spforge 0.0.0__tar.gz

spforge-0.0.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

spforge-0.0.0/MANIFEST.in

@@ -0,0 +1,3 @@
+include requirements.txt
+recursive-include examples/nba/data *.parquet
+recursive-include examples/lol/data *.parquet

spforge-0.0.0/PKG-INFO

@@ -0,0 +1,155 @@
+Metadata-Version: 2.4
+Name: spforge
+Version: 0.0.0
+Summary: A flexible framework for generating features, ratings, and building machine learning or other models for training and inference on sports data.
+Home-page: https://github.com/Hiderdk/player-performance-ratings
+Author: Mathias Holmstrøm
+Author-email: mathiasholmstom@gmail.com
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy>=1.23.4
+Requires-Dist: optuna>=3.4.0
+Requires-Dist: pandas>=2.0.0
+Requires-Dist: pendulum>=1.0.0
+Requires-Dist: scikit_learn>=1.3.1
+Requires-Dist: lightgbm>=4.0.0
+Requires-Dist: narwhals>=1.31.0
+Requires-Dist: polars>=1.17.0
+Requires-Dist: pytest>=8.0.0
+Requires-Dist: pyarrow>=19.0.0
+Dynamic: author
+Dynamic: author-email
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license-file
+Dynamic: requires-dist
+Dynamic: summary
+
+# spforge
+
+Framework designed to predict outcomes in sports games using player-based ratings or other forms of engineered features such as rolling means.
+Ratings can be used to predict game-winner, but also other outcomes such as total points scored, total yards gained, etc.
+
+## Installation
+
+```
+pip install spforge
+```
+
+
+## Examples
+Ensure you have a dataset where each row is a unique combination of game_ids and player_ids.
+There are multiple different use-cases for the framework, such as:
+1. Creating ratings for players/teams.
+2. Predicting the outcome.
+3. Creating features or other types of data-transformations
+
+### Predicting Game-Winner
+
+Ensure you have a dataset where each row is a unique combination of game_ids and player_ids. 
+Even if the concept of a player doesn't exist in the dataset, you can use team_id instead of player_id.
+
+Utilizing a rating model can be as simple as:
+
+```
+import pandas as pd
+from sklearn.linear_model import LogisticRegression
+
+from spforge.pipeline import Pipeline
+from spforge.predictor import GameTeamPredictor, SklearnPredictor
+
+from spforge.ratings import UpdateRatingGenerator
+
+from spforge.data_structures import ColumnNames
+from spforge.ratings.rating_calculators import MatchRatingGenerator
+
+df = pd.read_parquet("data/game_player_subsample.parquet")
+
+# Defines the column names as they appear in the dataframe
+column_names = ColumnNames(
+    team_id="team_id",
+    match_id="game_id",
+    start_date="start_date",
+    player_id="player_name",
+)
+# Sorts the dataframe. The dataframe must always be sorted as below
+df = df.sort_values(
+    by=[
+        column_names.start_date,
+        column_names.match_id,
+        column_names.team_id,
+        column_names.player_id,
+    ]
+)
+
+# Drops games with less or more than 2 teams
+df = (
+    df.assign(
+        team_count=df.groupby(column_names.match_id)[column_names.team_id].transform(
+            "nunique"
+        )
+    )
+    .loc[lambda x: x.team_count == 2]
+    .drop(columns=["team_count"])
+)
+
+# Pretends the last 10 games are future games. The most will be trained on everything before that.
+most_recent_10_games = df[column_names.match_id].unique()[-10:]
+historical_df = df[~df[column_names.match_id].isin(most_recent_10_games)]
+future_df = df[df[column_names.match_id].isin(most_recent_10_games)].drop(
+    columns=["won"]
+)
+
+# Defining a simple rating-generator. It will use the "won" column to update the ratings.
+# In contrast to a typical Elo, ratings will follow players.
+
+match_rating_generator = MatchRatingGenerator(rating_change_multiplier=30)
+
+rating_generator = UpdateRatingGenerator(
+    performance_column="won", match_rating_generator=match_rating_generator
+)
+
+# Defines the predictor. A machine-learning model will be used to predict game winner on a game-team-level.
+# Mean team-ratings will be calculated (from player-level) and rating-difference between the 2 teams calculated.
+# It will also use the location of the game as a feature.
+predictor = GameTeamPredictor(
+    game_id_colum=column_names.match_id,
+    team_id_column=column_names.team_id,
+    predictor=SklearnPredictor(
+        estimator_features=["location"], target="won", estimator=LogisticRegression()
+    ),
+    one_hot_encode_cat_features=True,
+)
+
+# Pipeline is whether we define all the steps. Other transformations can take place as well.
+# However, in our simple example we only have a simple rating-generator and a predictor.
+pipeline = Pipeline(
+    rating_generators=rating_generator,
+    predictor=predictor,
+    column_names=column_names,
+)
+
+# Trains the model and returns historical predictions
+pipeline.train(df=historical_df)
+
+# Future predictions on future results
+future_predictions = pipeline.predict(df=future_df)
+
+# Grouping predictions from game-player level to game-level.
+team_grouped_predictions = future_predictions.groupby(column_names.match_id).first()[
+    [
+        column_names.start_date,
+        column_names.team_id,
+        "team_id_opponent",
+        predictor.pred_column,
+    ]
+]
+
+print(team_grouped_predictions)
+
+```
+
+## Further Examples
+
+

