├── .envrc ├── .github └── images │ └── bert-classification-tutorial.001.jpeg ├── .gitignore ├── .tool-versions ├── LICENSE ├── README.md ├── poetry.lock ├── poetry.toml ├── pyproject.toml ├── results ├── all.csv └── best.csv └── src ├── aggregate.py ├── download.sh ├── prepare.py ├── train.py └── utils.py /.envrc: -------------------------------------------------------------------------------- 1 | dotenv 2 | export TOKENIZERS_PARALLELISM="false" 3 | export TF_CPP_MIN_LOG_LEVEL="2" 4 | export TRANSFORMERS_VERBOSITY="error" 5 | export DATASETS_VERBOSITY="error" 6 | export PYTHONPATH="$PWD:$PYTHONPATH" 7 | export TF_FORCE_GPU_ALLOW_GROWTH="true" 8 | -------------------------------------------------------------------------------- /.github/images/bert-classification-tutorial.001.jpeg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hppRC/bert-classification-tutorial/8ca0d5a7090ab44ebfa34f697704d5c2c4e5a5dd/.github/images/bert-classification-tutorial.001.jpeg -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | !.envrc 2 | /prev 3 | /data 4 | /datasets 5 | /outputs 6 | /scripts 7 | 8 | # Byte-compiled / optimized / DLL files 9 | __pycache__/ 10 | *.py[cod] 11 | *$py.class 12 | 13 | # C extensions 14 | *.so 15 | 16 | # Distribution / packaging 17 | .Python 18 | build/ 19 | develop-eggs/ 20 | dist/ 21 | downloads/ 22 | eggs/ 23 | .eggs/ 24 | lib/ 25 | lib64/ 26 | parts/ 27 | sdist/ 28 | var/ 29 | wheels/ 30 | share/python-wheels/ 31 | *.egg-info/ 32 | .installed.cfg 33 | *.egg 34 | MANIFEST 35 | 36 | # PyInstaller 37 | # Usually these files are written by a python script from a template 38 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 39 | *.manifest 40 | *.spec 41 | 42 | # Installer logs 43 | pip-log.txt 44 | pip-delete-this-directory.txt 45 | 46 | # Unit test / coverage reports 47 | htmlcov/ 48 | .tox/ 49 | .nox/ 50 | .coverage 51 | .coverage.* 52 | .cache 53 | nosetests.xml 54 | coverage.xml 55 | *.cover 56 | *.py,cover 57 | .hypothesis/ 58 | .pytest_cache/ 59 | cover/ 60 | 61 | # Translations 62 | *.mo 63 | *.pot 64 | 65 | # Django stuff: 66 | *.log 67 | local_settings.py 68 | db.sqlite3 69 | db.sqlite3-journal 70 | 71 | # Flask stuff: 72 | instance/ 73 | .webassets-cache 74 | 75 | # Scrapy stuff: 76 | .scrapy 77 | 78 | # Sphinx documentation 79 | docs/_build/ 80 | 81 | # PyBuilder 82 | .pybuilder/ 83 | target/ 84 | 85 | # Jupyter Notebook 86 | .ipynb_checkpoints 87 | 88 | # IPython 89 | profile_default/ 90 | ipython_config.py 91 | 92 | # pyenv 93 | # For a library or package, you might want to ignore these files since the code is 94 | # intended to run in multiple environments; otherwise, check them in: 95 | # .python-version 96 | 97 | # pipenv 98 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 99 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 100 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 101 | # install all needed dependencies. 102 | #Pipfile.lock 103 | 104 | # poetry 105 | # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. 106 | # This is especially recommended for binary packages to ensure reproducibility, and is more 107 | # commonly ignored for libraries. 108 | # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control 109 | #poetry.lock 110 | 111 | # pdm 112 | # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. 113 | #pdm.lock 114 | # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it 115 | # in version control. 116 | # https://pdm.fming.dev/#use-with-ide 117 | .pdm.toml 118 | 119 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm 120 | __pypackages__/ 121 | 122 | # Celery stuff 123 | celerybeat-schedule 124 | celerybeat.pid 125 | 126 | # SageMath parsed files 127 | *.sage.py 128 | 129 | # Environments 130 | .env 131 | .venv 132 | env/ 133 | venv/ 134 | ENV/ 135 | env.bak/ 136 | venv.bak/ 137 | 138 | # Spyder project settings 139 | .spyderproject 140 | .spyproject 141 | 142 | # Rope project settings 143 | .ropeproject 144 | 145 | # mkdocs documentation 146 | /site 147 | 148 | # mypy 149 | .mypy_cache/ 150 | .dmypy.json 151 | dmypy.json 152 | 153 | # Pyre type checker 154 | .pyre/ 155 | 156 | # pytype static type analyzer 157 | .pytype/ 158 | 159 | # Cython debug symbols 160 | cython_debug/ 161 | 162 | # PyCharm 163 | # JetBrains specific template is maintained in a separate JetBrains.gitignore that can 164 | # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore 165 | # and can be added to the global gitignore or merged into this file. For a more nuclear 166 | # option (not recommended) you can uncomment the following to ignore the entire idea folder. 167 | #.idea/ 168 | -------------------------------------------------------------------------------- /.tool-versions: -------------------------------------------------------------------------------- 1 | python 3.10.9 2 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | MIT License 2 | 3 | Copyright (c) 2023 Hayato Tsukagoshi 4 | 5 | Permission is hereby granted, free of charge, to any person obtaining a copy 6 | of this software and associated documentation files (the "Software"), to deal 7 | in the Software without restriction, including without limitation the rights 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell 9 | copies of the Software, and to permit persons to whom the Software is 10 | furnished to do so, subject to the following conditions: 11 | 12 | The above copyright notice and this permission notice shall be included in all 13 | copies or substantial portions of the Software. 14 | 15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE 18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE 21 | SOFTWARE. 22 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # BERT Classification Tutorial 2 | 3 | 4 | ## はじめに 5 | 6 | Googleが2018年に発表した[BERT](https://arxiv.org/abs/1810.04805)は、その性能の高さや利便性から、今やあらゆる自然言語処理タスクで汎用的に用いられるようになっています。 7 | 8 | BERTは**事前学習済み言語モデル (Pretrained Language Model)** と呼ばれるモデルの一種で、大量のテキストで事前にモデルの学習をおこなっておくことで、様々なタスクに利用できる言語知識を獲得しています。 9 | この言語知識を転用することで、多様なタスクについて、今までよりも少ない学習データで非常に高い性能を発揮できることがわかっています。 10 | 11 | BERTをテキスト分類などのタスクに適用する際は、BERTを微調整(fine-tuning)することでタスクを解きます。 12 | 例えば、ある映画のレビューが好意的(positive)か否定的(negative)かを分類するタスクを考えると、微調整の流れは以下のようになります。 13 | 14 | 1. レビューテキストを事前学習済みのBERTに入力する 15 | 2. BERTから得られる出力を用いてpositiveかnegativeかの分類を行う 16 | 3. 分類タスクにおける損失を計算し、損失をBERTに逆伝播させてBERTのパラメータを更新する 17 | 18 | BERTは近年では[基盤モデル(Foundation Models)](https://arxiv.org/abs/2108.07258)とも呼ばれており、BERTの派生モデルも大量に登場しています。 19 | 20 | さて、BERTが登場したのは2018年でした。 21 | 当時はRNNやLSTMと呼ばれるモデル構造が主流であり、[Transformer](https://arxiv.org/abs/1706.03762)と呼ばれるモデル構造をベースにしたBERTは、かなり目新しいものでした。 22 | また、PyTorchなど深層学習用のライブラリもまだまだ発展途上であり、近年までBERTを取り巻く環境は混沌としていました。 23 | 24 | しかし、2023年になって、BERTを利用するための環境が非常に整ってきました。 25 | その代表例が[HuggingFace](https://huggingface.co)が公開している[Transformers](https://github.com/huggingface/transformers)というライブラリです。 26 | 27 | Transformersを用いることで、BERTをはじめとする様々な事前学習済みモデルたちを簡単にダウンロード・利用できます。 28 | Transformersは[PyTorch](https://pytorch.org/)や[Tensorflow](https://www.tensorflow.org/), [Jax](https://github.com/google/jax)/[Flax](https://github.com/google/flax)といった様々な深層学習用ライブラリと同時に利用できるので、環境を選ばずに事前学習済みモデルたちにアクセスすることができるようになりました。 29 | 30 | Transformersの別の良さとしては、事前学習済みモデルのアップロードも簡単であるというのも特筆すべき点です。 31 | これにより、研究や企業応用など、そのユースケースを問わず、様々なモデルをTransformersを通じて簡単にやりとりすることができるようになりました。 32 | いまや誰でも簡単に、自作のBERTをHuggingFaceのサーバ上に公開し、広く一般に使用してもらうことができます。 33 | 34 | さて、このようにBERTをはじめとして、事前学習済みモデルを取り巻く環境は極めて急速に整備がされてきました。 35 | しかし、実際にBERTを用いてどのようにタスクを解けば良いか、というのは実はそこまで整備されていません(著者の感想)。 36 | 37 | 日々更新されていくライブラリ、特に最新のPython, PyTorch, Transformersなどに対応した、BERTを用いてタスクを解くための高品質なテンプレートはほとんど存在しません。 38 | 39 | 特に自然言語処理の初学者にとっては、「研究や実験をどのように開始したらよいかわからない」「よい設計、実験管理をどのように行えば良いかわからない」というのは非常に苦しいものです。 40 | 41 | 自然言語処理(に限りませんが)の研究や実験に取り組む際には、理解しやすく、自分が取り組むタスクに比較的近いテンプレート・参考実装が存在することのメリットは計り知れません。 42 | 43 | そこで、BERTを用いたテキスト分類をテーマとしたモダンで高品質な深層学習用のテンプレート実装を目指して、本実装を公開します。 44 | 具体的には、本実装は「livedoorニュースコーパスをBERTを用いて分類する」流れを実装したものです。 45 | 46 | 本実装の主要な貢献は以下です。 47 | 1. Python 3.10, PyTorch 2.0, Transformers 4.30 以上に対応したモダンな記法・実装 48 | 2. Type Hintsを活用し、出来るだけ依存ライブラリとコード量を減らして、過度な抽象化を避けた見通しのよい設計 49 | 3. データ準備 → 訓練 & 評価 という実験プロセスの実装指針の提供 50 | 4. 一般的な評価値の算出を含む実験テンプレートとして、その他のタスクにも簡単に利用できる汎用的な実装 51 | 52 | 本実装については[自然言語処理 30巻 2号に掲載の学会記事](https://www.jstage.jst.go.jp/article/jnlp/30/2/30_867/_article/-char/ja)でも解説しておりますので、ぜひ併せてご覧ください。 53 | 以降の節では、本実装を俯瞰しつつ、主要な項目について述べます。 54 | 55 | ## 実装の全体像 56 | 57 | 本実装は「livedoorニュースコーパスをBERTを用いて分類する」流れを実装したものです。 58 | 59 | 以下が、本実装の概要図です。 60 | 61 | ![overview](./.github/images/bert-classification-tutorial.001.jpeg) 62 | 63 | 64 | 全体としては 65 | 1. 生データのダウンロード(初回のみ) 66 | 2. 生データを前処理してJSONL形式の実験用データセットを作成(初回のみ) 67 | 3. モデルの訓練と評価 68 | という流れになっています。 69 | 70 | データの前処理部分は事前に済ませるので、何度も重たい処理をする必要はありません。 71 | また、データを事前に訓練・開発・テストセットに分割するので、様々なモデル・実験条件で比較評価を行いたい場合も、平等な評価(同じ訓練・評価データセットを用いた実験)が可能です。 72 | 73 | さらに、本実装ではJupyter NotebookなどNotebook形式のファイルは一切利用していません。 74 | これは経験上、Notebook形式のファイルのデバッグが極めて困難であり、バグの温床になることが多いと感じているためです。 75 | 76 | したがって本実装は、ターミナル上でコマンドを実行していれば一連の流れが全て完了するように設計しています。 77 | 具体的には、各プログラムがコマンドライン引数を受け取るようになっており、プログラムの挙動を変更するために、プログラムを変更する必要はないように実装しています。 78 | 79 | 以降の節で詳しく説明しますが、本実装では以下のコマンドを実行すれば、環境構築・データセット作成・訓練&評価の全てが行えるようになっています(コマンドを実行するディレクトリはプロジェクトルート、つまり、`src`ディレクトリや`run.sh`ファイルがあるディレクトリを想定しています)。 80 | 81 | ```bash 82 | poetry install 83 | 84 | bash src/download.sh 85 | poetry run python src/prepare.py 86 | 87 | poetry run python src/train.py 88 | ``` 89 | 90 | それでは、それぞれの要素について説明します。 91 | 92 | ## 環境構築, Installation 93 | 94 | まず、環境構築について説明します。 95 | 96 | 本実装は**Python 3.10 以上** での実行を想定しています。 97 | Python 3.10は、match文の導入やwith文の改善など様々な利便性の向上がなされている他、[Pythonが高速化の計画を進めていること](https://forest.watch.impress.co.jp/docs/news/1451751.html)もあり、早い段階で新しいPythonに適応しておくことのメリットは大きいと考えたためです。 98 | 99 | また、Python 3.10では、Type Hints (型注釈)が以前のバージョンより自然に書けるようになっており、今までよりも堅牢かつ可読性の高いコードを書きやすくなっています。 100 | そのため、公開実装のためのPythonとしても優れていると考えました。 101 | 102 | 次に、Pythonの環境を構築する上でおすすめの方法を2つ紹介するので、どちらか好きな方で環境構築をしてみてください。 103 | 104 | ### 1. Install with poetry 105 | 106 | 1つめの環境構築法は、Pythonパッケージのパッケージマネージャである[Poetry](https://python-poetry.org/)を使ったものです。 107 | Poetryを用いることで、インストールするPythonパッケージの依存関係やバージョンを比較的精密に管理することができます。 108 | 109 | Poetryを利用する場合は別途[pyenv](https://github.com/pyenv/pyenv), [anyenv](https://github.com/anyenv/anyenv), [asdf](https://asdf-vm.com/)(おすすめ)といったPythonのバージョン管理ができるツールを用いて、Python 3.10をインストールしておく必要がある点に注意してください。 110 | また、Poetryのバージョンとしては`1.5.1`以上が必要になります。 111 | 112 | Poetryを利用した環境構築は、以下のようにすれば完了します。 113 | 114 | ```bash 115 | poetry install 116 | ``` 117 | 118 | ### 2. Install with conda & pip 119 | 120 | 2つめの環境構築法は、[Miniconda](https://docs.conda.io/projects/continuumio-conda/en/latest/user-guide/install/index.html)を使ったものです。 121 | Minicondaは、科学計算用ライブラリを簡単にインストールできるパッケージマネージャであるAnacondaの縮小版です。 122 | 123 | Minicondaを用いる環境構築では、通常さまざまなパッケージを`conda`コマンドでインストールします。 124 | しかし、`conda`コマンドでインストールできるパッケージはしばしば古く、管理が難しいことがあります。 125 | 126 | したがって今回は、Minicondaを用いてPython 3.10の仮想環境を構築し、その仮想環境の中にpip (Pythonのデフォルトのパッケージ管理ツール)でライブラリをインストールします。 127 | ただ、PyTorchは通常通り`conda`コマンドでインストールします。 128 | これは、PyTorchのインストールには非常に多くの複雑怪奇な依存関係が存在する(例えば、システムのGCCのバージョンなど)ため、これらに関連して発生する問題をできるだけ避けるためです。 129 | そのため、順番としては、`conda`でPyTorchをインストールしたあとに、`pip`のみを用いて必要なパッケージをインストールしていく、という流れになります。 130 | 131 | 環境構築は以下のようにコマンドを実行すれば完了すると思います。 132 | なお、`pytorch-cuda=11.8`のように記載している部分は、GPUを利用した計算を行うためのソフトウェアであるCUDAのバージョンを記載する必要があります。 133 | お使いの実行環境に適したCUDAのバージョンを指定してください。 134 | 135 | ```bash 136 | conda create -n bert-classification-tutorial python=3.10 137 | conda activate bert-classification-tutorial 138 | 139 | // see: https://pytorch.org/get-started/locally/ 140 | conda install pytorch pytorch-cuda=11.8 -c pytorch -c nvidia 141 | pip install tqdm "transformers[ja,sentencepiece]" typed-argument-parser tokenizers numpy pandas more-itertools scikit-learn scipy 142 | ``` 143 | 144 | ### 補足 145 | 146 | 以降はPoetryを用いて環境構築をした場合のコマンドを紹介しますが、minicondaを用いて環境構築をした場合は、`poetry run python`と書いてある部分を`python`に読み替えてください。 147 | 148 | 環境変数として以下の値を設定しておくと、warningsやメッセージが煩わしくなくて便利です(警告メッセージを消す設定が含まれるので、自己責任でお願いします)。 149 | 150 | ```sh:.envrc 151 | export TF_CPP_MIN_LOG_LEVEL="2" 152 | export TOKENIZERS_PARALLELISM="false" 153 | export TRANSFORMERS_VERBOSITY="error" 154 | export DATASETS_VERBOSITY="error" 155 | export PYTHONPATH="$PWD:$PYTHONPATH" 156 | ``` 157 | 158 | 特に、`PYTHONPATH`の設定は、`conda`で仮想環境を作成した場合は必要になります。 159 | Pythonにおける自作モジュールのimportのため、[direnv](https://github.com/direnv/direnv)などのツールを用いて`.envrc`に記述されている環境変数の設定、または上述の`PYTHONPATH`設定をお願いします。 160 | 161 | 162 | ## データセット作成 163 | 164 | 次に、データセットの作成と前処理について説明します。 165 | 166 | 本実装では、分類対象のテキストとしてRONDHUIT社が公開する[livedoorニュースコーパス](http://www.rondhuit.com/download.html#ldcc)を用います。 167 | 168 | livedoorニュースコーパスは、9つのカテゴリのニュース記事が集約されたデータセットです。 169 | 通常、ニュース記事のタイトルと本文を用いて、そのニュース記事がどのカテゴリにあてはまるかを分類する9値分類を行います。 170 | 171 | 実際のデータの一部を、以下の示します。 172 | 173 | ```txt:movie-enter-5844065.txt 174 | http://news.livedoor.com/article/detail/5844065/ 175 | 2011-09-07T19:35:00+0900 176 | ハリウッド最強のタッグが贈る感動巨編『リアル・スティール』、数量限定BE@RBRICKストラップ付き鑑賞券を発売 177 | 　スティーブン・スピルバーグ率いるドリームワークスが、魂を揺さぶる感動と、エキサイティングなアクションを兼ね備えた、渾身のエンターテイメントを世に放つ。 178 | ... 179 | ``` 180 | 181 | 本実装では、以下のコマンドを実行すればデータセットのダウンロードと前処理が完了するようになっています。 182 | 183 | ```bash 184 | bash src/download.sh 185 | 186 | poetry run python src/prepare.py 187 | ``` 188 | 189 | 流れとしては、まず`src/download.sh`がデータセットのダウンロードと生データの展開を行います。 190 | 191 | 次に、`src/prepare.py`を実行することで、生データをJSONL形式(1行ごとにJSON形式のデータが書き込まれている形式)に変換します。 192 | その際、NFKC正規化などの前処理も実行します。 193 | 194 | JSONL形式は近年よく利用されるようになってきたデータ形式であり、素直にPythonで読み込むことが可能である点、csv/tsvと比較して配列や階層のあるオブジェクトの表現が自然な点などから、機械学習用途で用いるには極めて扱いやすいデータ形式です。 195 | 本実装もJSONL形式でデータをやりとりするようになっています。 196 | 197 | 上記の前処理に加えて、分類モデルの訓練のため、分類先となるカテゴリを文字列から数値に変換し、その変換表も保存します。 198 | 変換表は以下のようになります。 199 | ラベルの変換表を保存しておくと何かと便利です。 200 | 201 | ```json:label2id.json 202 | { 203 | "dokujo-tsushin": 0, 204 | "it-life-hack": 1, 205 | "kaden-channel": 2, 206 | "livedoor-homme": 3, 207 | "movie-enter": 4, 208 | "peachy": 5, 209 | "smax": 6, 210 | "sports-watch": 7, 211 | "topic-news": 8 212 | } 213 | ``` 214 | 215 | また、全データを訓練(train):開発(val):テスト(test)=8:1:1の割合に分割します。 216 | これにより、訓練中に開発セットを用いて、モデルが過学習していないかの確認が行えるようになります。 217 | テストセットは最終的な評価にのみ用います。 218 | 219 | 保存されたデータセットは以下のような形式になっています。 220 | ``` 221 | datasets/livedoor 222 | ├── label2id.json 223 | ├── all.jsonl (7367行) 224 | ├── test.jsonl (736行) 225 | ├── val.jsonl (736行) 226 | └── train.jsonl (5895行) 227 | ``` 228 | 229 | 230 | ## 訓練 & 評価 231 | 232 | 次に、BERTの微調整(訓練)について説明します。 233 | 234 | といっても、本実装では、1つのコマンドで訓練から評価までを一貫して行えるようにしてあるので非常に簡単です。 235 | 236 | 以下のコマンドを実行することで、`cl-tohoku/bert-base-japanese-v2`を用いたテキスト分類モデルの訓練が実行できます。 237 | 238 | ```bash 239 | poetry run python src/train.py --model_name cl-tohoku/bert-base-japanese-v2 240 | ``` 241 | 242 | この時、`--model_name`に与える引数を例えば`bert-base-multilingual-cased`にすることで、多言語BERTを用いた学習が実行できます。 243 | 244 | また、ほとんどの設定をコマンドライン引数として与えられるようにしているので、以下のように複数の設定を変更して実行することも可能です。 245 | 246 | ```bash 247 | poetry run python src/train.py \ 248 | --model_name studio-ousia/luke-japanese-base-lite \ 249 | --batch_size 32 \ 250 | --epochs 10 \ 251 | --lr 5e-5 \ 252 | --num_warmup_epochs 1 253 | ``` 254 | 255 | 特筆すべき点としては、本実装では学習後のモデルは保存せず、訓練のたびに評価値を算出し、評価値のみを保存するようにしていることが挙げられます。 256 | 257 | 「学習済みモデルを保存」→「保存済みモデルを読み込んで評価」、という流れの実装はよくありますが、この実装は実験の途中でどのモデルを使用していたのか忘れてしまったり、モデルの構造が学習時と変わってしまっていたり、評価用データを間違えてしまったり、といった問題が発生しやすいと考えています。 258 | 259 | そこで本実装では、訓練のたびに必要な評価を行ってその結果のみを保存しておき、モデルは保存しない方針を採用しました。 260 | これにより、モデルの構造を変化させたり、学習・評価データを変化させた場合でも、訓練をし直すだけで常に間違いのない結果を得られます。 261 | 262 | 研究における実験プロセスの中では、間違いのない実験結果を積み重ねていくことが、研究を進めていく上で最も重要だと考えているので、間違いが発生しづらいこの方針はスジがよいと考えています。 263 | 264 | 本実装において、実験結果は `outputs/[モデル名]/[年月日]/[時分秒]`のディレクトリに保存されます。 265 | 実際には、以下のようなディレクトリ構造で結果が保存されます。 266 | 267 | ``` 268 | outputs/bert-base-multilingual-cased 269 | └── 2023-01-13 270 | └── 05-38-02 271 | ├── config.json 272 | ├── log.csv 273 | ├── test-metrics.json 274 | └── val-metrics.json 275 | ``` 276 | 277 | `config.json`が実験時の設定で、このファイルに記述してある値を用いることで、同じ実験を再現することができるようにしてあります。 278 | また、`log.csv`に学習過程における開発セットでのepochごとの評価値を記録してあります。 