.568869785188989, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': True}",0.9994327096687942,0.9995480595809865,0.9994137161216524,0.9993942885918461,0.9993316264766978,0.9994240800879954,7.06937049958788e-05,30 +179.577468585968,4.106296508981874,40.34269556999207,0.26426604777366214,0.26926469100861766,50000,1,True,"{'clf__alpha': 0.26926469100861766, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9994855764600447,0.9995625180197272,0.9994617493867075,0.9994519402836922,0.9993940749328813,0.9994711718166105,5.4688547431263856e-05,22 +180.07850928306578,1.9026909412159843,40.19584636688232,0.529133470192371,0.0011299516083106617,50000,5,False,"{'clf__alpha': 0.0011299516083106617, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': False}",0.9995192522159649,0.9995865101051221,0.9994905758549967,0.9994663365722266,0.9994229309660482,0.9994971211428716,5.4726381003571416e-05,14 +178.33516745567323,2.4801536266572843,39.37163686752319,0.7318234335563606,1.7123375973163957,50000,2,True,"{'clf__alpha': 1.7123375973163957, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': True}",0.9994615300199184,0.999552894061906,0.9994377486682763,0.9994327309786926,0.9993700359716023,0.9994509879400791,5.9258432767544464e-05,27 +181.40138845443727,2.4486699191294923,42.40215873718262,0.5414115775064003,0.008386394780402555,150000,5,True,"{'clf__alpha': 0.008386394780402555, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.9995577312988756,0.9995768911458807,0.9995241736873763,0.9995000172504678,0.9994758057014205,0.9995269238168042,3.685219985532882e-05,6 +179.89861445426942,2.2397895901823657,42.43971920013428,0.801955692110986,0.27541439213320285,150000,3,False,"{'clf__alpha': 0.27541439213320285, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': False}",0.9995336994666826,0.9995625186366538,0.9995001989541197,0.9994856005993064,0.9994565696835641,0.9995077174680652,3.698651680232671e-05,11 +176.41440687179565,2.473969634245733,41.2836829662323,0.6164389981564166,0.03666421832063719,100000,5,False,"{'clf__alpha': 0.03666421832063719, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': False}",0.9995240342500755,0.9995865231551544,0.9995001741665546,0.9994952134781729,0.9994469555010503,0.9995105801102016,4.547717644970816e-05,10 +177.02482481002806,1.6831589879613773,40.88335399627685,0.6463654999859955,0.017654048052495066,100000,2,False,"{'clf__alpha': 0.017654048052495066, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.9995288435959998,0.9995913030592991,0.9995001741665546,0.9994952199228285,0.9994517557504407,0.9995134592990246,4.60713036579524e-05,9 +174.46911997795104,1.205856225075011,38.5815269947052,0.6673262907051613,0.18655260217376815,50000,3,False,"{'clf__alpha': 0.18655260217376815, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': False}",0.9994904056294822,0.9995625380827391,0.999456982882405,0.9994471307873959,0.999398875422474,0.9994711865608993,5.426564032907957e-05,21 +174.52138967514037,2.0261869847322767,41.64196615219116,0.6475449289218526,1.2604664585649445,100000,2,False,"{'clf__alpha': 1.2604664585649445, 'vectorizer__max_features': 100000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.999514422525577,0.9995672900542285,0.999485792626277,0.9994807748432412,0.9994180999946433,0.9994932760087935,4.855711554716074e-05,16 +178.7157156944275,1.8929462191138253,42.690262746810916,0.649892735521762,5.089035297840705,150000,5,True,"{'clf__alpha': 5.089035297840705, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.9995144529580344,0.9995624835470529,0.9994617400607141,0.9994615351060427,0.9994228733110754,0.999484616996584,4.862467448434028e-05,19 +180.28352484703063,2.6027717731205633,42.5411714553833,1.0001677490465184,0.002259279742015694,150000,5,True,"{'clf__alpha': 0.002259279742015694, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.999562539891316,0.9995816924811075,0.9995241799999822,0.9995048165262943,0.9994806013087218,0.9995307660414845,3.697656955483518e-05,2 +173.7641206741333,5.267985646710402,38.77903513908386,0.3496393170402777,6.993395623207703,50000,5,True,"{'clf__alpha': 6.993395623207703, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.9994375163110342,0.9995528818581657,0.9994185238121023,0.9993990901396921,0.9993364187476648,0.9994288861737319,7.070334658923941e-05,28 +172.5068754673004,5.551517085376473,37.57438454627991,1.1329255930476316,0.012172958098369959,50000,5,False,"{'clf__alpha': 0.012172958098369959, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': False}",0.9995096333771288,0.9995769362702305,0.9994857922250743,0.9994615257887755,0.9994181343060455,0.9994904043934509,5.279342942260194e-05,17 +176.37773752212524,2.5020184078912067,39.07694482803345,1.2536158041213945,7.261414516028823,50000,1,True,"{'clf__alpha': 7.261414516028823, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9994375163110342,0.9995528818581657,0.9994185238121023,0.9993990901396921,0.9993364187476648,0.9994288861737319,7.070334658923941e-05,28 +175.7485737323761,4.2940508734710665,40.47864632606506,1.8069847548873035,1.6172900811143125,50000,1,True,"{'clf__alpha': 1.6172900811143125, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9994615300199184,0.999552894061906,0.9994377486682763,0.9994327309786926,0.9993748400758187,0.9994519487609225,5.796286641984938e-05,25 +174.29218530654907,2.8407529765026998,41.648845720291135,0.6449471954446119,0.04938623547724713,50000,5,False,"{'clf__alpha': 0.04938623547724713, 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': False}",0.9994952121214582,0.999567340028545,0.9994761738053975,0.9994519289430447,0.9994085075974835,0.9994798324991858,5.2484924624493094e-05,20 +182.19757442474366,2.3089220080909376,44.781263494491576,0.3562210154676401,0.0010521761868451127,150000,3,True,"{'clf__alpha': 0.0010521761868451127, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': True}",0.999562539891316,0.9995768911458807,0.9995289874102504,0.9995096101715948,0.9994805924202372,0.9995317242078559,3.4930327807280526e-05,1 +179.41104254722595,4.42215661073489,42.871167755126955,1.7661220014902792,0.7004349545230055,150000,1,True,"{'clf__alpha': 0.7004349545230055, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.9995240719493675,0.9995624930628428,0.999485786804644,0.9994711761459716,0.9994565633762755,0.9995000182678204,3.848222900282146e-05,12 +171.46404509544374,2.7420333372466694,38.20491189956665,1.5372990579708117,0.001977782851246271,150000,2,True,"{'clf__alpha': 0.001977782851246271, 'vectorizer__max_features': 150000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': True}",0.999562539891316,0.9995816924811075,0.9995241799999822,0.9995048165262943,0.9994806013087218,0.9995307660414845,3.697656955483518e-05,2 diff --git a/naive_bayes/europarl/tfidf_char_ngram_3_5/run_metadata.json b/naive_bayes/europarl/tfidf_char_ngram_3_5/run_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..835616135e817bd15e0824bbb9fd19915389ef22 --- /dev/null +++ b/naive_bayes/europarl/tfidf_char_ngram_3_5/run_metadata.json @@ -0,0 +1,24 @@ +{ + "run_name": "tfidf_char_ngram_3_5", + "tags": { + "feature_type": "tfidf", + "n_gram_range": "(3,5)", + "dataset_version": "europarl", + "vectorizer_class": "TfidfVectorizer" + }, + "params": { + "clf__alpha": "0.0010521761868451127", + "vectorizer__max_features": "150000", + "vectorizer__min_df": "3", + "vectorizer__sublinear_tf": "True" + }, + "metrics": { + "accuracy": 0.9995076108741061, + "f1_macro": 0.9995076408779338, + "precision_macro": 0.999508545285817, + "recall_macro": 0.9995071225683201, + "inference_time_total_s": 39.4089, + "inference_time_ms_per_sample": 0.151598, + "throughput_samples_per_sec": 6596.41 + } +} \ No newline at end of file diff --git a/naive_bayes/exorde-social-media-december-2024-week1/bow_char_ngram_3_5/classification_report.txt b/naive_bayes/exorde-social-media-december-2024-week1/bow_char_ngram_3_5/classification_report.txt new file mode 100644 index 0000000000000000000000000000000000000000..7c1423f764319d6be9931417e7d7b2ecf90aef79 --- /dev/null +++ b/naive_bayes/exorde-social-media-december-2024-week1/bow_char_ngram_3_5/classification_report.txt @@ -0,0 +1,30 @@ + precision recall f1-score support + + ca 0.93 0.93 0.93 3501 + da 0.93 0.82 0.87 3175 + de 0.99 0.91 0.95 19988 + el 1.00 0.97 0.99 2671 + en 0.81 0.97 0.88 19955 + es 0.68 0.97 0.80 20014 + fi 0.79 0.87 0.83 4341 + fr 0.98 0.99 0.98 19964 + hr 0.87 0.92 0.90 1723 + it 0.98 0.93 0.95 19940 + ja 0.95 0.87 0.91 19926 + ko 0.91 0.82 0.86 9596 + lt 0.86 0.88 0.87 385 + mk 0.96 0.95 0.95 369 + nb 0.74 0.85 0.80 1657 + nl 0.98 0.95 0.97 10778 + pl 0.96 0.95 0.96 7536 + pt 0.97 0.99 0.98 19948 + ro 0.91 0.94 0.92 2756 + ru 0.99 0.96 0.97 19824 + sl 0.52 0.77 0.62 713 + sv 0.97 0.93 0.95 6856 + uk 0.97 0.90 0.93 4517 + zh 0.82 0.53 0.64 19968 + + accuracy 0.90 240101 + macro avg 0.89 0.90 0.89 240101 +weighted avg 0.91 0.90 0.90 240101 diff --git a/naive_bayes/exorde-social-media-december-2024-week1/bow_char_ngram_3_5/cv_results.csv b/naive_bayes/exorde-social-media-december-2024-week1/bow_char_ngram_3_5/cv_results.csv new file mode 100644 index 0000000000000000000000000000000000000000..e06b99afcc0118fbeb294ae2a7c5105a01116711 --- /dev/null +++ b/naive_bayes/exorde-social-media-december-2024-week1/bow_char_ngram_3_5/cv_results.csv @@ -0,0 +1,31 @@ +mean_fit_time,std_fit_time,mean_score_time,std_score_time,param_clf__alpha,param_vectorizer__max_features,param_vectorizer__min_df,params,split0_test_score,split1_test_score,split2_test_score,split3_test_score,split4_test_score,mean_test_score,std_test_score,rank_test_score +198.84860262870788,2.8985499141630107,26.40721936225891,0.8158197185441436,0.03148911647956861,50000,3,"{'clf__alpha': np.float64(0.03148911647956861), 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.854694936867776,0.8518857293872713,0.8534397949292062,0.8536712391342302,0.8531394045639976,0.8533662209764963,0.0009063372610180765,23 +196.19953207969667,1.6811475947402066,25.346618366241454,0.5237552014444936,0.8471801418819978,50000,1,"{'clf__alpha': np.float64(0.8471801418819978), 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1}",0.8413990355502833,0.8405908494090397,0.8423523264559686,0.8416465367034935,0.8401973928693397,0.841237228197625,0.000766318764796306,27 +199.81227054595948,2.7681128713147256,28.358481073379515,0.6181397260835527,0.004207988669606638,150000,3,"{'clf__alpha': np.float64(0.004207988669606638), 'vectorizer__max_features': 150000, 'vectorizer__min_df': 3}",0.8928759148438181,0.8913683125041666,0.8919472494752375,0.8921824313682457,0.8926928189203517,0.8922133454223639,0.0005393952981209581,2 +196.2825095653534,4.4769301811524835,26.32966742515564,0.6944662691232799,0.0017073967431528124,50000,5,"{'clf__alpha': np.float64(0.0017073967431528124), 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.8583744059699757,0.8552650851502861,0.8559562049185979,0.8571949283132524,0.8568443248443822,0.856726989839299,0.0010656442689918283,20 +200.06026134490966,4.231781274817531,28.43337845802307,0.3773144452828136,0.003727925903376985,150000,2,"{'clf__alpha': np.float64(0.003727925903376985), 'vectorizer__max_features': 150000, 'vectorizer__min_df': 2}",0.893155053002304,0.8917077512931617,0.8920606880907601,0.8923716415845,0.8930785954264463,0.8924747458794344,0.0005652976384562373,1 +201.42684082984925,4.277617152519565,27.52471375465393,0.324244846566333,0.0016813042706040674,100000,2,"{'clf__alpha': np.float64(0.0016813042706040674), 'vectorizer__max_features': 100000, 'vectorizer__min_df': 2}",0.881071322425366,0.8791809236311791,0.8801195821523556,0.8813363796614263,0.8818692680282672,0.8807154951797187,0.0009542876430286883,7 +194.5423987865448,4.10337525228907,26.580855321884155,0.8973312200026481,0.0010071984838809194,50000,1,"{'clf__alpha': np.float64(0.0010071984838809194), 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1}",0.8587285599082332,0.8551033755425118,0.8563014579307188,0.8574627810927197,0.8570786843517278,0.8569349717651823,0.0012060082024610925,19 +194.03527727127076,1.8015696679194015,28.222278022766112,0.8628573421524243,0.016480446427978974,100000,1,"{'clf__alpha': np.float64(0.016480446427978974), 