Rename wikiclass to articlequality

Bug: T181820

.travis.yml

@@ -22,7 +22,7 @@ install:
 
 script:
   - flake8 . --ignore=E722 --exclude=.svn,CVS,.bzr,.hg,.git,__pycache__,.tox,.eggs,*.egg,doc,examples
-  - coverage run --source wikiclass -m pytest wikiclass -m "not nottravis"
+  - coverage run --source articlequality -m pytest articlequality -m "not nottravis"
 
 after_success:
   - coverage report

Makefile

@@ -57,14 +57,14 @@ datasets/enwiki.labeling_revisions.w_cache.30k.json: \
 		datasets/enwiki.labeling_revisions.w_text.30k.json
 	cat $< | \
 	./utility extract_from_text \
-	  wikiclass.feature_lists.enwiki.wp10 \
+	  articlequality.feature_lists.enwiki.wp10 \
 	  --verbose > $@
 
 datasets/enwiki.labeling_revisions.w_cache.nettrom_30k.json: \
 		datasets/enwiki.labeling_revisions.nettrom_30k.json
 	cat $< | \
 	revscoring extract \
-	  wikiclass.feature_lists.enwiki.wp10 \
+	  articlequality.feature_lists.enwiki.wp10 \
 	  --host https://en.wikipedia.org \
 	  --verbose > $@
 
@@ -73,7 +73,7 @@ tuning_reports/enwiki.nettrom_wp10.md: \
 	cat $< | \
 	revscoring tune \
 	  config/classifiers.params.yaml \
-	  wikiclass.feature_lists.enwiki.wp10 \
+	  articlequality.feature_lists.enwiki.wp10 \
 	  wp10 \
 	  accuracy.macro \
 	  --pop-rate '"Stub"=0.5762822268640726' \
@@ -90,7 +90,7 @@ models/enwiki.nettrom_wp10.gradient_boosting.model: \
 	cat $< | \
 	revscoring cv_train \
 	  revscoring.scoring.models.GradientBoosting \
-	  wikiclass.feature_lists.enwiki.wp10 \
+	  articlequality.feature_lists.enwiki.wp10 \
 	  wp10 \
 	  --version $(wp10_major_minor).1 \
 	  -p 'n_estimators=700' \
@@ -151,7 +151,7 @@ datasets/frwiki.labeling_revisions.w_cache.9k.json: \
 		datasets/frwiki.labeling_revisions.w_text.9k.json
 	cat $< | \
 	./utility extract_from_text \
-	  wikiclass.feature_lists.frwiki.wp10 \
+	  articlequality.feature_lists.frwiki.wp10 \
 	  --verbose > $@
 
 
@@ -160,7 +160,7 @@ tuning_reports/frwiki.wp10.md: \
 	cat $< | \
 	revscoring tune \
 	  config/classifiers.params.yaml \
-	  wikiclass.feature_lists.frwiki.wp10 \
+	  articlequality.feature_lists.frwiki.wp10 \
 	  wp10 \
 	  accuracy.macro \
 	  --pop-rate '"e"=0.7314705724717468' \
@@ -178,7 +178,7 @@ models/frwiki.wp10.gradient_boosting.model: \
 	cat $< | \
 	revscoring cv_train \
 	  revscoring.scoring.models.GradientBoosting \
-	  wikiclass.feature_lists.frwiki.wp10 \
+	  articlequality.feature_lists.frwiki.wp10 \
 	  wp10 \
 	  --version $(wp10_major_minor).0 \
 	  -p 'learning_rate=0.01' \
@@ -231,15 +231,15 @@ datasets/frwikisource.labeled_revisions.w_cache.20k_balanced_2017.json: \
 		datasets/frwikisource.labeled_revisions.with_text.20k_balanced_2017.json
 	cat $< | \
 	./utility extract_from_text \
-	  wikiclass.feature_lists.frwikisource.pagelevel \
+	  articlequality.feature_lists.frwikisource.pagelevel \
 	  --verbose > $@
 