279 | 280 | そして、`val-metrics.json`と`test-metrics.json`に、開発セットの評価値が最もよかった時点でのモデルを用いた、開発セットとテストセットに対する評価値を記録してあります。 281 | 282 | 実際の`test-metrics.json`は以下のようになっています。 283 | 284 | ```json:test-metrics.json 285 | { 286 | "loss": 2.845567681340744, 287 | "accuracy": 0.9619565217391305, 288 | "precision": 0.9561782755165722, 289 | "recall": 0.9562792450871114, 290 | "f1": 0.9559338777925345 291 | } 292 | ``` 293 | 294 | ### その他 295 | 296 | `src/utils.py`に、`list[dict]`なデータをJSONL形式で保存・読み込む関数や、`list[dict]`の平均を取る関数、乱数シード値の設定を行う関数など、さまざまな便利関数を定義してあります。 297 | ぜひご利用ください。 298 | 299 | また、`src/aggregate.py`を実行することで、`outputs`ディレクトリ以下の結果を単一のcsvファイルにまとめることができます。このスクリプトは適宜改造してお使いください。 300 | 301 | 302 | ### Windows上での実行に際する注意 303 | 304 | Windows上で本プロジェクトを実行する際は、マルチプロセス処理に関する問題から、`src/train.py`中の`DataLoader`クラスに与える`num_workers`引数を`0`にする必要があります([参考](https://github.com/woven-planet/l5kit/issues/130#issuecomment-687817549))。 305 | したがって、OSとしてWindowsをお使いの方は、`src/train.py`中の`num_workers=4`という記述を`num_workers=0`に書き換えてください。 306 | この場合、多少モデルの訓練時間が伸びることが想定されますが、訓練されたモデルの性能や学習過程に影響はないと思われます。 307 | 308 | ## 評価実験 309 | 310 | 最後に、本実装によって、livedoorニュースコーパスの9値分類を行う評価実験を実施したので、その実験について述べます。 311 | 312 | 評価実験では、17種類の日本語・多言語モデルについて訓練を行いました。 313 | ハイパーパラメータの調整として、学習率を1e-5, 3e-5, 5e-5に設定してそれぞれ実験を行い、開発セットでのmacro平均F値が最も高くなった学習率を最終的なテストセットでの評価に用いました。 314 | 315 | 実験結果に対する注意ですが、実験は単一の乱数シード値で1度しか実施しておらず、分割交差検証も行っていないので、実験結果の正確性は高くありません。 316 | したがって、以下の結果は過度に信用せず、参考程度に見てもらうよう、お願いいたします。 317 | ちゃんとした研究論文では、5分割交差検証による実験や、異なる乱数シードで10回実験を行いその平均を評価指標とする、などの手順がよく用いられます。 318 | 319 | では、結果を以下の表に示します。 320 | 実験したモデル数が多いので、まずは 200M (2億) パラメータ以下の比較的小規模なモデルの結果についてみてみます。 321 | 322 | | Models (< 200 M) | Params | Accuracy | Precision | Recall | F1 | 323 | | ------------------------------------------------------------------------------------------------------------------------- | -----: | :------: | :-------: | :----: | :-------: | 324 | | [studio-ousia/luke-japanese-base-lite](https://huggingface.co/studio-ousia/luke-japanese-base-lite) | 133 M | 97.01 | 96.72 | 96.29 | **96.46** | 325 | | [cl-tohoku/bert-base-japanese-v2](https://huggingface.co/cl-tohoku/bert-base-japanese-v2) | 111 M | 96.88 | 96.42 | 96.46 | 96.43 | 326 | | [cl-tohoku/bert-base-japanese-v3](https://huggingface.co/cl-tohoku/bert-base-japanese-v3) | 111 M | 96.88 | 96.59 | 96.28 | 96.39 | 327 | | | | | | | 328 | | [cl-tohoku/bert-base-japanese](https://huggingface.co/cl-tohoku/bert-base-japanese) | 110 M | 96.74 | 96.20 | 96.16 | 96.16 | 329 | | [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) | 177 M | 96.60 | 96.25 | 96.06 | 96.12 | 330 | | | | | | | 331 | | [cl-tohoku/bert-base-japanese-char-v3](https://huggingface.co/cl-tohoku/bert-base-japanese-char-v3) | 91 M | 96.33 | 95.69 | 95.75 | 95.70 | 332 | | [cl-tohoku/bert-base-japanese-char-v2](https://huggingface.co/cl-tohoku/bert-base-japanese-char-v2) | 90 M | 96.06 | 95.62 | 95.26 | 95.39 | 333 | | | | | | | 334 | | [cl-tohoku/bert-base-japanese-whole-word-masking](https://huggingface.co/cl-tohoku/bert-base-japanese-whole-word-masking) | 110 M | 95.79 | 95.24 | 95.25 | 95.21 | 335 | | [cl-tohoku/bert-base-japanese-char](https://huggingface.co/cl-tohoku/bert-base-japanese-char) | 89 M | 95.11 | 94.91 | 93.82 | 94.17 | 336 | 337 | 表中のParamsはそれぞれのモデルのパラメータ数を示します。 338 | なお、Accuracy (正解率)以外の値、つまりPrecision (精度)、Recall (再現率)、F1はmacro平均を取った値であり、これらの評価指標の値は%表記されています。 339 | モデルとその評価結果は、F値が高い順に上から並んでいます。 340 | この表の結果は`src/aggregate.py`を実行することで得られます(パラメータ数は手元でPyTorchを使って計算し直しているので、公式発表と違う値になっているかもしれません)。 341 | 342 | 結果から、Studio Ousiaの日本語LUKE-baseが最もよいF値を示していることがわかります。 343 | 一方で、`luke-japanese-base-lite`は2位の東北大BERT-base v2と比較して若干パラメータ数が大きい(差: 20M == 2000万)です。 344 | ただ、一般に機械学習モデルは乱数シード値によって性能が多少ブレますが、今回の実験では単一の乱数シード値でしか実験を行っていないため、この結果の差異は誤差の範囲であるかもしれません。 345 | また、今回の評価実験では`cl-tohoku/bert-base-japanese-v2`と`cl-tohoku/bert-base-japanese-v3`の違いはほとんどありませんでしたが、学習コーパスの多様性などから、とりあえずでの利用を考えるなら`cl-tohoku/bert-base-japanese-v3`が優秀そうです。 346 | 347 | 全体についてみてみると、パラメータ数が比較的大きい多言語BERT (bert-base-multilingual-cased)より日本語単言語モデルの方が性能が高そうです。 348 | また、文字ベースのモデルたちはそこまで性能が高くないこともわかります。 349 | ライブドアニュースコーパスは記事本文まで入力する場合かなり長い事例を多く含むので、文字ベースモデルでは入力系列長が足りない(今回はmax=512)のかもしれません。 350 | 351 | 結果から、パラメータ数の軽微な違いや性能のブレの心配はあるものの、上位のモデルたちはそのほかのモデルより性能が高そうなので、BERT-baseサイズのモデルを利用したい場合は、まず`studio-ousia/luke-japanese-base-lite`や`cl-tohoku/bert-base-japanese-v3`の利用を考えてみるのが良さそうです。 352 | 353 | 次に、200 Mパラメータ以上のより大きなモデルの結果についてみてみます。 354 | 355 | | Models (>= 200 M) | Params | Accuracy | Precision | Recall | F1 | 356 | | ----------------------------------------------------------------------------------------------------- | -----: | :------: | :-------: | :----: | :-------: | 357 | | [studio-ousia/luke-japanese-large-lite](https://huggingface.co/studio-ousia/luke-japanese-large-lite) | 413 M | 97.83 | 97.82 | 97.22 | **97.47** | 358 | | [cl-tohoku/bert-large-japanese](https://huggingface.co/cl-tohoku/bert-large-japanese) | 337 M | 97.55 | 97.13 | 97.10 | 97.10 | 359 | | [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) | 559 M | 97.15 | 97.36 | 96.49 | 96.83 | 360 | | [studio-ousia/mluke-large-lite](https://huggingface.co/studio-ousia/mluke-large-lite) | 560 M | 97.28 | 97.25 | 96.56 | 96.83 | 361 | | | | | | | 362 | | [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) | 278 M | 97.15 | 96.71 | 96.58 | 96.63 | 363 | | [studio-ousia/mluke-base-lite](https://huggingface.co/studio-ousia/mluke-base-lite) | 278 M | 97.01 | 96.61 | 96.63 | 96.60 | 364 | | | | | | | 365 | | [cl-tohoku/bert-large-japanese-v2](https://huggingface.co/cl-tohoku/bert-large-japanese-v2) | 337 M | 96.74 | 96.57 | 96.10 | 96.26 | 366 | | [cl-tohoku/bert-large-japanese-char-v2](https://huggingface.co/cl-tohoku/bert-large-japanese-char-v2) | 311 M | 95.92 | 95.73 | 95.17 | 95.38 | 367 | 368 | 369 | 結果から、こちらでもやはりStudio Ousiaの日本語LUKE-largeが最も高い性能を達成していることがわかります。 370 | 日本語LUKE-largeは日本語LUKE-baseと比較してパラメータ数が3倍程度になっていますが、F値が1ポイント向上しており、モデルを大きくすることの有効性が伺えます。 371 | 372 | 全体として、比較的小規模のモデルよりも高い性能を示したモデルが多くモデルサイズを増大させることによる性能向上が観察できました。 373 | 374 | これらの結果は本リポジトリの`results`ディレクトリに保存されています。 375 | モデルごとに最も開発セットでの性能が高かった学習率を用いて、テストセットでの評価を行った結果が`results/best.csv`に保存してあります。 376 | また、すべての学習率での評価結果は、`results/all.csv`に保存してあります。 377 | お手持ちのタスクでの実験の参考にぜひお使いください。 378 | 379 | ## おわりに 380 | 381 | BERTを用いたテキスト分類をテーマとしたモダンで高品質な深層学習用のテンプレート実装を目指し、本実装を公開しました。 382 | 383 | 本実装が研究・企業応用・個人利用問わずさまざまな方のお役に立てれば幸いです。 384 | 385 | 質問・バグ報告などがあればどんなことでも[Issue](https://github.com/hppRC/bert-classification-tutorial/issues)にお書きください。 386 | 387 | 388 | ## 参考文献 389 | 390 | - [【実装解説】日本語版BERTでlivedoorニュース分類：Google Colaboratoryで（PyTorch）](https://qiita.com/sugulu_Ogawa_ISID/items/697bd03499c1de9cf082) 391 | - [Livedoorニュースコーパスを文書分類にすぐ使えるように整形する](https://radiology-nlp.hatenablog.com/entry/2019/11/25/124219) 392 | - [BERTによる日本語構文解析の精度向上](https://www.anlp.jp/proceedings/annual_meeting/2019/pdf_dir/F2-4.pdf) 393 | - [研究のためのPython開発環境](https://zenn.dev/zenizeni/books/a64578f98450c2) 394 | - https://github.com/yoheikikuta/bert-japanese/blob/master/notebook/finetune-to-livedoor-corpus.ipynb 395 | - https://github.com/sonoisa/t5-japanese/blob/main/t5_japanese_classification.ipynb 396 | - https://gist.github.com/kanjirz50/1ef6813df7faed3838629a3eea73774b 397 | - https://www.pytry3g.com/entry/2018/04/03/194202 398 | - https://www.nlp.ecei.tohoku.ac.jp/news-release/3284/ 399 | - https://github.com/cl-tohoku/bert-japanese/tree/v2.0 400 | 401 | ## 著者情報・引用 402 | 403 | 作者: [Hayato Tsukagoshi](https://hpprc.dev) \ 404 | email: [research.tsukagoshi.hayato@gmail.com](mailto:research.tsukagoshi.hayato@gmail.com) 405 | 関連学会記事: [BERTによるテキスト分類チュートリアル](https://www.jstage.jst.go.jp/article/jnlp/30/2/30_867/_article/-char/ja) 406 | 407 | 論文等で本実装を参照する場合は、以下をお使いください。 408 | 409 | ```bibtex 410 | @article{ 411 | hayato-tsukagoshi-2023-bert-classification-tutorial,, 412 | title={{BERT によるテキスト分類チュートリアル}}, 413 | author={塚越 駿 and 平子 潤}, 414 | journal={自然言語処理}, 415 | volume={30}, 416 | number={2}, 417 | pages={867-873}, 418 | year={2023}, 419 | doi={10.5715/jnlp.30.867}, 420 | url = {https://www.jstage.jst.go.jp/article/jnlp/30/2/30_867/_article/-char/ja}, 421 | } 422 | ``` 423 | -------------------------------------------------------------------------------- /poetry.lock: -------------------------------------------------------------------------------- 1 | # This file is automatically @generated by Poetry 1.8.2 and should not be changed by hand. 2 | 3 | [[package]] 4 | name = "certifi" 5 | version = "2024.2.2" 6 | description = "Python package for providing Mozilla's CA Bundle." 7 | optional = false 8 | python-versions = ">=3.6" 9 | files = [ 10 | {file = "certifi-2024.2.2-py3-none-any.whl", hash = "sha256:dc383c07b76109f368f6106eee2b593b04a011ea4d55f652c6ca24a754d1cdd1"}, 11 | {file = "certifi-2024.2.2.tar.gz", hash = "sha256:0569859f95fc761b18b45ef421b1290a0f65f147e92a1e5eb3e635f9a5e4e66f"}, 12 | ] 13 | 14 | [[package]] 15 | name = "charset-normalizer" 16 | version = "3.3.2" 17 | description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet." 18 | optional = false 19 | python-versions = ">=3.7.0" 20 | files = [ 21 | {file = "charset-normalizer-3.3.2.tar.gz", hash = "sha256:f30c3cb33b24454a82faecaf01b19c18562b1e89558fb6c56de4d9118a032fd5"}, 22 | {file = "charset_normalizer-3.3.2-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:25baf083bf6f6b341f4121c2f3c548875ee6f5339300e08be3f2b2ba1721cdd3"}, 23 | {file = "charset_normalizer-3.3.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:06435b539f889b1f6f4ac1758871aae42dc3a8c0e24ac9e60c2384973ad73027"}, 24 | {file = "charset_normalizer-3.3.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:9063e24fdb1e498ab71cb7419e24622516c4a04476b17a2dab57e8baa30d6e03"}, 25 | {file = "charset_normalizer-3.3.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6897af51655e3691ff853668779c7bad41579facacf5fd7253b0133308cf000d"}, 26 | {file = "charset_normalizer-3.3.2-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1d3193f4a680c64b4b6a9115943538edb896edc190f0b222e73761716519268e"}, 27 | {file = "charset_normalizer-3.3.2-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:cd70574b12bb8a4d2aaa0094515df2463cb429d8536cfb6c7ce983246983e5a6"}, 28 | {file = "charset_normalizer-3.3.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8465322196c8b4d7ab6d1e049e4c5cb460d0394da4a27d23cc242fbf0034b6b5"}, 29 | {file = "charset_normalizer-3.3.2-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a9a8e9031d613fd2009c182b69c7b2c1ef8239a0efb1df3f7c8da66d5dd3d537"}, 30 | {file = "charset_normalizer-3.3.2-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:beb58fe5cdb101e3a055192ac291b7a21e3b7ef4f67fa1d74e331a7f2124341c"}, 31 | {file = "charset_normalizer-3.3.2-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:e06ed3eb3218bc64786f7db41917d4e686cc4856944f53d5bdf83a6884432e12"}, 32 | {file = "charset_normalizer-3.3.2-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:2e81c7b9c8979ce92ed306c249d46894776a909505d8f5a4ba55b14206e3222f"}, 33 | {file = "charset_normalizer-3.3.2-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:572c3763a264ba47b3cf708a44ce965d98555f618ca42c926a9c1616d8f34269"}, 34 | {file = "charset_normalizer-3.3.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:fd1abc0d89e30cc4e02e4064dc67fcc51bd941eb395c502aac3ec19fab46b519"}, 35 | {file = "charset_normalizer-3.3.2-cp310-cp310-win32.whl", hash = "sha256:3d47fa203a7bd9c5b6cee4736ee84ca03b8ef23193c0d1ca99b5089f72645c73"}, 36 | {file = "charset_normalizer-3.3.2-cp310-cp310-win_amd64.whl", hash = "sha256:10955842570876604d404661fbccbc9c7e684caf432c09c715ec38fbae45ae09"}, 37 | {file = "charset_normalizer-3.3.2-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:802fe99cca7457642125a8a88a084cef28ff0cf9407060f7b93dca5aa25480db"}, 38 | {file = "charset_normalizer-3.3.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:573f6eac48f4769d667c4442081b1794f52919e7edada77495aaed9236d13a96"}, 39 | {file = "charset_normalizer-3.3.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:549a3a73da901d5bc3ce8d24e0600d1fa85524c10287f6004fbab87672bf3e1e"}, 40 | {file = "charset_normalizer-3.3.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f27273b60488abe721a075bcca6d7f3964f9f6f067c8c4c605743023d7d3944f"}, 41 | {file = "charset_normalizer-3.3.2-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1ceae2f17a9c33cb48e3263960dc5fc8005351ee19db217e9b1bb15d28c02574"}, 42 | {file = "charset_normalizer-3.3.2-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:65f6f63034100ead094b8744b3b97965785388f308a64cf8d7c34f2f2e5be0c4"}, 43 | {file = "charset_normalizer-3.3.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:753f10e867343b4511128c6ed8c82f7bec3bd026875576dfd88483c5c73b2fd8"}, 44 | {file = "charset_normalizer-3.3.2-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4a78b2b446bd7c934f5dcedc588903fb2f5eec172f3d29e52a9096a43722adfc"}, 45 | {file = "charset_normalizer-3.3.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:e537484df0d8f426ce2afb2d0f8e1c3d0b114b83f8850e5f2fbea0e797bd82ae"}, 46 | {file = "charset_normalizer-3.3.2-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:eb6904c354526e758fda7167b33005998fb68c46fbc10e013ca97f21ca5c8887"}, 47 | {file = "charset_normalizer-3.3.2-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:deb6be0ac38ece9ba87dea880e438f25ca3eddfac8b002a2ec3d9183a454e8ae"}, 48 | {file = "charset_normalizer-3.3.2-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:4ab2fe47fae9e0f9dee8c04187ce5d09f48eabe611be8259444906793ab7cbce"}, 49 | {file = "charset_normalizer-3.3.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:80402cd6ee291dcb72644d6eac93785fe2c8b9cb30893c1af5b8fdd753b9d40f"}, 50 | {file = "charset_normalizer-3.3.2-cp311-cp311-win32.whl", hash = "sha256:7cd13a2e3ddeed6913a65e66e94b51d80a041145a026c27e6bb76c31a853c6ab"}, 51 | {file = "charset_normalizer-3.3.2-cp311-cp311-win_amd64.whl", hash = "sha256:663946639d296df6a2bb2aa51b60a2454ca1cb29835324c640dafb5ff2131a77"}, 52 | {file = "charset_normalizer-3.3.2-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:0b2b64d2bb6d3fb9112bafa732def486049e63de9618b5843bcdd081d8144cd8"}, 53 | {file = "charset_normalizer-3.3.2-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:ddbb2551d7e0102e7252db79ba445cdab71b26640817ab1e3e3648dad515003b"}, 54 | {file = "charset_normalizer-3.3.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:55086ee1064215781fff39a1af09518bc9255b50d6333f2e4c74ca09fac6a8f6"}, 55 | {file = "charset_normalizer-3.3.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8f4a014bc36d3c57402e2977dada34f9c12300af536839dc38c0beab8878f38a"}, 56 | {file = "charset_normalizer-3.3.2-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a10af20b82360ab00827f916a6058451b723b4e65030c5a18577c8b2de5b3389"}, 57 | {file = "charset_normalizer-3.3.2-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8d756e44e94489e49571086ef83b2bb8ce311e730092d2c34ca8f7d925cb20aa"}, 58 | {file = "charset_normalizer-3.3.