Page MenuHomePhabricator
Paste P84751

Revert Risk Threshold Analysis Results
ActivePublic

Authored by gkyziridis on Nov 4 2025, 1:12 PM.
Tags
None
Referenced Files
F69949820: Revert Risk Threshold Analysis Results
Nov 6 2025, 10:26 AM
F69907710: Revert Risk Threshold Analysis Results
Nov 5 2025, 3:05 PM
F69906857: Revert Risk Threshold Analysis Results
Nov 5 2025, 1:43 PM
F69906536: Revert Risk Threshold Analysis Results
Nov 5 2025, 12:56 PM
F69906133: Revert Risk Threshold Analysis Results
Nov 5 2025, 11:39 AM
F69906108: Revert Risk Threshold Analysis Results
Nov 5 2025, 11:36 AM
F69905813: Revert Risk Threshold Analysis Results
Nov 5 2025, 11:20 AM
F69905708: Revert Risk Threshold Analysis Results
Nov 5 2025, 11:04 AM
Subscribers
============ - dewiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (3584827, 17)
- Duplicate rows found and removed: 102417
- Clean data shape: (3482410, 17)
- Unique revision_ids: 3482410 | Data Shape: 3482410 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (3381092, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_dewiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.5600801110267639
- confusion_matrix_dewiki.png saved!
- False Positive Rate is: 0.14999585634039994
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 2759048 486875
reverted 26904 108265
============ - jawiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (2175370, 17)
- Duplicate rows found and removed: 66848
- Clean data shape: (2108522, 17)
- Unique revision_ids: 2108522 | Data Shape: 2108522 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (2072019, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_jawiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.7807799577713013
- confusion_matrix_jawiki.png saved!
- False Positive Rate is: 0.1500011156591438
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1714231 302514
reverted 24482 30792
============ - viwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (423602, 17)
- Duplicate rows found and removed: 16144
- Clean data shape: (407458, 17)
- Unique revision_ids: 407458 | Data Shape: 407458 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (392368, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_viwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.672927737236023
- confusion_matrix_viwiki.png saved!
- False Positive Rate is: 0.1500055161947405
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 315886 55747
reverted 3017 17718
============ - thwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (355836, 17)
- Duplicate rows found and removed: 7081
- Clean data shape: (348755, 17)
- Unique revision_ids: 348755 | Data Shape: 348755 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (335084, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_thwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.7088555693626404
- confusion_matrix_thwiki.png saved!
- False Positive Rate is: 0.14999475309329
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 267302 47169
reverted 2915 17698
============ - nowiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (219267, 17)
- Duplicate rows found and removed: 4787
- Clean data shape: (214480, 17)
- Unique revision_ids: 214480 | Data Shape: 214480 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (210459, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_nowiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.567750096321106
- confusion_matrix_nowiki.png saved!
- False Positive Rate is: 0.14995173769563921
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 168205 29672
reverted 992 11590
============ - elwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (214446, 17)
- Duplicate rows found and removed: 12313
- Clean data shape: (202133, 17)
- Unique revision_ids: 202133 | Data Shape: 202133 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (196606, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_elwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8070309162139893
- confusion_matrix_elwiki.png saved!
- False Positive Rate is: 0.15001066465405502
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 155418 27429
reverted 3345 10414
============ - hywiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (98459, 17)
- Duplicate rows found and removed: 1737
- Clean data shape: (96722, 17)
- Unique revision_ids: 96722 | Data Shape: 96722 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (95113, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_hywiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6658406257629395
- confusion_matrix_hywiki.png saved!
- False Positive Rate is: 0.14995779494837996
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 78549 13857
reverted 487 2220
============ - hiwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (66121, 17)
- Duplicate rows found and removed: 1266
- Clean data shape: (64855, 17)
- Unique revision_ids: 64855 | Data Shape: 64855 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (62611, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_hiwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8786675930023193
- confusion_matrix_hiwiki.png saved!
- False Positive Rate is: 0.14998627504803733
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 46449 8196
reverted 3445 4521
============ - bgwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (132472, 17)
- Duplicate rows found and removed: 3490
- Clean data shape: (128982, 17)
- Unique revision_ids: 128982 | Data Shape: 128982 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (123505, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_bgwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8672560453414917
- confusion_matrix_bgwiki.png saved!
- False Positive Rate is: 0.1500045516613564
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 93372 16478
reverted 3266 10389
============ - dawiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (89244, 17)
- Duplicate rows found and removed: 939
- Clean data shape: (88305, 17)
- Unique revision_ids: 88305 | Data Shape: 88305 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (87250, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_dawiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.7409616112709045
- confusion_matrix_dawiki.png saved!
- False Positive Rate is: 0.14990577351379133
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 69468 12250
reverted 576 4956
============ - hrwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (92623, 17)
- Duplicate rows found and removed: 2677
- Clean data shape: (89946, 17)
- Unique revision_ids: 89946 | Data Shape: 89946 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (85694, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_hrwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.5204998850822449
- confusion_matrix_hrwiki.png saved!
- False Positive Rate is: 0.15007170661749641
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 66376 11720
reverted 635 6963
============ - skwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (72376, 17)
- Duplicate rows found and removed: 2844
- Clean data shape: (69532, 17)
- Unique revision_ids: 69532 | Data Shape: 69532 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (65873, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_skwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8890475034713745
- confusion_matrix_skwiki.png saved!
- False Positive Rate is: 0.15
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 49963 8817
reverted 1975 5118
============ - mswiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (126531, 17)
- Duplicate rows found and removed: 3069
- Clean data shape: (123462, 17)
- Unique revision_ids: 123462 | Data Shape: 123462 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (116344, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_mswiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.9427589774131775
- confusion_matrix_mswiki.png saved!
- False Positive Rate is: 0.149979524979525
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 91333 16115
reverted 6203 2693
============ - euwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (109812, 17)
- Duplicate rows found and removed: 367
- Clean data shape: (109445, 17)
- Unique revision_ids: 109445 | Data Shape: 109445 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (108889, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_euwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.4504416882991791
- confusion_matrix_euwiki.png saved!
- False Positive Rate is: 0.14992396119659573
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 89995 15872
reverted 400 2622
============ - slwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (70752, 17)
- Duplicate rows found and removed: 216
- Clean data shape: (70536, 17)
- Unique revision_ids: 70536 | Data Shape: 70536 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (69708, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_slwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8655992746353149
- confusion_matrix_slwiki.png saved!
- False Positive Rate is: 0.14985160946655507
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 55859 9846
reverted 913 3090
============ - ltwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (110380, 17)
- Duplicate rows found and removed: 350
- Clean data shape: (110030, 17)
- Unique revision_ids: 110030 | Data Shape: 110030 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (108931, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_ltwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.3519546389579773
- confusion_matrix_ltwiki.png saved!
- False Positive Rate is: 0.14997548477652692
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 88417 15600
reverted 132 4782
============ - tawiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (68969, 17)
- Duplicate rows found and removed: 125
- Clean data shape: (68844, 17)
- Unique revision_ids: 68844 | Data Shape: 68844 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (68354, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_tawiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6359190344810486
- confusion_matrix_tawiki.png saved!
- False Positive Rate is: 0.14996949359365466
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 55728 9832
reverted 331 2463
============ - zh_yuewiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (46976, 17)
- Duplicate rows found and removed: 1303
- Clean data shape: (45673, 17)
- Unique revision_ids: 45673 | Data Shape: 45673 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (44725, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_zh_yuewiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8573755621910095
- confusion_matrix_zh_yuewiki.png saved!
- False Positive Rate is: 0.15008259079170835
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 36532 6451
reverted 1049 693
============ - kawiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (62524, 17)
- Duplicate rows found and removed: 438
- Clean data shape: (62086, 17)
- Unique revision_ids: 62086 | Data Shape: 62086 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (60871, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_kawiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.4605609178543091
- confusion_matrix_kawiki.png saved!
- False Positive Rate is: 0.14997275389959813
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 49917 8807
reverted 484 1663
============ - eowiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (99614, 17)
- Duplicate rows found and removed: 523
- Clean data shape: (99091, 17)
- Unique revision_ids: 99091 | Data Shape: 99091 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (98754, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_eowiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.34750446677207947
- confusion_matrix_eowiki.png saved!
- False Positive Rate is: 0.15014543042302395
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 83273 14712
reverted 247 522
============ - glwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (131204, 17)
- Duplicate rows found and removed: 381
- Clean data shape: (130823, 17)
- Unique revision_ids: 130823 | Data Shape: 130823 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (129653, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_glwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.2695479691028595
- confusion_matrix_glwiki.png saved!
- False Positive Rate is: 0.1500246828450309
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 108473 19146
reverted 203 1831
============ - urwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (809991, 17)
- Duplicate rows found and removed: 703
- Clean data shape: (809288, 17)
- Unique revision_ids: 809288 | Data Shape: 809288 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (808440, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_urwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.26034781336784363
- confusion_matrix_urwiki.png saved!
- False Positive Rate is: 0.15495951241396233
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 681875 125039
reverted 307 1219
============ - sqwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (44462, 17)
- Duplicate rows found and removed: 1311
- Clean data shape: (43151, 17)
- Unique revision_ids: 43151 | Data Shape: 43151 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (41855, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_sqwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.5832709074020386
- confusion_matrix_sqwiki.png saved!
- False Positive Rate is: 0.15289276562191997
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 34379 6205
reverted 137 1134
============ - mywiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (13635, 17)
- Duplicate rows found and removed: 130
- Clean data shape: (13505, 17)
- Unique revision_ids: 13505 | Data Shape: 13505 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (13104, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_mywiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8719736337661743
- confusion_matrix_mywiki.png saved!
- False Positive Rate is: 0.14975177016358754
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 10447 1840
reverted 273 544
============ - ckbwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (54359, 17)
- Duplicate rows found and removed: 323
- Clean data shape: (54036, 17)
- Unique revision_ids: 54036 | Data Shape: 54036 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (53591, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_ckbwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.2797521650791168
- confusion_matrix_ckbwiki.png saved!
- False Positive Rate is: 0.1489317372528222
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 44933 7863
reverted 71 724
============ - knwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (23237, 17)
- Duplicate rows found and removed: 30
- Clean data shape: (23207, 17)
- Unique revision_ids: 23207 | Data Shape: 23207 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (23131, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_knwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.44861292839050293
- confusion_matrix_knwiki.png saved!
- False Positive Rate is: 0.1506315089740749
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 19166 3399
reverted 63 503
============ - shwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (184833, 17)
- Duplicate rows found and removed: 606
- Clean data shape: (184227, 17)
- Unique revision_ids: 184227 | Data Shape: 184227 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (183350, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_shwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.11731643974781036
- confusion_matrix_shwiki.png saved!
- False Positive Rate is: 0.1495637631888746
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 154594 27188
reverted 23 1545
============ - uzwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (126041, 17)
- Duplicate rows found and removed: 1545
- Clean data shape: (124496, 17)
- Unique revision_ids: 124496 | Data Shape: 124496 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (122319, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_uzwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.5346587300300598
- confusion_matrix_uzwiki.png saved!
- False Positive Rate is: 0.14997637370055353
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 100738 17774
reverted 331 3476
============ - cebwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (173433, 17)
- Duplicate rows found and removed: 96
- Clean data shape: (173337, 17)
- Unique revision_ids: 173337 | Data Shape: 173337 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (173122, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_cebwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.010278036817908287
- confusion_matrix_cebwiki.png saved!