 tuning_reports/frwikisource.page_level.md: \
 		datasets/frwikisource.labeled_revisions.w_cache.20k_balanced_2017.json
 	cat $< | \
 	revscoring tune \
 	  config/classifiers.params.yaml \
-	  wikiclass.feature_lists.frwikisource.pagelevel \
+	  articlequality.feature_lists.frwikisource.pagelevel \
 	  page_level \
 	  accuracy.macro \
 	  --pop-rate '"4"=0.17270922526244023' \
@@ -255,7 +255,7 @@ models/frwikisource.page_level.gradient_boosting.model: \
 	cat $< | \
 	revscoring cv_train \
 	  revscoring.scoring.models.GradientBoosting \
-	  wikiclass.feature_lists.frwikisource.pagelevel \
+	  articlequality.feature_lists.frwikisource.pagelevel \
 	  page_level \
 	  --version $(page_level_major_minor).0 \
 	  -p 'n_estimators=700' \
@@ -310,15 +310,15 @@ datasets/ruwiki.labeling_revisions.w_cache.8k.json: \
 		datasets/ruwiki.labeling_revisions.w_text.8k.json
 	cat $< | \
 	./utility extract_from_text \
-	  wikiclass.feature_lists.ruwiki.wp10 \
+	  articlequality.feature_lists.ruwiki.wp10 \
 	  --verbose > $@
 
 tuning_reports/ruwiki.wp10.md: \
 		datasets/ruwiki.labeling_revisions.w_cache.8k.json
 	cat $< | \
 	revscoring tune \
 	  config/classifiers.params.yaml \
-	  wikiclass.feature_lists.ruwiki.wp10 \
+	  articlequality.feature_lists.ruwiki.wp10 \
 	  wp10 \
 	  accuracy.macro \
 	  --pop-rate '"IV"=0.4872864906832298' \
@@ -337,7 +337,7 @@ models/ruwiki.wp10.gradient_boosting.model: \
 	cat $< | \
 	revscoring cv_train \
 	  revscoring.scoring.models.GradientBoosting \
-	  wikiclass.feature_lists.ruwiki.wp10 \
+	  articlequality.feature_lists.ruwiki.wp10 \
 	  wp10 \
 	  --version $(wp10_major_minor).0 \
 	  -p 'max_depth=5' \
@@ -386,15 +386,15 @@ datasets/trwiki.labeling_revisions.w_cache.2k.json: \
 		datasets/trwiki.labeling_revisions.w_text.2k.json
 	cat $< | \
 	./utility extract_from_text \
-	  wikiclass.feature_lists.trwiki.wp10 \
+	  articlequality.feature_lists.trwiki.wp10 \
 	  --verbose > $@
 
 tuning_reports/trwiki.wp10.md: \
 		datasets/trwiki.labeling_revisions.w_cache.2k.json
 	cat $< | \
 	revscoring tune \
 	  config/classifiers.params.yaml \
-	  wikiclass.feature_lists.trwiki.wp10 \
+	  articlequality.feature_lists.trwiki.wp10 \
 	  wp10 \
 	  accuracy.macro \
 	  --pop-rate '"taslak"=0.5804005556841861' \
@@ -412,7 +412,7 @@ models/trwiki.wp10.gradient_boosting.model: \
 	cat $< | \
 	revscoring cv_train \
 	  revscoring.scoring.models.GradientBoosting \
-	  wikiclass.feature_lists.trwiki.wp10 \
+	  articlequality.feature_lists.trwiki.wp10 \
 	  wp10 \
 	  --version $(wp10_major_minor).0 \
 	  -p 'max_depth=5' \
@@ -478,15 +478,15 @@ datasets/wikidatawiki.labeling_revisions.w_cache.5k.json: \
 		datasets/wikidatawiki.labeling_revisions.w_text.5k.json
 	cat $< | \
 	./utility extract_from_text \
-	  wikiclass.feature_lists.wikidatawiki.item_quality \
+	  articlequality.feature_lists.wikidatawiki.item_quality \
 	  --verbose > $@
 
 tuning_reports/wikidatawiki.item_quality.md: \
 		datasets/wikidatawiki.labeling_revisions.w_cache.5k.json
 	cat $< | \
 	revscoring tune \
 	  config/classifiers.params.yaml \
-	  wikiclass.feature_lists.wikidatawiki.item_quality \
+	  articlequality.feature_lists.wikidatawiki.item_quality \
 	  item_quality \
 	  accuracy.macro \
 	  --labels '"A","B","C","D","E"' \
@@ -498,7 +498,7 @@ models/wikidatawiki.item_quality.rf.model: \
 	cat $< | \
 	revscoring cv_train \
 	  revscoring.scoring.models.RandomForest \
-	  wikiclass.feature_lists.wikidatawiki.item_quality \
+	  articlequality.feature_lists.wikidatawiki.item_quality \
 	  item_quality \
 	  --version $(item_quality_major_minor).0 \
 	  -p 'n_estimators=20' \

README.md

@@ -5,18 +5,18 @@ This library provides a set of utilities for performing automatic detection of a
 **Compatible with Python 3.x only.**  Sorry.
 