spforge-0.0.0/README.md

@@ -0,0 +1,127 @@
+# spforge
+
+Framework designed to predict outcomes in sports games using player-based ratings or other forms of engineered features such as rolling means.
+Ratings can be used to predict game-winner, but also other outcomes such as total points scored, total yards gained, etc.
+
+## Installation
+
+```
+pip install spforge
+```
+
+
+## Examples
+Ensure you have a dataset where each row is a unique combination of game_ids and player_ids.
+There are multiple different use-cases for the framework, such as:
+1. Creating ratings for players/teams.
+2. Predicting the outcome.
+3. Creating features or other types of data-transformations
+
+### Predicting Game-Winner
+
+Ensure you have a dataset where each row is a unique combination of game_ids and player_ids. 
+Even if the concept of a player doesn't exist in the dataset, you can use team_id instead of player_id.
+
+Utilizing a rating model can be as simple as:
+
+```
+import pandas as pd
+from sklearn.linear_model import LogisticRegression
+
+from spforge.pipeline import Pipeline
+from spforge.predictor import GameTeamPredictor, SklearnPredictor
+
+from spforge.ratings import UpdateRatingGenerator
+
+from spforge.data_structures import ColumnNames
+from spforge.ratings.rating_calculators import MatchRatingGenerator
+
+df = pd.read_parquet("data/game_player_subsample.parquet")
+
+# Defines the column names as they appear in the dataframe
+column_names = ColumnNames(
+    team_id="team_id",
+    match_id="game_id",
+    start_date="start_date",
+    player_id="player_name",
+)
+# Sorts the dataframe. The dataframe must always be sorted as below
+df = df.sort_values(
+    by=[
+        column_names.start_date,
+        column_names.match_id,
+        column_names.team_id,
+        column_names.player_id,
+    ]
+)
+
+# Drops games with less or more than 2 teams
+df = (
+    df.assign(
+        team_count=df.groupby(column_names.match_id)[column_names.team_id].transform(
+            "nunique"
+        )
+    )
+    .loc[lambda x: x.team_count == 2]
+    .drop(columns=["team_count"])
+)
+
+# Pretends the last 10 games are future games. The most will be trained on everything before that.
+most_recent_10_games = df[column_names.match_id].unique()[-10:]
+historical_df = df[~df[column_names.match_id].isin(most_recent_10_games)]
+future_df = df[df[column_names.match_id].isin(most_recent_10_games)].drop(
+    columns=["won"]
+)
+
+# Defining a simple rating-generator. It will use the "won" column to update the ratings.
+# In contrast to a typical Elo, ratings will follow players.
+
+match_rating_generator = MatchRatingGenerator(rating_change_multiplier=30)
+
+rating_generator = UpdateRatingGenerator(
+    performance_column="won", match_rating_generator=match_rating_generator
+)
+
+# Defines the predictor. A machine-learning model will be used to predict game winner on a game-team-level.
+# Mean team-ratings will be calculated (from player-level) and rating-difference between the 2 teams calculated.
+# It will also use the location of the game as a feature.
+predictor = GameTeamPredictor(
+    game_id_colum=column_names.match_id,
+    team_id_column=column_names.team_id,
+    predictor=SklearnPredictor(
+        estimator_features=["location"], target="won", estimator=LogisticRegression()
+    ),
+    one_hot_encode_cat_features=True,
+)
+
+# Pipeline is whether we define all the steps. Other transformations can take place as well.
+# However, in our simple example we only have a simple rating-generator and a predictor.
+pipeline = Pipeline(
+    rating_generators=rating_generator,
+    predictor=predictor,
+    column_names=column_names,
+)
+
+# Trains the model and returns historical predictions
+pipeline.train(df=historical_df)
+
+# Future predictions on future results
+future_predictions = pipeline.predict(df=future_df)
+
+# Grouping predictions from game-player level to game-level.
+team_grouped_predictions = future_predictions.groupby(column_names.match_id).first()[
+    [
+        column_names.start_date,
+        column_names.team_id,
+        "team_id_opponent",
+        predictor.pred_column,
+    ]
+]
+
+print(team_grouped_predictions)
+
+```
+
+## Further Examples
+
+