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:90d558489962fd4918143277a773316e56c72da56ec7aa3dc3dbbe20fdfed15b"}, 59 | {file = "charset_normalizer-3.3.2-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6ac7ffc7ad6d040517be39eb591cac5ff87416c2537df6ba3cba3bae290c0fed"}, 60 | {file = "charset_normalizer-3.3.2-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:7ed9e526742851e8d5cc9e6cf41427dfc6068d4f5a3bb03659444b4cabf6bc26"}, 61 | {file = "charset_normalizer-3.3.2-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:8bdb58ff7ba23002a4c5808d608e4e6c687175724f54a5dade5fa8c67b604e4d"}, 62 | {file = "charset_normalizer-3.3.2-cp312-cp312-musllinux_1_1_ppc64le.whl", hash = "sha256:6b3251890fff30ee142c44144871185dbe13b11bab478a88887a639655be1068"}, 63 | {file = "charset_normalizer-3.3.2-cp312-cp312-musllinux_1_1_s390x.whl", hash = "sha256:b4a23f61ce87adf89be746c8a8974fe1c823c891d8f86eb218bb957c924bb143"}, 64 | {file = "charset_normalizer-3.3.2-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:efcb3f6676480691518c177e3b465bcddf57cea040302f9f4e6e191af91174d4"}, 65 | {file = "charset_normalizer-3.3.2-cp312-cp312-win32.whl", hash = "sha256:d965bba47ddeec8cd560687584e88cf699fd28f192ceb452d1d7ee807c5597b7"}, 66 | {file = "charset_normalizer-3.3.2-cp312-cp312-win_amd64.whl", hash = "sha256:96b02a3dc4381e5494fad39be677abcb5e6634bf7b4fa83a6dd3112607547001"}, 67 | {file = "charset_normalizer-3.3.2-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:95f2a5796329323b8f0512e09dbb7a1860c46a39da62ecb2324f116fa8fdc85c"}, 68 | {file = "charset_normalizer-3.3.2-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c002b4ffc0be611f0d9da932eb0f704fe2602a9a949d1f738e4c34c75b0863d5"}, 69 | {file = "charset_normalizer-3.3.2-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a981a536974bbc7a512cf44ed14938cf01030a99e9b3a06dd59578882f06f985"}, 70 | {file = "charset_normalizer-3.3.2-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:3287761bc4ee9e33561a7e058c72ac0938c4f57fe49a09eae428fd88aafe7bb6"}, 71 | {file = "charset_normalizer-3.3.2-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:42cb296636fcc8b0644486d15c12376cb9fa75443e00fb25de0b8602e64c1714"}, 72 | {file = "charset_normalizer-3.3.2-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0a55554a2fa0d408816b3b5cedf0045f4b8e1a6065aec45849de2d6f3f8e9786"}, 73 | {file = "charset_normalizer-3.3.2-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:c083af607d2515612056a31f0a8d9e0fcb5876b7bfc0abad3ecd275bc4ebc2d5"}, 74 | {file = "charset_normalizer-3.3.2-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:87d1351268731db79e0f8e745d92493ee2841c974128ef629dc518b937d9194c"}, 75 | {file = "charset_normalizer-3.3.2-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:bd8f7df7d12c2db9fab40bdd87a7c09b1530128315d047a086fa3ae3435cb3a8"}, 76 | {file = "charset_normalizer-3.3.2-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:c180f51afb394e165eafe4ac2936a14bee3eb10debc9d9e4db8958fe36afe711"}, 77 | {file = "charset_normalizer-3.3.2-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:8c622a5fe39a48f78944a87d4fb8a53ee07344641b0562c540d840748571b811"}, 78 | {file = "charset_normalizer-3.3.2-cp37-cp37m-win32.whl", hash = "sha256:db364eca23f876da6f9e16c9da0df51aa4f104a972735574842618b8c6d999d4"}, 79 | {file = "charset_normalizer-3.3.2-cp37-cp37m-win_amd64.whl", hash = "sha256:86216b5cee4b06df986d214f664305142d9c76df9b6512be2738aa72a2048f99"}, 80 | {file = "charset_normalizer-3.3.2-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:6463effa3186ea09411d50efc7d85360b38d5f09b870c48e4600f63af490e56a"}, 81 | {file = "charset_normalizer-3.3.2-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:6c4caeef8fa63d06bd437cd4bdcf3ffefe6738fb1b25951440d80dc7df8c03ac"}, 82 | {file = "charset_normalizer-3.3.2-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:37e55c8e51c236f95b033f6fb391d7d7970ba5fe7ff453dad675e88cf303377a"}, 83 | {file = "charset_normalizer-3.3.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fb69256e180cb6c8a894fee62b3afebae785babc1ee98b81cdf68bbca1987f33"}, 84 | {file = "charset_normalizer-3.3.2-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ae5f4161f18c61806f411a13b0310bea87f987c7d2ecdbdaad0e94eb2e404238"}, 85 | {file = "charset_normalizer-3.3.2-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b2b0a0c0517616b6869869f8c581d4eb2dd83a4d79e0ebcb7d373ef9956aeb0a"}, 86 | {file = "charset_normalizer-3.3.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:45485e01ff4d3630ec0d9617310448a8702f70e9c01906b0d0118bdf9d124cf2"}, 87 | {file = "charset_normalizer-3.3.2-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:eb00ed941194665c332bf8e078baf037d6c35d7c4f3102ea2d4f16ca94a26dc8"}, 88 | {file = "charset_normalizer-3.3.2-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:2127566c664442652f024c837091890cb1942c30937add288223dc895793f898"}, 89 | {file = "charset_normalizer-3.3.2-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:a50aebfa173e157099939b17f18600f72f84eed3049e743b68ad15bd69b6bf99"}, 90 | {file = "charset_normalizer-3.3.2-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:4d0d1650369165a14e14e1e47b372cfcb31d6ab44e6e33cb2d4e57265290044d"}, 91 | {file = "charset_normalizer-3.3.2-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:923c0c831b7cfcb071580d3f46c4baf50f174be571576556269530f4bbd79d04"}, 92 | {file = "charset_normalizer-3.3.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:06a81e93cd441c56a9b65d8e1d043daeb97a3d0856d177d5c90ba85acb3db087"}, 93 | {file = "charset_normalizer-3.3.2-cp38-cp38-win32.whl", hash = "sha256:6ef1d82a3af9d3eecdba2321dc1b3c238245d890843e040e41e470ffa64c3e25"}, 94 | {file = "charset_normalizer-3.3.2-cp38-cp38-win_amd64.whl", hash = "sha256:eb8821e09e916165e160797a6c17edda0679379a4be5c716c260e836e122f54b"}, 95 | {file = "charset_normalizer-3.3.2-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:c235ebd9baae02f1b77bcea61bce332cb4331dc3617d254df3323aa01ab47bd4"}, 96 | {file = "charset_normalizer-3.3.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:5b4c145409bef602a690e7cfad0a15a55c13320ff7a3ad7ca59c13bb8ba4d45d"}, 97 | {file = "charset_normalizer-3.3.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:68d1f8a9e9e37c1223b656399be5d6b448dea850bed7d0f87a8311f1ff3dabb0"}, 98 | {file = "charset_normalizer-3.3.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:22afcb9f253dac0696b5a4be4a1c0f8762f8239e21b99680099abd9b2b1b2269"}, 99 | {file = "charset_normalizer-3.3.2-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e27ad930a842b4c5eb8ac0016b0a54f5aebbe679340c26101df33424142c143c"}, 100 | {file = "charset_normalizer-3.3.2-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:1f79682fbe303db92bc2b1136016a38a42e835d932bab5b3b1bfcfbf0640e519"}, 101 | {file = "charset_normalizer-3.3.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b261ccdec7821281dade748d088bb6e9b69e6d15b30652b74cbbac25e280b796"}, 102 | {file = "charset_normalizer-3.3.2-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:122c7fa62b130ed55f8f285bfd56d5f4b4a5b503609d181f9ad85e55c89f4185"}, 103 | {file = "charset_normalizer-3.3.2-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:d0eccceffcb53201b5bfebb52600a5fb483a20b61da9dbc885f8b103cbe7598c"}, 104 | {file = "charset_normalizer-3.3.2-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:9f96df6923e21816da7e0ad3fd47dd8f94b2a5ce594e00677c0013018b813458"}, 105 | {file = "charset_normalizer-3.3.2-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:7f04c839ed0b6b98b1a7501a002144b76c18fb1c1850c8b98d458ac269e26ed2"}, 106 | {file = "charset_normalizer-3.3.2-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:34d1c8da1e78d2e001f363791c98a272bb734000fcef47a491c1e3b0505657a8"}, 107 | {file = "charset_normalizer-3.3.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:ff8fa367d09b717b2a17a052544193ad76cd49979c805768879cb63d9ca50561"}, 108 | {file = "charset_normalizer-3.3.2-cp39-cp39-win32.whl", hash = "sha256:aed38f6e4fb3f5d6bf81bfa990a07806be9d83cf7bacef998ab1a9bd660a581f"}, 109 | {file = "charset_normalizer-3.3.2-cp39-cp39-win_amd64.whl", hash = "sha256:b01b88d45a6fcb69667cd6d2f7a9aeb4bf53760d7fc536bf679ec94fe9f3ff3d"}, 110 | {file = "charset_normalizer-3.3.2-py3-none-any.whl", hash = "sha256:3e4d1f6587322d2788836a99c69062fbb091331ec940e02d12d179c1d53e25fc"}, 111 | ] 112 | 113 | [[package]] 114 | name = "cmake" 115 | version = "3.29.2" 116 | description = "CMake is an open-source, cross-platform family of tools designed to build, test and package software" 117 | optional = false 118 | python-versions = ">=3.7" 119 | files = [ 120 | {file = "cmake-3.29.2-py3-none-macosx_10_10_universal2.macosx_10_10_x86_64.macosx_11_0_arm64.macosx_11_0_universal2.whl", hash = "sha256:1d40c5451d6467b20a0a6015a5a6b6dc86f61b83f71f935740485b259100a34e"}, 121 | {file = "cmake-3.29.2-py3-none-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:ed3108e646cd65a4e23fa1cbe8123569a29334a3f2a8ce214d871406b161bedb"}, 122 | {file = "cmake-3.29.2-py3-none-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:40aafe612b03a9fa140cca4024ba60b74cd92372f3f349d8062cba1f021e5001"}, 123 | {file = "cmake-3.29.2-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:027eebe9bb74c31759581a543f27bc1828fc76e6fc45b2b48b51f27847904669"}, 124 | {file = "cmake-3.29.2-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f1f087985fc2460476b0901716fbddb2fd69b7fe7bf1350e1ab5dc508d22600e"}, 125 | {file = "cmake-3.29.2-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:df2c63ce6d504aa4c91a42fd22d3887065ab029569691deb56ec19d0decd0ae9"}, 126 | {file = "cmake-3.29.2-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:6ea5ce007893d7d1363e13433dde1c0c7c344372213a90ff3c56e896a335301d"}, 127 | {file = "cmake-3.29.2-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f9e941e73202cfa667ee488d1d88b8a758b516dcfa2a2728e73dbdcbfbdebf57"}, 128 | {file = "cmake-3.29.2-py3-none-musllinux_1_1_aarch64.whl", hash = "sha256:37222e23485338c72b7ea51f865d8c6847d519f7e2222922fb70b4896ca6e897"}, 129 | {file = "cmake-3.29.2-py3-none-musllinux_1_1_i686.whl", hash = "sha256:eeed08932c748647488280dc97ac00bcfeae5d760451105200cfe66c52ce6468"}, 130 | {file = "cmake-3.29.2-py3-none-musllinux_1_1_ppc64le.whl", hash = "sha256:db7a05df020ba67bacd3070dd1645c76ca96fabd06d6aaa63288fd845706e47a"}, 131 | {file = "cmake-3.29.2-py3-none-musllinux_1_1_s390x.whl", hash = "sha256:83b35de822ddabaaa184a7d8f9827381350c42d627689c775b214347f57c9e41"}, 132 | {file = "cmake-3.29.2-py3-none-musllinux_1_1_x86_64.whl", hash = "sha256:cc0e36752e581430a93e58a268e515bb4ec1373b9e9911571f2cac1d2a6b5bec"}, 133 | {file = "cmake-3.29.2-py3-none-win32.whl", hash = "sha256:a941e26fba81cf74832c8a0e17e007452e05b6ad4941b3d2d18c75faa4a677d8"}, 134 | {file = "cmake-3.29.2-py3-none-win_amd64.whl", hash = "sha256:23336c8ca01205d18d92ed8de6c54e570c352a58e378b7f9adc02ef00f433960"}, 135 | {file = "cmake-3.29.2-py3-none-win_arm64.whl", hash = "sha256:e722a949f7c91084dba61f8f17a9854787182ab711ed0b84b1507b24a8e12e25"}, 136 | {file = "cmake-3.29.2.tar.gz", hash = "sha256:6a4c1185cb2eca7263190a5754d0c9edf738d9e50bff464f78f48d0c05318e7c"}, 137 | ] 138 | 139 | [package.extras] 140 | test = ["coverage (>=4.2)", "pytest (>=3.0.3)", "pytest-cov (>=2.4.0)"] 141 | 142 | [[package]] 143 | name = "colorama" 144 | version = "0.4.6" 145 | description = "Cross-platform colored terminal text." 146 | optional = false 147 | python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,>=2.7" 148 | files = [ 149 | {file = "colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6"}, 150 | {file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"}, 151 | ] 152 | 153 | [[package]] 154 | name = "docstring-parser" 155 | version = "0.16" 156 | description = "Parse Python docstrings in reST, Google and Numpydoc format" 157 | optional = false 158 | python-versions = ">=3.6,<4.0" 159 | files = [ 160 | {file = "docstring_parser-0.16-py3-none-any.whl", hash = "sha256:bf0a1387354d3691d102edef7ec124f219ef639982d096e26e3b60aeffa90637"}, 161 | {file = "docstring_parser-0.16.tar.gz", hash = "sha256:538beabd0af1e2db0146b6bd3caa526c35a34d61af9fd2887f3a8a27a739aa6e"}, 162 | ] 163 | 164 | [[package]] 165 | name = "filelock" 166 | version = "3.13.4" 167 | description = "A platform independent file lock." 168 | optional = false 169 | python-versions = ">=3.8" 170 | files = [ 171 | {file = "filelock-3.13.4-py3-none-any.whl", hash = "sha256:404e5e9253aa60ad457cae1be07c0f0ca90a63931200a47d9b6a6af84fd7b45f"}, 172 | {file = "filelock-3.13.4.tar.gz", hash = "sha256:d13f466618bfde72bd2c18255e269f72542c6e70e7bac83a0232d6b1cc5c8cf4"}, 173 | ] 174 | 175 | [package.extras] 176 | docs = ["furo (>=2023.9.10)", "sphinx (>=7.2.6)", "sphinx-autodoc-typehints (>=1.25.2)"] 177 | testing = ["covdefaults (>=2.3)", "coverage (>=7.3.2)", "diff-cover (>=8.0.1)", "pytest (>=7.4.3)", "pytest-cov (>=4.1)", "pytest-mock (>=3.12)", "pytest-timeout (>=2.2)"] 178 | typing = ["typing-extensions (>=4.8)"] 179 | 180 | [[package]] 181 | name = "fsspec" 182 | version = "2024.3.1" 183 | description = "File-system specification" 184 | optional = false 185 | python-versions = ">=3.8" 186 | files = [ 187 | {file = "fsspec-2024.3.1-py3-none-any.whl", hash = "sha256:918d18d41bf73f0e2b261824baeb1b124bcf771767e3a26425cd7dec3332f512"}, 188 | {file = "fsspec-2024.3.1.tar.gz", hash = "sha256:f39780e282d7d117ffb42bb96992f8a90795e4d0fb0f661a70ca39fe9c43ded9"}, 189 | ] 190 | 191 | [package.extras] 192 | abfs = ["adlfs"] 193 | adl = ["adlfs"] 194 | arrow = ["pyarrow (>=1)"] 195 | dask = ["dask", "distributed"] 196 | devel = ["pytest", "pytest-cov"] 197 | dropbox = ["dropbox", "dropboxdrivefs", "requests"] 198 | full = ["adlfs", "aiohttp (!=4.0.0a0,!=4.0.0a1)", "dask", "distributed", "dropbox", "dropboxdrivefs", "fusepy", "gcsfs", "libarchive-c", "ocifs", "panel", "paramiko", "pyarrow (>=1)", "pygit2", "requests", "s3fs", "smbprotocol", "tqdm"] 199 | fuse = ["fusepy"] 200 | gcs = ["gcsfs"] 201 | git = ["pygit2"] 202 | github = ["requests"] 203 | gs = ["gcsfs"] 204 | gui = ["panel"] 205 | hdfs = ["pyarrow (>=1)"] 206 | http = ["aiohttp (!=4.0.0a0,!=4.0.0a1)"] 207 | libarchive = ["libarchive-c"] 208 | oci = ["ocifs"] 209 | s3 = ["s3fs"] 210 | sftp = ["paramiko"] 211 | smb = ["smbprotocol"] 212 | ssh = ["paramiko"] 213 | tqdm = ["tqdm"] 214 | 215 | [[package]] 216 | name = "fugashi" 217 | version = "1.3.2" 218 | description = "A Cython MeCab wrapper for fast, pythonic Japanese tokenization." 219 | optional = false 220 | python-versions = ">=3.7" 221 | files = [ 222 | {file = "fugashi-1.3.2-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:583e7a14e6ddf8a03b500bec30d708f72e98035ab43e2c92940dd9c36ee63de9"}, 223 | {file = "fugashi-1.3.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:6c67023cdc1b059b05751c1785c794c24d8862f37a16cdb805e33c7d7ae0c19d"}, 224 | {file = "fugashi-1.3.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:6b2e21be33ed72621d9f4a601a33c00b38052df947f297d792b221a33337f094"}, 225 | {file = "fugashi-1.3.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:af7abac3037c7421b075782897766b8f453f28ef3bbadd3e7d69c9df409a48a8"}, 226 | {file = "fugashi-1.3.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6b915d936e3eb30d50fde86889f8ab56968e5cb4d0ceeb497ac1bb6c58531f87"}, 227 | {file = "fugashi-1.3.2-cp310-cp310-win_amd64.whl", hash = "sha256:8dc57d07809fbecdfc277d50028d5b8d23fb4c0ed12e6d6f7f565709c18848a4"}, 228 | {file = "fugashi-1.3.2-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:50243df8758f5fb90bd2801e557168e613df61fa4d488acfe364070e8a4a234c"}, 229 | {file = "fugashi-1.3.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:9c9fb77c42e6b421e5c20f74179ed479255545b40a28f9983f264a8b19a30374"}, 230 | {file = "fugashi-1.3.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:6fdef6be3489279c670459a55b2dfa876c0856b3fc96b3590aa801f37af6b827"}, 231 | {file = "fugashi-1.3.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2b2ebe0d6722e05000a959df303e06937939009f4eef0b8692018eb019496013"}, 232 | {file = "fugashi-1.3.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:85d8e3a9e9d92f555525b2719153e7d3e4ec71d0bae0b076b5495634039b8490"}, 233 | {file = "fugashi-1.3.2-cp311-cp311-win_amd64.whl", hash = "sha256:9774bb52930fa17ebab17f8bcf2b5d20b6ef529b425ea65affb29a3307c003f8"}, 234 | {file = "fugashi-1.3.2-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:fcfb3908059f4dd15d7fda64edd3c027b4da668bf1731f147aa888f5db01bd6c"}, 235 | {file = "fugashi-1.3.2-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:49b44261f2051c43a9e31816d85bb89e5563c3e4c03ff7830d1ebf5942888cf9"}, 236 | {file = "fugashi-1.3.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:3a2d8aecb2a239de33bcb70806b7688001e72f68bde68961c6f2899155f15f87"}, 237 | {file = "fugashi-1.3.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4e24864e92ad3acf3c0b8f645e33d543fe569544bb6ee9728cb281325aa76d06"}, 238 | {file = "fugashi-1.3.