 * **Install:** ``pip install wikiclass``
-* **Models:** https://github.com/wiki-ai/wikiclass/tree/master/models
+* **Models:** https://github.com/wiki-ai/articlequality/tree/master/models
 * **Documentation:** http://pythonhosted.org/wikiclass
 
 ## Basic usage
 
-    >>> import wikiclass
+    >>> import articlequality
     >>> from revscoring import Model
     >>>
     >>> scorer_model = Model.load(open("models/enwiki.nettrom_wp10.gradient_boosting.model", "rb"))
     >>>
     >>> text = "I am the text of a page.  I have a <ref>word</ref>"
-    >>> wikiclass.score(scorer_model, text)
+    >>> articlequality.score(scorer_model, text)
     {'prediction': 'stub',
      'probability': {'stub': 0.27156163795807853,
                      'b': 0.14707452309674252,

wikiclass/about.py → articlequality/about.py

@@ -1,8 +1,8 @@
-__name__ = "wikiclass"
+__name__ = "articlequality"
 __version__ = "0.3.2"
 __author__ = "Aaron Halfaker / Morten Warncke-Wang"
 __author_email__ = "[email protected]"
 __description__ = "A library for performing automatic detection of " + \
                   "assessment classes of Wikipedia articles."
-__url__ = "https://github.com/wiki-ai/wikiclass"
+__url__ = "https://github.com/wiki-ai/articlequality"
 __license__ = "MIT"

articlequality/extractors/__init__.py

@@ -0,0 +1,16 @@
+"""
+This module provides a set of :class:`articlequality.Extractor` s that
+implement a strategy for identifying article quality labeling events
+historically.  These labelings are used as training data to build prediction
+models.
+
+Supported wikis
+---------------
+.. automodule:: articlequality.extractors.enwiki
+
+.. automodule:: articlequality.extractors.frwiki
+
+Base classes
+------------
+.. automodule:: articlequality.extractors.extractor
+"""

wikiclass/extractors/enwiki.py → articlequality/extractors/enwiki.py

@@ -52,7 +52,7 @@ def normalize_project_name(template_name):
 sys.modules[__name__] = TemplateExtractor(
     __name__,
     doc="""
-wikiclass.extractors.enwiki
+articlequality.extractors.enwiki
 +++++++++++++++++++++++++++
 
 This extractor looks for instances of templates that contain

wikiclass/extractors/extractor.py → articlequality/extractors/extractor.py

@@ -1,8 +1,8 @@
 """
-.. autoclass:: wikiclass.Extractor
+.. autoclass:: articlequality.Extractor
     :members:
 
-.. autoclass:: wikiclass.TemplateExtractor
+.. autoclass:: articlequality.TemplateExtractor
     :members:
     :inherited-members:
 """

wikiclass/extractors/frwiki.py → articlequality/extractors/frwiki.py

@@ -51,7 +51,7 @@ def normalize_label(value):
 sys.modules[__name__] = TemplateExtractor(
     __name__,
     doc="""
-wikiclass.extractors.frwiki
+articlequality.extractors.frwiki
 +++++++++++++++++++++++++++
 
 This extractor looks for instances of the "wikiprojet" template on article talk

wikiclass/extractors/ruwiki.py → articlequality/extractors/ruwiki.py

@@ -53,7 +53,7 @@ def normalize_label(value):
 sys.modules[__name__] = TemplateExtractor(
     __name__,
     doc="""
-wikiclass.extractors.ruwiki
+articlequality.extractors.ruwiki
 +++++++++++++++++++++++++++
 
 This extractor looks for instances of templates on article talk pages

wikiclass/extractors/trwiki.py → articlequality/extractors/trwiki.py

@@ -63,7 +63,7 @@ def normalize_label(value):
 sys.modules[__name__] = TemplateExtractor(
     __name__,
     doc="""
-wikiclass.extractors.trwiki
+articlequality.extractors.trwiki
 +++++++++++++++++++++++++++
 
