{ "algorithm": "word-unigram-and-bigram Laplace-smoothed classifier", "class_counts": { "cnpj_destructive_normalization": 4, "cnpj_digit_only_validation": 4, "cnpj_numeric_storage": 4, "compatible": 4, "rtc_context_review": 4, "rtc_incomplete": 4, "rtc_suspect_class_code": 4 }, "labels": [ "cnpj_destructive_normalization", "cnpj_digit_only_validation", "cnpj_numeric_storage", "compatible", "rtc_context_review", "rtc_incomplete", "rtc_suspect_class_code" ], "metrics": { "test": { "accuracy": 1.0, "majority_baseline_accuracy": 0.14285714285714285, "majority_baseline_label": "cnpj_destructive_normalization", "per_label_recall": { "cnpj_destructive_normalization": 1.0, "cnpj_digit_only_validation": 1.0, "cnpj_numeric_storage": 1.0, "compatible": 1.0, "rtc_context_review": 1.0, "rtc_incomplete": 1.0, "rtc_suspect_class_code": 1.0 }, "rows": 7 }, "train": { "accuracy": 1.0, "majority_baseline_accuracy": 0.14285714285714285, "majority_baseline_label": "cnpj_destructive_normalization", "per_label_recall": { "cnpj_destructive_normalization": 1.0, "cnpj_digit_only_validation": 1.0, "cnpj_numeric_storage": 1.0, "compatible": 1.0, "rtc_context_review": 1.0, "rtc_incomplete": 1.0, "rtc_suspect_class_code": 1.0 }, "rows": 28 }, "validation": { "accuracy": 1.0, "majority_baseline_accuracy": 0.14285714285714285, "majority_baseline_label": "cnpj_destructive_normalization", "per_label_recall": { "cnpj_destructive_normalization": 1.0, "cnpj_digit_only_validation": 1.0, "cnpj_numeric_storage": 1.0, "compatible": 1.0, "rtc_context_review": 1.0, "rtc_incomplete": 1.0, "rtc_suspect_class_code": 1.0 }, "rows": 7 } }, "model_type": "multinomial_naive_bayes", "seed": "deterministic-no-randomness", "token_counts": { "cnpj_destructive_normalization": { "0": 1, "9": 1, "clean": 1, "clean_cnpj": 1, "cleancnpj": 1, "cnpj": 4, "const": 2, "d": 3, "digits": 1, "g": 2, "javascript": 1, "php": 1, "preg_replace": 1, "python": 1, "r": 1, "re": 1, "replace": 2, "signal:cnpj_normalization": 4, "sintético": 4, "sub": 1, "tipo": 4, "trecho": 4, "typescript": 1, "value": 1, "word:0__9": 1, "word:9__g": 1, "word:clean__preg_replace": 1, "word:clean_cnpj__re": 1, "word:cleancnpj__cnpj": 1, "word:cnpj__replace": 1, "word:const__cleancnpj": 1, "word:const__digits": 1, "word:d__cnpj": 2, "word:d__g": 1, "word:digits__value": 1, "word:g__cnpj": 1, "word:javascript__trecho": 1, "word:php__trecho": 1, "word:preg_replace__d": 1, "word:python__trecho": 1, "word:r__d": 1, "word:re__sub": 1, "word:replace__0": 1, "word:replace__d": 1, "word:sintético__clean": 1, "word:sintético__clean_cnpj": 1, "word:sintético__const": 2, "word:sub__r": 1, "word:tipo__javascript": 1, "word:tipo__php": 1, "word:tipo__python": 1, "word:tipo__typescript": 1, "word:trecho__sintético": 4, "word:typescript__trecho": 1, "word:value__replace": 1 }, "cnpj_digit_only_validation": { "0": 2, "14": 4, "9": 2, "bool": 1, "cnpj": 5, "csharp": 1, "d": 2, "error": 1, "false": 1, "fullmatch": 1, "if": 2, "inválido": 1, "ismatch": 1, "java": 1, "javascript": 1, "matches": 1, "new": 1, "ok": 1, "python": 1, "r": 1, "re": 1, "regex": 1, "return": 2, "signal:cnpj_digits_only": 4, "sintético": 4, "test": 1, "throw": 1, "tipo": 4, "trecho": 4, "var": 1, "word:0__9": 2, "word:14__cnpj": 1, "word:14__return": 1, "word:14__test": 1, "word:9__14": 2, "word:bool__re": 1, "word:cnpj__0": 1, "word:cnpj__inválido": 1, "word:cnpj__matches": 1, "word:cnpj__throw": 1, "word:csharp__trecho": 1, "word:d__14": 2, "word:error__cnpj": 