spforge-0.0.0/examples/__init__.py

@@ -0,0 +1,2 @@
+from .nba.data.utils import get_sub_sample_nba_data
+from .lol.data.utils import get_sub_sample_lol_data

spforge-0.0.0/examples/lol/data/utils.py

@@ -0,0 +1,20 @@
+import os
+from pathlib import Path
+from typing import Union
+
+import polars as pl
+import pandas as pd
+
+
+def get_sub_sample_lol_data(
+    as_pandas: bool = True, as_polars: bool = False
+) -> Union[pd.DataFrame]:
+    script_dir = Path(__file__).parent
+    file_path = os.path.join(script_dir, "subsample_lol_data.parquet")
+
+    if as_polars:
+        return pl.read_parquet(file_path)
+    elif as_pandas:
+        return pd.read_parquet(file_path)
+    else:
+        raise ValueError("Must specify either as_pandas or as_polars")

spforge-0.0.0/examples/lol/pipeline_transformer_example.py

@@ -0,0 +1,158 @@
+from lightgbm import LGBMRegressor
+from sklearn.linear_model import LogisticRegression
+
+from examples import get_sub_sample_lol_data
+from spforge import ColumnNames
+from spforge.cross_validator import MatchKFoldCrossValidator
+from spforge.pipeline_transformer import PipelineTransformer
+from spforge.predictor import (
+    GameTeamPredictor,
+    SklearnPredictor,
+)
+from spforge.predictor.classifier import NegativeBinomialPredictor
+from spforge.ratings import (
+    UpdateRatingGenerator,
+    RatingKnownFeatures,
+)
+from spforge.ratings.performance_generator import (
+    PerformancesGenerator,
+    Performance,
+    ColumnWeight,
+)
+from spforge.transformers import LagTransformer
+from spforge.transformers import (
+    RollingMeanTransformer,
+)
+
+column_names = ColumnNames(
+    team_id="teamname",
+    match_id="gameid",
+    start_date="date",
+    player_id="playername",
+    league="league",
+    position="position",
+)
+df = get_sub_sample_lol_data(as_pandas=True)
+df = (
+    df.loc[lambda x: x.position != "team"]
+    .assign(team_count=df.groupby("gameid")["teamname"].transform("nunique"))
+    .loc[lambda x: x.team_count == 2]
+    .assign(
+        player_count=df.groupby(["gameid", "teamname"])["playername"].transform(
+            "nunique"
+        )
+    )
+    .loc[lambda x: x.player_count == 5]
+)
+df = df.assign(team_count=df.groupby("gameid")["teamname"].transform("nunique")).loc[
+    lambda x: x.team_count == 2
+]
+
+df = df.drop_duplicates(subset=["gameid", "playername"])
+
+# Pretends the last 10 games are future games. The most will be trained on everything before that.
+most_recent_10_games = df[column_names.match_id].unique()[-10:]
+historical_df = df[~df[column_names.match_id].isin(most_recent_10_games)]
+future_df = df[df[column_names.match_id].isin(most_recent_10_games)].drop(
+    columns=["result"]
+)
+
+rating_generator_result = UpdateRatingGenerator(
+    features_out=[RatingKnownFeatures.RATING_DIFFERENCE_PROJECTED],
+    performance_column="result",
+)
+