 This extractor looks for instances of the "VikiProje" template on article talk

articlequality/utilities/__init__.py

@@ -0,0 +1,26 @@
+"""
+This module implements a set of utilities for extracting labeling events, text
+and features from the command-line.  When the articlequality python package is
+installed, a `articlequality` utility should be available from the commandline.
+Run `revscoring -h` for more information:
+
+articlequality extract_from_text
+++++++++++++++++++++++++++
+.. automodule:: articlequality.utilities.extract_from_text
+
+articlequality extract_labelings
++++++++++++++++++++++++++++
+.. automodule:: articlequality.utilities.extract_labelings
+
+articlequality extract_text
+++++++++++++++++++++++
+.. automodule:: articlequality.utilities.extract_text
+
+articlequality fetch_text
+++++++++++++++++++++
+.. automodule:: articlequality.utilities.fetch_text
+
+articlequality score
++++++++++++++++
+.. automodule:: articlequality.utilities.score
+"""

wikiclass/utilities/extract_from_text.py → articlequality/utilities/extract_from_text.py

@@ -1,5 +1,5 @@
 """
-``$ wikclass extract_from_text -h``
+``$ articlequality extract_from_text -h``
 ::
 
     Extracts dependents from a labeling doc containing text and an

wikiclass/utilities/extract_labelings.py → articlequality/utilities/extract_labelings.py

@@ -1,5 +1,5 @@
 """
-``$ wikclass extract_labelings -h``
+``$ articlequality extract_labelings -h``
 ::
 
     Extracts labels from an XML dump and writes out labeled observations for
@@ -60,7 +60,7 @@ def main(argv=None):
 
 def load_extractor(extractor_name):
     try:
-        return import_module("wikiclass.extractors." + extractor_name)
+        return import_module("articlequality.extractors." + extractor_name)
     except ImportError:
         raise RuntimeError("Could not load extractor for '{0}'"
                            .format(extractor_name))
@@ -92,7 +92,7 @@ def extract_labelings(dump, extractor=None, verbose=False):
     :Parameters:
         dump : :class:`mwxml.Dump`
             The XML dump file to extract labelings from
-        extractor : :class:`wikiclass.Extractor`
+        extractor : :class:`articlequality.Extractor`
             An extractor to apply to the XML dump.  If no extractor is
             provided, an extract will be looked up based on <dbname> in the XML
             dump's <siteinfo> block.

wikiclass/utilities/extract_text.py → articlequality/utilities/extract_text.py

@@ -1,5 +1,5 @@
 """
-``$ wikclass extract_text -h``
+``$ articlequality extract_text -h``
 ::
 
     Extracts text & metadata for labelings using XML dumps.

wikiclass/utilities/fetch_item_info.py → articlequality/utilities/fetch_item_info.py

@@ -1,5 +1,5 @@
 """
-``$ wikclass fetch_item_info -h``
+``$ articlequality fetch_item_info -h``
 ::
 
     Annotates wikibase items with additional information
@@ -57,7 +57,7 @@ def main(argv=None):
     claims = args['--claim']
 
     session = mwapi.Session(args['--api-host'],
-                            user_agent="WikiClass fetch_text utility.")
+                            user_agent="ArticleQuality fetch_text utility.")
 
     verbose = args['--verbose']
 

wikiclass/utilities/fetch_text.py → articlequality/utilities/fetch_text.py

@@ -1,5 +1,5 @@
 """
-``$ wikclass fetch_text -h``
+``$ articlequality fetch_text -h``
 ::
 
     Fetches text & metadata for labelings using a MediaWiki API.
@@ -41,7 +41,7 @@ def main(argv=None):
         output = open(args['--output'])
 
     session = mwapi.Session(args['--api-host'],
-                            user_agent="WikiClass fetch_text utility.")
+                            user_agent="ArticleQaulity fetch_text utility.")
 
     verbose = args['--verbose']
 

wikiclass/utilities/score.py → articlequality/utilities/score.py

@@ -1,5 +1,5 @@
 """
-``$ wikclass score -h``
+``$ articlequality score -h``
 ::
 
     Applies a scoring model to a chunch of text.