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ea942e45214a99844146ce0e0f1ac43bff6e2ccbf6d1cbfde4f2bed9ca0951b1"}, 239 | {file = "fugashi-1.3.2-cp312-cp312-win_amd64.whl", hash = "sha256:da61498017e5cbee65c6eff88a13e17b45a5e3b0428733e99168344b8ff95da5"}, 240 | {file = "fugashi-1.3.2-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:18cd37369c1df25e56ef55ea31b3daaa14cfaae805d0ad51ae1274f749f3748d"}, 241 | {file = "fugashi-1.3.2-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:63a6c360c1d5e8c4ffa55f1459550146a204401c5fb8cc01d4ba593586ed328a"}, 242 | {file = "fugashi-1.3.2-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a9ed34c799e945f013345a02cf27a5bc97e383b76c3127afe09008cf92b5858d"}, 243 | {file = "fugashi-1.3.2-cp37-cp37m-win_amd64.whl", hash = "sha256:213c543e00c80fd601926b03fe489ebd6140d6022a78e2398dcbae7032a9166f"}, 244 | {file = "fugashi-1.3.2-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:107a37140c51396776810294aa47d6b92f767f834f1b9e50ca35046a63f31dfd"}, 245 | {file = "fugashi-1.3.2-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:13001a977d0a87e174defaa7a7d5c512da0fd021beabe80ce8eb94694a9563a8"}, 246 | {file = "fugashi-1.3.2-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:1ad77258f97547d906cc822192c6c2c99a54290b0ca8c127368e11e0a0365245"}, 247 | {file = "fugashi-1.3.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2d3345d2c61dd9d056442e271887a189cc2831a5365c3b8bdcccd4395b54f4fe"}, 248 | {file = "fugashi-1.3.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f1cb923fbdfccc5d750accd32c9b929603852d6626b162834370b4b3245bb8c2"}, 249 | {file = "fugashi-1.3.2-cp38-cp38-win_amd64.whl", hash = "sha256:6072a18d1f8428eb19a199ee3d8f1b01c310d15baec96aa7a9fa533e1ce60673"}, 250 | {file = "fugashi-1.3.2-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:7e392f2c57068bb892c45c1b69067c3dde94b633c81c725a613ee7defe09de47"}, 251 | {file = "fugashi-1.3.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:85de463fc30390c06d985f52fcfd422acf7ada6b13f723721ca964854b9ae435"}, 252 | {file = "fugashi-1.3.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:5a640da3824aba966209fc425b2b19c38d22a3da637f83b4a7df83cb94376b87"}, 253 | {file = "fugashi-1.3.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:11e95f57b78152be3a0a1a1e77d7887cfc25c30412d5f5825711b75ea6d415be"}, 254 | {file = "fugashi-1.3.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:409b83f136a3c2da805cd999bd7e1792e7c71fa8e0637f77bdec2b6fd070a3bb"}, 255 | {file = "fugashi-1.3.2-cp39-cp39-win_amd64.whl", hash = "sha256:51eed11fee767597cfe735bd01326eb06deb2283112e29e9e5bdc954750e7a24"}, 256 | {file = "fugashi-1.3.2-pp310-pypy310_pp73-macosx_10_9_x86_64.whl", hash = "sha256:bc99b6e8f003c7a0e53e0f486caa1547f0ca8f86777610ea92af6e2f40ca212a"}, 257 | {file = "fugashi-1.3.2-pp37-pypy37_pp73-macosx_10_9_x86_64.whl", hash = "sha256:4c7e97655d1d3f3f5d5c5da6ac7f31f187177a39f1557f9d3f683772a2e30815"}, 258 | {file = "fugashi-1.3.2-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:54865ba40c35b3180d9c7cf629a1f3e430bca626dcd6ee6288bc5245c044edea"}, 259 | {file = "fugashi-1.3.2-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:21d2dac5b085632f1f9a24edf5d7ccaeb3272be672e4aa37a0b219fc7a3b0655"}, 260 | {file = "fugashi-1.3.2.tar.gz", hash = "sha256:964980b5d227ee41af7570542aaab56b1298c44416271cba5d8ff9a58ab40748"}, 261 | ] 262 | 263 | [package.extras] 264 | unidic = ["unidic"] 265 | unidic-lite = ["unidic-lite"] 266 | 267 | [[package]] 268 | name = "huggingface-hub" 269 | version = "0.22.2" 270 | description = "Client library to download and publish models, datasets and other repos on the huggingface.co hub" 271 | optional = false 272 | python-versions = ">=3.8.0" 273 | files = [ 274 | {file = "huggingface_hub-0.22.2-py3-none-any.whl", hash = "sha256:3429e25f38ccb834d310804a3b711e7e4953db5a9e420cc147a5e194ca90fd17"}, 275 | {file = "huggingface_hub-0.22.2.tar.gz", hash = "sha256:32e9a9a6843c92f253ff9ca16b9985def4d80a93fb357af5353f770ef74a81be"}, 276 | ] 277 | 278 | [package.dependencies] 279 | filelock = "*" 280 | fsspec = ">=2023.5.0" 281 | packaging = ">=20.9" 282 | pyyaml = ">=5.1" 283 | requests = "*" 284 | tqdm = ">=4.42.1" 285 | typing-extensions = ">=3.7.4.3" 286 | 287 | [package.extras] 288 | all = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "gradio", "jedi", "minijinja (>=1.0)", "mypy (==1.5.1)", "numpy", "pytest", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-rerunfailures", "pytest-vcr", "pytest-xdist", "ruff (>=0.3.0)", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "typing-extensions (>=4.8.0)", "urllib3 (<2.0)"] 289 | cli = ["InquirerPy (==0.3.4)"] 290 | dev = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "gradio", "jedi", "minijinja (>=1.0)", "mypy (==1.5.1)", "numpy", "pytest", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-rerunfailures", "pytest-vcr", "pytest-xdist", "ruff (>=0.3.0)", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "typing-extensions (>=4.8.0)", "urllib3 (<2.0)"] 291 | fastai = ["fastai (>=2.4)", "fastcore (>=1.3.27)", "toml"] 292 | hf-transfer = ["hf-transfer (>=0.1.4)"] 293 | inference = ["aiohttp", "minijinja (>=1.0)"] 294 | quality = ["mypy (==1.5.1)", "ruff (>=0.3.0)"] 295 | tensorflow = ["graphviz", "pydot", "tensorflow"] 296 | tensorflow-testing = ["keras (<3.0)", "tensorflow"] 297 | testing = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "gradio", "jedi", "minijinja (>=1.0)", "numpy", "pytest", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-rerunfailures", "pytest-vcr", "pytest-xdist", "soundfile", "urllib3 (<2.0)"] 298 | torch = ["safetensors", "torch"] 299 | typing = ["types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "typing-extensions (>=4.8.0)"] 300 | 301 | [[package]] 302 | name = "idna" 303 | version = "3.7" 304 | description = "Internationalized Domain Names in Applications (IDNA)" 305 | optional = false 306 | python-versions = ">=3.5" 307 | files = [ 308 | {file = "idna-3.7-py3-none-any.whl", hash = "sha256:82fee1fc78add43492d3a1898bfa6d8a904cc97d8427f683ed8e798d07761aa0"}, 309 | {file = "idna-3.7.tar.gz", hash = "sha256:028ff3aadf0609c1fd278d8ea3089299412a7a8b9bd005dd08b9f8285bcb5cfc"}, 310 | ] 311 | 312 | [[package]] 313 | name = "ipadic" 314 | version = "1.0.0" 315 | description = "IPAdic packaged for Python" 316 | optional = false 317 | python-versions = "*" 318 | files = [ 319 | {file = "ipadic-1.0.0.tar.gz", hash = "sha256:f5923d31eca6131acaaf18ed28d8998665b1347b640d3a6476f64650e9a71c07"}, 320 | ] 321 | 322 | [[package]] 323 | name = "jinja2" 324 | version = "3.1.3" 325 | description = "A very fast and expressive template engine." 326 | optional = false 327 | python-versions = ">=3.7" 328 | files = [ 329 | {file = "Jinja2-3.1.3-py3-none-any.whl", hash = "sha256:7d6d50dd97d52cbc355597bd845fabfbac3f551e1f99619e39a35ce8c370b5fa"}, 330 | {file = "Jinja2-3.1.3.tar.gz", hash = "sha256:ac8bd6544d4bb2c9792bf3a159e80bba8fda7f07e81bc3aed565432d5925ba90"}, 331 | ] 332 | 333 | [package.dependencies] 334 | MarkupSafe = ">=2.0" 335 | 336 | [package.extras] 337 | i18n = ["Babel (>=2.7)"] 338 | 339 | [[package]] 340 | name = "joblib" 341 | version = "1.4.0" 342 | description = "Lightweight pipelining with Python functions" 343 | optional = false 344 | python-versions = ">=3.8" 345 | files = [ 346 | {file = "joblib-1.4.0-py3-none-any.whl", hash = "sha256:42942470d4062537be4d54c83511186da1fc14ba354961a2114da91efa9a4ed7"}, 347 | {file = "joblib-1.4.0.tar.gz", hash = "sha256:1eb0dc091919cd384490de890cb5dfd538410a6d4b3b54eef09fb8c50b409b1c"}, 348 | ] 349 | 350 | [[package]] 351 | name = "lit" 352 | version = "18.1.3" 353 | description = "A Software Testing Tool" 354 | optional = false 355 | python-versions = "*" 356 | files = [ 357 | {file = "lit-18.1.3-py3-none-any.whl", hash = "sha256:cd3632b8653a60324a3391b462c2f5782e1dbce387336498e6922b0c8ef93fba"}, 358 | {file = "lit-18.1.3.tar.gz", hash = "sha256:e44e81daecc060a550533e69cd0fb47d6a63bf1f9fed01be278465834cffa041"}, 359 | ] 360 | 361 | [[package]] 362 | name = "markupsafe" 363 | version = "2.1.5" 364 | description = "Safely add untrusted strings to HTML/XML markup." 365 | optional = false 366 | python-versions = ">=3.7" 367 | files = [ 368 | {file = "MarkupSafe-2.1.5-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:a17a92de5231666cfbe003f0e4b9b3a7ae3afb1ec2845aadc2bacc93ff85febc"}, 369 | {file = "MarkupSafe-2.1.5-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:72b6be590cc35924b02c78ef34b467da4ba07e4e0f0454a2c5907f473fc50ce5"}, 370 | {file = "MarkupSafe-2.1.5-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e61659ba32cf2cf1481e575d0462554625196a1f2fc06a1c777d3f48e8865d46"}, 371 | {file = "MarkupSafe-2.1.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2174c595a0d73a3080ca3257b40096db99799265e1c27cc5a610743acd86d62f"}, 372 | {file = "MarkupSafe-2.1.5-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ae2ad8ae6ebee9d2d94b17fb62763125f3f374c25618198f40cbb8b525411900"}, 373 | {file = "MarkupSafe-2.1.5-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:075202fa5b72c86ad32dc7d0b56024ebdbcf2048c0ba09f1cde31bfdd57bcfff"}, 374 | {file = "MarkupSafe-2.1.5-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:598e3276b64aff0e7b3451b72e94fa3c238d452e7ddcd893c3ab324717456bad"}, 375 | {file = "MarkupSafe-2.1.5-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:fce659a462a1be54d2ffcacea5e3ba2d74daa74f30f5f143fe0c58636e355fdd"}, 376 | {file = "MarkupSafe-2.1.5-cp310-cp310-win32.whl", hash = "sha256:d9fad5155d72433c921b782e58892377c44bd6252b5af2f67f16b194987338a4"}, 377 | {file = "MarkupSafe-2.1.5-cp310-cp310-win_amd64.whl", hash = "sha256:bf50cd79a75d181c9181df03572cdce0fbb75cc353bc350712073108cba98de5"}, 378 | {file = "MarkupSafe-2.1.5-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:629ddd2ca402ae6dbedfceeba9c46d5f7b2a61d9749597d4307f943ef198fc1f"}, 379 | {file = "MarkupSafe-2.1.5-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:5b7b716f97b52c5a14bffdf688f971b2d5ef4029127f1ad7a513973cfd818df2"}, 380 | {file = "MarkupSafe-2.1.5-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6ec585f69cec0aa07d945b20805be741395e28ac1627333b1c5b0105962ffced"}, 381 | {file = "MarkupSafe-2.1.5-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b91c037585eba9095565a3556f611e3cbfaa42ca1e865f7b8015fe5c7336d5a5"}, 382 | {file = "MarkupSafe-2.1.5-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7502934a33b54030eaf1194c21c692a534196063db72176b0c4028e140f8f32c"}, 383 | {file = "MarkupSafe-2.1.5-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:0e397ac966fdf721b2c528cf028494e86172b4feba51d65f81ffd65c63798f3f"}, 384 | {file = "MarkupSafe-2.1.5-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:c061bb86a71b42465156a3ee7bd58c8c2ceacdbeb95d05a99893e08b8467359a"}, 385 | {file = "MarkupSafe-2.1.5-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:3a57fdd7ce31c7ff06cdfbf31dafa96cc533c21e443d57f5b1ecc6cdc668ec7f"}, 386 | {file = "MarkupSafe-2.1.5-cp311-cp311-win32.whl", hash = "sha256:397081c1a0bfb5124355710fe79478cdbeb39626492b15d399526ae53422b906"}, 387 | {file = "MarkupSafe-2.1.5-cp311-cp311-win_amd64.whl", hash = "sha256:2b7c57a4dfc4f16f7142221afe5ba4e093e09e728ca65c51f5620c9aaeb9a617"}, 388 | {file = "MarkupSafe-2.1.5-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:8dec4936e9c3100156f8a2dc89c4b88d5c435175ff03413b443469c7c8c5f4d1"}, 389 | {file = "MarkupSafe-2.1.5-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:3c6b973f22eb18a789b1460b4b91bf04ae3f0c4234a0a6aa6b0a92f6f7b951d4"}, 390 | {file = "MarkupSafe-2.1.5-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ac07bad82163452a6884fe8fa0963fb98c2346ba78d779ec06bd7a6262132aee"}, 391 | {file = "MarkupSafe-2.1.5-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f5dfb42c4604dddc8e4305050aa6deb084540643ed5804d7455b5df8fe16f5e5"}, 392 | {file = "MarkupSafe-2.1.5-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ea3d8a3d18833cf4304cd2fc9cbb1efe188ca9b5efef2bdac7adc20594a0e46b"}, 393 | {file = "MarkupSafe-2.1.5-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:d050b3361367a06d752db6ead6e7edeb0009be66bc3bae0ee9d97fb326badc2a"}, 394 | {file = "MarkupSafe-2.1.5-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:bec0a414d016ac1a18862a519e54b2fd0fc8bbfd6890376898a6c0891dd82e9f"}, 395 | {file = "MarkupSafe-2.1.5-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:58c98fee265677f63a4385256a6d7683ab1832f3ddd1e66fe948d5880c21a169"}, 396 | {file = "MarkupSafe-2.1.5-cp312-cp312-win32.whl", hash = "sha256:8590b4ae07a35970728874632fed7bd57b26b0102df2d2b233b6d9d82f6c62ad"}, 397 | {file = "MarkupSafe-2.1.5-cp312-cp312-win_amd64.whl", hash = "sha256:823b65d8706e32ad2df51ed89496147a42a2a6e01c13cfb6ffb8b1e92bc910bb"}, 398 | {file = "MarkupSafe-2.1.5-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:c8b29db45f8fe46ad280a7294f5c3ec36dbac9491f2d1c17345be8e69cc5928f"}, 399 | {file = "MarkupSafe-2.1.5-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ec6a563cff360b50eed26f13adc43e61bc0c04d94b8be985e6fb24b81f6dcfdf"}, 400 | {file = "MarkupSafe-2.1.5-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a549b9c31bec33820e885335b451286e2969a2d9e24879f83fe904a5ce59d70a"}, 401 | {file = "MarkupSafe-2.1.5-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4f11aa001c540f62c6166c7726f71f7573b52c68c31f014c25cc7901deea0b52"}, 402 | {file = "MarkupSafe-2.1.5-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:7b2e5a267c855eea6b4283940daa6e88a285f5f2a67f2220203786dfa59b37e9"}, 403 | {file = "MarkupSafe-2.1.5-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:2d2d793e36e230fd32babe143b04cec8a8b3eb8a3122d2aceb4a371e6b09b8df"}, 404 | {file = "MarkupSafe-2.1.5-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:ce409136744f6521e39fd8e2a24c53fa18ad67aa5bc7c2cf83645cce5b5c4e50"}, 405 | {file = "MarkupSafe-2.1.5-cp37-cp37m-win32.whl", hash = "sha256:4096e9de5c6fdf43fb4f04c26fb114f61ef0bf2e5604b6ee3019d51b69e8c371"}, 406 | {file = "MarkupSafe-2.1.5-cp37-cp37m-win_amd64.whl", hash = "sha256:4275d846e41ecefa46e2015117a9f491e57a71ddd59bbead77e904dc02b1bed2"}, 407 | {file = "MarkupSafe-2.1.5-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:656f7526c69fac7f600bd1f400991cc282b417d17539a1b228617081106feb4a"}, 408 | {file = "MarkupSafe-2.1.5-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:97cafb1f3cbcd3fd2b6fbfb99ae11cdb14deea0736fc2b0952ee177f2b813a46"}, 409 | {file = "MarkupSafe-2.1.5-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1f3fbcb7ef1f16e48246f704ab79d79da8a46891e2da03f8783a5b6fa41a9532"}, 410 | {file = "MarkupSafe-2.1.5-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fa9db3f79de01457b03d4f01b34cf91bc0048eb2c3846ff26f66687c2f6d16ab"}, 411 | {file = "MarkupSafe-2.1.5-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ffee1f21e5ef0d712f9033568f8344d5da8cc2869dbd08d87c84656e6a2d2f68"}, 412 | {file = "MarkupSafe-2.1.5-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:5dedb4db619ba5a2787a94d877bc8ffc0566f92a01c0ef214865e54ecc9ee5e0"}, 413 | {file = "MarkupSafe-2.1.5-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:30b600cf0a7ac9234b2638fbc0fb6158ba5bdcdf46aeb631ead21248b9affbc4"}, 414 | {file = "MarkupSafe-2.1.5-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:8dd717634f5a044f860435c1d8c16a270ddf0ef8588d4887037c5028b859b0c3"}, 415 | {file = "MarkupSafe-2.1.5-cp38-cp38-win32.whl", hash = "sha256:daa4ee5a243f0f20d528d939d06670a298dd39b1ad5f8a72a4275124a7819eff"}, 416 | {file = "MarkupSafe-2.1.5-cp38-cp38-win_amd64.whl", hash = "sha256:619bc166c4f2de5caa5a633b8b7326fbe98e0ccbfacabd87268a2b15ff73a029"}, 417 | {file = "MarkupSafe-2.1.5-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:7a68b554d356a91cce1236aa7682dc01df0edba8d043fd1ce607c49dd3c1edcf"}, 418 | {file = "MarkupSafe-2.1.5-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:db0b55e0f3cc0be60c1f19efdde9a637c32740486004f20d1cff53c3c0ece4d2"}, 419 | {file = "MarkupSafe-2.1.5-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3e53af139f8579a6d5f7b76549125f0d94d7e630761a2111bc431fd820e163b8"}, 420 | {file = "MarkupSafe-2.1.5-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:17b950fccb810b3293638215058e432159d2b71005c74371d784862b7e4683f3"}, 421 | {file = "MarkupSafe-2.1.5-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4c31f53cdae6ecfa91a77820e8b151dba54ab528ba65dfd235c80b086d68a465"}, 422 | {file = "MarkupSafe-2.1.5-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:bff1b4290a66b490a2f4719358c0cdcd9bafb6b8f061e45c7a2460866bf50c2e"}, 423 | {file = "MarkupSafe-2.1.5-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:bc1667f8b83f48511b94671e0e441401371dfd0f0a795c7daa4a3cd1dde55bea"}, 424 | {file = "MarkupSafe-2.1.5-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:5049256f536511ee3f7e1b3f87d1d1209d327e818e6ae1365e8653d7e3abb6a6"}, 425 | {file = "MarkupSafe-2.1.5-cp39-cp39-win32.whl", hash = "sha256:00e046b6dd71aa03a41079792f8473dc494d564611a8f89bbbd7cb93295ebdcf"}, 426 | {file = "MarkupSafe-2.1.5-cp39-cp39-win_amd64.whl", hash = "sha256:fa173ec60341d6bb97a89f5ea19c85c5643c1e7dedebc22f5181eb73573142c5"}, 427 | {file = "MarkupSafe-2.1.5.tar.gz", hash = "sha256:d283d37a890ba4c1ae73ffadf8046435c76e7bc2247bbb63c00bd1a709c6544b"}, 428 | ] 429 | 430 | [[package]] 431 | name = "more-itertools" 432 | version = "9.1.0" 433 | description = "More routines for operating on iterables, beyond itertools" 434 | optional = false 435 | python-versions = ">=3.7" 436 | files = [ 437 | {file = "more-itertools-9.1.0.tar.gz", hash = "sha256:cabaa341ad0389ea83c17a94566a53ae4c9d07349861ecb14dc6d0345cf9ac5d"}, 438 | {file = "more_itertools-9.1.0-py3-none-any.whl", hash = "sha256:d2bc7f02446e86a68911e58ded76d6561eea00cddfb2a91e7019bbb586c799f3"}, 439 | ] 440 | 441 | [[package]] 442 | name = "mpmath" 443 | version = "1.3.0" 444 | description = "Python library for arbitrary-precision floating-point arithmetic" 445 | optional = false 446 | python-versions = "*" 447 | files = [ 448 | {file = "mpmath-1.3.0-py3-none-any.whl", hash = "sha256:a0b2b9fe80bbcd81a6647ff13108738cfb482d481d826cc0e02f5b35e5c88d2c"}, 449 | {file = "mpmath-1.3.0.tar.gz", hash = "sha256:7a28eb2a9774d00c7bc92411c19a89209d5da7c4c9a9e227be8330a23a25b91f"}, 450 | ] 451 | 452 | [package.extras] 453 | develop = ["codecov", "pycodestyle", "pytest (>=4.6)", "pytest-cov", "wheel"] 454 | docs = ["sphinx"] 455 | gmpy = ["gmpy2 (>=2.1.0a4)"] 456 | tests = ["pytest (>=4.6)"] 457 | 458 | [[package]] 459 | name = "mypy-extensions" 460 | version = "1.0.0" 461 | description = "Type system extensions for programs checked with the mypy type checker." 