- False Positive Rate is: 0.15000752410607832
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 146860 25918
reverted 0 344
============ - be_x_oldwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (16161, 17)
- Duplicate rows found and removed: 463
- Clean data shape: (15698, 17)
- Unique revision_ids: 15698 | Data Shape: 15698 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (15541, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_be_x_oldwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6138502955436707
- confusion_matrix_be_x_oldwiki.png saved!
- False Positive Rate is: 0.0797570056829316
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 14088 1221
reverted 59 173
============ - aswiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (52428, 17)
- Duplicate rows found and removed: 73
- Clean data shape: (52355, 17)
- Unique revision_ids: 52355 | Data Shape: 52355 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (52199, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_aswiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.25013989210128784
- confusion_matrix_aswiki.png saved!
- False Positive Rate is: 0.14994291022390804
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 43925 7748
reverted 288 238
============ - newiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (9322, 17)
- Duplicate rows found and removed: 34
- Clean data shape: (9288, 17)
- Unique revision_ids: 9288 | Data Shape: 9288 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (9186, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_newiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8242648243904114
- confusion_matrix_newiki.png saved!
- False Positive Rate is: 0.15088920799734895
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 7687 1366
reverted 52 81
============ - gawiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (14898, 17)
- Duplicate rows found and removed: 28
- Clean data shape: (14870, 17)
- Unique revision_ids: 14870 | Data Shape: 14870 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (14762, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_gawiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.4082460403442383
- confusion_matrix_gawiki.png saved!
- False Positive Rate is: 0.1525214408233276
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 12352 2223
reverted 23 164
============ - kuwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (35850, 17)
- Duplicate rows found and removed: 934
- Clean data shape: (34916, 17)
- Unique revision_ids: 34916 | Data Shape: 34916 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (34053, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_kuwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.34288907051086426
- confusion_matrix_kuwiki.png saved!
- False Positive Rate is: 0.1499506538366642
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 27562 4862
reverted 297 1332
============ - scowiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (3887, 17)
- Duplicate rows found and removed: 11
- Clean data shape: (3876, 17)
- Unique revision_ids: 3876 | Data Shape: 3876 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (3743, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_scowiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8366231918334961
- confusion_matrix_scowiki.png saved!
- False Positive Rate is: 0.150074294205052
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 2860 505
reverted 140 238
============ - arzwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1117144, 17)
- Duplicate rows found and removed: 931
- Clean data shape: (1116213, 17)
- Unique revision_ids: 1116213 | Data Shape: 1116213 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (1114143, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_arzwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.07260608673095703
- confusion_matrix_arzwiki.png saved!
- False Positive Rate is: 0.14979367968963228
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 943871 166296
reverted 1197 2779
============ - bawiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (3383, 17)
- Duplicate rows found and removed: 26
- Clean data shape: (3357, 17)
- Unique revision_ids: 3357 | Data Shape: 3357 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (3273, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_bawiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6595543622970581
- confusion_matrix_bawiki.png saved!
- False Positive Rate is: 0.15389447236180903
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 2694 490
reverted 23 66
============ - ttwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (16375, 17)
- Duplicate rows found and removed: 151
- Clean data shape: (16224, 17)
- Unique revision_ids: 16224 | Data Shape: 16224 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (16051, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_ttwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.3884022533893585
- confusion_matrix_ttwiki.png saved!
- False Positive Rate is: 0.15
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 13379 2361
reverted 30 281
============ - astwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (54583, 17)
- Duplicate rows found and removed: 61
- Clean data shape: (54522, 17)
- Unique revision_ids: 54522 | Data Shape: 54522 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (54352, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_astwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.14954642951488495
- confusion_matrix_astwiki.png saved!
- False Positive Rate is: 0.1501871055424199
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 45646 8067
reverted 108 531
============ - jvwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (24642, 17)
- Duplicate rows found and removed: 271
- Clean data shape: (24371, 17)
- Unique revision_ids: 24371 | Data Shape: 24371 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (23993, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_jvwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.3876338005065918
- confusion_matrix_jvwiki.png saved!
- False Positive Rate is: 0.14963239981301263
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 20010 3521
reverted 46 416
============ - ocwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (13512, 17)
- Duplicate rows found and removed: 93
- Clean data shape: (13419, 17)
- Unique revision_ids: 13419 | Data Shape: 13419 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (13106, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_ocwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8661872148513794
- confusion_matrix_ocwiki.png saved!
- False Positive Rate is: 0.1494781118554292
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 10919 1919
reverted 134 134
============ - lbwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (40412, 17)
- Duplicate rows found and removed: 22
- Clean data shape: (40390, 17)
- Unique revision_ids: 40390 | Data Shape: 40390 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (40249, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_lbwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.4311239421367645
- confusion_matrix_lbwiki.png saved!
- False Positive Rate is: 0.15055673714500187
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 33948 6017
reverted 72 212
============ - satwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (13345, 17)
- Duplicate rows found and removed: 3
- Clean data shape: (13342, 17)
- Unique revision_ids: 13342 | Data Shape: 13342 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (13325, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_satwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.23358190059661865
- confusion_matrix_satwiki.png saved!
- False Positive Rate is: 0.1493526046371575
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 11300 1984
reverted 22 19
============ - mnwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (16184, 17)
- Duplicate rows found and removed: 237
- Clean data shape: (15947, 17)
- Unique revision_ids: 15947 | Data Shape: 15947 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (15475, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_mnwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.759356677532196
- confusion_matrix_mnwiki.png saved!
- False Positive Rate is: 0.14961234895578682
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 12175 2142
reverted 593 565
============ - azbwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (5036, 17)
- Duplicate rows found and removed: 39
- Clean data shape: (4997, 17)
- Unique revision_ids: 4997 | Data Shape: 4997 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (4869, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_azbwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6210681200027466
- confusion_matrix_azbwiki.png saved!
- False Positive Rate is: 0.14925373134328357
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 3819 670
reverted 39 341
============ - guwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (7997, 17)
- Duplicate rows found and removed: 283
- Clean data shape: (7714, 17)
- Unique revision_ids: 7714 | Data Shape: 7714 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (7196, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_guwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.3249874413013458
- confusion_matrix_guwiki.png saved!
- False Positive Rate is: 0.150709805216243
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 5145 913
reverted 48 1090
============ - brwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (23918, 17)
- Duplicate rows found and removed: 767
- Clean data shape: (23151, 17)
- Unique revision_ids: 23151 | Data Shape: 23151 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (22932, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_brwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.5656294822692871
- confusion_matrix_brwiki.png saved!
- False Positive Rate is: 0.14589478318291876
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 19401 3314
reverted 76 141
============ - warwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (100096, 17)
- Duplicate rows found and removed: 65
- Clean data shape: (100031, 17)
- Unique revision_ids: 100031 | Data Shape: 100031 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (99898, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_warwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.1372111439704895
- confusion_matrix_warwiki.png saved!
- False Positive Rate is: 0.12320709833482218
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 87354 12275
reverted 4 265
============ - siwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (14475, 17)
- Duplicate rows found and removed: 169
- Clean data shape: (14306, 17)
- Unique revision_ids: 14306 | Data Shape: 14306 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (13773, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_siwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6435396075248718
- confusion_matrix_siwiki.png saved!
- False Positive Rate is: 0.15085417937766932
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 11134 1978
reverted 76 585
============ - minwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (9955, 17)
- Duplicate rows found and removed: 43
- Clean data shape: (9912, 17)
- Unique revision_ids: 9912 | Data Shape: 9912 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (9850, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_minwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.17035524547100067
- confusion_matrix_minwiki.png saved!
- False Positive Rate is: 0.15234974915531893
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 8279 1488
reverted 2 81
============ - wuuwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (11232, 17)
- Duplicate rows found and removed: 62
- Clean data shape: (11170, 17)
- Unique revision_ids: 11170 | Data Shape: 11170 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (10850, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_wuuwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.4011421799659729
- confusion_matrix_wuuwiki.png saved!
- False Positive Rate is: 0.15026799387442571
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 8878 1570
reverted 35 367
============ - sowiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (5870, 17)
- Duplicate rows found and removed: 325
- Clean data shape: (5545, 17)
- Unique revision_ids: 5545 | Data Shape: 5545 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (5308, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_sowiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.9336830377578735
- confusion_matrix_sowiki.png saved!
- False Positive Rate is: 0.15108783239323126
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 4214 750
reverted 229 115
============ - orwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (10688, 17)
- Duplicate rows found and removed: 29
- Clean data shape: (10659, 17)
- Unique revision_ids: 10659 | Data Shape: 10659 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (10629, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_orwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.2776014506816864
- confusion_matrix_orwiki.png saved!
- False Positive Rate is: 0.14711033274956217
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 8766 1512
reverted 94 257
============ - tgwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (6459, 17)
- Duplicate rows found and removed: 17
- Clean data shape: (6442, 17)
- Unique revision_ids: 6442 | Data Shape: 6442 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (6396, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_tgwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.7084928154945374
- confusion_matrix_tgwiki.png saved!
- False Positive Rate is: 0.15035720219305532
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 5114 905
reverted 56 321
============ - yiwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1017, 17)
- Duplicate rows found and removed: 42
- Clean data shape: (975, 17)
- Unique revision_ids: 975 | Data Shape: 975 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (915, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_yiwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.9127264022827148
- confusion_matrix_yiwiki.png saved!
- False Positive Rate is: 0.1519302615193026
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 681 122
reverted 35 77
============ - avkwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (403, 17)
- Duplicate rows found and removed: 2
- Clean data shape: (401, 17)
- Unique revision_ids: 401 | Data Shape: 401 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (389, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_avkwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6609903573989868
- confusion_matrix_avkwiki.png saved!
- False Positive Rate is: 0.0582010582010582
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 356 22
reverted 3 8
============ - kywiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (15408, 17)
- Duplicate rows found and removed: 195
- Clean data shape: (15213, 17)
- Unique revision_ids: 15213 | Data Shape: 15213 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (14849, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_kywiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.4734741747379303
- confusion_matrix_kywiki.png saved!
- False Positive Rate is: 0.14982746721877158
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 12319 2171
reverted 52 307
============ - zh_min_nanwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (10256, 17)
- Duplicate rows found and removed: 66
- Clean data shape: (10190, 17)
- Unique revision_ids: 10190 | Data Shape: 10190 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (10076, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_zh_min_nanwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8590548634529114
- confusion_matrix_zh_min_nanwiki.png saved!
- False Positive Rate is: 0.14965291955900367
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 8330 1466
reverted 180 100
============ - kmwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (6365, 17)
- Duplicate rows found and removed: 108
- Clean data shape: (6257, 17)
- Unique revision_ids: 6257 | Data Shape: 6257 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (6125, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_kmwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8932412266731262
- confusion_matrix_kmwiki.png saved!
- False Positive Rate is: 0.15156196361139718
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 4943 883
reverted 158 141
============ - zh_classicalwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1503, 17)
- Duplicate rows found and removed: 5
- Clean data shape: (1498, 17)
- Unique revision_ids: 1498 | Data Shape: 1498 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (1444, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_zh_classicalwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8159477710723877
- confusion_matrix_zh_classicalwiki.png saved!
- False Positive Rate is: 0.14254224834680382
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1167 194
reverted 10 73
============ - hywwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (3077, 17)
- Duplicate rows found and removed: 55
- Clean data shape: (3022, 17)
- Unique revision_ids: 3022 | Data Shape: 3022 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (3000, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_hywwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.36386242508888245
- confusion_matrix_hywwiki.png saved!
- False Positive Rate is: 0.16043507817811012
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 2470 472
reverted 5 53
============ - alswiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (3247, 17)
- Duplicate rows found and removed: 74
- Clean data shape: (3173, 17)
- Unique revision_ids: 3173 | Data Shape: 3173 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (2987, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_alswiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6351034641265869
- confusion_matrix_alswiki.png saved!