1, "word:fullmatch__r": 1, "word:if__cnpj": 1, "word:if__d": 1, "word:ismatch__cnpj": 1, "word:java__trecho": 1, "word:javascript__trecho": 1, "word:matches__0": 1, "word:new__error": 1, "word:ok__regex": 1, "word:python__trecho": 1, "word:r__d": 1, "word:re__fullmatch": 1, "word:regex__ismatch": 1, "word:return__bool": 1, "word:return__false": 1, "word:sintético__if": 2, "word:sintético__return": 1, "word:sintético__var": 1, "word:test__cnpj": 1, "word:throw__new": 1, "word:tipo__csharp": 1, "word:tipo__java": 1, "word:tipo__javascript": 1, "word:tipo__python": 1, "word:trecho__sintético": 4, "word:var__ok": 1 }, "cnpj_numeric_storage": { "0": 1, "14": 1, "add": 1, "alter": 1, "bigint": 3, "clients": 1, "cnpj": 4, "create": 2, "customers": 1, "db": 1, "emitters": 1, "integer": 1, "not": 1, "null": 1, "numeric": 1, "prisma": 1, "signal:cnpj_numeric": 4, "sintético": 4, "sql": 3, "table": 3, "tipo": 4, "trecho": 4, "word:14__0": 1, "word:add__cnpj": 1, "word:alter__table": 1, "word:bigint__db": 1, "word:bigint__not": 1, "word:clients__add": 1, "word:cnpj__bigint": 2, "word:cnpj__integer": 1, "word:cnpj__numeric": 1, "word:create__table": 2, "word:customers__cnpj": 1, "word:db__bigint": 1, "word:emitters__cnpj": 1, "word:not__null": 1, "word:numeric__14": 1, "word:prisma__trecho": 1, "word:sintético__alter": 1, "word:sintético__cnpj": 1, "word:sintético__create": 2, "word:sql__trecho": 3, "word:table__clients": 1, "word:table__customers": 1, "word:table__emitters": 1, "word:tipo__prisma": 1, "word:tipo__sql": 3, "word:trecho__sintético": 4 }, "compatible": { "14": 1, "canonical": 2, "char": 1, "cnpj": 3, "company": 1, "const": 1, "create": 1, "g": 1, "normalize_cnpj": 1, "not": 1, "null": 1, "php": 1, "preg_replace": 1, "python": 1, "r": 1, "re": 1, "replace": 1, "return": 1, "s": 3, "signal:compatible_or_other": 4, "sintético": 4, "sql": 1, "strtoupper": 1, "sub": 1, "table": 1, "tipo": 4, "touppercase": 1, "trecho": 4, "typescript": 1, "upper": 1, "v": 2, "word:14__not": 1, "word:canonical__cnpj": 1, "word:canonical__strtoupper": 1, "word:char__14": 1, "word:cnpj__char": 1, "word:cnpj__replace": 1, "word:company__cnpj": 1, "word:const__canonical": 1, "word:create__table": 1, "word:g__touppercase": 1, "word:normalize_cnpj__v": 1, "word:not__null": 1, "word:php__trecho": 1, "word:preg_replace__s": 1, "word:python__trecho": 1, "word:r__s": 1, "word:re__sub": 1, "word:replace__s": 1, "word:return__re": 1, "word:s__cnpj": 1, "word:s__g": 1, "word:s__v": 1, "word:sintético__canonical": 1, "word:sintético__const": 1, "word:sintético__create": 1, "word:sintético__normalize_cnpj": 1, "word:sql__trecho": 1, "word:strtoupper__preg_replace": 1, "word:sub__r": 1, "word:table__company": 1, "word:tipo__php": 1, "word:tipo__python": 1, "word:tipo__sql": 1, "word:tipo__typescript": 1, "word:trecho__sintético": 4, "word:typescript__trecho": 1, "word:v__return": 1, "word:v__upper": 1 }, "rtc_context_review": { "build": 2, "createnfse": 1, "data": 2, "def": 1, "document": 1, "e": 3, "emitir": 1, "emitir_nfe": 1, "function": 2, "gerarnfce": 1, "java": 1, "javascript": 1, "makexml": 1, "nf": 1, "nfc": 1, "nfe": 1, "nfs": 1, "order": 5, "pedido": 2, "php": 1, "python": 1, "return": 4, "serialize": 1, "signal:fiscal_context_without_rtc": 4, "sintético": 4, "tipo": 4, "trecho": 4, "word:build__nfe": 1, "word:build__nfs": 1, "word:createnfse__order": 1, "word:data__return": 1, "word:def__emitir_nfe": 1, "word:document__createnfse": 1, "word:e__data": 1, "word:e__order": 