'vectorizer__max_features': 100000, 'vectorizer__min_df': 1}",0.8783652191303087,0.8767034442298846,0.876954631004493,0.8782995120335045,0.8782187405139323,0.8777083093824245,0.0007237922358898793,10 +195.25944147109985,3.3669601690955266,26.174091339111328,0.4943778811786903,0.05342937261279776,50000,3,"{'clf__alpha': np.float64(0.05342937261279776), 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.8538565234433584,0.8505167445433343,0.8519738271408096,0.8523552062096006,0.8520654873714856,0.8521535577417177,0.0010639521804086786,26 +198.05568060874938,2.0102332285771753,28.20524878501892,0.9812741327193453,0.2801635158716261,100000,5,"{'clf__alpha': np.float64(0.2801635158716261), 'vectorizer__max_features': 100000, 'vectorizer__min_df': 5}",0.8677618840486124,0.8671250755789504,0.8681297256491969,0.8696762938831624,0.8692509851828721,0.8683887928685587,0.0009442612276479408,17 +197.1409905910492,1.609360417855341,29.317536544799804,0.44826305060752064,0.01474275315991467,150000,2,"{'clf__alpha': np.float64(0.01474275315991467), 'vectorizer__max_features': 150000, 'vectorizer__min_df': 2}",0.8898622375010717,0.8889940707164635,0.8894651089536939,0.8895819477781414,0.891165341240839,0.889813741238042,0.0007316155953471669,5 +197.22594699859619,1.1250000035002774,27.48650016784668,0.8370755898402533,0.0023036990230378648,100000,3,"{'clf__alpha': np.float64(0.0023036990230378648), 'vectorizer__max_features': 100000, 'vectorizer__min_df': 3}",0.8807461225201217,0.8786547836195927,0.8799289371509986,0.8809375615067093,0.8815429853018163,0.8803620780198477,0.0009975648963207356,8 +197.4591600894928,4.509976477944834,25.83747625350952,1.3804963959911054,0.03387255565852149,50000,3,"{'clf__alpha': np.float64(0.03387255565852149), 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.854670148330258,0.8518250981604174,0.85337649041939,0.8536031016294219,0.85299002322785,0.8532929723534675,0.0009215423946323017,24 +201.36441011428832,9.133514334552174,29.071390056610106,0.7385001077597216,2.752717392942941,150000,1,"{'clf__alpha': np.float64(2.752717392942941), 'vectorizer__max_features': 150000, 'vectorizer__min_df': 1}",0.8721042546616155,0.8701694050230865,0.8741033839450902,0.8722389912903713,0.872302484898734,0.8721837039637794,0.0012462783993736624,13 +201.0686677455902,8.932328372146294,27.050504684448242,0.42156411866917515,0.06338653441536259,100000,5,"{'clf__alpha': np.float64(0.06338653441536259), 'vectorizer__max_features': 100000, 'vectorizer__min_df': 5}",0.8742521830805473,0.8731312261563904,0.8737294751964028,0.8742373604770446,0.8755729191984916,0.8741846328217754,0.0008064138358781386,12 +196.9793462753296,6.216462498474484,26.939627265930177,0.3161584528145298,5.872283616443723,100000,2,"{'clf__alpha': np.float64(5.872283616443723), 'vectorizer__max_features': 100000, 'vectorizer__min_df': 2}",0.8299709805656486,0.8301090311870784,0.8319702335631982,0.8302578729705257,0.8331702981971278,0.8310956832967158,0.001265640542571951,30 +195.2045087814331,2.9237782186297148,27.869155168533325,1.362977545210179,0.034806953267852714,100000,1,"{'clf__alpha': np.float64(0.034806953267852714), 'vectorizer__max_features': 100000, 'vectorizer__min_df': 1}",0.8761330793143055,0.8745190552815642,0.8754766924938747,0.8767121992986256,0.8770155436309098,0.875971314003856,0.0008965712893347233,11 +199.47459020614625,2.639220626107126,28.95550193786621,1.1643822897354188,0.008386394780402562,150000,5,"{'clf__alpha': np.float64(0.008386394780402562), 'vectorizer__max_features': 150000, 'vectorizer__min_df': 5}",0.8915524310683609,0.8902748079733876,0.8906760674448275,0.8909464719010334,0.8921033986772103,0.891110635412964,0.000647328168133141,4 +200.33923325538635,7.009334077574621,25.962979221343993,0.8197193993443881,0.003077180271250686,50000,5,"{'clf__alpha': np.float64(0.003077180271250686), 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.8581318213137843,0.8547060837171978,0.8554920083713515,0.8565561050619861,0.8563575221205149,0.856248708116967,0.0011493244298265318,21 +194.54922394752504,5.982425124433334,27.936185789108276,1.2436441736596269,0.0013726318898045872,100000,1,"{'clf__alpha': np.float64(0.0013726318898045872), 'vectorizer__max_features': 100000, 'vectorizer__min_df': 1}",0.8813899539630964,0.8796131711632746,0.8804320781922462,0.8815268719165816,0.8819129151795609,0.8809749980829521,0.0008373501248229087,6 +194.96736092567443,1.9579865680211688,27.71783266067505,1.309699197564463,0.010842262717330166,100000,2,"{'clf__alpha': np.float64(0.010842262717330166), 'vectorizer__max_features': 100000, 'vectorizer__min_df': 2}",0.8790572364041385,0.8771976031943653,0.8777150082889262,0.8792982838411326,0.8787863067495878,0.8784108876956301,0.0008127097228163858,9 +197.23320474624634,2.2337269880930934,28.56111888885498,1.5372141318411559,0.12030178871154672,100000,5,"{'clf__alpha': np.float64(0.12030178871154672), 'vectorizer__max_features': 100000, 'vectorizer__min_df': 5}",0.8716137655035624,0.8706024712535422,0.8717921004796397,0.872007380777097,0.8735386152247028,0.8719108666477089,0.0009458491853445589,14 +197.7459002017975,5.6724493182682485,30.52015142440796,1.3074016986245989,0.0054880470007660455,150000,2,"{'clf__alpha': np.float64(0.0054880470007660455), 'vectorizer__max_features': 150000, 'vectorizer__min_df': 2}",0.8921716184320442,0.8911481144502207,0.8913453348552159,0.8917989453477633,0.8926593826526609,0.8918246791475809,0.0005486838392529371,3 +195.84744844436645,4.782384042888245,27.47884306907654,1.0987291774551384,1.2604664585649468,100000,2,"{'clf__alpha': np.float64(1.2604664585649468), 'vectorizer__max_features': 100000, 'vectorizer__min_df': 2}",0.8631249570957603,0.8634151819055682,0.8647383928080717,0.8653859200134679,0.8641247396471864,0.8641578382940109,0.0008324308805993282,18 +199.74891738891603,5.861214126870427,27.836450719833373,1.0310969182570315,3.7958531426706403,100000,3,"{'clf__alpha': np.float64(3.7958531426706403), 'vectorizer__max_features': 100000, 'vectorizer__min_df': 