shimaenagaboost 0.1.0__tar.gz

shimaenagaboost-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 S.I
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

shimaenagaboost-0.1.0/MANIFEST.in

@@ -0,0 +1,3 @@
+include LICENSE
+include THIRD_PARTY_NOTICES.md
+include README.md

shimaenagaboost-0.1.0/PKG-INFO

@@ -0,0 +1,165 @@
+Metadata-Version: 2.4
+Name: shimaenagaboost
+Version: 0.1.0
+Summary: ShimaenagaBoost: Attentive Histogram GBDT with sample-level token attention
+Author: ShimaenagaBoost Authors
+License: MIT
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: THIRD_PARTY_NOTICES.md
+Requires-Dist: numpy>=1.20
+Provides-Extra: sklearn
+Requires-Dist: scikit-learn>=1.0; extra == "sklearn"
+Provides-Extra: dev
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: scikit-learn; extra == "dev"
+Requires-Dist: pandas; extra == "dev"
+Dynamic: author
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: license
+Dynamic: license-file
+Dynamic: provides-extra
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# ShimaenagaBoost
+
+**Attentive Histogram GBDT — サンプル単位のトークン注意機構を備えた勾配ブースティング**
+
+ShimaenagaBoost は、LightGBM スタイルのヒストグラムベース GBDT に、サンプルごとの
+トークン注意機構(attention)を組み込んだ機械学習ライブラリです。特徴量を
+「トークン」と呼ぶサブセットに分割して各トークンごとに木を成長させ、
+サンプルごとに学習された注意重みでそれらを混合します。これにより、
+純粋な GBDT では捉えにくい特徴グループ間の相互作用を表現できます。
+
+---
+
+## インストール
+
+### 必要環境
+
+- C++17 コンパイラ(GCC ≥ 9, Clang ≥ 11, MSVC 2019 以降)
+- CMake ≥ 3.20
+- Python ≥ 3.8 + NumPy
+- scikit-learn(sklearn 互換 API と examples の実行に使用)
+- (オプション)pybind11 — ネイティブ拡張としてビルドする場合のみ
+
+### Python パッケージの利用
+
+```bash
+pip install shimaenagaboost
+```
+---
+
+## クイックスタート
+
+```python
+from shimaenagaboost import ShimaenagaBoostRegressor, ShimaenagaBoostClassifier, ShimaenagaBoostRanker
+```
+
+### 回帰
+
+```python
+from sklearn.datasets import fetch_california_housing
+from sklearn.model_selection import train_test_split
+from shimaenagaboost import ShimaenagaBoostRegressor
+
+data = fetch_california_housing()
+X_train, X_test, y_train, y_test = train_test_split(
+    data.data, data.target, test_size=0.2, random_state=42
+)
+
+model = ShimaenagaBoostRegressor(
+    tier=1,             # Tier-1: Attentive Readout
+    num_tokens=4,       # 特徴を 4 グループに分割
+    num_heads=2,        # 注意ヘッド数
+    d_attn=4,           # 注意埋め込み次元
+    num_iterations=300,
+    learning_rate=0.05,
+)
+model.fit(X_train, y_train)
+y_pred = model.predict(X_test)
+```
+
+### 二値分類
+
+```python
+from sklearn.datasets import load_breast_cancer
+from sklearn.model_selection import train_test_split
+from shimaenagaboost import ShimaenagaBoostClassifier
+
+data = load_breast_cancer()
+X_train, X_test, y_train, y_test = train_test_split(
+    data.data, data.target, test_size=0.2, random_state=42
+)
+
+clf = ShimaenagaBoostClassifier(
+    num_class=1,        # 1 = 二値(既定)
+    tier=1,
+    num_tokens=4,
+    num_iterations=200,
+)
+clf.fit(X_train, y_train)
+proba = clf.predict_proba(X_test)   # shape (n, 2)
+labels = clf.predict(X_test)
+```
+
+### 多クラス分類
+
+```python
+from sklearn.datasets import load_iris
+from sklearn.model_selection import train_test_split
+from shimaenagaboost import ShimaenagaBoostClassifier
+
+data = load_iris()
+X_train, X_test, y_train, y_test = train_test_split(
+    data.data, data.target, test_size=0.2, random_state=42
+)
+
+clf = ShimaenagaBoostClassifier(
+    num_class=3,        # K クラス softmax
+    tier=1,
+    num_tokens=2,
+    num_iterations=100,
+)
+clf.fit(X_train, y_train)
+proba = clf.predict_proba(X_test)   # shape (n, 3)
+```
+
+### ランキング(LambdaMART)
+
+```python
+from shimaenagaboost import ShimaenagaBoostRanker
+
+# group: クエリごとのサンプル数(合計 = len(X_train))
+model = ShimaenagaBoostRanker(tier=1, num_iterations=200)
+model.fit(X_train, y_train, group=group_train)
+scores = model.predict(X_test)
+
+# 検証セット付き(eval_group 必須 — valid の NDCG をクエリ単位で計算するため)
+model.fit(X_train, y_train, group=group_train,
+          eval_set=[(X_valid, y_valid)], eval_group=[group_valid],
+          early_stopping_rounds=50)
+```
+
+### モデルの保存・ロード
+
+```python
+model.save_model("model.sbb")       # バイナリ形式 (.sbb, 形式 v3)
+
+# ロード: 同じ設定でインスタンスを作り、一度 fit で booster を初期化してから load
+loaded = ShimaenagaBoostRegressor(tier=1, num_tokens=4)
+loaded.fit(X_tiny, y_tiny)          # booster の初期化(小さなデータで可)
+loaded.load_model("model.sbb")
+pred = loaded.predict(X_test)
+```
+
+
+## ライセンス
+
+MIT License. <br/>
+詳細は [LICENSE](LICENSE) を参照してください。<br/>
+サードパーティの著作権表示は [THIRD_PARTY_NOTICES.md](THIRD_PARTY_NOTICES.md) を参照してください。

