Initial commit

.flake8

+[flake8]
+max-line-length = 88
\ No newline at end of file

.gitignore

+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+.vscode/
\ No newline at end of file

language_models/__init__.py

+__version__ = '0.1.0'

language_models/train.py

+import argparse
+import json
+import logging
+from dataclasses import asdict, dataclass
+from pathlib import Path
+from typing import Tuple
+
+import pandas as pd
+from sklearn.metrics import confusion_matrix
+from xgboost import XGBClassifier
+
+
+@dataclass(frozen=True)
+class Performance:
+    true_positive: int
+    true_negative: int
+    false_positive: int
+    false_negative: int
+
+
+LABEL = "damaging"
+FEATURES = [
+    "delta_num_categories",
+    "delta_num_headings",
+    "delta_num_media",
+    "delta_num_refs",
+    "delta_num_wikilinks",
+    "delta_page_length",
+]
+
+
+def split_by_language(
+    data_df: pd.DataFrame, wiki_db: str
+) -> Tuple[pd.DataFrame, pd.DataFrame]:
+    language_df = data_df[data_df["wiki_db"] == wiki_db]
+    other_languages_df = data_df[data_df["wiki_db"] != wiki_db]
+    return language_df, other_languages_df
+
+
+def train(X: pd.DataFrame, y: pd.Series) -> XGBClassifier:
+    logging.info(f"Training gradient boosted classifier: {len(X)} examples")
+    model = XGBClassifier()
+    model.fit(X, y, verbose=True)
+    return model
+
+
+def calculate_performance(
+    model: XGBClassifier, X: pd.DataFrame, y: pd.Series
+) -> Performance:
+    logging.info(f"Calculating model performance metrics: {len(X)} examples")
+    y_pred = model.predict(X)
+    tn, fp, fn, tp = confusion_matrix(y, y_pred).ravel()
+    logging.info(f"tn: {tn}, fp: {fp}, fn: {fn}, tp: {tp}")
+    return Performance(
+        true_positive=int(tp),
+        true_negative=int(tn),
+        false_positive=int(fp),
+        false_negative=int(fn),
+    )
+
+
+def main() -> None:
+    logging.basicConfig(level=logging.INFO)
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--data",
+        type=Path,
+        required=True,
+        help="Path to training data",
+    )
+    parser.add_argument(
+        "--models",
+        type=Path,
+        required=True,
+        help="Directory to write the serialized models",
+    )
+    parser.add_argument(
+        "--performance",
+        type=Path,
+        required=True,
+        help="Directory to write the performance metrics for models",
+    )
+    args = parser.parse_args()
+    data_path = args.data
+    models_dir = args.models
+    performance_dir = args.performance
+
+    data_df = pd.read_csv(data_path, sep="\t", compression="gzip")
+    data_df = data_df[~data_df[LABEL].isnull()]
+    data_df[LABEL] = data_df[LABEL].astype(bool)
+    logging.info(f"Loaded {len(data_df)} training examples")
+
+    for wiki_db in data_df["wiki_db"].unique():
+        logging.info(f"Current language: {wiki_db}")
+        language_df, other_languages_df = split_by_language(data_df, wiki_db)
+        model = train(other_languages_df[FEATURES], other_languages_df[LABEL])
+        model_performance = calculate_performance(
+            model, language_df[FEATURES], language_df[LABEL]
+        )
+
+        model_path = models_dir / f"{wiki_db}.json"
+        logging.info(f"Writing model to {model_path}")
+        model.save_model(model_path)
+
+        performance_path = performance_dir / f"{wiki_db}.json"
+        logging.info(f"Writing model performance metrics to {performance_path}")
+        with open(performance_path, "w") as f:
+            json.dump(asdict(model_performance), f)
+
+
+if __name__ == "__main__":
+    main()

pyproject.toml

+[tool.poetry]
+name = "language-models"
+version = "0.1.0"
+description = ""
+authors = ["Muniza <maslam-ctr@wikimedia.org>"]
+
+[tool.poetry.dependencies]
+python = "^3.7.2"
+xgboost = "^1.6.1"
+pandas = "1.3"
+scikit-learn = "1.0"
+
+[tool.poetry.dev-dependencies]
+pytest = "^5.2"
+flake8 = "^5.0.1"
+black = "^22.6.0"
+isort = "^5.10.1"
+mypy = "^0.971"
+
+[build-system]
+requires = ["poetry-core>=1.0.0"]
+build-backend = "poetry.core.masonry.api"