3}",0.8521056322030375,0.8502454302297463,0.8535076491931486,0.8518555674220935,0.8533563263149718,0.8522141210725994,0.0011827021606641438,25 +195.33834538459777,5.65265476189015,27.83552565574646,0.2928285065682966,4.869640941520899,100000,3,"{'clf__alpha': np.float64(4.869640941520899), 'vectorizer__max_features': 100000, 'vectorizer__min_df': 3}",0.8388107871962075,0.8388909640125735,0.8413505168828171,0.8392883072072393,0.8414706609675634,0.8399622472532802,0.0011941781883992725,28 +192.45549793243407,3.2846807837487955,27.282026624679567,1.2236745830349585,0.12115379992469588,100000,5,"{'clf__alpha': np.float64(0.12115379992469588), 'vectorizer__max_features': 100000, 'vectorizer__min_df': 5}",0.8716671328532507,0.870543513774262,0.8717521469641089,0.8720136913972096,0.8735407816288161,0.8719034533235295,0.0009613712049897544,15 +194.8657655239105,5.892359966021688,25.59177174568176,1.120147441122217,2.38855581786886,50000,2,"{'clf__alpha': np.float64(2.38855581786886), 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2}",0.8383275414986455,0.8363830139125384,0.838666812658043,0.8377923923227195,0.8365197036001074,0.8375378927984107,0.0009309381946942766,29 +202.92109942436218,13.60054933106762,24.33919768333435,0.4321495302808992,0.1441346937111033,100000,1,"{'clf__alpha': np.float64(0.1441346937111033), 'vectorizer__max_features': 100000, 'vectorizer__min_df': 1}",0.8710087223422912,0.8699143389452747,0.8710673530338487,0.8717526092846858,0.8728002904956366,0.8713086628203474,0.0009501973854859281,16 +178.71372871398927,5.390764709733593,21.14928674697876,1.1355549845916653,0.013296521457299506,50000,1,"{'clf__alpha': np.float64(0.013296521457299506), 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1}",0.8560825704969504,0.8528753687525263,0.8545187620685879,0.8553037429460916,0.8548078985789203,0.8547176685686153,0.0010628465846754317,22 diff --git a/naive_bayes/exorde-social-media-december-2024-week1/bow_char_ngram_3_5/run_metadata.json b/naive_bayes/exorde-social-media-december-2024-week1/bow_char_ngram_3_5/run_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..e27d0ef998a39415af92e544bb113db851066c8b --- /dev/null +++ b/naive_bayes/exorde-social-media-december-2024-week1/bow_char_ngram_3_5/run_metadata.json @@ -0,0 +1,23 @@ +{ + "run_name": "bow_char_ngram_3_5", + "tags": { + "feature_type": "bow", + "n_gram_range": "(3,5)", + "dataset_version": "exorde-social-media-december-2024-week1", + "vectorizer_class": "CountVectorizer" + }, + "params": { + "clf__alpha": "0.003727925903376985", + "vectorizer__max_features": "150000", + "vectorizer__min_df": "2" + }, + "metrics": { + "accuracy": 0.9017538452567878, + "f1_macro": 0.8920617425563245, + "precision_macro": 0.8947399877920855, + "recall_macro": 0.8985844045189012, + "inference_time_total_s": 27.2778, + "inference_time_ms_per_sample": 0.11361, + "throughput_samples_per_sec": 8802.06 + } +} \ No newline at end of file diff --git a/naive_bayes/exorde-social-media-december-2024-week1/tfidf_char_ngram_3_5/classification_report.txt b/naive_bayes/exorde-social-media-december-2024-week1/tfidf_char_ngram_3_5/classification_report.txt new file mode 100644 index 0000000000000000000000000000000000000000..e4e5aeb4e0e16e65206bf687a08c67b47ea93168 --- /dev/null +++ b/naive_bayes/exorde-social-media-december-2024-week1/tfidf_char_ngram_3_5/classification_report.txt @@ -0,0 +1,30 @@ + precision recall f1-score support + + ca 0.96 0.92 0.94 3501 + da 0.93 0.84 0.88 3175 + de 0.98 0.91 0.95 19988 + el 1.00 0.97 0.99 2671 + en 0.79 0.97 0.87 19955 + es 0.68 0.98 0.80 20014 + fi 0.79 0.88 0.83 4341 + fr 0.98 0.99 0.98 19964 + hr 0.90 0.92 0.91 1723 + it 0.97 0.94 0.95 19940 + ja 0.96 0.86 0.91 19926 + ko 0.94 0.81 0.87 9596 + lt 0.93 0.88 0.90 385 + mk 0.99 0.93 0.96 369 + nb 0.80 0.82 0.81 1657 + nl 0.98 0.96 0.97 10778 + pl 0.97 0.95 0.96 7536 + pt 0.97 0.99 0.98 19948 + ro 0.95 0.94 0.94 2756 + ru 0.99 0.96 0.97 19824 + sl 0.70 0.73 0.72 713 + sv 0.98 0.93 0.95 6856 + uk 0.98 0.89 0.93 4517 + zh 0.83 0.54 0.66 19968 + + accuracy 0.90 240101 + macro avg 0.91 0.90 0.90 240101 +weighted avg 0.91 0.90 0.90 240101 diff --git a/naive_bayes/exorde-social-media-december-2024-week1/tfidf_char_ngram_3_5/cv_results.csv b/naive_bayes/exorde-social-media-december-2024-week1/tfidf_char_ngram_3_5/cv_results.csv new file mode 100644 index 0000000000000000000000000000000000000000..0bddbf0789b2726e49a9b75819c228797ece26dd --- /dev/null +++ b/naive_bayes/exorde-social-media-december-2024-week1/tfidf_char_ngram_3_5/cv_results.csv @@ -0,0 +1,31 @@ +mean_fit_time,std_fit_time,mean_score_time,std_score_time,param_clf__alpha,param_vectorizer__max_features,param_vectorizer__min_df,param_vectorizer__sublinear_tf,params,split0_test_score,split1_test_score,split2_test_score,split3_test_score,split4_test_score,mean_test_score,std_test_score,rank_test_score +194.8067481994629,11.157249997518186,26.03569688796997,0.8726033344184816,0.03148911647956861,50000,3,True,"{'clf__alpha': np.float64(0.03148911647956861), 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': True}",0.8670551350934718,0.8663234078535352,0.8675722146586932,0.8663471550738174,0.8667471981845493,0.8668090221728134,0.00046818778923977863,14 +193.4535388469696,7.919030213210218,25.771350955963136,0.8700387010779081,1.3145103232150122,50000,3,False,"{'clf__alpha': np.float64(1.3145103232150122), 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': False}",0.7753832227120293,0.7748004078359111,0.7762564962266826,0.7754766962607298,0.7745455536412654,0.7752924753353236,0.0005952362817815891,23 +200.20854086875914,5.976392212956508,29.03509740829468,0.8539116033378128,0.004207053950287938,150000,3,False,"{'clf__alpha': np.float64(0.004207053950287938), 'vectorizer__max_features': 150000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': False}",0.9014353065862103,0.8993836861772028,0.8997359289205482,0.897955306979474,0.9001469234466706,0.8997314304220211,0.0011270660331926473,5 +192.56922783851624,1.1815797632993132,28.412693405151366,0.3742799581418529,0.02161894240657444,150000,2,True,"{'clf__alpha': np.float64(0.02161894240657444), 