Upload results/dataset_stats.json with huggingface_hub
Browse files- results/dataset_stats.json +142 -0
results/dataset_stats.json
ADDED
|
@@ -0,0 +1,142 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"dataset": "DODa",
|
| 4 |
+
"repo": "atlasia/DODa",
|
| 5 |
+
"text_col": "darija",
|
| 6 |
+
"total_rows": 87741,
|
| 7 |
+
"total_processed": 87741,
|
| 8 |
+
"ar": {
|
| 9 |
+
"count": 0,
|
| 10 |
+
"min": 0,
|
| 11 |
+
"max": 0,
|
| 12 |
+
"mean": 0.0,
|
| 13 |
+
"median": 0.0
|
| 14 |
+
},
|
| 15 |
+
"az": {
|
| 16 |
+
"count": 87739,
|
| 17 |
+
"min": 2,
|
| 18 |
+
"max": 155,
|
| 19 |
+
"mean": 23.96,
|
| 20 |
+
"median": 21.0
|
| 21 |
+
},
|
| 22 |
+
"mi": {
|
| 23 |
+
"count": 2,
|
| 24 |
+
"min": 11,
|
| 25 |
+
"max": 12,
|
| 26 |
+
"mean": 11.5,
|
| 27 |
+
"median": 11.5
|
| 28 |
+
},
|
| 29 |
+
"ALL": {
|
| 30 |
+
"count": 87741,
|
| 31 |
+
"min": 2,
|
| 32 |
+
"max": 155,
|
| 33 |
+
"mean": 23.96,
|
| 34 |
+
"median": 21.0
|
| 35 |
+
}
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"dataset": "Darija-Wiki",
|
| 39 |
+
"repo": "atlasia/Moroccan-Darija-Wiki-Dataset",
|
| 40 |
+
"text_col": "content",
|
| 41 |
+
"total_rows": 10044,
|
| 42 |
+
"total_processed": 10044,
|
| 43 |
+
"ar": {
|
| 44 |
+
"count": 9570,
|
| 45 |
+
"min": 31,
|
| 46 |
+
"max": 43065,
|
| 47 |
+
"mean": 761.42,
|
| 48 |
+
"median": 506.0
|
| 49 |
+
},
|
| 50 |
+
"az": {
|
| 51 |
+
"count": 1,
|
| 52 |
+
"min": 3616,
|
| 53 |
+
"max": 3616,
|
| 54 |
+
"mean": 3616.0,
|
| 55 |
+
"median": 3616.0
|
| 56 |
+
},
|
| 57 |
+
"mi": {
|
| 58 |
+
"count": 473,
|
| 59 |
+
"min": 66,
|
| 60 |
+
"max": 95926,
|
| 61 |
+
"mean": 2631.33,
|
| 62 |
+
"median": 914.0
|
| 63 |
+
},
|
| 64 |
+
"ALL": {
|
| 65 |
+
"count": 10044,
|
| 66 |
+
"min": 31,
|
| 67 |
+
"max": 95926,
|
| 68 |
+
"mean": 849.76,
|
| 69 |
+
"median": 508.0
|
| 70 |
+
}
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"dataset": "Atlaset",
|
| 74 |
+
"repo": "atlasia/Atlaset",
|
| 75 |
+
"text_col": "text",
|
| 76 |
+
"total_rows": 1170963,
|
| 77 |
+
"total_processed": 1170963,
|
| 78 |
+
"ar": {
|
| 79 |
+
"count": 1082406,
|
| 80 |
+
"min": 3,
|
| 81 |
+
"max": 429082,
|
| 82 |
+
"mean": 783.54,
|
| 83 |
+
"median": 94.5
|
| 84 |
+
},
|
| 85 |
+
"az": {
|
| 86 |
+
"count": 9897,
|
| 87 |
+
"min": 3,
|
| 88 |
+
"max": 228575,
|
| 89 |
+
"mean": 204.23,
|
| 90 |
+
"median": 29.0
|
| 91 |
+
},
|
| 92 |
+
"mi": {
|
| 93 |
+
"count": 78660,
|
| 94 |
+
"min": 4,
|
| 95 |
+
"max": 96263,
|
| 96 |
+
"mean": 421.6,
|
| 97 |
+
"median": 115.0
|
| 98 |
+
},
|
| 99 |
+
"ALL": {
|
| 100 |
+
"count": 1170963,
|
| 101 |
+
"min": 3,
|
| 102 |
+
"max": 429082,
|
| 103 |
+
"mean": 754.33,
|
| 104 |
+
"median": 86.0
|
| 105 |
+
}
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"dataset": "Ours (daa-pairs)",
|
| 109 |
+
"repo": "OiQ/daa-pairs",
|
| 110 |
+
"text_col": "arabic",
|
| 111 |
+
"total_rows": 112814,
|
| 112 |
+
"total_processed": 112814,
|
| 113 |
+
"ar": {
|
| 114 |
+
"count": 84293,
|
| 115 |
+
"min": 19,
|
| 116 |
+
"max": 153,
|
| 117 |
+
"mean": 65.97,
|
| 118 |
+
"median": 65.0
|
| 119 |
+
},
|
| 120 |
+
"az": {
|
| 121 |
+
"count": 43,
|
| 122 |
+
"min": 48,
|
| 123 |
+
"max": 94,
|
| 124 |
+
"mean": 69.49,
|
| 125 |
+
"median": 66.0
|
| 126 |
+
},
|
| 127 |
+
"mi": {
|
| 128 |
+
"count": 28478,
|
| 129 |
+
"min": 27,
|
| 130 |
+
"max": 143,
|
| 131 |
+
"mean": 68.94,
|
| 132 |
+
"median": 68.0
|
| 133 |
+
},
|
| 134 |
+
"ALL": {
|
| 135 |
+
"count": 112814,
|
| 136 |
+
"min": 19,
|
| 137 |
+
"max": 153,
|
| 138 |
+
"mean": 66.72,
|
| 139 |
+
"median": 66.0
|
| 140 |
+
}
|
| 141 |
+
}
|
| 142 |
+
]
|