shimaenagaboost-0.1.0/README.md

@@ -0,0 +1,138 @@
+# ShimaenagaBoost
+
+**Attentive Histogram GBDT — サンプル単位のトークン注意機構を備えた勾配ブースティング**
+
+ShimaenagaBoost は、LightGBM スタイルのヒストグラムベース GBDT に、サンプルごとの
+トークン注意機構(attention)を組み込んだ機械学習ライブラリです。特徴量を
+「トークン」と呼ぶサブセットに分割して各トークンごとに木を成長させ、
+サンプルごとに学習された注意重みでそれらを混合します。これにより、
+純粋な GBDT では捉えにくい特徴グループ間の相互作用を表現できます。
+
+---
+
+## インストール
+
+### 必要環境
+
+- C++17 コンパイラ(GCC ≥ 9, Clang ≥ 11, MSVC 2019 以降)
+- CMake ≥ 3.20
+- Python ≥ 3.8 + NumPy
+- scikit-learn(sklearn 互換 API と examples の実行に使用)
+- (オプション)pybind11 — ネイティブ拡張としてビルドする場合のみ
+
+### Python パッケージの利用
+
+```bash
+pip install shimaenagaboost
+```
+---
+
+## クイックスタート
+
+```python
+from shimaenagaboost import ShimaenagaBoostRegressor, ShimaenagaBoostClassifier, ShimaenagaBoostRanker
+```
+
+### 回帰
+
+```python
+from sklearn.datasets import fetch_california_housing
+from sklearn.model_selection import train_test_split
+from shimaenagaboost import ShimaenagaBoostRegressor
+
+data = fetch_california_housing()
+X_train, X_test, y_train, y_test = train_test_split(
+    data.data, data.target, test_size=0.2, random_state=42
+)
+
+model = ShimaenagaBoostRegressor(
+    tier=1,             # Tier-1: Attentive Readout
+    num_tokens=4,       # 特徴を 4 グループに分割
+    num_heads=2,        # 注意ヘッド数
+    d_attn=4,           # 注意埋め込み次元
+    num_iterations=300,
+    learning_rate=0.05,
+)
+model.fit(X_train, y_train)
+y_pred = model.predict(X_test)
+```
+
+### 二値分類
+
+```python
+from sklearn.datasets import load_breast_cancer
+from sklearn.model_selection import train_test_split
+from shimaenagaboost import ShimaenagaBoostClassifier
+
+data = load_breast_cancer()
+X_train, X_test, y_train, y_test = train_test_split(
+    data.data, data.target, test_size=0.2, random_state=42
+)
+
+clf = ShimaenagaBoostClassifier(
+    num_class=1,        # 1 = 二値(既定)
+    tier=1,
+    num_tokens=4,
+    num_iterations=200,
+)
+clf.fit(X_train, y_train)
+proba = clf.predict_proba(X_test)   # shape (n, 2)
+labels = clf.predict(X_test)
+```
+
+### 多クラス分類
+
+```python
+from sklearn.datasets import load_iris
+from sklearn.model_selection import train_test_split
+from shimaenagaboost import ShimaenagaBoostClassifier
+
+data = load_iris()
+X_train, X_test, y_train, y_test = train_test_split(
+    data.data, data.target, test_size=0.2, random_state=42
+)
+
+clf = ShimaenagaBoostClassifier(
+    num_class=3,        # K クラス softmax
+    tier=1,
+    num_tokens=2,
+    num_iterations=100,
+)
+clf.fit(X_train, y_train)
+proba = clf.predict_proba(X_test)   # shape (n, 3)
+```
+
+### ランキング(LambdaMART)
+
+```python
+from shimaenagaboost import ShimaenagaBoostRanker
+
+# group: クエリごとのサンプル数(合計 = len(X_train))
+model = ShimaenagaBoostRanker(tier=1, num_iterations=200)
+model.fit(X_train, y_train, group=group_train)
+scores = model.predict(X_test)
+
+# 検証セット付き(eval_group 必須 — valid の NDCG をクエリ単位で計算するため)
+model.fit(X_train, y_train, group=group_train,
+          eval_set=[(X_valid, y_valid)], eval_group=[group_valid],
+          early_stopping_rounds=50)
+```
+
+### モデルの保存・ロード
+
+```python
+model.save_model("model.sbb")       # バイナリ形式 (.sbb, 形式 v3)
+
+# ロード: 同じ設定でインスタンスを作り、一度 fit で booster を初期化してから load
+loaded = ShimaenagaBoostRegressor(tier=1, num_tokens=4)
+loaded.fit(X_tiny, y_tiny)          # booster の初期化(小さなデータで可)
+loaded.load_model("model.sbb")
+pred = loaded.predict(X_test)
+```
+
+
+## ライセンス
+
+MIT License. <br/>
+詳細は [LICENSE](LICENSE) を参照してください。<br/>
+サードパーティの著作権表示は [THIRD_PARTY_NOTICES.md](THIRD_PARTY_NOTICES.md) を参照してください。