2, "word:emitir__data": 1, "word:emitir_nfe__pedido": 1, "word:function__emitir": 1, "word:function__gerarnfce": 1, "word:gerarnfce__order": 1, "word:java__trecho": 1, "word:javascript__trecho": 1, "word:makexml__nf": 1, "word:nf__e": 1, "word:nfc__e": 1, "word:nfe__pedido": 1, "word:nfs__e": 1, "word:order__order": 1, "word:order__return": 2, "word:pedido__return": 1, "word:php__trecho": 1, "word:python__trecho": 1, "word:return__build": 2, "word:return__makexml": 1, "word:return__serialize": 1, "word:serialize__nfc": 1, "word:sintético__def": 1, "word:sintético__document": 1, "word:sintético__function": 2, "word:tipo__java": 1, "word:tipo__javascript": 1, "word:tipo__php": 1, "word:tipo__python": 1, "word:trecho__sintético": 4 }, "rtc_incomplete": { "000": 1, "000001": 1, "cclasstrib": 2, "cst": 4, "ibscbs": 8, "nfe": 2, "signal:ibscbs_group": 4, "signal:ibscbs_incomplete": 4, "sintético": 4, "tax": 2, "tipo": 4, "trecho": 4, "word:000001__cclasstrib": 1, "word:000__cst": 1, "word:cclasstrib__000001": 1, "word:cclasstrib__ibscbs": 1, "word:cst__000": 1, "word:cst__cst": 1, "word:cst__ibscbs": 2, "word:ibscbs__cclasstrib": 1, "word:ibscbs__cst": 2, "word:ibscbs__ibscbs": 1, "word:ibscbs__nfe": 1, "word:ibscbs__tax": 1, "word:nfe__ibscbs": 1, "word:sintético__ibscbs": 2, "word:sintético__nfe": 1, "word:sintético__tax": 1, "word:tax__ibscbs": 1, "word:tipo__xml": 4, "word:trecho__sintético": 4, "word:xml__trecho": 4, "xml": 4 }, "rtc_suspect_class_code": { "12": 1, "12345": 1, "1234567": 1, "3456": 1, "abc123": 1, "cclasstrib": 8, "signal:bad_cclasstrib": 4, "sintético": 4, "tipo": 4, "trecho": 4, "word:1234567__cclasstrib": 1, "word:12345__cclasstrib": 1, "word:12__3456": 1, "word:3456__cclasstrib": 1, "word:abc123__cclasstrib": 1, "word:cclasstrib__12": 1, "word:cclasstrib__12345": 1, "word:cclasstrib__1234567": 1, "word:cclasstrib__abc123": 1, "word:sintético__cclasstrib": 4, "word:tipo__xml": 4, "word:trecho__sintético": 4, "word:xml__trecho": 4, "xml": 4 } }, "token_totals": { "cnpj_destructive_normalization": 80, "cnpj_digit_only_validation": 100, "cnpj_numeric_storage": 80, "compatible": 90, "rtc_context_review": 96, "rtc_incomplete": 76, "rtc_suspect_class_code": 58 }, "training_data": "dougdotcon/fiscalcheck-ptbr-compatibility train split only", "vocabulary": [ "0", "000", "000001", "12", "12345", "1234567", "14", "3456", "9", "abc123", "add", "alter", "bigint", "bool", "build", "canonical", "cclasstrib", "char", "clean", "clean_cnpj", "cleancnpj", "clients", "cnpj", "company", "const", "create", "createnfse", "csharp", "cst", "customers", "d", "data", "db", "def", "digits", "document", "e", "emitir", "emitir_nfe", "emitters", "error", "false", "fullmatch", "function", "g", "gerarnfce", "ibscbs", "if", "integer", "inválido", "ismatch", "java", "javascript", "makexml", "matches", "new", "nf", "nfc", "nfe", "nfs", "normalize_cnpj", "not", "null", "numeric", "ok", "order", "pedido", "php", "preg_replace", "prisma", "python", "r", "re", "regex", "replace", "return", "s", "serialize", "signal:bad_cclasstrib", "signal:cnpj_digits_only", "signal:cnpj_normalization", "signal:cnpj_numeric", "signal:compatible_or_other", "signal:fiscal_context_without_rtc", "signal:ibscbs_group", "signal:ibscbs_incomplete", "sintético", "sql", "strtoupper", "sub", "table", "tax", "test", "throw", "tipo", "touppercase", "trecho", "typescript", "upper", "v", "value", "var", "word:000001__cclasstrib", "word:000__cst", "word:0__9", "word:1234567__cclasstrib", "word