462 | optional = false 463 | python-versions = ">=3.5" 464 | files = [ 465 | {file = "mypy_extensions-1.0.0-py3-none-any.whl", hash = "sha256:4392f6c0eb8a5668a69e23d168ffa70f0be9ccfd32b5cc2d26a34ae5b844552d"}, 466 | {file = "mypy_extensions-1.0.0.tar.gz", hash = "sha256:75dbf8955dc00442a438fc4d0666508a9a97b6bd41aa2f0ffe9d2f2725af0782"}, 467 | ] 468 | 469 | [[package]] 470 | name = "networkx" 471 | version = "3.2.1" 472 | description = "Python package for creating and manipulating graphs and networks" 473 | optional = false 474 | python-versions = ">=3.9" 475 | files = [ 476 | {file = "networkx-3.2.1-py3-none-any.whl", hash = "sha256:f18c69adc97877c42332c170849c96cefa91881c99a7cb3e95b7c659ebdc1ec2"}, 477 | {file = "networkx-3.2.1.tar.gz", hash = "sha256:9f1bb5cf3409bf324e0a722c20bdb4c20ee39bf1c30ce8ae499c8502b0b5e0c6"}, 478 | ] 479 | 480 | [package.extras] 481 | default = ["matplotlib (>=3.5)", "numpy (>=1.22)", "pandas (>=1.4)", "scipy (>=1.9,!=1.11.0,!=1.11.1)"] 482 | developer = ["changelist (==0.4)", "mypy (>=1.1)", "pre-commit (>=3.2)", "rtoml"] 483 | doc = ["nb2plots (>=0.7)", "nbconvert (<7.9)", "numpydoc (>=1.6)", "pillow (>=9.4)", "pydata-sphinx-theme (>=0.14)", "sphinx (>=7)", "sphinx-gallery (>=0.14)", "texext (>=0.6.7)"] 484 | extra = ["lxml (>=4.6)", "pydot (>=1.4.2)", "pygraphviz (>=1.11)", "sympy (>=1.10)"] 485 | test = ["pytest (>=7.2)", "pytest-cov (>=4.0)"] 486 | 487 | [[package]] 488 | name = "numpy" 489 | version = "1.26.4" 490 | description = "Fundamental package for array computing in Python" 491 | optional = false 492 | python-versions = ">=3.9" 493 | files = [ 494 | {file = "numpy-1.26.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:9ff0f4f29c51e2803569d7a51c2304de5554655a60c5d776e35b4a41413830d0"}, 495 | {file = "numpy-1.26.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:2e4ee3380d6de9c9ec04745830fd9e2eccb3e6cf790d39d7b98ffd19b0dd754a"}, 496 | {file = "numpy-1.26.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d209d8969599b27ad20994c8e41936ee0964e6da07478d6c35016bc386b66ad4"}, 497 | {file = "numpy-1.26.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ffa75af20b44f8dba823498024771d5ac50620e6915abac414251bd971b4529f"}, 498 | {file = "numpy-1.26.4-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:62b8e4b1e28009ef2846b4c7852046736bab361f7aeadeb6a5b89ebec3c7055a"}, 499 | {file = "numpy-1.26.4-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:a4abb4f9001ad2858e7ac189089c42178fcce737e4169dc61321660f1a96c7d2"}, 500 | {file = "numpy-1.26.4-cp310-cp310-win32.whl", hash = "sha256:bfe25acf8b437eb2a8b2d49d443800a5f18508cd811fea3181723922a8a82b07"}, 501 | {file = "numpy-1.26.4-cp310-cp310-win_amd64.whl", hash = "sha256:b97fe8060236edf3662adfc2c633f56a08ae30560c56310562cb4f95500022d5"}, 502 | {file = "numpy-1.26.4-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:4c66707fabe114439db9068ee468c26bbdf909cac0fb58686a42a24de1760c71"}, 503 | {file = "numpy-1.26.4-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:edd8b5fe47dab091176d21bb6de568acdd906d1887a4584a15a9a96a1dca06ef"}, 504 | {file = "numpy-1.26.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7ab55401287bfec946ced39700c053796e7cc0e3acbef09993a9ad2adba6ca6e"}, 505 | {file = "numpy-1.26.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:666dbfb6ec68962c033a450943ded891bed2d54e6755e35e5835d63f4f6931d5"}, 506 | {file = "numpy-1.26.4-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:96ff0b2ad353d8f990b63294c8986f1ec3cb19d749234014f4e7eb0112ceba5a"}, 507 | {file = "numpy-1.26.4-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:60dedbb91afcbfdc9bc0b1f3f402804070deed7392c23eb7a7f07fa857868e8a"}, 508 | {file = "numpy-1.26.4-cp311-cp311-win32.whl", hash = "sha256:1af303d6b2210eb850fcf03064d364652b7120803a0b872f5211f5234b399f20"}, 509 | {file = "numpy-1.26.4-cp311-cp311-win_amd64.whl", hash = "sha256:cd25bcecc4974d09257ffcd1f098ee778f7834c3ad767fe5db785be9a4aa9cb2"}, 510 | {file = "numpy-1.26.4-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:b3ce300f3644fb06443ee2222c2201dd3a89ea6040541412b8fa189341847218"}, 511 | {file = "numpy-1.26.4-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:03a8c78d01d9781b28a6989f6fa1bb2c4f2d51201cf99d3dd875df6fbd96b23b"}, 512 | {file = "numpy-1.26.4-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9fad7dcb1aac3c7f0584a5a8133e3a43eeb2fe127f47e3632d43d677c66c102b"}, 513 | {file = "numpy-1.26.4-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:675d61ffbfa78604709862923189bad94014bef562cc35cf61d3a07bba02a7ed"}, 514 | {file = "numpy-1.26.4-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:ab47dbe5cc8210f55aa58e4805fe224dac469cde56b9f731a4c098b91917159a"}, 515 | {file = "numpy-1.26.4-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:1dda2e7b4ec9dd512f84935c5f126c8bd8b9f2fc001e9f54af255e8c5f16b0e0"}, 516 | {file = "numpy-1.26.4-cp312-cp312-win32.whl", hash = "sha256:50193e430acfc1346175fcbdaa28ffec49947a06918b7b92130744e81e640110"}, 517 | {file = "numpy-1.26.4-cp312-cp312-win_amd64.whl", hash = "sha256:08beddf13648eb95f8d867350f6a018a4be2e5ad54c8d8caed89ebca558b2818"}, 518 | {file = "numpy-1.26.4-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:7349ab0fa0c429c82442a27a9673fc802ffdb7c7775fad780226cb234965e53c"}, 519 | {file = "numpy-1.26.4-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:52b8b60467cd7dd1e9ed082188b4e6bb35aa5cdd01777621a1658910745b90be"}, 520 | {file = "numpy-1.26.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d5241e0a80d808d70546c697135da2c613f30e28251ff8307eb72ba696945764"}, 521 | {file = "numpy-1.26.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f870204a840a60da0b12273ef34f7051e98c3b5961b61b0c2c1be6dfd64fbcd3"}, 522 | {file = "numpy-1.26.4-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:679b0076f67ecc0138fd2ede3a8fd196dddc2ad3254069bcb9faf9a79b1cebcd"}, 523 | {file = "numpy-1.26.4-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:47711010ad8555514b434df65f7d7b076bb8261df1ca9bb78f53d3b2db02e95c"}, 524 | {file = "numpy-1.26.4-cp39-cp39-win32.whl", hash = "sha256:a354325ee03388678242a4d7ebcd08b5c727033fcff3b2f536aea978e15ee9e6"}, 525 | {file = "numpy-1.26.4-cp39-cp39-win_amd64.whl", hash = "sha256:3373d5d70a5fe74a2c1bb6d2cfd9609ecf686d47a2d7b1d37a8f3b6bf6003aea"}, 526 | {file = "numpy-1.26.4-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:afedb719a9dcfc7eaf2287b839d8198e06dcd4cb5d276a3df279231138e83d30"}, 527 | {file = "numpy-1.26.4-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:95a7476c59002f2f6c590b9b7b998306fba6a5aa646b1e22ddfeaf8f78c3a29c"}, 528 | {file = "numpy-1.26.4-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:7e50d0a0cc3189f9cb0aeb3a6a6af18c16f59f004b866cd2be1c14b36134a4a0"}, 529 | {file = "numpy-1.26.4.tar.gz", hash = "sha256:2a02aba9ed12e4ac4eb3ea9421c420301a0c6460d9830d74a9df87efa4912010"}, 530 | ] 531 | 532 | [[package]] 533 | name = "packaging" 534 | version = "24.0" 535 | description = "Core utilities for Python packages" 536 | optional = false 537 | python-versions = ">=3.7" 538 | files = [ 539 | {file = "packaging-24.0-py3-none-any.whl", hash = "sha256:2ddfb553fdf02fb784c234c7ba6ccc288296ceabec964ad2eae3777778130bc5"}, 540 | {file = "packaging-24.0.tar.gz", hash = "sha256:eb82c5e3e56209074766e6885bb04b8c38a0c015d0a30036ebe7ece34c9989e9"}, 541 | ] 542 | 543 | [[package]] 544 | name = "pandas" 545 | version = "2.2.2" 546 | description = "Powerful data structures for data analysis, time series, and statistics" 547 | optional = false 548 | python-versions = ">=3.9" 549 | files = [ 550 | {file = "pandas-2.2.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:90c6fca2acf139569e74e8781709dccb6fe25940488755716d1d354d6bc58bce"}, 551 | {file = "pandas-2.2.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:c7adfc142dac335d8c1e0dcbd37eb8617eac386596eb9e1a1b77791cf2498238"}, 552 | {file = "pandas-2.2.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4abfe0be0d7221be4f12552995e58723c7422c80a659da13ca382697de830c08"}, 553 | {file = "pandas-2.2.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8635c16bf3d99040fdf3ca3db669a7250ddf49c55dc4aa8fe0ae0fa8d6dcc1f0"}, 554 | {file = "pandas-2.2.2-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:40ae1dffb3967a52203105a077415a86044a2bea011b5f321c6aa64b379a3f51"}, 555 | {file = "pandas-2.2.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:8e5a0b00e1e56a842f922e7fae8ae4077aee4af0acb5ae3622bd4b4c30aedf99"}, 556 | {file = "pandas-2.2.2-cp310-cp310-win_amd64.whl", hash = "sha256:ddf818e4e6c7c6f4f7c8a12709696d193976b591cc7dc50588d3d1a6b5dc8772"}, 557 | {file = "pandas-2.2.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:696039430f7a562b74fa45f540aca068ea85fa34c244d0deee539cb6d70aa288"}, 558 | {file = "pandas-2.2.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:8e90497254aacacbc4ea6ae5e7a8cd75629d6ad2b30025a4a8b09aa4faf55151"}, 559 | {file = "pandas-2.2.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:58b84b91b0b9f4bafac2a0ac55002280c094dfc6402402332c0913a59654ab2b"}, 560 | {file = "pandas-2.2.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6d2123dc9ad6a814bcdea0f099885276b31b24f7edf40f6cdbc0912672e22eee"}, 561 | {file = "pandas-2.2.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:2925720037f06e89af896c70bca73459d7e6a4be96f9de79e2d440bd499fe0db"}, 562 | {file = "pandas-2.2.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:0cace394b6ea70c01ca1595f839cf193df35d1575986e484ad35c4aeae7266c1"}, 563 | {file = "pandas-2.2.2-cp311-cp311-win_amd64.whl", hash = "sha256:873d13d177501a28b2756375d59816c365e42ed8417b41665f346289adc68d24"}, 564 | {file = "pandas-2.2.2-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:9dfde2a0ddef507a631dc9dc4af6a9489d5e2e740e226ad426a05cabfbd7c8ef"}, 565 | {file = "pandas-2.2.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:e9b79011ff7a0f4b1d6da6a61aa1aa604fb312d6647de5bad20013682d1429ce"}, 566 | {file = "pandas-2.2.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1cb51fe389360f3b5a4d57dbd2848a5f033350336ca3b340d1c53a1fad33bcad"}, 567 | {file = "pandas-2.2.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:eee3a87076c0756de40b05c5e9a6069c035ba43e8dd71c379e68cab2c20f16ad"}, 568 | {file = "pandas-2.2.2-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:3e374f59e440d4ab45ca2fffde54b81ac3834cf5ae2cdfa69c90bc03bde04d76"}, 569 | {file = "pandas-2.2.2-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:43498c0bdb43d55cb162cdc8c06fac328ccb5d2eabe3cadeb3529ae6f0517c32"}, 570 | {file = "pandas-2.2.2-cp312-cp312-win_amd64.whl", hash = "sha256:d187d355ecec3629624fccb01d104da7d7f391db0311145817525281e2804d23"}, 571 | {file = "pandas-2.2.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:0ca6377b8fca51815f382bd0b697a0814c8bda55115678cbc94c30aacbb6eff2"}, 572 | {file = "pandas-2.2.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:9057e6aa78a584bc93a13f0a9bf7e753a5e9770a30b4d758b8d5f2a62a9433cd"}, 573 | {file = "pandas-2.2.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:001910ad31abc7bf06f49dcc903755d2f7f3a9186c0c040b827e522e9cef0863"}, 574 | {file = "pandas-2.2.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:66b479b0bd07204e37583c191535505410daa8df638fd8e75ae1b383851fe921"}, 575 | {file = "pandas-2.2.2-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:a77e9d1c386196879aa5eb712e77461aaee433e54c68cf253053a73b7e49c33a"}, 576 | {file = "pandas-2.2.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:92fd6b027924a7e178ac202cfbe25e53368db90d56872d20ffae94b96c7acc57"}, 577 | {file = "pandas-2.2.2-cp39-cp39-win_amd64.whl", hash = "sha256:640cef9aa381b60e296db324337a554aeeb883ead99dc8f6c18e81a93942f5f4"}, 578 | {file = "pandas-2.2.2.tar.gz", hash = "sha256:9e79019aba43cb4fda9e4d983f8e88ca0373adbb697ae9c6c43093218de28b54"}, 579 | ] 580 | 581 | [package.dependencies] 582 | numpy = {version = ">=1.22.4", markers = "python_version < \"3.11\""} 583 | python-dateutil = ">=2.8.2" 584 | pytz = ">=2020.1" 585 | tzdata = ">=2022.7" 586 | 587 | [package.extras] 588 | all = ["PyQt5 (>=5.15.9)", "SQLAlchemy (>=2.0.0)", "adbc-driver-postgresql (>=0.8.0)", "adbc-driver-sqlite (>=0.8.0)", "beautifulsoup4 (>=4.11.2)", "bottleneck (>=1.3.6)", "dataframe-api-compat (>=0.1.7)", "fastparquet (>=2022.12.0)", "fsspec (>=2022.11.0)", "gcsfs (>=2022.11.0)", "html5lib (>=1.1)", "hypothesis (>=6.46.1)", "jinja2 (>=3.1.2)", "lxml (>=4.9.2)", "matplotlib (>=3.6.3)", "numba (>=0.56.4)", "numexpr (>=2.8.4)", "odfpy (>=1.4.1)", "openpyxl (>=3.1.0)", "pandas-gbq (>=0.19.0)", "psycopg2 (>=2.9.6)", "pyarrow (>=10.0.1)", "pymysql (>=1.0.2)", "pyreadstat (>=1.2.0)", "pytest (>=7.3.2)", "pytest-xdist (>=2.2.0)", "python-calamine (>=0.1.7)", "pyxlsb (>=1.0.10)", "qtpy (>=2.3.0)", "s3fs (>=2022.11.0)", "scipy (>=1.10.0)", "tables (>=3.8.0)", "tabulate (>=0.9.0)", "xarray (>=2022.12.0)", "xlrd (>=2.0.1)", "xlsxwriter (>=3.0.5)", "zstandard (>=0.19.0)"] 589 | aws = ["s3fs (>=2022.11.0)"] 590 | clipboard = ["PyQt5 (>=5.15.9)", "qtpy (>=2.3.0)"] 591 | compression = ["zstandard (>=0.19.0)"] 592 | computation = ["scipy (>=1.10.0)", "xarray (>=2022.12.0)"] 593 | consortium-standard = ["dataframe-api-compat (>=0.1.7)"] 594 | excel = ["odfpy (>=1.4.1)", "openpyxl (>=3.1.0)", "python-calamine (>=0.1.7)", "pyxlsb (>=1.0.10)", "xlrd (>=2.0.1)", "xlsxwriter (>=3.0.5)"] 595 | feather = ["pyarrow (>=10.0.1)"] 596 | fss = ["fsspec (>=2022.11.0)"] 597 | gcp = ["gcsfs (>=2022.11.0)", "pandas-gbq (>=0.19.0)"] 598 | hdf5 = ["tables (>=3.8.0)"] 599 | html = ["beautifulsoup4 (>=4.11.2)", "html5lib (>=1.1)", "lxml (>=4.9.2)"] 600 | mysql = ["SQLAlchemy (>=2.0.0)", "pymysql (>=1.0.2)"] 601 | output-formatting = ["jinja2 (>=3.1.2)", "tabulate (>=0.9.0)"] 602 | parquet = ["pyarrow (>=10.0.1)"] 603 | performance = ["bottleneck (>=1.3.6)", "numba (>=0.56.4)", "numexpr (>=2.8.4)"] 604 | plot = ["matplotlib (>=3.6.3)"] 605 | postgresql = ["SQLAlchemy (>=2.0.0)", "adbc-driver-postgresql (>=0.8.0)", "psycopg2 (>=2.9.6)"] 606 | pyarrow = ["pyarrow (>=10.0.1)"] 607 | spss = ["pyreadstat (>=1.2.0)"] 608 | sql-other = ["SQLAlchemy (>=2.0.0)", "adbc-driver-postgresql (>=0.8.0)", "adbc-driver-sqlite (>=0.8.0)"] 609 | test = ["hypothesis (>=6.46.1)", "pytest (>=7.3.2)", "pytest-xdist (>=2.2.0)"] 610 | xml = ["lxml (>=4.9.2)"] 611 | 612 | [[package]] 613 | name = "plac" 614 | version = "1.4.3" 615 | description = "The smartest command line arguments parser in the world" 616 | optional = false 617 | python-versions = "*" 618 | files = [ 619 | {file = "plac-1.4.3-py2.py3-none-any.whl", hash = "sha256:8a84fde8f950c9de6588a2d53c9deeac3ba1ddb456d887a33228460cf6549750"}, 620 | {file = "plac-1.4.3.tar.gz", hash = "sha256:d4cb3387b2113a28aebd509433d0264a4e5d9bb7c1a86db4fbd0a8f11af74eb3"}, 621 | ] 622 | 623 | [[package]] 624 | name = "protobuf" 625 | version = "5.26.1" 626 | description = "" 627 | optional = false 628 | python-versions = ">=3.8" 629 | files = [ 630 | {file = "protobuf-5.26.1-cp310-abi3-win32.whl", hash = "sha256:3c388ea6ddfe735f8cf69e3f7dc7611e73107b60bdfcf5d0f024c3ccd3794e23"}, 631 | {file = "protobuf-5.26.1-cp310-abi3-win_amd64.whl", hash = "sha256:e6039957449cb918f331d32ffafa8eb9255769c96aa0560d9a5bf0b4e00a2a33"}, 632 | {file = "protobuf-5.26.1-cp37-abi3-macosx_10_9_universal2.whl", hash = "sha256:38aa5f535721d5bb99861166c445c4105c4e285c765fbb2ac10f116e32dcd46d"}, 633 | {file = "protobuf-5.26.1-cp37-abi3-manylinux2014_aarch64.whl", hash = "sha256:fbfe61e7ee8c1860855696e3ac6cfd1b01af5498facc6834fcc345c9684fb2ca"}, 634 | {file = "protobuf-5.26.1-cp37-abi3-manylinux2014_x86_64.whl", hash = "sha256:f7417703f841167e5a27d48be13389d52ad705ec09eade63dfc3180a959215d7"}, 635 | {file = "protobuf-5.26.1-cp38-cp38-win32.whl", hash = "sha256:d693d2504ca96750d92d9de8a103102dd648fda04540495535f0fec7577ed8fc"}, 636 | {file = "protobuf-5.26.1-cp38-cp38-win_amd64.whl", hash = "sha256:9b557c317ebe6836835ec4ef74ec3e994ad0894ea424314ad3552bc6e8835b4e"}, 637 | {file = "protobuf-5.26.1-cp39-cp39-win32.whl", hash = "sha256:b9ba3ca83c2e31219ffbeb9d76b63aad35a3eb1544170c55336993d7a18ae72c"}, 638 | {file = "protobuf-5.26.1-cp39-cp39-win_amd64.whl", hash = "sha256:7ee014c2c87582e101d6b54260af03b6596728505c79f17c8586e7523aaa8f8c"}, 639 | {file = "protobuf-5.26.1-py3-none-any.whl", hash = "sha256:da612f2720c0183417194eeaa2523215c4fcc1a1949772dc65f05047e08d5932"}, 640 | {file = "protobuf-5.26.1.tar.gz", hash = "sha256:8ca2a1d97c290ec7b16e4e5dff2e5ae150cc1582f55b5ab300d45cb0dfa90e51"}, 641 | ] 642 | 643 | [[package]] 644 | name = "python-dateutil" 645 | version = "2.9.0.post0" 646 | description = "Extensions to the standard Python datetime module" 647 | optional = false 648 | python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,>=2.7" 649 | files = [ 650 | {file = "python-dateutil-2.9.0.post0.tar.gz", hash = "sha256:37dd54208da7e1cd875388217d5e00ebd4179249f90fb72437e91a35459a0ad3"}, 651 | {file = "python_dateutil-2.9.0.post0-py2.py3-none-any.whl", hash = "sha256:a8b2bc7bffae282281c8140a97d3aa9c14da0b136dfe83f850eea9a5f7470427"}, 652 | ] 653 | 654 | [package.dependencies] 655 | six = ">=1.5" 656 | 657 | [[package]] 658 | name = "pytz" 659 | version = "2024.1" 660 | description = "World timezone definitions, modern and historical" 661 | optional = false 662 | python-versions = "*" 663 | files = [ 664 | {file = "pytz-2024.1-py2.py3-none-any.whl", hash = "sha256:328171f4e3623139da4983451950b28e95ac706e13f3f2630a879749e7a8b319"}, 665 | {file = "pytz-2024.1.tar.gz", hash = "sha256:2a29735ea9c18baf14b448846bde5a48030ed267578472d8955cd0e7443a9812"}, 666 | ] 667 | 668 | [[package]] 669 | name = "pyyaml" 670 | version = "6.0.1" 671 | description = "YAML parser and emitter for Python" 672 | optional = false 673 | python-versions = ">=3.6" 674 | files = [ 675 | {file = "PyYAML-6.0.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:d858aa552c999bc8a8d57426ed01e40bef403cd8ccdd0fc5f6f04a00414cac2a"}, 676 | {file = "PyYAML-6.0.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:fd66fc5d0da6d9815ba2cebeb4205f95818ff4b79c3ebe268e75d961704af52f"}, 677 | {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:69b023b2b4daa7548bcfbd4aa3da05b3a74b772db9e23b982788168117739938"}, 678 | {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:81e0b275a9ecc9c0c0c07b4b90ba548307583c125f54d5b6946cfee6360c733d"}, 679 | {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ba336e390cd8e4d1739f42dfe9bb83a3cc2e80f567d8805e11b46f4a943f5515"}, 680 | {file = "PyYAML-6.0.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:326c013efe8048858a6d312ddd31d56e468118ad4cdeda36c719bf5bb6192290"}, 681 | {file = "PyYAML-6.0.1-cp310-cp310-win32.whl", hash = "sha256:bd4af7373a854424dabd882decdc5579653d7868b8fb26dc7d0e99f823aa5924"}, 682 | {file = "PyYAML-6.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:fd1592b3fdf65fff2ad0004b5e363300ef59ced41c2e6b3a99d4089fa8c5435d"}, 683 | {file = "PyYAML-6.0.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:6965a7bc3cf88e5a1c3bd2e0b5c22f8d677dc88a455344035f03399034eb3007"}, 684 | {file = "PyYAML-6.0.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:f003ed9ad21d6a4713f0a9b5a7a0a79e08dd0f221aff4525a2be4c346ee60aab"}, 685 | {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:42f8152b8dbc4fe7d96729ec2b99c7097d656dc1213a3229ca5383f973a5ed6d"}, 686 | {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:062582fca9fabdd2c8b54a3ef1c978d786e0f6b3a1510e0ac93ef59e0ddae2bc"}, 687 | {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d2b04aac4d386b172d5b9692e2d2da8de7bfb6c387fa4f801fbf6fb2e6ba4673"}, 688 | {file = "PyYAML-6.0.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:e7d73685e87afe9f3b36c799222440d6cf362062f78be1013661b00c5c6f678b"}, 689 | {file = "PyYAML-6.0.1-cp311-cp311-win32.whl", hash = "sha256:1635fd110e8d85d55237ab316b5b011de701ea0f29d07611174a1b42f1444741"}, 690 | {file = "PyYAML-6.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:bf07ee2fef7014951eeb99f56f39c9bb4af143d8aa3c21b1677805985307da34"}, 691 | {file = "PyYAML-6.0.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:855fb52b0dc35af121542a76b9a84f8d1cd886ea97c84703eaa6d88e37a2ad28"}, 692 | {file = "PyYAML-6.0.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:40df9b996c2b73138957fe23a16a4f0ba614f4c0efce1e9406a184b6d07fa3a9"}, 693 | {file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a08c6f0fe150303c1c6b71ebcd7213c2858041a7e01975da3a99aed1e7a378ef"}, 694 | {file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c22bec3fbe2524cde73d7ada88f6566758a8f7227bfbf93a408a9d86bcc12a0"}, 695 | {file = "PyYAML-6.0.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8d4e9c88387b0f5c7d5f281e55304de64cf7f9c0021a3525bd3b1c542da3b0e4"}, 696 | {file = "PyYAML-6.0.1-cp312-cp312-win32.whl", hash = "sha256:d483d2cdf104e7c9fa60c544d92981f12ad66a457afae824d146093b8c294c54"}, 697 | {file = "PyYAML-6.0.1-cp312-cp312-win_amd64.whl", hash = "sha256:0d3304d8c0adc42be59c5f8a4d9e3d7379e6955ad754aa9d6ab7a398b59dd1df"}, 698 | {file = "PyYAML-6.0.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:50550eb667afee136e9a77d6dc71ae76a44df8b3e51e41b77f6de2932bfe0f47"}, 699 | {file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1fe35611261b29bd1de0070f0b2f47cb6ff71fa6595c077e42bd0c419fa27b98"}, 700 | {file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:704219a11b772aea0d8ecd7058d0082713c3562b4e271b849ad7dc4a5c90c13c"}, 701 | {file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:afd7e57eddb1a54f0f1a974bc4391af8bcce0b444685d936840f125cf046d5bd"}, 702 | {file = "PyYAML-6.0.1-cp36-cp36m-win32.whl", hash = "sha256:fca0e3a251908a499833aa292323f32437106001d436eca0e6e7833256674585"}, 703 | {file = "PyYAML-6.0.1-cp36-cp36m-win_amd64.whl", hash = "sha256:f22ac1c3cac4dbc50079e965eba2c1058622631e526bd9afd45fedd49ba781fa"}, 704 | {file = "PyYAML-6.0.1-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:b1275ad35a5d18c62a7220633c913e1b42d44b46ee12554e5fd39c70a243d6a3"}, 705 | {file = "PyYAML-6.0.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:18aeb1bf9a78867dc38b259769503436b7c72f7a1f1f4c93ff9a17de54319b27"}, 706 | {file = "PyYAML-6.0.1-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:596106435fa6ad000c2991a98fa58eeb8656ef2325d7e158344fb33864ed87e3"}, 707 | {file = "PyYAML-6.0.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:baa90d3f661d43131ca170712d903e6295d1f7a0f595074f151c0aed377c9b9c"}, 708 | {file = "PyYAML-6.0.1-cp37-cp37m-win32.whl", hash = "sha256:9046c58c4395dff28dd494285c82ba00b546adfc7ef001486fbf0324bc174fba"}, 709 | {file = "PyYAML-6.0.1-cp37-cp37m-win_amd64.whl", hash = "sha256:4fb147e7a67ef577a588a0e2c17b6db51dda102c71de36f8549b6816a96e1867"}, 710 | {file = "PyYAML-6.0.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:1d4c7e777c441b20e32f52bd377e0c409713e8bb1386e1099c2415f26e479595"}, 711 | {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a0cd17c15d3bb3fa06978b4e8958dcdc6e0174ccea823003a106c7d4d7899ac5"}, 712 | {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:28c119d996beec18c05208a8bd78cbe4007878c6dd15091efb73a30e90539696"}, 713 | {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7e07cbde391ba96ab58e532ff4803f79c4129397514e1413a7dc761ccd755735"}, 714 | {file = "PyYAML-6.0.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:49a183be227561de579b4a36efbb21b3eab9651dd81b1858589f796549873dd6"}, 715 | {file = "PyYAML-6.0.1-cp38-cp38-win32.whl", hash = "sha256:184c5108a2aca3c5b3d3bf9395d50893a7ab82a38004c8f61c258d4428e80206"}, 716 | {file = "PyYAML-6.0.1-cp38-cp38-win_amd64.whl", hash = "sha256:1e2722cc9fbb45d9b87631ac70924c11d3a401b2d7f410cc0e3bbf249f2dca62"}, 717 | {file = "PyYAML-6.0.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:9eb6caa9a297fc2c2fb8862bc5370d0303ddba53ba97e71f08023b6cd73d16a8"}, 718 | {file = "PyYAML-6.0.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:c8098ddcc2a85b61647b2590f825f3db38891662cfc2fc776415143f599bb859"}, 719 | {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5773183b6446b2c99bb77e77595dd486303b4faab2b086e7b17bc6bef28865f6"}, 720 | {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b786eecbdf8499b9ca1d697215862083bd6d2a99965554781d0d8d1ad31e13a0"}, 721 | {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bc1bf2925a1ecd43da378f4db9e4f799775d6367bdb94671027b73b393a7c42c"}, 722 | {file = "PyYAML-6.0.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:04ac92ad1925b2cff1db0cfebffb6ffc43457495c9b3c39d3fcae417d7125dc5"}, 723 | {file = "PyYAML-6.0.1-cp39-cp39-win32.whl", hash = "sha256:faca3bdcf85b2fc05d06ff3fbc1f83e1391b3e724afa3feba7d13eeab355484c"}, 724 | {file = "PyYAML-6.0.1-cp39-cp39-win_amd64.whl", hash = "sha256:510c9deebc5c0225e8c96813043e62b680ba2f9c50a08d3724c7f28a747d1486"}, 725 | {file = "PyYAML-6.0.1.tar.gz", hash = "sha256:bfdf460b1736c775f2ba9f6a92bca30bc2095067b8a9d77876d1fad6cc3b4a43"}, 726 | ] 727 | 728 | [[package]] 729 | name = "regex" 730 | version = "2024.4.16" 731 | description = "Alternative regular expression module, to replace re." 732 | optional = false 733 | python-versions = ">=3.7" 734 | files = [ 735 | {file = "regex-2024.4.16-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:fb83cc090eac63c006871fd24db5e30a1f282faa46328572661c0a24a2323a08"}, 736 | {file = "regex-2024.4.16-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:8c91e1763696c0eb66340c4df98623c2d4e77d0746b8f8f2bee2c6883fd1fe18"}, 737 | {file = "regex-2024.4.16-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:10188fe732dec829c7acca7422cdd1bf57d853c7199d5a9e96bb4d40db239c73"}, 738 | {file = "regex-2024.4.16-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:956b58d692f235cfbf5b4f3abd6d99bf102f161ccfe20d2fd0904f51c72c4c66"}, 739 | {file = "regex-2024.4.16-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a70b51f55fd954d1f194271695821dd62054d949efd6368d8be64edd37f55c86"}, 740 | {file = "regex-2024.4.16-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:5c02fcd2bf45162280613d2e4a1ca3ac558ff921ae4e308ecb307650d3a6ee51"}, 741 | {file = "regex-2024.4.16-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c4ed75ea6892a56896d78f11006161eea52c45a14994794bcfa1654430984b22"}, 742 | {file = "regex-2024.4.16-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:bd727ad276bb91928879f3aa6396c9a1d34e5e180dce40578421a691eeb77f47"}, 743 | {file = "regex-2024.4.16-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:7cbc5d9e8a1781e7be17da67b92580d6ce4dcef5819c1b1b89f49d9678cc278c"}, 744 | {file = "regex-2024.4.16-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:78fddb22b9ef810b63ef341c9fcf6455232d97cfe03938cbc29e2672c436670e"}, 745 | {file = "regex-2024.4.16-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:445ca8d3c5a01309633a0c9db57150312a181146315693273e35d936472df912"}, 746 | {file = "regex-2024.4.16-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:95399831a206211d6bc40224af1c635cb8790ddd5c7493e0bd03b85711076a53"}, 747 | {file = "regex-2024.4.16-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:7731728b6568fc286d86745f27f07266de49603a6fdc4d19c87e8c247be452af"}, 748 | {file = "regex-2024.4.16-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:4facc913e10bdba42ec0aee76d029aedda628161a7ce4116b16680a0413f658a"}, 749 | {file = "regex-2024.4.16-cp310-cp310-win32.whl", hash = "sha256:911742856ce98d879acbea33fcc03c1d8dc1106234c5e7d068932c945db209c0"}, 750 | {file = "regex-2024.4.16-cp310-cp310-win_amd64.whl", hash = "sha256:e0a2df336d1135a0b3a67f3bbf78a75f69562c1199ed9935372b82215cddd6e2"}, 751 | {file = "regex-2024.4.16-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:1210365faba7c2150451eb78ec5687871c796b0f1fa701bfd2a4a25420482d26"}, 752 | {file = "regex-2024.4.16-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:9ab40412f8cd6f615bfedea40c8bf0407d41bf83b96f6fc9ff34976d6b7037fd"}, 753 | {file = "regex-2024.4.16-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:fd80d1280d473500d8086d104962a82d77bfbf2b118053824b7be28cd5a79ea5"}, 754 | {file = "regex-2024.4.16-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7bb966fdd9217e53abf824f437a5a2d643a38d4fd5fd0ca711b9da683d452969"}, 755 | {file = "regex-2024.4.16-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:20b7a68444f536365af42a75ccecb7ab41a896a04acf58432db9e206f4e525d6"}, 756 | {file = "regex-2024.4.16-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b74586dd0b039c62416034f811d7ee62810174bb70dffcca6439f5236249eb09"}, 757 | {file = "regex-2024.4.16-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0c8290b44d8b0af4e77048646c10c6e3aa583c1ca67f3b5ffb6e06cf0c6f0f89"}, 758 | {file = "regex-2024.4.16-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f2d80a6749724b37853ece57988b39c4e79d2b5fe2869a86e8aeae3bbeef9eb0"}, 759 | {file = "regex-2024.4.16-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:3a1018e97aeb24e4f939afcd88211ace472ba566efc5bdf53fd8fd7f41fa7170"}, 760 | {file = "regex-2024.4.16-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:8d015604ee6204e76569d2f44e5a210728fa917115bef0d102f4107e622b08d5"}, 761 | {file = "regex-2024.4.16-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:3d5ac5234fb5053850d79dd8eb1015cb0d7d9ed951fa37aa9e6249a19aa4f336"}, 762 | {file = "regex-2024.4.16-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:0a38d151e2cdd66d16dab550c22f9521ba79761423b87c01dae0a6e9add79c0d"}, 763 | {file = "regex-2024.4.16-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:159dc4e59a159cb8e4e8f8961eb1fa5d58f93cb1acd1701d8aff38d45e1a84a6"}, 764 | {file = "regex-2024.4.16-cp311-cp311-win32.whl", hash = "sha256:ba2336d6548dee3117520545cfe44dc28a250aa091f8281d28804aa8d707d93d"}, 765 | {file = "regex-2024.4.16-cp311-cp311-win_amd64.whl", hash = "sha256:8f83b6fd3dc3ba94d2b22717f9c8b8512354fd95221ac661784df2769ea9bba9"}, 766 | {file = "regex-2024.4.16-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:80b696e8972b81edf0af2a259e1b2a4a661f818fae22e5fa4fa1a995fb4a40fd"}, 767 | {file = "regex-2024.4.16-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:d61ae114d2a2311f61d90c2ef1358518e8f05eafda76eaf9c772a077e0b465ec"}, 768 | {file = "regex-2024.4.16-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:8ba6745440b9a27336443b0c285d705ce73adb9ec90e2f2004c64d95ab5a7598"}, 