+rating_generator_player_kills = UpdateRatingGenerator(
+    features_out=[RatingKnownFeatures.RATING_MEAN_PROJECTED],
+    performances_generator=PerformancesGenerator(
+        performances=Performance(
+            name="performance_kills",
+            weights=[
+                ColumnWeight(name="kills", weight=1),
+            ],
+        ),
+    ),
+)
+
+lag_generators = [
+    LagTransformer(
+        features=["kills", "deaths", "result"], lag_length=3, granularity=["playername"]
+    ),
+    RollingMeanTransformer(
+        features=["kills", "deaths", "result"],
+        window=20,
+        min_periods=1,
+        granularity=["playername"],
+    ),
+]
+
+transformer = PipelineTransformer(
+    column_names=column_names,
+    rating_generators=[rating_generator_result, rating_generator_player_kills],
+    lag_transformers=lag_generators,
+)
+
+historical_df = transformer.fit_transform(historical_df)
+
+game_winner_predictor = GameTeamPredictor(
+    predictor=SklearnPredictor(
+        estimator=LogisticRegression(),
+        target="result",
+        features=[RatingKnownFeatures.RATING_DIFFERENCE_PROJECTED],
+    ),
+    one_hot_encode_cat_features=True,
+    impute_missing_values=True,
+    game_id_colum=column_names.match_id,
+    team_id_column=column_names.team_id,
+)
+
+player_kills_predictor = SklearnPredictor(
+    estimator=LGBMRegressor(verbose=-100),
+    target="kills",
+    features=[game_winner_predictor.pred_column],
+    features_contain_str=["rolling_mean_kills", "lag_kills"],
+)
+
+cross_validator_game_winner = MatchKFoldCrossValidator(
+    date_column_name=column_names.start_date,
+    match_id_column_name=column_names.match_id,
+    predictor=game_winner_predictor,
+)
+
+game_winner_predictor.train(historical_df)
+historical_df = cross_validator_game_winner.generate_validation_df(
+    historical_df, column_names
+)
+
+cross_validator_player_kills = MatchKFoldCrossValidator(
+    date_column_name=column_names.start_date,
+    match_id_column_name=column_names.match_id,
+    predictor=player_kills_predictor,
+)
+
+player_kills_predictor.train(historical_df)
+print(player_kills_predictor.features)
+historical_df = cross_validator_player_kills.generate_validation_df(
+    historical_df, column_names
+)
+
+future_df = transformer.transform(future_df)
+future_df = game_winner_predictor.predict(future_df)
+future_df = player_kills_predictor.predict(future_df)
+
+probability_predictor = NegativeBinomialPredictor(
+    target="kills",
+    point_estimate_pred_column=player_kills_predictor.pred_column,
+    relative_error_predictor=SklearnPredictor(
+        estimator=LGBMRegressor(),
+        target=None,
+        features=["position"],
+        convert_cat_features_to_cat_dtype=True,
+    ),
+    max_value=15,
+)
+
+probability_predictor.train(historical_df)
+future_df = probability_predictor.predict(future_df)
+
+print(future_df.head(10))