'vectorizer__max_features': 150000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': True}",0.8982322415458045,0.897373241453456,0.8974315705527706,0.8949973875989069,0.8975360278924206,0.8971140938086718,0.0011024225048847593,8 +198.48401851654052,9.020224618754648,27.45368037223816,0.5719612523260679,7.579479953348009,100000,2,False,"{'clf__alpha': np.float64(7.579479953348009), 'vectorizer__max_features': 100000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.6819580773644782,0.6807412868212254,0.6819140781520788,0.6826195116722333,0.6802242330262188,0.6814914374072469,0.0008760664861991749,29 +198.82388429641725,6.890048567145885,26.219569158554076,0.5776772014682187,0.005337032762603957,50000,1,False,"{'clf__alpha': np.float64(0.005337032762603957), 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': False}",0.8702502768633552,0.8680983178300142,0.8687084200561225,0.8684787875610972,0.8686282339910859,0.8688328072603351,0.0007391004187863366,12 +196.87145800590514,7.319932829193065,26.876163530349732,0.8878366736581031,0.27964859516062457,50000,5,True,"{'clf__alpha': np.float64(0.27964859516062457), 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.8315165482096291,0.8286363617205944,0.8315998685707083,0.8327451579695495,0.8327733491385754,0.8314542571218112,0.0015081144593997275,19 +197.83445382118225,1.9007796821997731,29.817796325683595,0.34478104140713456,0.014618962793704957,150000,3,False,"{'clf__alpha': np.float64(0.014618962793704957), 'vectorizer__max_features': 150000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': False}",0.8991541447266259,0.8982281807504737,0.8979993481369997,0.8959902303258754,0.8980691928792616,0.8978882193638473,0.00103591545738909,7 +194.71314086914063,1.3529709762778321,30.27339925765991,0.6590924542362594,0.0015369603110608836,150000,2,False,"{'clf__alpha': np.float64(0.0015369603110608836), 'vectorizer__max_features': 150000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.9022825630963919,0.9002973814025239,0.9004582527611916,0.8993572197010082,0.9005616778531133,0.9005914189628458,0.0009474483791847309,2 +196.98335099220276,2.8344880483813375,29.525963163375856,0.5149137815892124,1.382623217936987,150000,5,True,"{'clf__alpha': np.float64(1.382623217936987), 'vectorizer__max_features': 150000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.7882792728460931,0.7863350756142798,0.7894740172495746,0.7866664106745548,0.7860830819044078,0.7873675716577819,0.0013019908462597806,21 +195.4759512424469,1.9102022474143343,25.513429594039916,0.17778664855821763,8.568869785189005,50000,3,True,"{'clf__alpha': np.float64(8.568869785189005), 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': True}",0.6763003061160328,0.6750585195547286,0.6764277119128247,0.675942999195302,0.6734752303872679,0.6754409534332312,0.0010931195764928032,30 +192.46249346733094,2.2353523092172494,26.866796588897706,0.9112564175180365,0.26926469100861794,50000,1,True,"{'clf__alpha': np.float64(0.26926469100861794), 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.8332075389816885,0.8298707868443592,0.8324783612538788,0.834491894126935,0.8335920386597232,0.832728123973317,0.0015693201951785267,18 +193.34971046447754,6.42687437649471,26.42855257987976,0.500859379060995,0.0011299516083106617,50000,5,False,"{'clf__alpha': np.float64(0.0011299516083106617), 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': False}",0.8708595550191692,0.8677471156071664,0.8687730070618951,0.8690814618367559,0.8688335703528766,0.8690589419755727,0.0010095696153252767,11 +186.61898703575133,1.9397414970705076,25.756798458099365,0.22097789033708723,1.7123375973163988,50000,2,True,"{'clf__alpha': np.float64(1.7123375973163988), 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': True}",0.7618408924642113,0.7609444330995462,0.7626867111225364,0.7626401057463728,0.7607166288459304,0.7617657542557195,0.0008238361969667453,25 +197.78706588745118,5.142697868944691,30.062007570266722,1.5523828781301992,0.008386394780402562,150000,5,True,"{'clf__alpha': np.float64(0.008386394780402562), 'vectorizer__max_features': 150000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.9003012688834394,0.8988223944876914,0.898736807348393,0.897094649275758,0.8990517347069797,0.8988013709404523,0.001022730183641983,6 +207.62618827819824,3.6449178436608287,30.080564498901367,0.4672693601014137,0.27541439213320307,150000,3,False,"{'clf__alpha': np.float64(0.27541439213320307), 'vectorizer__max_features': 150000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': False}",0.8570345355298565,0.8559624470651936,0.8580333338592118,0.8575163269302714,0.8587047699173613,0.8574502826603789,0.000927852279063346,16 +189.5176525592804,1.0219347050231888,28.029519701004027,0.17888263065202334,0.036664218320637224,100000,5,False,"{'clf__alpha': np.float64(0.036664218320637224), 'vectorizer__max_features': 100000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': False}",0.8856850694294414,0.8860311835515926,0.885952043354381,0.8858120794406285,0.8862407886309026,0.8859442328813891,0.00018984043923098208,10 +195.0661904811859,5.965133253846554,28.189308309555052,1.4434781924889426,0.017654048052495083,100000,2,False,"{'clf__alpha': np.float64(0.017654048052495083), 'vectorizer__max_features': 100000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.8877553399378831,0.8873958822198595,0.8876746415767105,0.88648901901474,0.887773103008557,0.88741759715155,0.00048358149985547983,9 +206.74314217567445,3.9714130408334043,27.069928073883055,0.3816924207588245,0.18655260217376832,50000,3,False,"{'clf__alpha': np.float64(0.18655260217376832), 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': False}",0.8472642114888487,0.8443231450296285,0.843192042485406,0.8467863531404493,0.8474713766836083,0.8458074257655881,0.0017258374843377008,17 +193.31830563545228,7.794895249273176,28.010476064682006,0.30967643729197575,1.2604664585649468,100000,2,False,"{'clf__alpha': np.float64(1.2604664585649468), 'vectorizer__max_features': 