:12345__cclasstrib", "word:12__3456", "word:14__0", "word:14__cnpj", "word:14__not", "word:14__return", "word:14__test", "word:3456__cclasstrib", "word:9__14", "word:9__g", "word:abc123__cclasstrib", "word:add__cnpj", "word:alter__table", "word:bigint__db", "word:bigint__not", "word:bool__re", "word:build__nfe", "word:build__nfs", "word:canonical__cnpj", "word:canonical__strtoupper", "word:cclasstrib__000001", "word:cclasstrib__12", "word:cclasstrib__12345", "word:cclasstrib__1234567", "word:cclasstrib__abc123", "word:cclasstrib__ibscbs", "word:char__14", "word:clean__preg_replace", "word:clean_cnpj__re", "word:cleancnpj__cnpj", "word:clients__add", "word:cnpj__0", "word:cnpj__bigint", "word:cnpj__char", "word:cnpj__integer", "word:cnpj__inválido", "word:cnpj__matches", "word:cnpj__numeric", "word:cnpj__replace", "word:cnpj__throw", "word:company__cnpj", "word:const__canonical", "word:const__cleancnpj", "word:const__digits", "word:create__table", "word:createnfse__order", "word:csharp__trecho", "word:cst__000", "word:cst__cst", "word:cst__ibscbs", "word:customers__cnpj", "word:d__14", "word:d__cnpj", "word:d__g", "word:data__return", "word:db__bigint", "word:def__emitir_nfe", "word:digits__value", "word:document__createnfse", "word:e__data", "word:e__order", "word:emitir__data", "word:emitir_nfe__pedido", "word:emitters__cnpj", "word:error__cnpj", "word:fullmatch__r", "word:function__emitir", "word:function__gerarnfce", "word:g__cnpj", "word:g__touppercase", "word:gerarnfce__order", "word:ibscbs__cclasstrib", "word:ibscbs__cst", "word:ibscbs__ibscbs", "word:ibscbs__nfe", "word:ibscbs__tax", "word:if__cnpj", "word:if__d", "word:ismatch__cnpj", "word:java__trecho", "word:javascript__trecho", "word:makexml__nf", "word:matches__0", "word:new__error", "word:nf__e", "word:nfc__e", "word:nfe__ibscbs", "word:nfe__pedido", "word:nfs__e", "word:normalize_cnpj__v", "word:not__null", "word:numeric__14", "word:ok__regex", "word:order__order", "word:order__return", "word:pedido__return", "word:php__trecho", "word:preg_replace__d", "word:preg_replace__s", "word:prisma__trecho", "word:python__trecho", "word:r__d", "word:r__s", "word:re__fullmatch", "word:re__sub", "word:regex__ismatch", "word:replace__0", "word:replace__d", "word:replace__s", "word:return__bool", "word:return__build", "word:return__false", "word:return__makexml", "word:return__re", "word:return__serialize", "word:s__cnpj", "word:s__g", "word:s__v", "word:serialize__nfc", "word:sintético__alter", "word:sintético__canonical", "word:sintético__cclasstrib", "word:sintético__clean", "word:sintético__clean_cnpj", "word:sintético__cnpj", "word:sintético__const", "word:sintético__create", "word:sintético__def", "word:sintético__document", "word:sintético__function", "word:sintético__ibscbs", "word:sintético__if", "word:sintético__nfe", "word:sintético__normalize_cnpj", "word:sintético__return", "word:sintético__tax", "word:sintético__var", "word:sql__trecho", "word:strtoupper__preg_replace", "word:sub__r", "word:table__clients", "word:table__company", "word:table__customers", "word:table__emitters", "word:tax__ibscbs", "word:test__cnpj", "word:throw__new", "word:tipo__csharp", "word:tipo__java", "word:tipo__javascript", "word:tipo__php", "word:tipo__prisma", "word:tipo__python", "word:tipo__sql", "word:tipo__typescript", "word:tipo__xml", "word:trecho__sintético", "word:typescript__trecho", "word:v__return", "word:v__upper", "word:value__replace", "word:var__ok", "word:xml__trecho", "xml" ] }