769 | {file = "regex-2024.4.16-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6295004b2dd37b0835ea5c14a33e00e8cfa3c4add4d587b77287825f3418d310"}, 770 | {file = "regex-2024.4.16-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4aba818dcc7263852aabb172ec27b71d2abca02a593b95fa79351b2774eb1d2b"}, 771 | {file = "regex-2024.4.16-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d0800631e565c47520aaa04ae38b96abc5196fe8b4aa9bd864445bd2b5848a7a"}, 772 | {file = "regex-2024.4.16-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:08dea89f859c3df48a440dbdcd7b7155bc675f2fa2ec8c521d02dc69e877db70"}, 773 | {file = "regex-2024.4.16-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:eeaa0b5328b785abc344acc6241cffde50dc394a0644a968add75fcefe15b9d4"}, 774 | {file = "regex-2024.4.16-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:4e819a806420bc010489f4e741b3036071aba209f2e0989d4750b08b12a9343f"}, 775 | {file = "regex-2024.4.16-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:c2d0e7cbb6341e830adcbfa2479fdeebbfbb328f11edd6b5675674e7a1e37730"}, 776 | {file = "regex-2024.4.16-cp312-cp312-musllinux_1_1_ppc64le.whl", hash = "sha256:91797b98f5e34b6a49f54be33f72e2fb658018ae532be2f79f7c63b4ae225145"}, 777 | {file = "regex-2024.4.16-cp312-cp312-musllinux_1_1_s390x.whl", hash = "sha256:d2da13568eff02b30fd54fccd1e042a70fe920d816616fda4bf54ec705668d81"}, 778 | {file = "regex-2024.4.16-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:370c68dc5570b394cbaadff50e64d705f64debed30573e5c313c360689b6aadc"}, 779 | {file = "regex-2024.4.16-cp312-cp312-win32.whl", hash = "sha256:904c883cf10a975b02ab3478bce652f0f5346a2c28d0a8521d97bb23c323cc8b"}, 780 | {file = "regex-2024.4.16-cp312-cp312-win_amd64.whl", hash = "sha256:785c071c982dce54d44ea0b79cd6dfafddeccdd98cfa5f7b86ef69b381b457d9"}, 781 | {file = "regex-2024.4.16-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:e2f142b45c6fed48166faeb4303b4b58c9fcd827da63f4cf0a123c3480ae11fb"}, 782 | {file = "regex-2024.4.16-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e87ab229332ceb127a165612d839ab87795972102cb9830e5f12b8c9a5c1b508"}, 783 | {file = "regex-2024.4.16-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:81500ed5af2090b4a9157a59dbc89873a25c33db1bb9a8cf123837dcc9765047"}, 784 | {file = "regex-2024.4.16-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b340cccad138ecb363324aa26893963dcabb02bb25e440ebdf42e30963f1a4e0"}, 785 | {file = "regex-2024.4.16-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2c72608e70f053643437bd2be0608f7f1c46d4022e4104d76826f0839199347a"}, 786 | {file = "regex-2024.4.16-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a01fe2305e6232ef3e8f40bfc0f0f3a04def9aab514910fa4203bafbc0bb4682"}, 787 | {file = "regex-2024.4.16-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:03576e3a423d19dda13e55598f0fd507b5d660d42c51b02df4e0d97824fdcae3"}, 788 | {file = "regex-2024.4.16-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:549c3584993772e25f02d0656ac48abdda73169fe347263948cf2b1cead622f3"}, 789 | {file = "regex-2024.4.16-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:34422d5a69a60b7e9a07a690094e824b66f5ddc662a5fc600d65b7c174a05f04"}, 790 | {file = "regex-2024.4.16-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:5f580c651a72b75c39e311343fe6875d6f58cf51c471a97f15a938d9fe4e0d37"}, 791 | {file = "regex-2024.4.16-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:3399dd8a7495bbb2bacd59b84840eef9057826c664472e86c91d675d007137f5"}, 792 | {file = "regex-2024.4.16-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:8d1f86f3f4e2388aa3310b50694ac44daefbd1681def26b4519bd050a398dc5a"}, 793 | {file = "regex-2024.4.16-cp37-cp37m-win32.whl", hash = "sha256:dd5acc0a7d38fdc7a3a6fd3ad14c880819008ecb3379626e56b163165162cc46"}, 794 | {file = "regex-2024.4.16-cp37-cp37m-win_amd64.whl", hash = "sha256:ba8122e3bb94ecda29a8de4cf889f600171424ea586847aa92c334772d200331"}, 795 | {file = "regex-2024.4.16-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:743deffdf3b3481da32e8a96887e2aa945ec6685af1cfe2bcc292638c9ba2f48"}, 796 | {file = "regex-2024.4.16-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:7571f19f4a3fd00af9341c7801d1ad1967fc9c3f5e62402683047e7166b9f2b4"}, 797 | {file = "regex-2024.4.16-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:df79012ebf6f4efb8d307b1328226aef24ca446b3ff8d0e30202d7ebcb977a8c"}, 798 | {file = "regex-2024.4.16-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e757d475953269fbf4b441207bb7dbdd1c43180711b6208e129b637792ac0b93"}, 799 | {file = "regex-2024.4.16-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4313ab9bf6a81206c8ac28fdfcddc0435299dc88cad12cc6305fd0e78b81f9e4"}, 800 | {file = "regex-2024.4.16-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d83c2bc678453646f1a18f8db1e927a2d3f4935031b9ad8a76e56760461105dd"}, 801 | {file = "regex-2024.4.16-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9df1bfef97db938469ef0a7354b2d591a2d438bc497b2c489471bec0e6baf7c4"}, 802 | {file = "regex-2024.4.16-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:62120ed0de69b3649cc68e2965376048793f466c5a6c4370fb27c16c1beac22d"}, 803 | {file = "regex-2024.4.16-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:c2ef6f7990b6e8758fe48ad08f7e2f66c8f11dc66e24093304b87cae9037bb4a"}, 804 | {file = "regex-2024.4.16-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:8fc6976a3395fe4d1fbeb984adaa8ec652a1e12f36b56ec8c236e5117b585427"}, 805 | {file = "regex-2024.4.16-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:03e68f44340528111067cecf12721c3df4811c67268b897fbe695c95f860ac42"}, 806 | {file = "regex-2024.4.16-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:ec7e0043b91115f427998febaa2beb82c82df708168b35ece3accb610b91fac1"}, 807 | {file = "regex-2024.4.16-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:c21fc21a4c7480479d12fd8e679b699f744f76bb05f53a1d14182b31f55aac76"}, 808 | {file = "regex-2024.4.16-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:12f6a3f2f58bb7344751919a1876ee1b976fe08b9ffccb4bbea66f26af6017b9"}, 809 | {file = "regex-2024.4.16-cp38-cp38-win32.whl", hash = "sha256:479595a4fbe9ed8f8f72c59717e8cf222da2e4c07b6ae5b65411e6302af9708e"}, 810 | {file = "regex-2024.4.16-cp38-cp38-win_amd64.whl", hash = "sha256:0534b034fba6101611968fae8e856c1698da97ce2efb5c2b895fc8b9e23a5834"}, 811 | {file = "regex-2024.4.16-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:a7ccdd1c4a3472a7533b0a7aa9ee34c9a2bef859ba86deec07aff2ad7e0c3b94"}, 812 | {file = "regex-2024.4.16-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:6f2f017c5be19984fbbf55f8af6caba25e62c71293213f044da3ada7091a4455"}, 813 | {file = "regex-2024.4.16-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:803b8905b52de78b173d3c1e83df0efb929621e7b7c5766c0843704d5332682f"}, 814 | {file = "regex-2024.4.16-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:684008ec44ad275832a5a152f6e764bbe1914bea10968017b6feaecdad5736e0"}, 815 | {file = "regex-2024.4.16-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:65436dce9fdc0aeeb0a0effe0839cb3d6a05f45aa45a4d9f9c60989beca78b9c"}, 816 | {file = "regex-2024.4.16-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:ea355eb43b11764cf799dda62c658c4d2fdb16af41f59bb1ccfec517b60bcb07"}, 817 | {file = "regex-2024.4.16-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:98c1165f3809ce7774f05cb74e5408cd3aa93ee8573ae959a97a53db3ca3180d"}, 818 | {file = "regex-2024.4.16-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:cccc79a9be9b64c881f18305a7c715ba199e471a3973faeb7ba84172abb3f317"}, 819 | {file = "regex-2024.4.16-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:00169caa125f35d1bca6045d65a662af0202704489fada95346cfa092ec23f39"}, 820 | {file = "regex-2024.4.16-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:6cc38067209354e16c5609b66285af17a2863a47585bcf75285cab33d4c3b8df"}, 821 | {file = "regex-2024.4.16-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:23cff1b267038501b179ccbbd74a821ac4a7192a1852d1d558e562b507d46013"}, 822 | {file = "regex-2024.4.16-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:b9d320b3bf82a39f248769fc7f188e00f93526cc0fe739cfa197868633d44701"}, 823 | {file = "regex-2024.4.16-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:89ec7f2c08937421bbbb8b48c54096fa4f88347946d4747021ad85f1b3021b3c"}, 824 | {file = "regex-2024.4.16-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:4918fd5f8b43aa7ec031e0fef1ee02deb80b6afd49c85f0790be1dc4ce34cb50"}, 825 | {file = "regex-2024.4.16-cp39-cp39-win32.whl", hash = "sha256:684e52023aec43bdf0250e843e1fdd6febbe831bd9d52da72333fa201aaa2335"}, 826 | {file = "regex-2024.4.16-cp39-cp39-win_amd64.whl", hash = "sha256:e697e1c0238133589e00c244a8b676bc2cfc3ab4961318d902040d099fec7483"}, 827 | {file = "regex-2024.4.16.tar.gz", hash = "sha256:fa454d26f2e87ad661c4f0c5a5fe4cf6aab1e307d1b94f16ffdfcb089ba685c0"}, 828 | ] 829 | 830 | [[package]] 831 | name = "requests" 832 | version = "2.31.0" 833 | description = "Python HTTP for Humans." 834 | optional = false 835 | python-versions = ">=3.7" 836 | files = [ 837 | {file = "requests-2.31.0-py3-none-any.whl", hash = "sha256:58cd2187c01e70e6e26505bca751777aa9f2ee0b7f4300988b709f44e013003f"}, 838 | {file = "requests-2.31.0.tar.gz", hash = "sha256:942c5a758f98d790eaed1a29cb6eefc7ffb0d1cf7af05c3d2791656dbd6ad1e1"}, 839 | ] 840 | 841 | [package.dependencies] 842 | certifi = ">=2017.4.17" 843 | charset-normalizer = ">=2,<4" 844 | idna = ">=2.5,<4" 845 | urllib3 = ">=1.21.1,<3" 846 | 847 | [package.extras] 848 | socks = ["PySocks (>=1.5.6,!=1.5.7)"] 849 | use-chardet-on-py3 = ["chardet (>=3.0.2,<6)"] 850 | 851 | [[package]] 852 | name = "rhoknp" 853 | version = "1.3.0" 854 | description = "Yet another Python binding for Juman++/KNP/KWJA" 855 | optional = false 856 | python-versions = ">=3.7,<4.0" 857 | files = [ 858 | {file = "rhoknp-1.3.0-py3-none-any.whl", hash = "sha256:41ee79bbd25e8e1142d555a2e714356fd810b9bf9bb610c75b3bcb704c37ac00"}, 859 | {file = "rhoknp-1.3.0.tar.gz", hash = "sha256:ccbac0bba6662b00a573f2d0361e64978901202c44c56b50b3ce2afa5dbb23b6"}, 860 | ] 861 | 862 | [package.extras] 863 | cli = ["PyYAML (>=6.0,<7.0)", "fastapi (>=0.92.0,<1)", "jinja2 (>=3.1.2,<4.0.0)", "rich (>=12.6)", "typer (>=0.6.1,<0.8)", "uvicorn (>=0.21.0,<1)"] 864 | 865 | [[package]] 866 | name = "safetensors" 867 | version = "0.4.3" 868 | description = "" 869 | optional = false 870 | python-versions = ">=3.7" 871 | files = [ 872 | {file = "safetensors-0.4.3-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:dcf5705cab159ce0130cd56057f5f3425023c407e170bca60b4868048bae64fd"}, 873 | {file = "safetensors-0.4.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:bb4f8c5d0358a31e9a08daeebb68f5e161cdd4018855426d3f0c23bb51087055"}, 874 | {file = "safetensors-0.4.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:70a5319ef409e7f88686a46607cbc3c428271069d8b770076feaf913664a07ac"}, 875 | {file = "safetensors-0.4.3-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:fb9c65bd82f9ef3ce4970dc19ee86be5f6f93d032159acf35e663c6bea02b237"}, 876 | {file = "safetensors-0.4.3-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:edb5698a7bc282089f64c96c477846950358a46ede85a1c040e0230344fdde10"}, 877 | {file = "safetensors-0.4.3-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:efcc860be094b8d19ac61b452ec635c7acb9afa77beb218b1d7784c6d41fe8ad"}, 878 | {file = "safetensors-0.4.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d88b33980222085dd6001ae2cad87c6068e0991d4f5ccf44975d216db3b57376"}, 879 | {file = "safetensors-0.4.3-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:5fc6775529fb9f0ce2266edd3e5d3f10aab068e49f765e11f6f2a63b5367021d"}, 880 | {file = "safetensors-0.4.3-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:9c6ad011c1b4e3acff058d6b090f1da8e55a332fbf84695cf3100c649cc452d1"}, 881 | {file = "safetensors-0.4.3-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:8c496c5401c1b9c46d41a7688e8ff5b0310a3b9bae31ce0f0ae870e1ea2b8caf"}, 882 | {file = "safetensors-0.4.3-cp310-none-win32.whl", hash = "sha256:38e2a8666178224a51cca61d3cb4c88704f696eac8f72a49a598a93bbd8a4af9"}, 883 | {file = "safetensors-0.4.3-cp310-none-win_amd64.whl", hash = "sha256:393e6e391467d1b2b829c77e47d726f3b9b93630e6a045b1d1fca67dc78bf632"}, 884 | {file = "safetensors-0.4.3-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:22f3b5d65e440cec0de8edaa672efa888030802e11c09b3d6203bff60ebff05a"}, 885 | {file = "safetensors-0.4.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:7c4fa560ebd4522adddb71dcd25d09bf211b5634003f015a4b815b7647d62ebe"}, 886 | {file = "safetensors-0.4.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e9afd5358719f1b2cf425fad638fc3c887997d6782da317096877e5b15b2ce93"}, 887 | {file = "safetensors-0.4.3-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:d8c5093206ef4b198600ae484230402af6713dab1bd5b8e231905d754022bec7"}, 888 | {file = "safetensors-0.4.3-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e0b2104df1579d6ba9052c0ae0e3137c9698b2d85b0645507e6fd1813b70931a"}, 889 | {file = "safetensors-0.4.3-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8cf18888606dad030455d18f6c381720e57fc6a4170ee1966adb7ebc98d4d6a3"}, 890 | {file = "safetensors-0.4.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0bf4f9d6323d9f86eef5567eabd88f070691cf031d4c0df27a40d3b4aaee755b"}, 891 | {file = "safetensors-0.4.3-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:585c9ae13a205807b63bef8a37994f30c917ff800ab8a1ca9c9b5d73024f97ee"}, 892 | {file = "safetensors-0.4.3-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:faefeb3b81bdfb4e5a55b9bbdf3d8d8753f65506e1d67d03f5c851a6c87150e9"}, 893 | {file = "safetensors-0.4.3-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:befdf0167ad626f22f6aac6163477fcefa342224a22f11fdd05abb3995c1783c"}, 894 | {file = "safetensors-0.4.3-cp311-none-win32.whl", hash = "sha256:a7cef55929dcbef24af3eb40bedec35d82c3c2fa46338bb13ecf3c5720af8a61"}, 895 | {file = "safetensors-0.4.3-cp311-none-win_amd64.whl", hash = "sha256:840b7ac0eff5633e1d053cc9db12fdf56b566e9403b4950b2dc85393d9b88d67"}, 896 | {file = "safetensors-0.4.3-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:22d21760dc6ebae42e9c058d75aa9907d9f35e38f896e3c69ba0e7b213033856"}, 897 | {file = "safetensors-0.4.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:8d22c1a10dff3f64d0d68abb8298a3fd88ccff79f408a3e15b3e7f637ef5c980"}, 898 | {file = "safetensors-0.4.3-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b1648568667f820b8c48317c7006221dc40aced1869908c187f493838a1362bc"}, 899 | {file = "safetensors-0.4.3-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:446e9fe52c051aeab12aac63d1017e0f68a02a92a027b901c4f8e931b24e5397"}, 900 | {file = "safetensors-0.4.3-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:fef5d70683643618244a4f5221053567ca3e77c2531e42ad48ae05fae909f542"}, 901 | {file = "safetensors-0.4.3-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2a1f4430cc0c9d6afa01214a4b3919d0a029637df8e09675ceef1ca3f0dfa0df"}, 902 | {file = "safetensors-0.4.