- False Positive Rate is: 0.14942528735632185
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 2146 377
reverted 21 443
============ - fywiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (9246, 17)
- Duplicate rows found and removed: 3
- Clean data shape: (9243, 17)
- Unique revision_ids: 9243 | Data Shape: 9243 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (9212, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_fywiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.5464207530021667
- confusion_matrix_fywiki.png saved!
- False Positive Rate is: 0.15011013215859031
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 7717 1363
reverted 36 96
============ - anwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (25105, 17)
- Duplicate rows found and removed: 56
- Clean data shape: (25049, 17)
- Unique revision_ids: 25049 | Data Shape: 25049 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (24873, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_anwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.3275045156478882
- confusion_matrix_anwiki.png saved!
- False Positive Rate is: 0.15239760849229267
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 20840 3747
reverted 19 267
============ - suwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (4387, 17)
- Duplicate rows found and removed: 81
- Clean data shape: (4306, 17)
- Unique revision_ids: 4306 | Data Shape: 4306 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (4211, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_suwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.7814511656761169
- confusion_matrix_suwiki.png saved!
- False Positive Rate is: 0.149812734082397
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 3405 600
reverted 91 115
============ - yowiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (4231, 17)
- Duplicate rows found and removed: 22
- Clean data shape: (4209, 17)
- Unique revision_ids: 4209 | Data Shape: 4209 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (4143, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_yowiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.832072913646698
- confusion_matrix_yowiki.png saved!
- False Positive Rate is: 0.14874596473801838
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 3428 599
reverted 33 83
============ - arywiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (22620, 17)
- Duplicate rows found and removed: 14
- Clean data shape: (22606, 17)
- Unique revision_ids: 22606 | Data Shape: 22606 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (22555, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_arywiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.11711876094341278
- confusion_matrix_arywiki.png saved!
- False Positive Rate is: 0.15008499597387492
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 18999 3355
reverted 36 165
============ - sdwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (15947, 17)
- Duplicate rows found and removed: 0
- Clean data shape: (15947, 17)
- Unique revision_ids: 15947 | Data Shape: 15947 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (15929, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_sdwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.4532212018966675
- confusion_matrix_sdwiki.png saved!
- False Positive Rate is: 0.1492377472596699
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 13505 2369
reverted 47 8
============ - vecwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1778, 17)
- Duplicate rows found and removed: 111
- Clean data shape: (1667, 17)
- Unique revision_ids: 1667 | Data Shape: 1667 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (1566, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_vecwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6318691968917847
- confusion_matrix_vecwiki.png saved!
- False Positive Rate is: 0.14884979702300405
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1258 220
reverted 11 77
============ - pswiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (3929, 17)
- Duplicate rows found and removed: 43
- Clean data shape: (3886, 17)
- Unique revision_ids: 3886 | Data Shape: 3886 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (3822, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_pswiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.5818879008293152
- confusion_matrix_pswiki.png saved!
- False Positive Rate is: 0.15012106537530268
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 3159 558
reverted 34 71
============ - ndswiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (3549, 17)
- Duplicate rows found and removed: 19
- Clean data shape: (3530, 17)
- Unique revision_ids: 3530 | Data Shape: 3530 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (3460, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_ndswiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.7050349712371826
- confusion_matrix_ndswiki.png saved!
- False Positive Rate is: 0.1526080476900149
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 2843 512
reverted 21 84
============ - banwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (5769, 17)
- Duplicate rows found and removed: 39
- Clean data shape: (5730, 17)
- Unique revision_ids: 5730 | Data Shape: 5730 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (5662, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_banwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.7351230978965759
- confusion_matrix_banwiki.png saved!
- False Positive Rate is: 0.14884055365809815
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 4735 828
reverted 27 72
============ - sahwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1471, 17)
- Duplicate rows found and removed: 20
- Clean data shape: (1451, 17)
- Unique revision_ids: 1451 | Data Shape: 1451 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (1417, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_sahwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8460126519203186
- confusion_matrix_sahwiki.png saved!
- False Positive Rate is: 0.15631848064280496
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1155 214
reverted 15 33
============ - tcywiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (8416, 17)
- Duplicate rows found and removed: 10
- Clean data shape: (8406, 17)
- Unique revision_ids: 8406 | Data Shape: 8406 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (8381, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_tcywiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.27785277366638184
- confusion_matrix_tcywiki.png saved!
- False Positive Rate is: 0.15046268477346472
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 7069 1252
reverted 43 17
============ - lijwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (4380, 17)
- Duplicate rows found and removed: 313
- Clean data shape: (4067, 17)
- Unique revision_ids: 4067 | Data Shape: 4067 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (4048, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_lijwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.3695965111255646
- confusion_matrix_lijwiki.png saved!
- False Positive Rate is: 0.14054726368159204
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 3455 565
reverted 3 25
============ - lmowiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (12464, 17)
- Duplicate rows found and removed: 174
- Clean data shape: (12290, 17)
- Unique revision_ids: 12290 | Data Shape: 12290 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (12185, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_lmowiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.21587315201759338
- confusion_matrix_lmowiki.png saved!
- False Positive Rate is: 0.1484974958263773
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 10201 1779
reverted 28 177
============ - barwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (2160, 17)
- Duplicate rows found and removed: 24
- Clean data shape: (2136, 17)
- Unique revision_ids: 2136 | Data Shape: 2136 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (2081, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_barwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.7210271954536438
- confusion_matrix_barwiki.png saved!
- False Positive Rate is: 0.1496023856858847
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1711 301
reverted 10 59
============ - bclwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (5677, 17)
- Duplicate rows found and removed: 30
- Clean data shape: (5647, 17)
- Unique revision_ids: 5647 | Data Shape: 5647 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (5556, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_bclwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.4005255103111267
- confusion_matrix_bclwiki.png saved!
- False Positive Rate is: 0.16381057674590013
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 4538 889
reverted 26 103
============ - cvwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (4718, 17)
- Duplicate rows found and removed: 3
- Clean data shape: (4715, 17)
- Unique revision_ids: 4715 | Data Shape: 4715 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (4689, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_cvwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.43576115369796753
- confusion_matrix_cvwiki.png saved!
- False Positive Rate is: 0.14930182599355532
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 3960 695
reverted 5 29
============ - mtwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (4454, 17)
- Duplicate rows found and removed: 7
- Clean data shape: (4447, 17)
- Unique revision_ids: 4447 | Data Shape: 4447 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (4430, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_mtwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.5258171558380127
- confusion_matrix_mtwiki.png saved!
- False Positive Rate is: 0.14901960784313725
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 3689 646
reverted 36 59
============ - iawiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (3487, 17)
- Duplicate rows found and removed: 303
- Clean data shape: (3184, 17)
- Unique revision_ids: 3184 | Data Shape: 3184 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (2648, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_iawiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.5953251719474792
- confusion_matrix_iawiki.png saved!
- False Positive Rate is: 0.14973694860380413
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 2101 370
reverted 48 129
============ - szywiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (852, 17)
- Duplicate rows found and removed: 2
- Clean data shape: (850, 17)
- Unique revision_ids: 850 | Data Shape: 850 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (847, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_szywiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.35294532775878906
- confusion_matrix_szywiki.png saved!
- False Positive Rate is: 0.13539192399049882
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 728 114
reverted 0 5
============ - cvwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (4718, 17)
- Duplicate rows found and removed: 3
- Clean data shape: (4715, 17)
- Unique revision_ids: 4715 | Data Shape: 4715 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (4689, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_cvwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.43576115369796753
- confusion_matrix_cvwiki.png saved!
- False Positive Rate is: 0.14930182599355532
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 3960 695
reverted 5 29
============ - mtwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (4454, 17)
- Duplicate rows found and removed: 7
- Clean data shape: (4447, 17)
- Unique revision_ids: 4447 | Data Shape: 4447 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (4430, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_mtwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.5258171558380127
- confusion_matrix_mtwiki.png saved!
- False Positive Rate is: 0.14901960784313725
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 3689 646
reverted 36 59
============ - iawiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (3487, 17)
- Duplicate rows found and removed: 303
- Clean data shape: (3184, 17)
- Unique revision_ids: 3184 | Data Shape: 3184 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (2648, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_iawiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.5953251719474792
- confusion_matrix_iawiki.png saved!
- False Positive Rate is: 0.14973694860380413
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 2101 370
reverted 48 129
============ - szywiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (852, 17)
- Duplicate rows found and removed: 2
- Clean data shape: (850, 17)
- Unique revision_ids: 850 | Data Shape: 850 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (847, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_szywiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.35294532775878906
- confusion_matrix_szywiki.png saved!
- False Positive Rate is: 0.13539192399049882
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 728 114
reverted 0 5
============ - pnbwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (7273, 17)
- Duplicate rows found and removed: 13
- Clean data shape: (7260, 17)
- Unique revision_ids: 7260 | Data Shape: 7260 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (7217, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_pnbwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.32891952991485596
- confusion_matrix_pnbwiki.png saved!
- False Positive Rate is: 0.15066202090592334
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 6094 1081
reverted 6 36
============ - scwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (921, 17)
- Duplicate rows found and removed: 4
- Clean data shape: (917, 17)
- Unique revision_ids: 917 | Data Shape: 917 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (884, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_scwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6216806173324585
- confusion_matrix_scwiki.png saved!
- False Positive Rate is: 0.15058823529411763
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 722 128
reverted 8 26
============ - cewiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (16255, 17)
- Duplicate rows found and removed: 16
- Clean data shape: (16239, 17)
- Unique revision_ids: 16239 | Data Shape: 16239 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (16222, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_cewiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.4421550929546356
- confusion_matrix_cewiki.png saved!
- False Positive Rate is: 0.15128284389489954
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 13728 2447
reverted 8 39
============ - vowiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (3479, 17)
- Duplicate rows found and removed: 36
- Clean data shape: (3443, 17)
- Unique revision_ids: 3443 | Data Shape: 3443 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (3405, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_vowiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.21234892308712006
- confusion_matrix_vowiki.png saved!
- False Positive Rate is: 0.15004439183190293
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 2872 507
reverted 2 24
============ - tkwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (3857, 17)
- Duplicate rows found and removed: 64
- Clean data shape: (3793, 17)
- Unique revision_ids: 3793 | Data Shape: 3793 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (3721, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_tkwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8397768139839172
- confusion_matrix_tkwiki.png saved!
- False Positive Rate is: 0.151440329218107
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 3093 552
reverted 24 52
============ - iowiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (7409, 17)
- Duplicate rows found and removed: 13
- Clean data shape: (7396, 17)
- Unique revision_ids: 7396 | Data Shape: 7396 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (7354, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_iowiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.4195224344730377
- confusion_matrix_iowiki.png saved!
- False Positive Rate is: 0.15097715386732727
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 6169 1097
reverted 35 53
============ - mnwwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (733, 17)
- Duplicate rows found and removed: 0
- Clean data shape: (733, 17)
- Unique revision_ids: 733 | Data Shape: 733 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (733, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_mnwwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.3484097719192505
- confusion_matrix_mnwwiki.png saved!
- False Positive Rate is: 0.12978142076502733
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 637 95
reverted 1 0
============ - sawiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1247, 17)
- Duplicate rows found and removed: 2
- Clean data shape: (1245, 17)
- Unique revision_ids: 1245 | Data Shape: 1245 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (1178, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_sawiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.797757089138031
- confusion_matrix_sawiki.png saved!
- False Positive Rate is: 0.14841628959276018
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 941 164
reverted 27 46
============ - quwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1905, 17)
- Duplicate rows found and removed: 9
- Clean data shape: (1896, 17)
- Unique revision_ids: 1896 | Data Shape: 1896 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (1869, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_quwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6781440377235413
- confusion_matrix_quwiki.png saved!
