Add app.py

.gitignore

@@ -0,0 +1,159 @@
+# 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
+.idea/
+
+# Gradio
+flagged/

README.md

@@ -1,13 +1,13 @@
 ---
 title: Ranking
-emoji: ⚡
+emoji: 💯
 colorFrom: green
 colorTo: purple
 sdk: gradio
 sdk_version: 3.41.2
 app_file: app.py
-pinned: false
+pinned: true
 license: apache-2.0
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+It's all about ranking.

app.py

@@ -0,0 +1,106 @@
+import typing
+
+import gradio as gr
+import numpy as np
+import numpy.typing as npt
+import pandas as pd
+
+
+# https://gist.github.com/dustalov/41678b70c40ba5a55430fa5e77b121d9#file-newman-py
+def aggregate(wins: npt.NDArray[np.int64], ties: npt.NDArray[np.int64], tolerance: float = 10e-6, limit: int = 20) \
+        -> npt.ArrayLike:
+    assert wins.shape == ties.shape, 'wins and ties shapes are different'
+
+    pi, v = np.random.rand(wins.shape[0]), np.random.rand()
+
+    converged, iterations = False, 0
+
+    while not converged:
+        iterations += 1
+
+        v_numerator = np.sum(
+            ties * (pi[:, None] + pi) / (pi[:, None] + pi + 2 * v * np.sqrt(pi[:, None] * pi))
+        ) / 2
+
+        v_denominator = np.sum(
+            wins * 2 * np.sqrt(pi[:, None] * pi) / (pi[:, None] + pi + 2 * v * np.sqrt(pi[:, None] * pi))
+        )
+
+        v = v_numerator / v_denominator
+
+        pi_old = pi.copy()
+
+        pi_numerator = np.sum(
+            (wins + ties / 2) * (pi + v * np.sqrt(pi[:, np.newaxis] * pi)) /
+            (pi[:, np.newaxis] + pi + 2 * np.sqrt(pi[:, np.newaxis] * pi)),
+            axis=1
+        )
+
+        pi_denominator = np.sum(
+            (wins + ties / 2) * (1 + v * np.sqrt(pi[:, np.newaxis] * pi)) /
+            (pi[:, np.newaxis] + pi + 2 * np.sqrt(pi[:, np.newaxis] * pi)),
+            axis=0
+        )
+
+        pi = pi_numerator / pi_denominator
+
+        converged = bool(np.all(np.abs(pi / (pi + 1) - pi_old / (pi_old + 1)) < tolerance)) or (iterations >= limit)
+
+    return pi
+
+
+def handler(file: typing.IO[bytes]) -> pd.DataFrame:
+    try:
+        df = pd.read_csv(file.name, dtype=str)
+    except ValueError as e:
+        raise gr.Error(f'Parsing error: {e}')
+
+    if not pd.Series(['left', 'right', 'winner']).isin(df.columns).all():
+        raise gr.Error('Columns must exist: left, right, winner')
+
+    if not df['winner'].isin(pd.Series(['left', 'right', 'tie'])).all():
+        raise gr.Error('Allowed winner values: left, right, tie')
+
+    df = df[['left', 'right', 'winner']]
+
+    df.dropna(axis='rows', inplace=True)
+
+    index = pd.Index(np.unique(df[['left', 'right']].values), name='item')
+
+    df_wins = pd.pivot_table(df[df['winner'].isin(['left', 'right'])],
+                             index='left', columns='right', values='winner',
+                             aggfunc='count', fill_value=0)
+    df_wins = df_wins.reindex(labels=index, columns=index, fill_value=0)
+
+    df_ties = pd.pivot_table(df[df['winner'] == 'tie'],
+                             index='left', columns='right', values='winner', aggfunc='count',
+                             fill_value=0)
+    df_ties = df_ties.reindex(labels=index, columns=index, fill_value=0)
+
+    wins = df_wins.to_numpy(dtype=np.int64)
+    ties = df_ties.to_numpy(dtype=np.int64)
+    ties += ties.T
+
+    scores = aggregate(wins, ties)
+
+    df_result = pd.DataFrame(data={'score': scores}, index=index)
+    df_result['rank'] = df_result['score'].rank(ascending=False).astype(int)
+    df_result.sort_values(by=['rank', 'score'], ascending=[True, False], inplace=True)
+    df_result.reset_index(inplace=True)
+
+    return df_result
+
+
+iface = gr.Interface(
+    fn=handler,
+    inputs=gr.File(
+        value='example.csv',
+        file_types=['.tsv', '.csv']
+    ),
+    outputs=gr.Dataframe(
+        headers=['item', 'score', 'rank']
+    ),
+    allow_flagging='never'
+)
+
+iface.launch()

example.csv

@@ -0,0 +1,5 @@
+left,right,winner
+a,b,left
+b,c,right
+c,a,left
+a,c,tie