shimaenagaboost-0.1.0/THIRD_PARTY_NOTICES.md

@@ -0,0 +1,123 @@
+# サードパーティ著作権表示 (Third-Party Notices)
+
+ShimaenagaBoost のビルド・配布物には、以下のサードパーティソフトウェアの一部が
+含まれます。
+
+## pybind11
+
+pybind11 はヘッダオンリーライブラリであり、`_shimaenagaboost` ネイティブ拡張の
+ビルド時にヘッダがコンパイル済みバイナリへ組み込まれます。
+
+- **Project**: https://github.com/pybind/pybind11
+- **License**: BSD 3-Clause
+
+```
+Copyright (c) 2016 Wenzel Jakob <wenzel.jakob@epfl.ch>, All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice,
+   this list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright notice,
+   this list of conditions and the following disclaimer in the documentation
+   and/or other materials provided with the distribution.
+
+3. Neither the name of the copyright holder nor the names of its
+   contributors may be used to endorse or promote products derived from
+   this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+```
+
+## NumPy
+
+NumPy は ShimaenagaBoost の実行時依存であり、配列データの受け渡しに使用されます。
+
+- **Project**: https://github.com/numpy/numpy
+- **License**: BSD 3-Clause
+
+```
+Copyright (c) 2005-2024, NumPy Developers.
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are
+met:
+
+    * Redistributions of source code must retain the above copyright
+       notice, this list of conditions and the following disclaimer.
+
+    * Redistributions in binary form must reproduce the above
+       copyright notice, this list of conditions and the following
+       disclaimer in the documentation and/or other materials provided
+       with the distribution.
+
+    * Neither the name of the NumPy Developers nor the names of any
+       contributors may be used to endorse or promote products derived
+       from this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS
+IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,
+THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
+CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+```
+
+## scikit-learn
+
+scikit-learn は ShimaenagaBoost の sklearn 互換 API (`sklearn_api.py`) の実行時
+依存です。
+
+- **Project**: https://github.com/scikit-learn/scikit-learn
+- **License**: BSD 3-Clause
+
+```
+BSD 3-Clause License
+
+Copyright (c) 2007-2024 The scikit-learn developers.
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice,
+   this list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright
+   notice, this list of conditions and the following disclaimer in the
+   documentation and/or other materials provided with the distribution.
+
+3. Neither the name of the copyright holder nor the names of its
+   contributors may be used to endorse or promote products derived from
+   this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+```

shimaenagaboost-0.1.0/pyproject.toml

@@ -0,0 +1,3 @@
+[build-system]
+requires = ["setuptools>=61", "wheel", "pybind11>=2.10", "cmake>=3.20"]
+build-backend = "setuptools.build_meta"

shimaenagaboost-0.1.0/python/shimaenagaboost/__init__.py

@@ -0,0 +1,35 @@
+"""
+ShimaenagaBoost: Attentive Histogram GBDT with sample-level token attention.
+sklearn-compatible API.
+"""
+from .sklearn_api import (
+    ShimaenagaBoostRegressor,
+    ShimaenagaBoostClassifier,
+    ShimaenagaBoostRanker,
+)
+
+# Try pybind11 extension first, fall back to ctypes backend.
+# _shimaenagaboost is a top-level sibling module (built by CMake into python/,
+# alongside this package), not a submodule of shimaenagaboost -- so it must be
+# imported absolutely, not via a relative "..".
+try:
+    from _shimaenagaboost import Dataset, Booster, Config
+    _backend = "pybind11"
+except ImportError:
+    try:
+        from ._ctypes_backend import Dataset, Booster
+        Config = None
+        _backend = "ctypes"
+    except Exception:
+        Dataset = Booster = Config = None
+        _backend = "none"
+
+__version__ = "0.1.0"
+__all__ = [
+    "ShimaenagaBoostRegressor",
+    "ShimaenagaBoostClassifier",
+    "ShimaenagaBoostRanker",
+    "Dataset",
+    "Booster",
+    "Config",
+]