- False Positive Rate is: 0.16584833606110203
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1529 304
reverted 8 28
============ - crhwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1792, 17)
- Duplicate rows found and removed: 15
- Clean data shape: (1777, 17)
- Unique revision_ids: 1777 | Data Shape: 1777 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (1753, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_crhwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.750942051410675
- confusion_matrix_crhwiki.png saved!
- False Positive Rate is: 0.15029239766081873
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1453 257
reverted 6 37
============ - bhwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (3561, 17)
- Duplicate rows found and removed: 67
- Clean data shape: (3494, 17)
- Unique revision_ids: 3494 | Data Shape: 3494 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (3376, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_bhwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.3270818591117859
- confusion_matrix_bhwiki.png saved!
- False Positive Rate is: 0.1329605467536502
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 2791 428
reverted 4 153
============ - lowiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (5248, 17)
- Duplicate rows found and removed: 38
- Clean data shape: (5210, 17)
- Unique revision_ids: 5210 | Data Shape: 5210 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (5150, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_lowiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.5496832728385925
- confusion_matrix_lowiki.png saved!
- False Positive Rate is: 0.15178571428571427
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 4275 765
reverted 26 84
============ - maiwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (2009, 17)
- Duplicate rows found and removed: 47
- Clean data shape: (1962, 17)
- Unique revision_ids: 1962 | Data Shape: 1962 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (1915, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_maiwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.42570507526397705
- confusion_matrix_maiwiki.png saved!
- False Positive Rate is: 0.16657652785289345
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1541 308
reverted 1 65
============ - diqwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (2705, 17)
- Duplicate rows found and removed: 35
- Clean data shape: (2670, 17)
- Unique revision_ids: 2670 | Data Shape: 2670 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (2575, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_diqwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.5013527870178223
- confusion_matrix_diqwiki.png saved!
- False Positive Rate is: 0.14007308160779536
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 2118 345
reverted 14 98
============ - liwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (5884, 17)
- Duplicate rows found and removed: 8
- Clean data shape: (5876, 17)
- Unique revision_ids: 5876 | Data Shape: 5876 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (5833, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_liwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.5055482983589172
- confusion_matrix_liwiki.png saved!
- False Positive Rate is: 0.14946928832434314
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 4888 859
reverted 36 50
============ - nds_nlwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (502, 17)
- Duplicate rows found and removed: 4
- Clean data shape: (498, 17)
- Unique revision_ids: 498 | Data Shape: 498 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (486, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_nds_nlwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8951061367988586
- confusion_matrix_nds_nlwiki.png saved!
- False Positive Rate is: 0.1522248243559719
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 362 65
reverted 35 24
============ - fowiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (2774, 17)
- Duplicate rows found and removed: 36
- Clean data shape: (2738, 17)
- Unique revision_ids: 2738 | Data Shape: 2738 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (2524, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_fowiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8035809993743896
- confusion_matrix_fowiki.png saved!
- False Positive Rate is: 0.15061224489795919
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 2081 369
reverted 18 56
============ - iewiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (2922, 17)
- Duplicate rows found and removed: 5
- Clean data shape: (2917, 17)
- Unique revision_ids: 2917 | Data Shape: 2917 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (2893, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_iewiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.5032959580421448
- confusion_matrix_iewiki.png saved!
- False Positive Rate is: 0.12857142857142856
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 2501 369
reverted 5 18
============ - kwwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (2258, 17)
- Duplicate rows found and removed: 22
- Clean data shape: (2236, 17)
- Unique revision_ids: 2236 | Data Shape: 2236 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (2216, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_kwwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.5901607871055603
- confusion_matrix_kwwiki.png saved!
- False Positive Rate is: 0.1548974943052392
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1855 340
reverted 7 14
============ - htwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (9527, 17)
- Duplicate rows found and removed: 56
- Clean data shape: (9471, 17)
- Unique revision_ids: 9471 | Data Shape: 9471 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (9423, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_htwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.4185045063495636
- confusion_matrix_htwiki.png saved!
- False Positive Rate is: 0.14988742360887744
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 7929 1398
reverted 20 76
============ - oswiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (9620, 17)
- Duplicate rows found and removed: 12
- Clean data shape: (9608, 17)
- Unique revision_ids: 9608 | Data Shape: 9608 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (9584, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_oswiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.3149448037147522
- confusion_matrix_oswiki.png saved!
- False Positive Rate is: 0.14967985724782198
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 8101 1426
reverted 30 27
============ - igwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (12511, 17)
- Duplicate rows found and removed: 23
- Clean data shape: (12488, 17)
- Unique revision_ids: 12488 | Data Shape: 12488 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (12402, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_igwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.3341909348964691
- confusion_matrix_igwiki.png saved!
- False Positive Rate is: 0.159463850528026
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 10347 1963
reverted 52 40
============ - pmswiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1613, 17)
- Duplicate rows found and removed: 20
- Clean data shape: (1593, 17)
- Unique revision_ids: 1593 | Data Shape: 1593 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (1529, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_pmswiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8976967334747314
- confusion_matrix_pmswiki.png saved!
- False Positive Rate is: 0.15279672578444747
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1242 224
reverted 45 18
============ - myvwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (327, 17)
- Duplicate rows found and removed: 0
- Clean data shape: (327, 17)
- Unique revision_ids: 327 | Data Shape: 327 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (325, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_myvwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.4775513708591461
- confusion_matrix_myvwiki.png saved!
- False Positive Rate is: 0.2006172839506173
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 259 65
reverted 1 0
============ - acewiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (652, 17)
- Duplicate rows found and removed: 30
- Clean data shape: (622, 17)
- Unique revision_ids: 622 | Data Shape: 622 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (521, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_acewiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8583618402481079
- confusion_matrix_acewiki.png saved!
- False Positive Rate is: 0.1543778801843318
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 367 67
reverted 29 58
============ - abwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (2116, 17)
- Duplicate rows found and removed: 38
- Clean data shape: (2078, 17)
- Unique revision_ids: 2078 | Data Shape: 2078 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (2004, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_abwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6387686729431152
- confusion_matrix_abwiki.png saved!
- False Positive Rate is: 0.14984059511158343
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1600 282
reverted 17 105
============ - tyvwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (958, 17)
- Duplicate rows found and removed: 6
- Clean data shape: (952, 17)
- Unique revision_ids: 952 | Data Shape: 952 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (944, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_tyvwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.7302069067955017
- confusion_matrix_tyvwiki.png saved!
- False Positive Rate is: 0.14683815648445875
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 796 137
reverted 2 9
============ - gdwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1116, 17)
- Duplicate rows found and removed: 6
- Clean data shape: (1110, 17)
- Unique revision_ids: 1110 | Data Shape: 1110 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (1094, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_gdwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6253749132156372
- confusion_matrix_gdwiki.png saved!
- False Positive Rate is: 0.17580340264650285
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 872 186
reverted 8 28
============ - mznwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (41589, 17)
- Duplicate rows found and removed: 39
- Clean data shape: (41550, 17)
- Unique revision_ids: 41550 | Data Shape: 41550 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (41077, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_mznwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.1651594638824463
- confusion_matrix_mznwiki.png saved!
- False Positive Rate is: 0.14594153435227777
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 34533 5901
reverted 2 641
============ - mgwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (23484, 17)
- Duplicate rows found and removed: 131
- Clean data shape: (23353, 17)
- Unique revision_ids: 23353 | Data Shape: 23353 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (23219, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_mgwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8254655599594116
- confusion_matrix_mgwiki.png saved!
- False Positive Rate is: 0.149770089774469
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 19415 3420
reverted 209 175
============ - cowiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1921, 17)
- Duplicate rows found and removed: 42
- Clean data shape: (1879, 17)
- Unique revision_ids: 1879 | Data Shape: 1879 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (1781, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_cowiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8178458213806152
- confusion_matrix_cowiki.png saved!
- False Positive Rate is: 0.1487553126897389
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1402 245
reverted 35 99
============ - xmfwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (10891, 17)
- Duplicate rows found and removed: 5
- Clean data shape: (10886, 17)
- Unique revision_ids: 10886 | Data Shape: 10886 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (10846, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_xmfwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.14220458269119263
- confusion_matrix_xmfwiki.png saved!
- False Positive Rate is: 0.14713263314434427
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 9176 1583
reverted 40 47
============ - wawiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (2550, 17)
- Duplicate rows found and removed: 5
- Clean data shape: (2545, 17)
- Unique revision_ids: 2545 | Data Shape: 2545 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (2526, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_wawiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6133654117584229
- confusion_matrix_wawiki.png saved!
- False Positive Rate is: 0.15860966839792248
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 2106 397
reverted 6 17
============ - nqowiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (336, 17)
- Duplicate rows found and removed: 4
- Clean data shape: (332, 17)
- Unique revision_ids: 332 | Data Shape: 332 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (317, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_nqowiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.7342619299888611
- confusion_matrix_nqowiki.png saved!
- False Positive Rate is: 0.18506493506493507
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 251 57
reverted 6 3
============ - pcdwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1939, 17)
- Duplicate rows found and removed: 50
- Clean data shape: (1889, 17)
- Unique revision_ids: 1889 | Data Shape: 1889 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (1853, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_pcdwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.5277352929115295
- confusion_matrix_pcdwiki.png saved!
- False Positive Rate is: 0.14205186020293123
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1522 252
reverted 10 69
============ - amwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (2892, 17)
- Duplicate rows found and removed: 273
- Clean data shape: (2619, 17)
- Unique revision_ids: 2619 | Data Shape: 2619 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (2296, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_amwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.9134624600410461
- confusion_matrix_amwiki.png saved!
- False Positive Rate is: 0.15059308922124806
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1647 292
reverted 160 197
============ - emlwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1211, 17)
- Duplicate rows found and removed: 5
- Clean data shape: (1206, 17)
- Unique revision_ids: 1206 | Data Shape: 1206 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (1184, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_emlwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6133654117584229
- confusion_matrix_emlwiki.png saved!
- False Positive Rate is: 0.16013925152306355
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 965 184
reverted 5 30
============ - scnwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (16480, 17)
- Duplicate rows found and removed: 17
- Clean data shape: (16463, 17)
- Unique revision_ids: 16463 | Data Shape: 16463 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (16393, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_scnwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.4262775778770447
- confusion_matrix_scnwiki.png saved!
- False Positive Rate is: 0.15029080559336716
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 13733 2429
reverted 114 117
============ - zuwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1943, 17)
- Duplicate rows found and removed: 20
- Clean data shape: (1923, 17)
- Unique revision_ids: 1923 | Data Shape: 1923 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (1864, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_zuwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.7980137467384338
- confusion_matrix_zuwiki.png saved!
- False Positive Rate is: 0.1474036850921273
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1527 264
reverted 29 44
============ - lldwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (3069, 17)
- Duplicate rows found and removed: 7
- Clean data shape: (3062, 17)
- Unique revision_ids: 3062 | Data Shape: 3062 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (3020, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_lldwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.4878181219100952
- confusion_matrix_lldwiki.png saved!
- False Positive Rate is: 0.16341627437794218
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 2488 486
reverted 11 35
============ - bjnwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1523, 17)
- Duplicate rows found and removed: 7
- Clean data shape: (1516, 17)
- Unique revision_ids: 1516 | Data Shape: 1516 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (1479, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_bjnwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6133654117584229
- confusion_matrix_bjnwiki.png saved!
