Update curated.py
Browse files- curated.py +7 -13
curated.py
CHANGED
|
@@ -63,26 +63,20 @@ wikipedia_filter = pd.DataFrame(
|
|
| 63 |
"Wikipedia",
|
| 64 |
],
|
| 65 |
"Lines Downloaded": [
|
| 66 |
-
"",
|
| 67 |
-
],
|
| 68 |
-
"Lines Remaining After Language Filter": [
|
| 69 |
-
"",
|
| 70 |
],
|
| 71 |
-
"Percent Removed": [
|
| 72 |
"0.00%",
|
| 73 |
],
|
| 74 |
-
"
|
| 75 |
-
"",
|
| 76 |
-
],
|
| 77 |
-
"Percent Removed": [
|
| 78 |
"1.86%",
|
| 79 |
],
|
| 80 |
-
"
|
| 81 |
-
"",
|
| 82 |
-
],
|
| 83 |
-
"Percent Removed": [
|
| 84 |
"0.00%",
|
| 85 |
],
|
|
|
|
|
|
|
|
|
|
| 86 |
"Total Percentage Remaining": [
|
| 87 |
"98.14%",
|
| 88 |
],
|
|
|
|
| 63 |
"Wikipedia",
|
| 64 |
],
|
| 65 |
"Lines Downloaded": [
|
| 66 |
+
"61614907",
|
|
|
|
|
|
|
|
|
|
| 67 |
],
|
| 68 |
+
"Percent Removed After Language Filter": [
|
| 69 |
"0.00%",
|
| 70 |
],
|
| 71 |
+
"Percent Removed After Min Word Count Filter": [
|
|
|
|
|
|
|
|
|
|
| 72 |
"1.86%",
|
| 73 |
],
|
| 74 |
+
"Percent Removed After Unigram Probability Filter": [
|
|
|
|
|
|
|
|
|
|
| 75 |
"0.00%",
|
| 76 |
],
|
| 77 |
+
"Lines Remaining After Local Dedup": [
|
| 78 |
+
"",
|
| 79 |
+
],
|
| 80 |
"Total Percentage Remaining": [
|
| 81 |
"98.14%",
|
| 82 |
],
|