100000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': False}",0.7866078301776103,0.7855850255740874,0.7882300993122157,0.7867673560246606,0.7849781411731206,0.7864336904523389,0.001114234977886146,22 +193.4433472633362,3.4913966165149226,29.148654842376708,1.4963621509872373,5.089035297840714,150000,5,True,"{'clf__alpha': np.float64(5.089035297840714), 'vectorizer__max_features': 150000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.709526398309999,0.7099181224279806,0.7101481323463773,0.710218067566842,0.7086502008281238,0.7096921842958646,0.0005742306886885951,26 +202.44547472000122,6.194536313456865,31.152665901184083,0.6522462252660091,0.002259279742015696,150000,5,True,"{'clf__alpha': np.float64(0.002259279742015696), 'vectorizer__max_features': 150000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.9019129550905052,0.8998889135574988,0.8997202732139216,0.8989249627359969,0.900232836705073,0.900135988260599,0.0009866547994073504,4 +194.42123918533326,8.137379874085067,26.224811935424803,0.8177917063605009,6.993395623207715,50000,5,True,"{'clf__alpha': np.float64(6.993395623207715), 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': True}",0.6884019896179371,0.6877524227563908,0.6887510764113296,0.6888943981388925,0.6869368234924117,0.6881473420833923,0.0007223226134613494,27 +189.0775972366333,1.5708262384287355,25.100347328186036,0.4892752152482508,0.01217295809836997,50000,5,False,"{'clf__alpha': np.float64(0.01217295809836997), 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': False}",0.8686554125200336,0.867654980578992,0.8681548433361671,0.8679012484751153,0.8678514362989143,0.8680435842418446,0.00034493638175943077,13 +196.2008424282074,0.9253334764819481,27.549531269073487,0.3634505953520919,7.261414516028836,50000,1,True,"{'clf__alpha': np.float64(7.261414516028836), 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.6862102853329851,0.6860242283388912,0.6868061933152164,0.6869807151635111,0.6846872824781235,0.6861417409257455,0.000809855748784935,28 +195.0577661037445,7.344112553756742,26.419468069076537,0.4816686741046733,1.6172900811143154,50000,1,True,"{'clf__alpha': np.float64(1.6172900811143154), 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.7657526974086913,0.7643176163345967,0.7659784942886967,0.7655217483502129,0.764294677692182,0.765173046814876,0.0007224440223344748,24 +187.44958896636962,1.1460549937373956,25.247872829437256,0.2910812598498079,0.04938623547724718,50000,5,False,"{'clf__alpha': np.float64(0.04938623547724718), 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5, 'vectorizer__sublinear_tf': False}",0.8651659862181935,0.8644857083957348,0.8657636439950259,0.8645838236542379,0.8642023897367052,0.8648403103999793,0.000558046677456029,15 +200.6359670162201,5.660906166793559,28.277960777282715,1.1784610773660755,0.0010521761868451127,150000,3,True,"{'clf__alpha': np.float64(0.0010521761868451127), 'vectorizer__max_features': 150000, 'vectorizer__min_df': 3, 'vectorizer__sublinear_tf': True}",0.9028195380278149,0.89980971002599,0.9008951977184368,0.8995882558647894,0.9004635152300833,0.9007152433734229,0.0011501215679110045,1 +202.50694303512574,8.553390423754639,26.62701025009155,0.43910677567772227,0.7004349545230062,150000,1,True,"{'clf__alpha': np.float64(0.7004349545230062), 'vectorizer__max_features': 150000, 'vectorizer__min_df': 1, 'vectorizer__sublinear_tf': True}",0.8180483961138277,0.816351977167132,0.8193374679248296,0.8160042016483379,0.8162497176557405,0.8171983521019734,0.001291560643137489,20 +187.84530243873596,6.376836091664769,23.984230279922485,0.9397245706110677,0.0019777828512462727,150000,2,True,"{'clf__alpha': np.float64(0.0019777828512462727), 'vectorizer__max_features': 150000, 'vectorizer__min_df': 2, 'vectorizer__sublinear_tf': True}",0.9017744753705523,0.8999181180658254,0.9000485977521935,0.8988999676474072,0.9002457580816836,0.9001773833835325,0.000924226500491721,3 diff --git a/naive_bayes/exorde-social-media-december-2024-week1/tfidf_char_ngram_3_5/run_metadata.json b/naive_bayes/exorde-social-media-december-2024-week1/tfidf_char_ngram_3_5/run_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..ba6878c89b49e7da1f66279c962a7a3b2e1f6431 --- /dev/null +++ b/naive_bayes/exorde-social-media-december-2024-week1/tfidf_char_ngram_3_5/run_metadata.json @@ -0,0 +1,24 @@ +{ + "run_name": "tfidf_char_ngram_3_5", + "tags": { + "feature_type": "tfidf", + "n_gram_range": "(3,5)", + "dataset_version": "exorde-social-media-december-2024-week1", + "vectorizer_class": "TfidfVectorizer" + }, + "params": { + "clf__alpha": "0.0010521761868451127", + "vectorizer__max_features": "150000", + "vectorizer__min_df": "3", + "vectorizer__sublinear_tf": "True" + }, + "metrics": { + "accuracy": 0.9033823266042207, + "f1_macro": 0.9011256971856657, + "precision_macro": 0.9135245793553155, + "recall_macro": 0.8960684387553793, + "inference_time_total_s": 27.5726, + "inference_time_ms_per_sample": 0.114838, + "throughput_samples_per_sec": 8707.95 + } +} \ No newline at end of file diff --git a/naive_bayes/flores_plus/bow_char_ngram_3_5/classification_report.txt b/naive_bayes/flores_plus/bow_char_ngram_3_5/classification_report.txt new file mode 100644 index 0000000000000000000000000000000000000000..58aaaab1db89fc82bc7388d6df783e747e61cc59 --- /dev/null +++ b/naive_bayes/flores_plus/bow_char_ngram_3_5/classification_report.txt @@ -0,0 +1,30 @@ + precision recall f1-score support + + ca 1.00 1.00 1.00 80 + da 0.87 0.90 0.89 94 + de 0.98 0.97 0.98 61 + el 1.00 1.00 1.00 62 + en 1.00 1.00 1.00 94 + es 0.97 0.98 0.97 58 + fi 1.00 1.00 1.00 84 + fr 1.00 1.00 1.00 55 + hr 0.99 1.00 0.99 98 + it 1.00 1.00 1.00 55 + ja 1.00 0.98 0.99 199 + ko 1.00 0.98 0.99 205 + lt 0.98 1.00 0.99 91 + mk 1.00 1.00 1.00 81 + nb 0.90 0.88 0.89 103 + nl 0.99 1.00 0.99 72 + pl 1.00 1.00 1.00 83 + pt 0.98 0.99 0.98 80 + ro 1.00 1.00 1.00 69 + ru 1.00 1.00 1.00 83 + sl 1.00 0.99 0.99 100 + sv 0.98 0.98 0.98 98 + uk 1.00 1.00 1.00 87 + zh 0.00 0.00 0.00 0 + + accuracy 0.98 2092 + macro avg 0.94 0.94 0.94 2092 +weighted avg 0.98 0.98 0.98 2092 diff --git