- False Positive Rate is: 0.12642045454545456
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1230 178
reverted 10 61
============ - frrwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1132, 17)
- Duplicate rows found and removed: 2
- Clean data shape: (1130, 17)
- Unique revision_ids: 1130 | Data Shape: 1130 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (1120, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_frrwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.65794438123703
- confusion_matrix_frrwiki.png saved!
- False Positive Rate is: 0.15170278637770898
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 822 147
reverted 123 28
============ - bat_smgwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (378, 17)
- Duplicate rows found and removed: 7
- Clean data shape: (371, 17)
- Unique revision_ids: 371 | Data Shape: 371 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (343, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_bat_smgwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.7381485104560852
- confusion_matrix_bat_smgwiki.png saved!
- False Positive Rate is: 0.1501597444089457
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 266 47
reverted 7 23
============ - sewiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (195, 17)
- Duplicate rows found and removed: 2
- Clean data shape: (193, 17)
- Unique revision_ids: 193 | Data Shape: 193 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (180, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_sewiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8541494011878967
- confusion_matrix_sewiki.png saved!
- False Positive Rate is: 0.1532258064516129
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 105 19
reverted 39 17
============ - lfnwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (320, 17)
- Duplicate rows found and removed: 3
- Clean data shape: (317, 17)
- Unique revision_ids: 317 | Data Shape: 317 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (300, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_lfnwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.804692268371582
- confusion_matrix_lfnwiki.png saved!
- False Positive Rate is: 0.14736842105263157
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 243 42
reverted 4 11
============ - vepwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (4682, 17)
- Duplicate rows found and removed: 0
- Clean data shape: (4682, 17)
- Unique revision_ids: 4682 | Data Shape: 4682 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (4669, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_vepwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.284596711397171
- confusion_matrix_vepwiki.png saved!
- False Positive Rate is: 0.15042918454935622
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 3959 701
reverted 3 6
============ - kabwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (845, 17)
- Duplicate rows found and removed: 182
- Clean data shape: (663, 17)
- Unique revision_ids: 663 | Data Shape: 663 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (649, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_kabwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.874995231628418
- confusion_matrix_kabwiki.png saved!
- False Positive Rate is: 0.11305732484076433
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 557 71
reverted 9 12
============ - ruewiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (4294, 17)
- Duplicate rows found and removed: 31
- Clean data shape: (4263, 17)
- Unique revision_ids: 4263 | Data Shape: 4263 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (4172, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_ruewiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.47483348846435547
- confusion_matrix_ruewiki.png saved!
- False Positive Rate is: 0.15271914576607898
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 3412 615
reverted 22 123
============ - ugwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (7340, 17)
- Duplicate rows found and removed: 0
- Clean data shape: (7340, 17)
- Unique revision_ids: 7340 | Data Shape: 7340 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (7331, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_ugwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.33279338479042053
- confusion_matrix_ugwiki.png saved!
- False Positive Rate is: 0.15025269771889085
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 6221 1100
reverted 4 6
============ - lezwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (338, 17)
- Duplicate rows found and removed: 0
- Clean data shape: (338, 17)
- Unique revision_ids: 338 | Data Shape: 338 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (338, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_lezwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.882215678691864
- confusion_matrix_lezwiki.png saved!
- False Positive Rate is: 0.15
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 272 48
reverted 1 17
============ - szlwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1874, 17)
- Duplicate rows found and removed: 35
- Clean data shape: (1839, 17)
- Unique revision_ids: 1839 | Data Shape: 1839 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (1728, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_szlwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6092071533203125
- confusion_matrix_szlwiki.png saved!
- False Positive Rate is: 0.14799025578562727
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1399 243
reverted 11 75
============ - frpwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (287, 17)
- Duplicate rows found and removed: 7
- Clean data shape: (280, 17)
- Unique revision_ids: 280 | Data Shape: 280 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (270, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_frpwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8332036137580872
- confusion_matrix_frpwiki.png saved!
- False Positive Rate is: 0.1646586345381526
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 208 41
reverted 9 12
============ - olowiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (492, 17)
- Duplicate rows found and removed: 1
- Clean data shape: (491, 17)
- Unique revision_ids: 491 | Data Shape: 491 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (481, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_olowiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.615082323551178
- confusion_matrix_olowiki.png saved!
- False Positive Rate is: 0.1670235546038544
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 389 78
reverted 3 11
============ - bpywiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (644, 17)
- Duplicate rows found and removed: 32
- Clean data shape: (612, 17)
- Unique revision_ids: 612 | Data Shape: 612 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (567, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_bpywiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.9044924974441528
- confusion_matrix_bpywiki.png saved!
- False Positive Rate is: 0.1461864406779661
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 403 69
reverted 30 65
============ - rwwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (11713, 17)
- Duplicate rows found and removed: 23
- Clean data shape: (11690, 17)
- Unique revision_ids: 11690 | Data Shape: 11690 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (11592, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_rwwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6023024320602417
- confusion_matrix_rwwiki.png saved!
- False Positive Rate is: 0.15309842041312272
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 9758 1764
reverted 24 46
============ - mhrwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1037, 17)
- Duplicate rows found and removed: 16
- Clean data shape: (1021, 17)
- Unique revision_ids: 1021 | Data Shape: 1021 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (999, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_mhrwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8115577101707458
- confusion_matrix_mhrwiki.png saved!
- False Positive Rate is: 0.14681724845995894
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 831 143
reverted 6 19
============ - gorwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1652, 17)
- Duplicate rows found and removed: 66
- Clean data shape: (1586, 17)
- Unique revision_ids: 1586 | Data Shape: 1586 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (1509, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_gorwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6311735510826111
- confusion_matrix_gorwiki.png saved!
- False Positive Rate is: 0.153954802259887
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1198 218
reverted 15 78
============ - dsbwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (708, 17)
- Duplicate rows found and removed: 5
- Clean data shape: (703, 17)
- Unique revision_ids: 703 | Data Shape: 703 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (688, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_dsbwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8436957001686096
- confusion_matrix_dsbwiki.png saved!
- False Positive Rate is: 0.14754098360655737
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 572 99
reverted 8 9
============ - rmwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (890, 17)
- Duplicate rows found and removed: 0
- Clean data shape: (890, 17)
- Unique revision_ids: 890 | Data Shape: 890 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (861, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_rmwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.7736589908599854
- confusion_matrix_rmwiki.png saved!
- False Positive Rate is: 0.15222772277227722
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 685 123
reverted 31 22
============ - glkwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (41120, 17)
- Duplicate rows found and removed: 179
- Clean data shape: (40941, 17)
- Unique revision_ids: 40941 | Data Shape: 40941 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (40369, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_glkwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.21582037210464478
- confusion_matrix_glkwiki.png saved!
- False Positive Rate is: 0.1461611232822147
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 34297 5871
reverted 12 189
============ - napwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (837, 17)
- Duplicate rows found and removed: 6
- Clean data shape: (831, 17)
- Unique revision_ids: 831 | Data Shape: 831 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (807, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_napwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.9015378952026367
- confusion_matrix_napwiki.png saved!
- False Positive Rate is: 0.14657534246575343
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 623 107
reverted 36 41
============ - gnwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1683, 17)
- Duplicate rows found and removed: 4
- Clean data shape: (1679, 17)
- Unique revision_ids: 1679 | Data Shape: 1679 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (1645, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_gnwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6133654117584229
- confusion_matrix_gnwiki.png saved!
- False Positive Rate is: 0.15346225826575172
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1357 246
reverted 4 38
============ - fiu_vrowiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (440, 17)
- Duplicate rows found and removed: 2
- Clean data shape: (438, 17)
- Unique revision_ids: 438 | Data Shape: 438 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (420, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_fiu_vrowiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6267386078834534
- confusion_matrix_fiu_vrowiki.png saved!
- False Positive Rate is: 0.14356435643564355
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 346 58
reverted 7 9
============ - snwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (713, 17)
- Duplicate rows found and removed: 24
- Clean data shape: (689, 17)
- Unique revision_ids: 689 | Data Shape: 689 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (636, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_snwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8449905514717102
- confusion_matrix_snwiki.png saved!
- False Positive Rate is: 0.1558219178082192
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 493 91
reverted 13 39
============ - hawwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (648, 17)
- Duplicate rows found and removed: 25
- Clean data shape: (623, 17)
- Unique revision_ids: 623 | Data Shape: 623 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (577, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_hawwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.7269960045814514
- confusion_matrix_hawwiki.png saved!
- False Positive Rate is: 0.15180265654648956
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 447 80
reverted 8 42
============ - gomwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (524, 17)
- Duplicate rows found and removed: 2
- Clean data shape: (522, 17)
- Unique revision_ids: 522 | Data Shape: 522 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (507, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_gomwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.791193425655365
- confusion_matrix_gomwiki.png saved!
- False Positive Rate is: 0.16359918200409
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 409 80
reverted 7 11
============ - atjwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (231, 17)
- Duplicate rows found and removed: 1
- Clean data shape: (230, 17)
- Unique revision_ids: 230 | Data Shape: 230 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (220, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_atjwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6775605082511902
- confusion_matrix_atjwiki.png saved!
- False Positive Rate is: 0.11650485436893204
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 182 24
reverted 6 8
============ - awawiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (985, 17)
- Duplicate rows found and removed: 20
- Clean data shape: (965, 17)
- Unique revision_ids: 965 | Data Shape: 965 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (914, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_awawiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.7764677405357361
- confusion_matrix_awawiki.png saved!
- False Positive Rate is: 0.14801864801864803
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 731 127
reverted 24 32
============ - hifwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (6520, 17)
- Duplicate rows found and removed: 61
- Clean data shape: (6459, 17)
- Unique revision_ids: 6459 | Data Shape: 6459 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (5989, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_hifwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.5998679995536804
- confusion_matrix_hifwiki.png saved!
- False Positive Rate is: 0.1495664739884393
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 4708 828
reverted 43 410
============ - vlswiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (2929, 17)
- Duplicate rows found and removed: 3
- Clean data shape: (2926, 17)
- Unique revision_ids: 2926 | Data Shape: 2926 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (2905, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_vlswiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.7379829287528992
- confusion_matrix_vlswiki.png saved!
- False Positive Rate is: 0.1499644633972992
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 2392 422
reverted 31 60
============ - hsbwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1658, 17)
- Duplicate rows found and removed: 23
- Clean data shape: (1635, 17)
- Unique revision_ids: 1635 | Data Shape: 1635 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (1594, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_hsbwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6192979216575623
- confusion_matrix_hsbwiki.png saved!
- False Positive Rate is: 0.14868421052631578
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1294 226
reverted 9 65
============ - papwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (15067, 17)
- Duplicate rows found and removed: 9
- Clean data shape: (15058, 17)
- Unique revision_ids: 15058 | Data Shape: 15058 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (15015, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_papwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.3176918029785156
- confusion_matrix_papwiki.png saved!
- False Positive Rate is: 0.14998307952622675
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 12559 2216
reverted 80 160
============ - ilowiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1793, 17)
- Duplicate rows found and removed: 102
- Clean data shape: (1691, 17)
- Unique revision_ids: 1691 | Data Shape: 1691 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (1593, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_ilowiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8618624210357666
- confusion_matrix_ilowiki.png saved!
- False Positive Rate is: 0.15263518138261464
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1238 223
reverted 24 108
============ - angwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (2230, 17)
- Duplicate rows found and removed: 37
- Clean data shape: (2193, 17)
- Unique revision_ids: 2193 | Data Shape: 2193 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (2089, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_angwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6236856579780579
- confusion_matrix_angwiki.png saved!
