This repository has been archived by the owner on Aug 9, 2024. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 35
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #34 from halfak/frwiki
Adds models and feature_lists for fr, fa and tr wiki. We have been using this in the Hackathon.
- Loading branch information
Showing
8 changed files
with
250 additions
and
62 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,44 @@ | ||
from revscoring.features import (diff, page, parent_revision, | ||
previous_user_revision, revision, user) | ||
from revscoring.features.modifiers import log | ||
|
||
from . import generic | ||
|
||
damaging = [ | ||
log(diff.added_symbolic_chars_ratio + 1), | ||
log(diff.chars_added + 1), | ||
log(diff.chars_removed + 1), | ||
diff.longest_repeated_char_added, | ||
diff.longest_token_added, | ||
log(diff.markup_chars_added + 1), | ||
log(diff.markup_chars_removed + 1), | ||
log(diff.numeric_chars_added + 1), | ||
log(diff.numeric_chars_removed + 1), | ||
diff.proportion_of_chars_added, | ||
diff.proportion_of_chars_removed, | ||
diff.proportion_of_markup_chars_added, | ||
diff.proportion_of_numeric_chars_added, | ||
diff.proportion_of_symbolic_chars_added, | ||
diff.proportion_of_uppercase_chars_added, | ||
log(diff.segments_added + 1), | ||
log(diff.segments_removed + 1), | ||
log(diff.symbolic_chars_added + 1), | ||
log(diff.symbolic_chars_removed + 1), | ||
log(diff.uppercase_chars_added + 1), | ||
log(diff.uppercase_chars_removed + 1), | ||
log(diff.words_added + 1), | ||
log(diff.words_removed + 1), | ||
diff.bytes_changed + 1, | ||
diff.bytes_changed_ratio, | ||
page.is_content_namespace, | ||
parent_revision.was_same_user, | ||
log(parent_revision.words + 1), | ||
log(user.age + 1), | ||
user.is_anon, | ||
user.is_bot, | ||
log(diff.added_misspellings_ratio + 1), | ||
log(diff.misspellings_added + 1), | ||
log(diff.misspellings_removed + 1), | ||
diff.proportion_of_misspellings_added, | ||
diff.proportion_of_misspellings_removed | ||
] |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,61 @@ | ||
from revscoring.features import (diff, page, parent_revision, | ||
previous_user_revision, revision, user) | ||
from revscoring.features.modifiers import log | ||
|
||
from . import generic | ||
|
||
damaging = [ | ||
log(diff.added_symbolic_chars_ratio + 1), | ||
log(diff.chars_added + 1), | ||
log(diff.chars_removed + 1), | ||
diff.longest_repeated_char_added, | ||
diff.longest_token_added, | ||
log(diff.markup_chars_added + 1), | ||
log(diff.markup_chars_removed + 1), | ||
log(diff.numeric_chars_added + 1), | ||
log(diff.numeric_chars_removed + 1), | ||
diff.proportion_of_chars_added, | ||
diff.proportion_of_chars_removed, | ||
diff.proportion_of_markup_chars_added, | ||
diff.proportion_of_numeric_chars_added, | ||
diff.proportion_of_symbolic_chars_added, | ||
diff.proportion_of_uppercase_chars_added, | ||
log(diff.segments_added + 1), | ||
log(diff.segments_removed + 1), | ||
log(diff.symbolic_chars_added + 1), | ||
log(diff.symbolic_chars_removed + 1), | ||
log(diff.uppercase_chars_added + 1), | ||
log(diff.uppercase_chars_removed + 1), | ||
log(diff.words_added + 1), | ||
log(diff.words_removed + 1), | ||
diff.bytes_changed + 1, | ||
diff.bytes_changed_ratio, | ||
page.is_content_namespace, | ||
parent_revision.was_same_user, | ||
log(parent_revision.words + 1), | ||
log(user.age + 1), | ||
user.is_anon, | ||
user.is_bot, | ||
log(diff.added_badwords_ratio + 1), | ||
log(diff.added_misspellings_ratio + 1), | ||
log(diff.badwords_added + 1), | ||
log(diff.badwords_removed + 1), | ||
log(diff.misspellings_added + 1), | ||
log(diff.misspellings_removed + 1), | ||
diff.proportion_of_badwords_added, | ||
diff.proportion_of_badwords_removed, | ||
diff.proportion_of_misspellings_added, | ||
diff.proportion_of_misspellings_removed | ||
] | ||
|
||
good_faith = generic.good_faith + [ | ||
log(diff.added_badwords_ratio + 1), | ||
log(diff.badwords_added + 1), | ||
log(diff.badwords_removed + 1), | ||
diff.proportion_of_badwords_added, | ||
diff.proportion_of_badwords_removed, | ||
diff.removed_badwords_ratio, | ||
log(parent_revision.badwords + 1), | ||
parent_revision.proportion_of_badwords, | ||
log(revision.badwords + 1) | ||
] |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,6 @@ | ||
from revscoring.languages import persian | ||
from revscoring.scorers import LinearSVCModel | ||
|
||
from ..feature_lists.fawiki import damaging | ||
|
||
damaging_linear_svc = LinearSVCModel(damaging, language=persian) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,6 @@ | ||
from revscoring.languages import french | ||
from revscoring.scorers import LinearSVCModel | ||
|
||
from ..feature_lists.frwiki import damaging | ||
|
||
damaging_linear_svc = LinearSVCModel(damaging, language=french) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,6 @@ | ||
from revscoring.languages import turkish | ||
from revscoring.scorers import LinearSVCModel | ||
|
||
from ..feature_lists.trwiki import damaging | ||
|
||
damaging_linear_svc = LinearSVCModel(damaging, language=turkish) |