a/naive_bayes/flores_plus/bow_char_ngram_3_5/cv_results.csv b/naive_bayes/flores_plus/bow_char_ngram_3_5/cv_results.csv new file mode 100644 index 0000000000000000000000000000000000000000..ebc2db39a6c27c6b6b5eec2fd6572388b506a7a1 --- /dev/null +++ b/naive_bayes/flores_plus/bow_char_ngram_3_5/cv_results.csv @@ -0,0 +1,31 @@ +mean_fit_time,std_fit_time,mean_score_time,std_score_time,param_clf__alpha,param_vectorizer__max_features,param_vectorizer__min_df,params,split0_test_score,split1_test_score,split2_test_score,split3_test_score,split4_test_score,mean_test_score,std_test_score,rank_test_score +2.440985584259033,0.1357939657861873,0.24460358619689943,0.009938398245004598,0.03148911647956861,50000,3,"{'clf__alpha': np.float64(0.03148911647956861), 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.95955406687566,0.9642280924590816,0.9593317063243615,0.9635304894295919,0.9669500562513731,0.9627188822680136,0.0029095797704802827,17 +2.766551876068115,0.0991465409011878,0.2416449546813965,0.007226284392918075,0.8471801418819978,50000,1,"{'clf__alpha': np.float64(0.8471801418819978), 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1}",0.974297083588406,0.9727955622896699,0.973601339705935,0.977376303631553,0.9751616119330783,0.9746463802297285,0.001572106254374586,7 +2.8059381008148194,0.04330065724686185,0.26615185737609864,0.00453417848823157,0.004207988669606638,150000,3,"{'clf__alpha': np.float64(0.004207988669606638), 'vectorizer__max_features': 150000, 'vectorizer__min_df': 3}",0.9613087253475083,0.9586859853629235,0.960385480534416,0.961623403020603,0.962487433022702,0.9608982054576305,0.0012943636995234795,22 +2.5843464374542235,0.14493411121186672,0.2213191032409668,0.011148219686997326,0.0017073967431528124,50000,5,"{'clf__alpha': np.float64(0.0017073967431528124), 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.953521011956793,0.9551441845095254,0.952064991851793,0.9586918707301476,0.9587737257041936,0.9556391569504905,0.00270742589101117,30 +2.642800521850586,0.13621643790259194,0.2777727127075195,0.007648676713334174,0.003727925903376985,150000,2,"{'clf__alpha': np.float64(0.003727925903376985), 'vectorizer__max_features': 150000, 'vectorizer__min_df': 2}",0.9606147180855842,0.9584738343944664,0.960106868201885,0.963554080722558,0.9630520747890516,0.961160315238709,0.0018938571027061638,21 +2.7137946128845214,0.15033223572934723,0.2652416229248047,0.005183826740453686,0.0016813042706040674,100000,2,"{'clf__alpha': np.float64(0.0016813042706040674), 'vectorizer__max_features': 100000, 'vectorizer__min_df': 2}",0.9582389803801941,0.9564212603212856,0.9585006227503451,0.9612155510037148,0.9592228493127039,0.9587198527536487,0.001552052995088869,27 +2.6936380863189697,0.06547937705962215,0.25110979080200196,0.01172217293070559,0.0010071984838809194,50000,1,"{'clf__alpha': np.float64(0.0010071984838809194), 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1}",0.9521744536436213,0.9551953344081029,0.953463117439355,0.9592234995751663,0.9599278850068316,0.9559968580146154,0.003083415169701254,29 +2.802554893493652,0.1242861535370986,0.2808356761932373,0.009927498484237147,0.016480446427978974,100000,1,"{'clf__alpha': np.float64(0.016480446427978974), 'vectorizer__max_features': 100000, 'vectorizer__min_df': 1}",0.9631621721714284,0.9609932432713933,0.9637506891152887,0.9636596276913295,0.9645782289855006,0.9632287922469882,0.0012067387860875646,16 +2.6316571712493895,0.057475461559078136,0.243918514251709,0.005272261518506407,0.05342937261279776,50000,3,"{'clf__alpha': np.float64(0.05342937261279776), 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.962299650253539,0.9643675645662344,0.9607318171942375,0.9643152323060874,0.9669568958324395,0.9637342320305076,0.0021069766550762324,15 +2.6695472240447997,0.06114278925506449,0.24832229614257811,0.006655237449362861,0.2801635158716261,100000,5,"{'clf__alpha': np.float64(0.2801635158716261), 'vectorizer__max_features': 100000, 'vectorizer__min_df': 5}",0.973215352158446,0.9706293596505536,0.970290726088948,0.97179610930507,0.9727670979589285,0.9717397290323891,0.0011461813949579678,8 +2.8206034660339356,0.07214951972061175,0.29311308860778806,0.006287650387851823,0.01474275315991467,150000,2,"{'clf__alpha': np.float64(0.01474275315991467), 'vectorizer__max_features': 150000, 'vectorizer__min_df': 2}",0.9624354983859039,0.9625710771858657,0.9625543913291933,0.9669165212459327,0.9662591371077055,0.9641473250509203,0.002004023125346624,14 +2.805575799942017,0.11623425240026754,0.2762087345123291,0.007329105352044993,0.0023036990230378648,100000,3,"{'clf__alpha': np.float64(0.0023036990230378648), 'vectorizer__max_features': 100000, 'vectorizer__min_df': 3}",0.9587728271887749,0.9566316012654192,0.9589153817558299,0.961278366797289,0.9607297678059815,0.9592655889626588,0.0016430730196517606,25 +2.6457993030548095,0.044892600947984806,0.23958148956298828,0.004155759064362292,0.03387255565852149,50000,3,"{'clf__alpha': np.float64(0.03387255565852149), 'vectorizer__max_features': 50000, 'vectorizer__min_df': 3}",0.95955406687566,0.9636128819608649,0.9593317063243615,0.9635304894295919,0.9669500562513731,0.9625958401683704,0.002855664387231527,18 +2.76582727432251,0.05246241235864698,0.28086028099060056,0.0055590378384970645,2.752717392942941,150000,1,"{'clf__alpha': np.float64(2.752717392942941), 'vectorizer__max_features': 150000, 'vectorizer__min_df': 1}",0.9737714837006337,0.9747871716597889,0.9729766383781838,0.9795061188310396,0.9769826972880682,0.9756048219715427,0.0023687839843304264,2 +2.6430598735809325,0.03776801051607376,0.24893226623535156,0.004009197397113372,0.06338653441536259,100000,5,"{'clf__alpha': np.float64(0.06338653441536259), 'vectorizer__max_features': 100000, 'vectorizer__min_df': 5}",0.9640321314812248,0.9637722862788843,0.9607616818922565,0.9634046652880295,0.9689920794395751,0.964192568875994,0.0026694365258648415,13 +2.7180052757263184,0.09403249339614114,0.27129302024841306,0.007858928305875972,5.872283616443723,100000,2,"{'clf__alpha': np.float64(5.872283616443723), 'vectorizer__max_features': 100000, 