- False Positive Rate is: 0.15792103948025987
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1685 316
reverted 6 82
============ - udmwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (263, 17)
- Duplicate rows found and removed: 3
- Clean data shape: (260, 17)
- Unique revision_ids: 260 | Data Shape: 260 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (242, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_udmwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.9283071756362915
- confusion_matrix_udmwiki.png saved!
- False Positive Rate is: 0.15486725663716813
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 191 35
reverted 12 4
============ - inhwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1889, 17)
- Duplicate rows found and removed: 4
- Clean data shape: (1885, 17)
- Unique revision_ids: 1885 | Data Shape: 1885 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (1845, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_inhwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.5125144124031067
- confusion_matrix_inhwiki.png saved!
- False Positive Rate is: 0.12583148558758314
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1577 227
reverted 11 30
============ - shnwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (38321, 17)
- Duplicate rows found and removed: 2
- Clean data shape: (38319, 17)
- Unique revision_ids: 38319 | Data Shape: 38319 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (38297, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_shnwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.39125075936317444
- confusion_matrix_shnwiki.png saved!
- False Positive Rate is: 0.14907627583683922
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 32564 5705
reverted 9 19
============ - roa_tarawiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (395, 17)
- Duplicate rows found and removed: 0
- Clean data shape: (395, 17)
- Unique revision_ids: 395 | Data Shape: 395 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (392, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_roa_tarawiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8557033538818359
- confusion_matrix_roa_tarawiki.png saved!
- False Positive Rate is: 0.14397905759162305
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 327 55
reverted 8 2
============ - pamwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1718, 17)
- Duplicate rows found and removed: 108
- Clean data shape: (1610, 17)
- Unique revision_ids: 1610 | Data Shape: 1610 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (1567, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_pamwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6135830283164978
- confusion_matrix_pamwiki.png saved!
- False Positive Rate is: 0.15053763440860216
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1185 210
reverted 8 164
============ - hakwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1724, 17)
- Duplicate rows found and removed: 11
- Clean data shape: (1713, 17)
- Unique revision_ids: 1713 | Data Shape: 1713 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (1686, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_hakwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.872566819190979
- confusion_matrix_hakwiki.png saved!
- False Positive Rate is: 0.14906457453228728
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1410 247
reverted 9 20
============ - xhwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (989, 17)
- Duplicate rows found and removed: 7
- Clean data shape: (982, 17)
- Unique revision_ids: 982 | Data Shape: 982 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (955, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_xhwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8263096809387207
- confusion_matrix_xhwiki.png saved!
- False Positive Rate is: 0.15570934256055363
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 732 135
reverted 61 27
============ - cdowiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (675, 17)
- Duplicate rows found and removed: 5
- Clean data shape: (670, 17)
- Unique revision_ids: 670 | Data Shape: 670 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (615, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_cdowiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.7494366765022278
- confusion_matrix_cdowiki.png saved!
- False Positive Rate is: 0.157439446366782
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 487 91
reverted 16 21
============ - crwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (354, 17)
- Duplicate rows found and removed: 73
- Clean data shape: (281, 17)
- Unique revision_ids: 281 | Data Shape: 281 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (192, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_crwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.9600421190261841
- confusion_matrix_crwiki.png saved!
- False Positive Rate is: 0.13924050632911392
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 68 11
reverted 61 52
============ - bowiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (2967, 17)
- Duplicate rows found and removed: 13
- Clean data shape: (2954, 17)
- Unique revision_ids: 2954 | Data Shape: 2954 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (2914, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_bowiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6828720569610596
- confusion_matrix_bowiki.png saved!
- False Positive Rate is: 0.1438721136767318
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 2410 405
reverted 61 38
============ - mwlwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1392, 17)
- Duplicate rows found and removed: 15
- Clean data shape: (1377, 17)
- Unique revision_ids: 1377 | Data Shape: 1377 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (1341, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_mwlwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.7521858215332031
- confusion_matrix_mwlwiki.png saved!
- False Positive Rate is: 0.15007656967840735
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1110 196
reverted 0 35
============ - kvwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1342, 17)
- Duplicate rows found and removed: 18
- Clean data shape: (1324, 17)
- Unique revision_ids: 1324 | Data Shape: 1324 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (1284, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_kvwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8378894925117493
- confusion_matrix_kvwiki.png saved!
- False Positive Rate is: 0.15024232633279483
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1052 186
reverted 17 29
============ - nvwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (531, 17)
- Duplicate rows found and removed: 25
- Clean data shape: (506, 17)
- Unique revision_ids: 506 | Data Shape: 506 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (366, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_nvwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.38992777466773987
- confusion_matrix_nvwiki.png saved!
- False Positive Rate is: 0.14798206278026907
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 190 33
reverted 24 119
============ - tiwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (305, 17)
- Duplicate rows found and removed: 35
- Clean data shape: (270, 17)
- Unique revision_ids: 270 | Data Shape: 270 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (260, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_tiwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.935514509677887
- confusion_matrix_tiwiki.png saved!
- False Positive Rate is: 0.13524590163934427
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 211 33
reverted 14 2
============ - lnwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1980, 17)
- Duplicate rows found and removed: 3
- Clean data shape: (1977, 17)
- Unique revision_ids: 1977 | Data Shape: 1977 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (1952, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_lnwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.613621175289154
- confusion_matrix_lnwiki.png saved!
- False Positive Rate is: 0.1809623430962343
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1566 346
reverted 11 29
============ - dinwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (43, 17)
- Duplicate rows found and removed: 0
- Clean data shape: (43, 17)
- Unique revision_ids: 43 | Data Shape: 43 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (40, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_dinwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.9743212461471558
- confusion_matrix_dinwiki.png saved!
- False Positive Rate is: 0.025
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 39 1
============ - pdcwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (494, 17)
- Duplicate rows found and removed: 30
- Clean data shape: (464, 17)
- Unique revision_ids: 464 | Data Shape: 464 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (426, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_pdcwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8773342967033386
- confusion_matrix_pdcwiki.png saved!
- False Positive Rate is: 0.1184573002754821
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 320 43
reverted 11 52
============ - wowiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (510, 17)
- Duplicate rows found and removed: 0
- Clean data shape: (510, 17)
- Unique revision_ids: 510 | Data Shape: 510 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (503, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_wowiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.9093973636627197
- confusion_matrix_wowiki.png saved!
- False Positive Rate is: 0.12627291242362526
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 429 62
reverted 9 3
============ - ladwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1057, 17)
- Duplicate rows found and removed: 8
- Clean data shape: (1049, 17)
- Unique revision_ids: 1049 | Data Shape: 1049 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (1023, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_ladwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6133739948272705
- confusion_matrix_ladwiki.png saved!
- False Positive Rate is: 0.15747241725175526
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 840 157
reverted 3 23
============ - kaawiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (25760, 17)
- Duplicate rows found and removed: 40
- Clean data shape: (25720, 17)
- Unique revision_ids: 25720 | Data Shape: 25720 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (25684, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_kaawiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.36563432216644287
- confusion_matrix_kaawiki.png saved!
- False Positive Rate is: 0.15022368730868849
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 21654 3828
reverted 121 81
============ - avwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1262, 17)
- Duplicate rows found and removed: 0
- Clean data shape: (1262, 17)
- Unique revision_ids: 1262 | Data Shape: 1262 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (1243, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_avwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6423503756523132
- confusion_matrix_avwiki.png saved!
- False Positive Rate is: 0.14775510204081632
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1044 181
reverted 4 14
============ - arcwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (198, 17)
- Duplicate rows found and removed: 5
- Clean data shape: (193, 17)
- Unique revision_ids: 193 | Data Shape: 193 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (172, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_arcwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8438354730606079
- confusion_matrix_arcwiki.png saved!
- False Positive Rate is: 0.14965986394557823
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 125 22
reverted 9 16
============ - nywiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (179, 17)
- Duplicate rows found and removed: 3
- Clean data shape: (176, 17)
- Unique revision_ids: 176 | Data Shape: 176 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (171, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_nywiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8020690679550171
- confusion_matrix_nywiki.png saved!
- False Positive Rate is: 0.15757575757575756
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 139 26
reverted 6 0
============ - cuwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (831, 17)
- Duplicate rows found and removed: 16
- Clean data shape: (815, 17)
- Unique revision_ids: 815 | Data Shape: 815 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (775, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_cuwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.828187108039856
- confusion_matrix_cuwiki.png saved!
- False Positive Rate is: 0.14421768707482993
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 629 106
reverted 21 19
============ - pflwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (785, 17)
- Duplicate rows found and removed: 13
- Clean data shape: (772, 17)
- Unique revision_ids: 772 | Data Shape: 772 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (756, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_pflwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6133654117584229
- confusion_matrix_pflwiki.png saved!
- False Positive Rate is: 0.07327001356852103
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 683 54
reverted 0 19
============ - csbwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (686, 17)
- Duplicate rows found and removed: 6
- Clean data shape: (680, 17)
- Unique revision_ids: 680 | Data Shape: 680 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (631, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_csbwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8540676236152649
- confusion_matrix_csbwiki.png saved!
- False Positive Rate is: 0.15198618307426598
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 491 88
reverted 21 31
============ - extwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (4192, 17)
- Duplicate rows found and removed: 5
- Clean data shape: (4187, 17)
- Unique revision_ids: 4187 | Data Shape: 4187 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (4138, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_extwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.5438408255577087
- confusion_matrix_extwiki.png saved!
- False Positive Rate is: 0.1488633585920313
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 3482 609
reverted 11 36
============ - miwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (745, 17)
- Duplicate rows found and removed: 3
- Clean data shape: (742, 17)
- Unique revision_ids: 742 | Data Shape: 742 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (730, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_miwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8816435933113098
- confusion_matrix_miwiki.png saved!
- False Positive Rate is: 0.1511627906976744
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 584 104
reverted 22 20
============ - aywiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (889, 17)
- Duplicate rows found and removed: 9
- Clean data shape: (880, 17)
- Unique revision_ids: 880 | Data Shape: 880 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (820, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_aywiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.7209958434104919
- confusion_matrix_aywiki.png saved!
- False Positive Rate is: 0.14915693904020752
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 656 115
reverted 12 37
============ - nrmwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (175, 17)
- Duplicate rows found and removed: 0
- Clean data shape: (175, 17)
- Unique revision_ids: 175 | Data Shape: 175 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (169, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_nrmwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8681466579437256
- confusion_matrix_nrmwiki.png saved!
- False Positive Rate is: 0.15432098765432098
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 137 25
reverted 2 5
============ - furwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (2744, 17)
- Duplicate rows found and removed: 7
- Clean data shape: (2737, 17)
- Unique revision_ids: 2737 | Data Shape: 2737 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (2707, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_furwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.9329590201377869
- confusion_matrix_furwiki.png saved!
- False Positive Rate is: 0.14930944382232175
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 2279 400
reverted 16 12
============ - cbk_zamwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (411, 17)
- Duplicate rows found and removed: 13
- Clean data shape: (398, 17)
- Unique revision_ids: 398 | Data Shape: 398 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (370, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_cbk_zamwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.7877727746963501
- confusion_matrix_cbk_zamwiki.png saved!
- False Positive Rate is: 0.1402439024390244
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 282 46
reverted 12 30
============ - newwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (2457, 17)
- Duplicate rows found and removed: 61
- Clean data shape: (2396, 17)
- Unique revision_ids: 2396 | Data Shape: 2396 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (2360, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_newwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.5211036801338196
- confusion_matrix_newwiki.png saved!
- False Positive Rate is: 0.15593952483801296
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1954 361
reverted 7 38
============ - nahwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (172, 17)
- Duplicate rows found and removed: 6
- Clean data shape: (166, 17)
- Unique revision_ids: 166 | Data Shape: 166 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (157, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_nahwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.9201942086219788
- confusion_matrix_nahwiki.png saved!
- False Positive Rate is: 0.10596026490066225
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 135 16
reverted 5 1
============ - gvwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (6286, 17)
- Duplicate rows found and removed: 25
- Clean data shape: (6261, 17)
- Unique revision_ids: 6261 | Data Shape: 6261 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (6218, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_gvwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.3498202860355377
- confusion_matrix_gvwiki.png saved!
- False Positive Rate is: 0.15668727627725348
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 5183 963
reverted 4 68
============ - omwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (891, 17)
- Duplicate rows found and removed: 7
- Clean data shape: (884, 17)
- Unique revision_ids: 884 | Data Shape: 884 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (834, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_omwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8401511311531067
- confusion_matrix_omwiki.png saved!
- False Positive Rate is: 0.17884130982367757
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 652 142
reverted 19 21
============ - klwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (598, 17)
- Duplicate rows found and removed: 26
- Clean data shape: (572, 17)
- Unique revision_ids: 572 | Data Shape: 572 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (382, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_klwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8161092400550842
- confusion_matrix_klwiki.png saved!
- False Positive Rate is: 0.14285714285714285
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 162 27
reverted 30 163
============ - zeawiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (11034, 17)
- Duplicate rows found and removed: 20
- Clean data shape: (11014, 17)
- Unique revision_ids: 11014 | Data Shape: 11014 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (10935, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_zeawiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.633648157119751
- confusion_matrix_zeawiki.png saved!
- False Positive Rate is: 0.1496655518394649
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 9153 1611
reverted 103 68
============ - smwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (664, 17)
- Duplicate rows found and removed: 0
- Clean data shape: (664, 17)
- Unique revision_ids: 664 | Data Shape: 664 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (658, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_smwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.7539634108543396
- confusion_matrix_smwiki.png saved!
- False Positive Rate is: 0.16411042944785276
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 545 107
reverted 2 4
============ - roa_rupwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (384, 17)
- Duplicate rows found and removed: 13
- Clean data shape: (371, 17)
- Unique revision_ids: 371 | Data Shape: 371 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (333, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_roa_rupwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6913049817085266
- confusion_matrix_roa_rupwiki.png saved!
- False Positive Rate is: 0.15960912052117263
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 258 49
reverted 6 20
============ - map_bmswiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (623, 17)
- Duplicate rows found and removed: 88
- Clean data shape: (535, 17)
- Unique revision_ids: 535 | Data Shape: 535 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (456, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_map_bmswiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.9081456065177917
- confusion_matrix_map_bmswiki.png saved!
- False Positive Rate is: 0.1488673139158576
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 263 46
reverted 80 67
============ - stwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1955, 17)
- Duplicate rows found and removed: 1
- Clean data shape: (1954, 17)
- Unique revision_ids: 1954 | Data Shape: 1954 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (1943, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_stwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.4744786024093628
- confusion_matrix_stwiki.png saved!
- False Positive Rate is: 0.14105925537493444
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1638 269
reverted 28 8
============ - kswiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (8284, 17)
- Duplicate rows found and removed: 1
- Clean data shape: (8283, 17)
- Unique revision_ids: 8283 | Data Shape: 8283 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (8270, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_kswiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.25549614429473877
- confusion_matrix_kswiki.png saved!
- False Positive Rate is: 0.14953838678328474
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 7001 1231
reverted 23 15
============ - bxrwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (707, 17)
- Duplicate rows found and removed: 0
- Clean data shape: (707, 17)
- Unique revision_ids: 707 | Data Shape: 707 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (698, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_bxrwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.842378556728363
- confusion_matrix_bxrwiki.png saved!
- False Positive Rate is: 0.1577424023154848
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 582 109
reverted 5 2
============ - kbpwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (169, 17)
- Duplicate rows found and removed: 7
- Clean data shape: (162, 17)
- Unique revision_ids: 162 | Data Shape: 162 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (148, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_kbpwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8215250372886658
- confusion_matrix_kbpwiki.png saved!
- False Positive Rate is: 0.16911764705882354
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 113 23
reverted 6 6
============ - fjwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (661, 17)
- Duplicate rows found and removed: 5
- Clean data shape: (656, 17)
- Unique revision_ids: 656 | Data Shape: 656 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (643, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_fjwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.4832654595375061
- confusion_matrix_fjwiki.png saved!
- False Positive Rate is: 0.09968354430379747
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 569 63
reverted 0 11
============ - ltgwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (176, 17)
- Duplicate rows found and removed: 2
- Clean data shape: (174, 17)
- Unique revision_ids: 174 | Data Shape: 174 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (161, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_ltgwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8122517466545105
- confusion_matrix_ltgwiki.png saved!
- False Positive Rate is: 0.13815789473684212
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 131 21
reverted 5 4
============ - gotwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (514, 17)
- Duplicate rows found and removed: 8
- Clean data shape: (506, 17)
- Unique revision_ids: 506 | Data Shape: 506 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (483, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_gotwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.7810843586921692
- confusion_matrix_gotwiki.png saved!
- False Positive Rate is: 0.16375545851528384
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 383 75
reverted 3 22
============ - ganwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (330, 17)
- Duplicate rows found and removed: 29
- Clean data shape: (301, 17)
- Unique revision_ids: 301 | Data Shape: 301 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (258, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_ganwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8062781095504761
- confusion_matrix_ganwiki.png saved!
- False Positive Rate is: 0.15126050420168066
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 202 36
reverted 9 11
============ - pagwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1110, 17)
- Duplicate rows found and removed: 208
- Clean data shape: (902, 17)
- Unique revision_ids: 902 | Data Shape: 902 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (734, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_pagwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.9537625908851624
- confusion_matrix_pagwiki.png saved!
- False Positive Rate is: 0.14937759336099585
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 410 72
reverted 141 111
============ - gagwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1700, 17)
- Duplicate rows found and removed: 15
- Clean data shape: (1685, 17)
- Unique revision_ids: 1685 | Data Shape: 1685 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (1657, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_gagwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.5600930452346802
- confusion_matrix_gagwiki.png saved!
- False Positive Rate is: 0.1434729064039409
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1391 233
reverted 4 29
============ - sswiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (839, 17)
- Duplicate rows found and removed: 2
- Clean data shape: (837, 17)
- Unique revision_ids: 837 | Data Shape: 837 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (832, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_sswiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6542070508003235
- confusion_matrix_sswiki.png saved!
- False Positive Rate is: 0.15158924205378974
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 694 124
reverted 6 8
============ - rmywiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (257, 17)
- Duplicate rows found and removed: 5
- Clean data shape: (252, 17)
- Unique revision_ids: 252 | Data Shape: 252 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (230, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_rmywiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.9060903191566467
- confusion_matrix_rmywiki.png saved!
- False Positive Rate is: 0.16097560975609757
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 172 33
reverted 14 11
============ - ffwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (36311, 17)
- Duplicate rows found and removed: 22
- Clean data shape: (36289, 17)
- Unique revision_ids: 36289 | Data Shape: 36289 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (36230, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_ffwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.3907754123210907
- confusion_matrix_ffwiki.png saved!
- False Positive Rate is: 0.14912814835316912
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 30742 5388
reverted 62 38
============ - nsowiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (697, 17)
- Duplicate rows found and removed: 29
- Clean data shape: (668, 17)
- Unique revision_ids: 668 | Data Shape: 668 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (632, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_nsowiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8198308944702148
- confusion_matrix_nsowiki.png saved!
- False Positive Rate is: 0.1445993031358885
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 491 83
reverted 27 31
============ - jbowiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (519, 17)
- Duplicate rows found and removed: 9
- Clean data shape: (510, 17)
- Unique revision_ids: 510 | Data Shape: 510 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (325, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_jbowiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.9296131730079651
- confusion_matrix_jbowiki.png saved!
- False Positive Rate is: 0.15023474178403756
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 181 32
reverted 78 34
============ - chrwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (953, 17)
- Duplicate rows found and removed: 228
- Clean data shape: (725, 17)
- Unique revision_ids: 725 | Data Shape: 725 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (604, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_chrwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.9158294200897217
- confusion_matrix_chrwiki.png saved!
- False Positive Rate is: 0.14814814814814814
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 322 56
reverted 111 115
============ - adywiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (160, 17)
- Duplicate rows found and removed: 10
- Clean data shape: (150, 17)
- Unique revision_ids: 150 | Data Shape: 150 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (136, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_adywiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8431930541992188
- confusion_matrix_adywiki.png saved!
- False Positive Rate is: 0.14285714285714285
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 96 16
reverted 9 15
============ - stqwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (215, 17)
- Duplicate rows found and removed: 0
- Clean data shape: (215, 17)
- Unique revision_ids: 215 | Data Shape: 215 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (193, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_stqwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8420207500457764
- confusion_matrix_stqwiki.png saved!
- False Positive Rate is: 0.14444444444444443
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 154 26
reverted 7 6
============ - tetwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (978, 17)
- Duplicate rows found and removed: 3
- Clean data shape: (975, 17)
- Unique revision_ids: 975 | Data Shape: 975 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (959, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_tetwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8080796599388123
- confusion_matrix_tetwiki.png saved!
- False Positive Rate is: 0.1554845580404686
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 793 146
reverted 8 12
============ - tnwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (2544, 17)
- Duplicate rows found and removed: 1
- Clean data shape: (2543, 17)
- Unique revision_ids: 2543 | Data Shape: 2543 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (2535, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_tnwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.5295730829238892
- confusion_matrix_tnwiki.png saved!
- False Positive Rate is: 0.15087579617834396
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 2133 379
reverted 9 14
============ - lgwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (2099, 17)
- Duplicate rows found and removed: 38
- Clean data shape: (2061, 17)
- Unique revision_ids: 2061 | Data Shape: 2061 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (2001, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_lgwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.5962941646575928
- confusion_matrix_lgwiki.png saved!
- False Positive Rate is: 0.14926133469179828
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1670 293
reverted 21 17
============ - dvwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (818, 17)
- Duplicate rows found and removed: 25
- Clean data shape: (793, 17)
- Unique revision_ids: 793 | Data Shape: 793 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (772, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_dvwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.9355606436729431
- confusion_matrix_dvwiki.png saved!
- False Positive Rate is: 0.15902964959568733
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 624 118
reverted 23 7
============ - gcrwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (128, 17)
- Duplicate rows found and removed: 3
- Clean data shape: (125, 17)
- Unique revision_ids: 125 | Data Shape: 125 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (108, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_gcrwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8253213167190552
- confusion_matrix_gcrwiki.png saved!
- False Positive Rate is: 0.16304347826086957
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 77 15
reverted 6 10
============ - tswiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (827, 17)
- Duplicate rows found and removed: 3
- Clean data shape: (824, 17)
- Unique revision_ids: 824 | Data Shape: 824 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (815, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_tswiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.7430192828178406
- confusion_matrix_tswiki.png saved!
- False Positive Rate is: 0.1545338441890166
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 662 121
reverted 22 10
============ - kbdwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (223, 17)
- Duplicate rows found and removed: 2
- Clean data shape: (221, 17)
- Unique revision_ids: 221 | Data Shape: 221 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (208, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_kbdwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.9053165316581726
- confusion_matrix_kbdwiki.png saved!
- False Positive Rate is: 0.10050251256281408
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 179 20
reverted 1 8
============ - novwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (526, 17)
- Duplicate rows found and removed: 1
- Clean data shape: (525, 17)
- Unique revision_ids: 525 | Data Shape: 525 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (514, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_novwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8247998356819153
- confusion_matrix_novwiki.png saved!