'vectorizer__min_df': 2}",0.9712591925812216,0.9747755667856476,0.9723513128635358,0.9778620635193441,0.9778717632404438,0.9748239797980386,0.0027328765101773153,6 +2.692630910873413,0.03271161346135932,0.27468104362487794,0.008686217976364886,0.034806953267852714,100000,1,"{'clf__alpha': np.float64(0.034806953267852714), 'vectorizer__max_features': 100000, 'vectorizer__min_df': 1}",0.9651578661535425,0.9632313387822203,0.9651032261777511,0.966224143201886,0.9691991619332022,0.9657831472497204,0.001961052233661312,12 +2.63905782699585,0.011054481842506406,0.24993543624877929,0.006049808242354968,0.008386394780402562,150000,5,"{'clf__alpha': np.float64(0.008386394780402562), 'vectorizer__max_features': 150000, 'vectorizer__min_df': 5}",0.9571043131472046,0.9603304343079738,0.9573447759820981,0.9606150730911488,0.9629385606362284,0.9596666314329309,0.0021909899260050872,24 +2.6797202110290526,0.08870350821209148,0.24502801895141602,0.008710494978909264,0.003077180271250686,50000,5,"{'clf__alpha': np.float64(0.003077180271250686), 'vectorizer__max_features': 50000, 'vectorizer__min_df': 5}",0.9541001056672682,0.9580159464849235,0.9528408563059463,0.9593496754203283,0.9593297015054939,0.9567272570767921,0.0027319059589898317,28 +2.7247461795806887,0.06629516023013483,0.2717141151428223,0.009072816691500044,0.0013726318898045872,100000,1,"{'clf__alpha': np.float64(0.0013726318898045872), 'vectorizer__max_features': 100000, 'vectorizer__min_df': 1}",0.9583017146310632,0.9557148484274474,0.9596039143341261,0.961327065612543,0.9598576061394111,0.9589610298289182,0.0018861423656948149,26 +2.7631514072418213,0.056742672888851244,0.2737913131713867,0.006691019191044921,0.010842262717330166,100000,2,"{'clf__alpha': np.float64(0.010842262717330166), 'vectorizer__max_features': 100000, 'vectorizer__min_df': 2}",0.9625924760387605,0.9599578092838624,0.9622344089648466,0.9626210635092837,0.9646763970204648,0.9624164309634435,0.0015005509319931892,19 +2.7257555961608886,0.11699760740480397,0.2501559257507324,0.008291556473076264,0.12030178871154672,100000,5,"{'clf__alpha': np.float64(0.12030178871154672), 'vectorizer__max_features': 100000, 'vectorizer__min_df': 5}",0.9666963712159402,0.9678327111563292,0.9645803902798396,0.9664062026029635,0.9689950484069156,0.9669021447323976,0.0014781775762036113,11 +2.8034964084625242,0.07938279117317795,0.29145212173461915,0.01341201310745785,0.0054880470007660455,150000,2,"{'clf__alpha': np.float64(0.0054880470007660455), 'vectorizer__max_features': 150000, 'vectorizer__min_df': 2}",0.9611866382911846,0.9590397298368987,0.9609282442092899,0.9646829347686954,0.9644588137624414,0.9620592721737019,0.002181731208073283,20 +2.7390448093414306,0.02958175610720149,0.2749150276184082,0.007192866507818819,1.2604664585649468,100000,2,"{'clf__alpha': np.float64(1.2604664585649468), 'vectorizer__max_features': 100000, 'vectorizer__min_df': 2}",0.9736639805353511,0.977055294863286,0.976052178606499,0.9770976439240977,0.978699147014325,0.9765136489887117,0.0016579744971318426,1 +2.7562952995300294,0.0811316606523062,0.27197747230529784,0.008899644980801385,3.7958531426706403,100000,3,"{'clf__alpha': np.float64(3.7958531426706403), 'vectorizer__max_features': 100000, 'vectorizer__min_df': 3}",0.9727850746881638,0.976616809761047,0.9723656063879147,0.9773691936997003,0.9766840544935704,0.9751641478060792,0.002134216177271503,4 +2.7739730358123778,0.11101727227426034,0.2683395862579346,0.00986234317452737,4.869640941520899,100000,3,"{'clf__alpha': np.float64(4.869640941520899), 'vectorizer__max_features': 100000, 'vectorizer__min_df': 3}",0.9718943531942056,0.9757651953196548,0.9734792137179882,0.977943644790605,0.9777433601542048,0.9753651534353317,0.002369292776647924,3 +2.654277467727661,0.04692766088006921,0.24721331596374513,0.004002581658961809,0.12115379992469588,100000,5,"{'clf__alpha': np.float64(0.12115379992469588), 'vectorizer__max_features': 100000, 'vectorizer__min_df': 5}",0.9666963712159402,0.9678327111563292,0.9645803902798396,0.9665975567314115,0.9689950484069156,0.9669404155580871,0.0014672788901949217,10 +2.701209831237793,0.0627803361217237,0.22618308067321777,0.006285905771275388,2.38855581786886,50000,2,"{'clf__alpha': np.float64(2.38855581786886), 'vectorizer__max_features': 50000, 'vectorizer__min_df': 2}",0.9726377853536495,0.9771788783592442,0.9728029177982949,0.9765824102532119,0.9756226059716988,0.9749649195472199,0.0018994865809209515,5 +2.687728834152222,0.1264659520510463,0.23989696502685548,0.013967110002934921,0.1441346937111033,100000,1,"{'clf__alpha': np.float64(0.1441346937111033), 'vectorizer__max_features': 100000, 'vectorizer__min_df': 1}",0.9736212664261868,0.9684273581216852,0.9696951514523475,0.9682724586635744,0.9731630667501687,0.9706358602827926,0.0023085711807427755,9 +2.4494739055633543,0.06871892866826083,0.20175533294677733,0.00822975183444112,0.013296521457299506,50000,1,"{'clf__alpha': np.float64(0.013296521457299506), 'vectorizer__max_features': 50000, 'vectorizer__min_df': 1}",0.958976645081751,0.9610642396439202,0.9581613613246293,0.9602531799958759,0.9657793306681492,0.9608469513428652,0.002662276607837062,23 diff --git a/naive_bayes/flores_plus/bow_char_ngram_3_5/run_metadata.json b/naive_bayes/flores_plus/bow_char_ngram_3_5/run_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..d0b4f057537ba14add16aa346b6c81896fc2a9a7 --- /dev/null +++ b/naive_bayes/flores_plus/bow_char_ngram_3_5/run_metadata.json @@ -0,0 +1,23 @@ +{ + "run_name": "bow_char_ngram_3_5", + "tags": { + "feature_type": "bow", + "n_gram_range": "(3,5)", + "dataset_version": "flores_plus", + "vectorizer_class": "CountVectorizer" + }, + "params": { + "clf__alpha": "1.2604664585649468", + "vectorizer__max_features": "100000", + "vectorizer__min_df": "2" + }, + "metrics": { + "accuracy": 0.9832695984703633, + "f1_macro": 0.9843630468698907, + "precision_macro": 0.9835833492657572, + "recall_macro": 0.9852272376066121, + "inference_time_total_s": 0.2273, + "inference_time_ms_per_sample": 0.108674, + "throughput_samples_per_sec": 9201.81 + } +} \ No newline at end of file