- False Positive Rate is: 0.15169660678642716
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 425 76
reverted 5 8
============ - twwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (3435, 17)
- Duplicate rows found and removed: 3
- Clean data shape: (3432, 17)
- Unique revision_ids: 3432 | Data Shape: 3432 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (3413, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_twwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.5095222592353821
- confusion_matrix_twwiki.png saved!
- False Positive Rate is: 0.11578323956174119
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 2986 391
reverted 9 27
============ - srnwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (161, 17)
- Duplicate rows found and removed: 1
- Clean data shape: (160, 17)
- Unique revision_ids: 160 | Data Shape: 160 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (149, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_srnwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8315097689628601
- confusion_matrix_srnwiki.png saved!
- False Positive Rate is: 0.17482517482517482
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 118 25
reverted 3 3
============ - mdfwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (8683, 17)
- Duplicate rows found and removed: 0
- Clean data shape: (8683, 17)
- Unique revision_ids: 8683 | Data Shape: 8683 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (8660, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_mdfwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.2540217638015747
- confusion_matrix_mdfwiki.png saved!
- False Positive Rate is: 0.15540384170330943
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 7299 1343
reverted 3 15
============ - kshwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (218, 17)
- Duplicate rows found and removed: 1
- Clean data shape: (217, 17)
- Unique revision_ids: 217 | Data Shape: 217 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (206, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_kshwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.7654833197593689
- confusion_matrix_kshwiki.png saved!
- False Positive Rate is: 0.1306532663316583
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 173 26
reverted 2 5
============ - tpiwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (202, 17)
- Duplicate rows found and removed: 0
- Clean data shape: (202, 17)
- Unique revision_ids: 202 | Data Shape: 202 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (196, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_tpiwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.9687272906303406
- confusion_matrix_tpiwiki.png saved!
- False Positive Rate is: 0.021164021164021163
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 185 4
reverted 6 1
============ - pihwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (110, 17)
- Duplicate rows found and removed: 1
- Clean data shape: (109, 17)
- Unique revision_ids: 109 | Data Shape: 109 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (91, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_pihwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8746289014816284
- confusion_matrix_pihwiki.png saved!
- False Positive Rate is: 0.19480519480519481
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 62 15
reverted 8 6
============ - biwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (310, 17)
- Duplicate rows found and removed: 28
- Clean data shape: (282, 17)
- Unique revision_ids: 282 | Data Shape: 282 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (249, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_biwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.798578143119812
- confusion_matrix_biwiki.png saved!
- False Positive Rate is: 0.13777777777777778
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 194 31
reverted 13 11
============ - iuwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (423, 17)
- Duplicate rows found and removed: 13
- Clean data shape: (410, 17)
- Unique revision_ids: 410 | Data Shape: 410 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (364, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_iuwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.9290987849235535
- confusion_matrix_iuwiki.png saved!
- False Positive Rate is: 0.14779874213836477
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 271 47
reverted 25 21
============ - bugwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (829, 17)
- Duplicate rows found and removed: 6
- Clean data shape: (823, 17)
- Unique revision_ids: 823 | Data Shape: 823 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (805, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_bugwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8452925682067871
- confusion_matrix_bugwiki.png saved!
- False Positive Rate is: 0.14863102998696218
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 653 114
reverted 27 11
============ - kgwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1633, 17)
- Duplicate rows found and removed: 4
- Clean data shape: (1629, 17)
- Unique revision_ids: 1629 | Data Shape: 1629 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (1605, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_kgwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.4633360207080841
- confusion_matrix_kgwiki.png saved!
- False Positive Rate is: 0.1471147748890298
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1345 232
reverted 8 20
============ - vewiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (243, 17)
- Duplicate rows found and removed: 6
- Clean data shape: (237, 17)
- Unique revision_ids: 237 | Data Shape: 237 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (217, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_vewiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8505914807319641
- confusion_matrix_vewiki.png saved!
- False Positive Rate is: 0.14432989690721648
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 166 28
reverted 15 8
============ - piwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (96, 17)
- Duplicate rows found and removed: 0
- Clean data shape: (96, 17)
- Unique revision_ids: 96 | Data Shape: 96 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (92, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_piwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.9070486426353455
- confusion_matrix_piwiki.png saved!
- False Positive Rate is: 0.12359550561797752
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 78 11
reverted 3 0
============ - krcwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (4382, 17)
- Duplicate rows found and removed: 22
- Clean data shape: (4360, 17)
- Unique revision_ids: 4360 | Data Shape: 4360 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (4352, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_krcwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.28637173771858215
- confusion_matrix_krcwiki.png saved!
- False Positive Rate is: 0.15777262180974477
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 3630 680
reverted 24 18
============ - jamwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (315, 17)
- Duplicate rows found and removed: 15
- Clean data shape: (300, 17)
- Unique revision_ids: 300 | Data Shape: 300 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (220, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_jamwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8582241535186768
- confusion_matrix_jamwiki.png saved!
- False Positive Rate is: 0.1518987341772152
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 134 24
reverted 24 38
============ - xalwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (895, 17)
- Duplicate rows found and removed: 36
- Clean data shape: (859, 17)
- Unique revision_ids: 859 | Data Shape: 859 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (478, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_xalwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.9615033268928528
- confusion_matrix_xalwiki.png saved!
- False Positive Rate is: 0.14915254237288136
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 251 44
reverted 60 123
============ - pntwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (372, 17)
- Duplicate rows found and removed: 24
- Clean data shape: (348, 17)
- Unique revision_ids: 348 | Data Shape: 348 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (338, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_pntwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8978685140609741
- confusion_matrix_pntwiki.png saved!
- False Positive Rate is: 0.15873015873015872
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 265 50
reverted 6 17
============ - towiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (222, 17)
- Duplicate rows found and removed: 6
- Clean data shape: (216, 17)
- Unique revision_ids: 216 | Data Shape: 216 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (120, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_towiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.7774780988693237
- confusion_matrix_towiki.png saved!
- False Positive Rate is: 0.16363636363636364
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 92 18
reverted 7 3
============ - tumwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (525, 17)
- Duplicate rows found and removed: 0
- Clean data shape: (525, 17)
- Unique revision_ids: 525 | Data Shape: 525 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (518, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_tumwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6807906031608582
- confusion_matrix_tumwiki.png saved!
- False Positive Rate is: 0.17221135029354206
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 423 88
reverted 1 6
============ - dzwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (949, 17)
- Duplicate rows found and removed: 7
- Clean data shape: (942, 17)
- Unique revision_ids: 942 | Data Shape: 942 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (923, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_dzwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.661038339138031
- confusion_matrix_dzwiki.png saved!
- False Positive Rate is: 0.14733178654292342
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 735 127
reverted 43 18
============ - chywiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (155, 17)
- Duplicate rows found and removed: 1
- Clean data shape: (154, 17)
- Unique revision_ids: 154 | Data Shape: 154 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (126, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_chywiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8710290193557739
- confusion_matrix_chywiki.png saved!
- False Positive Rate is: 0.14953271028037382
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 91 16
reverted 12 7
============ - ikwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (227, 17)
- Duplicate rows found and removed: 4
- Clean data shape: (223, 17)
- Unique revision_ids: 223 | Data Shape: 223 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (200, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_ikwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6205543875694275
- confusion_matrix_ikwiki.png saved!
- False Positive Rate is: 0.15819209039548024
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 149 28
reverted 1 22
============ - koiwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (216, 17)
- Duplicate rows found and removed: 2
- Clean data shape: (214, 17)
- Unique revision_ids: 214 | Data Shape: 214 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (209, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_koiwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8761064410209656
- confusion_matrix_koiwiki.png saved!
- False Positive Rate is: 0.06829268292682927
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 191 14
reverted 3 1
============ - bmwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (194, 17)
- Duplicate rows found and removed: 4
- Clean data shape: (190, 17)
- Unique revision_ids: 190 | Data Shape: 190 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (155, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_bmwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.9002848267555237
- confusion_matrix_bmwiki.png saved!
- False Positive Rate is: 0.14814814814814814
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 115 20
reverted 11 9
============ - eewiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (1284, 17)
- Duplicate rows found and removed: 7
- Clean data shape: (1277, 17)
- Unique revision_ids: 1277 | Data Shape: 1277 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (1266, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_eewiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6407523155212402
- confusion_matrix_eewiki.png saved!
- False Positive Rate is: 0.14297124600638977
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 1073 179
reverted 4 10
============ - rnwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (217, 17)
- Duplicate rows found and removed: 7
- Clean data shape: (210, 17)
- Unique revision_ids: 210 | Data Shape: 210 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (199, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_rnwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.805659830570221
- confusion_matrix_rnwiki.png saved!
- False Positive Rate is: 0.14754098360655737
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 156 27
reverted 7 9
============ - lbewiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (694, 17)
- Duplicate rows found and removed: 6
- Clean data shape: (688, 17)
- Unique revision_ids: 688 | Data Shape: 688 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (651, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_lbewiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.6905577182769775
- confusion_matrix_lbewiki.png saved!
- False Positive Rate is: 0.15522875816993464
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 517 95
reverted 3 36
============ - zawiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (206, 17)
- Duplicate rows found and removed: 3
- Clean data shape: (203, 17)
- Unique revision_ids: 203 | Data Shape: 203 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (172, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_zawiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.7917940020561218
- confusion_matrix_zawiki.png saved!
- False Positive Rate is: 0.18
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 123 27
reverted 4 18
============ - kiwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (190, 17)
- Duplicate rows found and removed: 2
- Clean data shape: (188, 17)
- Unique revision_ids: 188 | Data Shape: 188 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (165, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_kiwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8098335266113281
- confusion_matrix_kiwiki.png saved!
- False Positive Rate is: 0.11409395973154363
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 132 17
reverted 2 14
============ - sgwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (146, 17)
- Duplicate rows found and removed: 0
- Clean data shape: (146, 17)
- Unique revision_ids: 146 | Data Shape: 146 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (139, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_sgwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8118735551834106
- confusion_matrix_sgwiki.png saved!
- False Positive Rate is: 0.09848484848484848
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 119 13
reverted 5 2
============ - chwiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (79, 17)
- Duplicate rows found and removed: 1
- Clean data shape: (78, 17)
- Unique revision_ids: 78 | Data Shape: 78 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (71, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_chwiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.9022724032402039
- confusion_matrix_chwiki.png saved!
- False Positive Rate is: 0.15254237288135594
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 50 9
reverted 7 5
============ - tywiki - ============
- Snapshot: 2025-06
- Date Window: 2024-08-01 00:00:00 - 2025-09-05 00:00:00
- Raw data shape: (92, 17)
- Duplicate rows found and removed: 5
- Clean data shape: (87, 17)
- Unique revision_ids: 87 | Data Shape: 87 | Same? : -> True
- Removing edits that are reverts from df | New Shape: (83, 17)
- Is any revert_risk_score NA? : False
- Is any user_edit_count NA? : False
- Is any time_to_revert NA? : False
- ROC_tywiki.png saved!
- Optimal threshold for 15.0% FPR is: 0.8348962664604187
- confusion_matrix_tywiki.png saved!
- False Positive Rate is: 0.2857142857142857
- CONFUSION MATRIX -
Predicted not reverted reverted
Actual
not reverted 55 22
reverted 6 0

Event Timeline

There are a very large number of changes, so older changes are hidden. Show Older Changes
gkyziridis updated the paste's language from shell to text.
gkyziridis updated the paste's language from text to autodetect.
gkyziridis updated the paste's language from autodetect to shell.
gkyziridis edited the content of this paste. (Show Details)
gkyziridis edited the content of this paste. (Show Details)
gkyziridis edited the content of this paste. (Show Details)