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2d603846a8585b9432a0fd415db1d4c57c0f860eb4aea21f92559ff9902bae4d"}, 903 | {file = "safetensors-0.4.3-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:a844cdb5d7cbc22f5f16c7e2a0271170750763c4db08381b7f696dbd2c78a361"}, 904 | {file = "safetensors-0.4.3-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:88887f69f7a00cf02b954cdc3034ffb383b2303bc0ab481d4716e2da51ddc10e"}, 905 | {file = "safetensors-0.4.3-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:ee463219d9ec6c2be1d331ab13a8e0cd50d2f32240a81d498266d77d07b7e71e"}, 906 | {file = "safetensors-0.4.3-cp312-none-win32.whl", hash = "sha256:d0dd4a1db09db2dba0f94d15addc7e7cd3a7b0d393aa4c7518c39ae7374623c3"}, 907 | {file = "safetensors-0.4.3-cp312-none-win_amd64.whl", hash = "sha256:d14d30c25897b2bf19b6fb5ff7e26cc40006ad53fd4a88244fdf26517d852dd7"}, 908 | {file = "safetensors-0.4.3-cp37-cp37m-macosx_10_12_x86_64.whl", hash = "sha256:d1456f814655b224d4bf6e7915c51ce74e389b413be791203092b7ff78c936dd"}, 909 | {file = "safetensors-0.4.3-cp37-cp37m-macosx_11_0_arm64.whl", hash = "sha256:455d538aa1aae4a8b279344a08136d3f16334247907b18a5c3c7fa88ef0d3c46"}, 910 | {file = "safetensors-0.4.3-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cf476bca34e1340ee3294ef13e2c625833f83d096cfdf69a5342475602004f95"}, 911 | {file = "safetensors-0.4.3-cp37-cp37m-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:02ef3a24face643456020536591fbd3c717c5abaa2737ec428ccbbc86dffa7a4"}, 912 | {file = "safetensors-0.4.3-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:7de32d0d34b6623bb56ca278f90db081f85fb9c5d327e3c18fd23ac64f465768"}, 913 | {file = "safetensors-0.4.3-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2a0deb16a1d3ea90c244ceb42d2c6c276059616be21a19ac7101aa97da448faf"}, 914 | {file = "safetensors-0.4.3-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c59d51f182c729f47e841510b70b967b0752039f79f1de23bcdd86462a9b09ee"}, 915 | {file = "safetensors-0.4.3-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:1f598b713cc1a4eb31d3b3203557ac308acf21c8f41104cdd74bf640c6e538e3"}, 916 | {file = "safetensors-0.4.3-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:5757e4688f20df083e233b47de43845d1adb7e17b6cf7da5f8444416fc53828d"}, 917 | {file = "safetensors-0.4.3-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:fe746d03ed8d193674a26105e4f0fe6c726f5bb602ffc695b409eaf02f04763d"}, 918 | {file = "safetensors-0.4.3-cp37-none-win32.whl", hash = "sha256:0d5ffc6a80f715c30af253e0e288ad1cd97a3d0086c9c87995e5093ebc075e50"}, 919 | {file = "safetensors-0.4.3-cp37-none-win_amd64.whl", hash = "sha256:a11c374eb63a9c16c5ed146457241182f310902bd2a9c18255781bb832b6748b"}, 920 | {file = "safetensors-0.4.3-cp38-cp38-macosx_10_12_x86_64.whl", hash = "sha256:b1e31be7945f66be23f4ec1682bb47faa3df34cb89fc68527de6554d3c4258a4"}, 921 | {file = "safetensors-0.4.3-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:03a4447c784917c9bf01d8f2ac5080bc15c41692202cd5f406afba16629e84d6"}, 922 | {file = "safetensors-0.4.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d244bcafeb1bc06d47cfee71727e775bca88a8efda77a13e7306aae3813fa7e4"}, 923 | {file = "safetensors-0.4.3-cp38-cp38-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:53c4879b9c6bd7cd25d114ee0ef95420e2812e676314300624594940a8d6a91f"}, 924 | {file = "safetensors-0.4.3-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:74707624b81f1b7f2b93f5619d4a9f00934d5948005a03f2c1845ffbfff42212"}, 925 | {file = "safetensors-0.4.3-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:0d52c958dc210265157573f81d34adf54e255bc2b59ded6218500c9b15a750eb"}, 926 | {file = "safetensors-0.4.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6f9568f380f513a60139971169c4a358b8731509cc19112369902eddb33faa4d"}, 927 | {file = "safetensors-0.4.3-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:0d9cd8e1560dfc514b6d7859247dc6a86ad2f83151a62c577428d5102d872721"}, 928 | {file = "safetensors-0.4.3-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:89f9f17b0dacb913ed87d57afbc8aad85ea42c1085bd5de2f20d83d13e9fc4b2"}, 929 | {file = "safetensors-0.4.3-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:1139eb436fd201c133d03c81209d39ac57e129f5e74e34bb9ab60f8d9b726270"}, 930 | {file = "safetensors-0.4.3-cp38-none-win32.whl", hash = "sha256:d9c289f140a9ae4853fc2236a2ffc9a9f2d5eae0cb673167e0f1b8c18c0961ac"}, 931 | {file = "safetensors-0.4.3-cp38-none-win_amd64.whl", hash = "sha256:622afd28968ef3e9786562d352659a37de4481a4070f4ebac883f98c5836563e"}, 932 | {file = "safetensors-0.4.3-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:8651c7299cbd8b4161a36cd6a322fa07d39cd23535b144d02f1c1972d0c62f3c"}, 933 | {file = "safetensors-0.4.3-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:e375d975159ac534c7161269de24ddcd490df2157b55c1a6eeace6cbb56903f0"}, 934 | {file = "safetensors-0.4.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:084fc436e317f83f7071fc6a62ca1c513b2103db325cd09952914b50f51cf78f"}, 935 | {file = "safetensors-0.4.3-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:41a727a7f5e6ad9f1db6951adee21bbdadc632363d79dc434876369a17de6ad6"}, 936 | {file = "safetensors-0.4.3-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e7dbbde64b6c534548696808a0e01276d28ea5773bc9a2dfb97a88cd3dffe3df"}, 937 | {file = "safetensors-0.4.3-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:bbae3b4b9d997971431c346edbfe6e41e98424a097860ee872721e176040a893"}, 938 | {file = "safetensors-0.4.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:01e4b22e3284cd866edeabe4f4d896229495da457229408d2e1e4810c5187121"}, 939 | {file = "safetensors-0.4.3-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:0dd37306546b58d3043eb044c8103a02792cc024b51d1dd16bd3dd1f334cb3ed"}, 940 | {file = "safetensors-0.4.3-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:d8815b5e1dac85fc534a97fd339e12404db557878c090f90442247e87c8aeaea"}, 941 | {file = "safetensors-0.4.3-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:e011cc162503c19f4b1fd63dfcddf73739c7a243a17dac09b78e57a00983ab35"}, 942 | {file = "safetensors-0.4.3-cp39-none-win32.whl", hash = "sha256:01feb3089e5932d7e662eda77c3ecc389f97c0883c4a12b5cfdc32b589a811c3"}, 943 | {file = "safetensors-0.4.3-cp39-none-win_amd64.whl", hash = "sha256:3f9cdca09052f585e62328c1c2923c70f46814715c795be65f0b93f57ec98a02"}, 944 | {file = "safetensors-0.4.3-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:1b89381517891a7bb7d1405d828b2bf5d75528299f8231e9346b8eba092227f9"}, 945 | {file = "safetensors-0.4.3-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:cd6fff9e56df398abc5866b19a32124815b656613c1c5ec0f9350906fd798aac"}, 946 | {file = "safetensors-0.4.3-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:840caf38d86aa7014fe37ade5d0d84e23dcfbc798b8078015831996ecbc206a3"}, 947 | {file = "safetensors-0.4.3-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f9650713b2cfa9537a2baf7dd9fee458b24a0aaaa6cafcea8bdd5fb2b8efdc34"}, 948 | {file = "safetensors-0.4.3-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:e4119532cd10dba04b423e0f86aecb96cfa5a602238c0aa012f70c3a40c44b50"}, 949 | {file = "safetensors-0.4.3-pp310-pypy310_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:e066e8861eef6387b7c772344d1fe1f9a72800e04ee9a54239d460c400c72aab"}, 950 | {file = "safetensors-0.4.3-pp310-pypy310_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:90964917f5b0fa0fa07e9a051fbef100250c04d150b7026ccbf87a34a54012e0"}, 951 | {file = "safetensors-0.4.3-pp37-pypy37_pp73-macosx_10_12_x86_64.whl", hash = "sha256:c41e1893d1206aa7054029681778d9a58b3529d4c807002c156d58426c225173"}, 952 | {file = "safetensors-0.4.3-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ae7613a119a71a497d012ccc83775c308b9c1dab454806291427f84397d852fd"}, 953 | {file = "safetensors-0.4.3-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4f9bac020faba7f5dc481e881b14b6425265feabb5bfc552551d21189c0eddc3"}, 954 | {file = "safetensors-0.4.3-pp37-pypy37_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:420a98f593ff9930f5822560d14c395ccbc57342ddff3b463bc0b3d6b1951550"}, 955 | {file = "safetensors-0.4.3-pp37-pypy37_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:f5e6883af9a68c0028f70a4c19d5a6ab6238a379be36ad300a22318316c00cb0"}, 956 | {file = "safetensors-0.4.3-pp37-pypy37_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:cdd0a3b5da66e7f377474599814dbf5cbf135ff059cc73694de129b58a5e8a2c"}, 957 | {file = "safetensors-0.4.3-pp38-pypy38_pp73-macosx_10_12_x86_64.whl", hash = "sha256:9bfb92f82574d9e58401d79c70c716985dc049b635fef6eecbb024c79b2c46ad"}, 958 | {file = "safetensors-0.4.3-pp38-pypy38_pp73-macosx_11_0_arm64.whl", hash = "sha256:3615a96dd2dcc30eb66d82bc76cda2565f4f7bfa89fcb0e31ba3cea8a1a9ecbb"}, 959 | {file = "safetensors-0.4.3-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:868ad1b6fc41209ab6bd12f63923e8baeb1a086814cb2e81a65ed3d497e0cf8f"}, 960 | {file = "safetensors-0.4.3-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b7ffba80aa49bd09195145a7fd233a7781173b422eeb995096f2b30591639517"}, 961 | {file = "safetensors-0.4.3-pp38-pypy38_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:c0acbe31340ab150423347e5b9cc595867d814244ac14218932a5cf1dd38eb39"}, 962 | {file = "safetensors-0.4.3-pp38-pypy38_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:19bbdf95de2cf64f25cd614c5236c8b06eb2cfa47cbf64311f4b5d80224623a3"}, 963 | {file = "safetensors-0.4.3-pp38-pypy38_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:b852e47eb08475c2c1bd8131207b405793bfc20d6f45aff893d3baaad449ed14"}, 964 | {file = "safetensors-0.4.3-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:5d07cbca5b99babb692d76d8151bec46f461f8ad8daafbfd96b2fca40cadae65"}, 965 | {file = "safetensors-0.4.3-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:1ab6527a20586d94291c96e00a668fa03f86189b8a9defa2cdd34a1a01acc7d5"}, 966 | {file = "safetensors-0.4.3-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:02318f01e332cc23ffb4f6716e05a492c5f18b1d13e343c49265149396284a44"}, 967 | {file = "safetensors-0.4.3-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ec4b52ce9a396260eb9731eb6aea41a7320de22ed73a1042c2230af0212758ce"}, 968 | {file = "safetensors-0.4.3-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:018b691383026a2436a22b648873ed11444a364324e7088b99cd2503dd828400"}, 969 | {file = "safetensors-0.4.3-pp39-pypy39_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:309b10dbcab63269ecbf0e2ca10ce59223bb756ca5d431ce9c9eeabd446569da"}, 970 | {file = "safetensors-0.4.3-pp39-pypy39_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:b277482120df46e27a58082df06a15aebda4481e30a1c21eefd0921ae7e03f65"}, 971 | {file = "safetensors-0.4.3.tar.gz", hash = "sha256:2f85fc50c4e07a21e95c24e07460fe6f7e2859d0ce88092838352b798ce711c2"}, 972 | ] 973 | 974 | [package.extras] 975 | all = ["safetensors[jax]", "safetensors[numpy]", "safetensors[paddlepaddle]", "safetensors[pinned-tf]", "safetensors[quality]", "safetensors[testing]", "safetensors[torch]"] 976 | dev = ["safetensors[all]"] 977 | jax = ["flax (>=0.6.3)", "jax (>=0.3.25)", "jaxlib (>=0.3.25)", "safetensors[numpy]"] 978 | mlx = ["mlx (>=0.0.9)"] 979 | numpy = ["numpy (>=1.21.6)"] 980 | paddlepaddle = ["paddlepaddle (>=2.4.1)", "safetensors[numpy]"] 981 | pinned-tf = ["safetensors[numpy]", "tensorflow (==2.11.0)"] 982 | quality = ["black (==22.3)", "click (==8.0.4)", "flake8 (>=3.8.3)", "isort (>=5.5.4)"] 983 | tensorflow = ["safetensors[numpy]", "tensorflow (>=2.11.0)"] 984 | testing = ["h5py (>=3.7.0)", "huggingface-hub (>=0.12.1)", "hypothesis (>=6.70.2)", "pytest (>=7.2.0)", "pytest-benchmark (>=4.0.0)", "safetensors[numpy]", "setuptools-rust (>=1.5.2)"] 985 | torch = ["safetensors[numpy]", "torch (>=1.10)"] 986 | 987 | [[package]] 988 | name = "scikit-learn" 989 | version = "1.4.2" 990 | description = "A set of python modules for machine learning and data mining" 991 | optional = false 992 | python-versions = ">=3.9" 993 | files = [ 994 | {file = "scikit-learn-1.4.2.tar.gz", hash = "sha256:daa1c471d95bad080c6e44b4946c9390a4842adc3082572c20e4f8884e39e959"}, 995 | {file = "scikit_learn-1.4.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:8539a41b3d6d1af82eb629f9c57f37428ff1481c1e34dddb3b9d7af8ede67ac5"}, 996 | {file = "scikit_learn-1.4.2-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:68b8404841f944a4a1459b07198fa2edd41a82f189b44f3e1d55c104dbc2e40c"}, 997 | {file = "scikit_learn-1.4.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:81bf5d8bbe87643103334032dd82f7419bc8c8d02a763643a6b9a5c7288c5054"}, 998 | {file = "scikit_learn-1.4.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:36f0ea5d0f693cb247a073d21a4123bdf4172e470e6d163c12b74cbb1536cf38"}, 999 | {file = "scikit_learn-1.4.2-cp310-cp310-win_amd64.whl", hash = "sha256:87440e2e188c87db80ea4023440923dccbd56fbc2d557b18ced00fef79da0727"}, 1000 | {file = "scikit_learn-1.4.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:45dee87ac5309bb82e3ea633955030df9bbcb8d2cdb30383c6cd483691c546cc"}, 1001 | {file = "scikit_learn-1.4.2-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:1d0b25d9c651fd050555aadd57431b53d4cf664e749069da77f3d52c5ad14b3b"}, 1002 | {file = "scikit_learn-1.4.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b0203c368058ab92efc6168a1507d388d41469c873e96ec220ca8e74079bf62e"}, 1003 | {file = "scikit_learn-1.4.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:44c62f2b124848a28fd695db5bc4da019287abf390bfce602ddc8aa1ec186aae"}, 1004 | {file = "scikit_learn-1.4.2-cp311-cp311-win_amd64.whl", hash = "sha256:5cd7b524115499b18b63f0c96f4224eb885564937a0b3477531b2b63ce331904"}, 1005 | {file = "scikit_learn-1.4.2-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:90378e1747949f90c8f385898fff35d73193dfcaec3dd75d6b542f90c4e89755"}, 1006 | {file = "scikit_learn-1.4.2-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:ff4effe5a1d4e8fed260a83a163f7dbf4f6087b54528d8880bab1d1377bd78be"}, 1007 | {file = "scikit_learn-1.4.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:671e2f0c3f2c15409dae4f282a3a619601fa824d2c820e5b608d9d775f91780c"}, 1008 | {file = "scikit_learn-1.4.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d36d0bc983336bbc1be22f9b686b50c964f593c8a9a913a792442af9bf4f5e68"}, 1009 | {file = "scikit_learn-1.4.2-cp312-cp312-win_amd64.whl", hash = "sha256:d762070980c17ba3e9a4a1e043ba0518ce4c55152032f1af0ca6f39b376b5928"}, 1010 | {file = "scikit_learn-1.4.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:d9993d5e78a8148b1d0fdf5b15ed92452af5581734129998c26f481c46586d68"}, 1011 | {file = "scikit_learn-1.4.2-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:426d258fddac674fdf33f3cb2d54d26f49406e2599dbf9a32b4d1696091d4256"}, 1012 | {file = "scikit_learn-1.4.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5460a1a5b043ae5ae4596b3126a4ec33ccba1b51e7ca2c5d36dac2169f62ab1d"}, 1013 | {file = "scikit_learn-1.4.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:49d64ef6cb8c093d883e5a36c4766548d974898d378e395ba41a806d0e824db8"}, 1014 | {file = "scikit_learn-1.4.2-cp39-cp39-win_amd64.whl", hash = "sha256:c97a50b05c194be9146d61fe87dbf8eac62b203d9e87a3ccc6ae9aed2dfaf361"}, 1015 | ] 1016 | 1017 | [package.dependencies] 1018 | joblib = ">=1.2.0" 1019 | numpy = ">=1.19.5" 1020 | scipy = ">=1.6.0" 1021 | threadpoolctl = ">=2.0.0" 1022 | 1023 | [package.extras] 1024 | benchmark = ["matplotlib (>=3.3.4)", "memory-profiler (>=0.57.0)", "pandas (>=1.1.5)"] 1025 | docs = ["Pillow (>=7.1.2)", "matplotlib (>=3.3.4)", "memory-profiler (>=0.57.0)", "numpydoc (>=1.2.0)", "pandas (>=1.1.5)", "plotly (>=5.14.0)", "pooch (>=1.6.0)", "scikit-image (>=0.17.2)", "seaborn (>=0.9.0)", "sphinx (>=6.0.0)", "sphinx-copybutton (>=0.5.2)", "sphinx-gallery (>=0.15.0)", "sphinx-prompt (>=1.3.0)", "sphinxext-opengraph (>=0.4.2)"] 1026 | examples = ["matplotlib (>=3.3.4)", "pandas (>=1.1.5)", "plotly (>=5.14.0)", "pooch (>=1.6.0)", "scikit-image (>=0.17.2)", "seaborn (>=0.9.0)"] 1027 | tests = ["black (>=23.3.0)", "matplotlib (>=3.3.4)", "mypy (>=1.3)", "numpydoc (>=1.2.0)", "pandas (>=1.1.5)", "polars (>=0.19.12)", "pooch (>=1.6.0)", "pyamg (>=4.0.0)", "pyarrow (>=12.0.0)", "pytest (>=7.1.2)", "pytest-cov (>=2.9.0)", "ruff (>=0.0.272)", "scikit-image (>=0.17.2)"] 1028 | 1029 | [[package]] 1030 | name = "scipy" 1031 | version = "1.13.0" 1032 | description = "Fundamental algorithms for scientific computing in Python" 1033 | optional = false 1034 | python-versions = ">=3.9" 1035 | files = [ 1036 | {file = "scipy-1.13.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:ba419578ab343a4e0a77c0ef82f088238a93eef141b2b8017e46149776dfad4d"}, 1037 | {file = "scipy-1.13.0-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:22789b56a999265431c417d462e5b7f2b487e831ca7bef5edeb56efe4c93f86e"}, 1038 | {file = "scipy-1.13.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:05f1432ba070e90d42d7fd836462c50bf98bd08bed0aa616c359eed8a04e3922"}, 1039 | {file = "scipy-1.13.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b8434f6f3fa49f631fae84afee424e2483289dfc30a47755b4b4e6b07b2633a4"}, 1040 | {file = "scipy-1.13.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:dcbb9ea49b0167de4167c40eeee6e167caeef11effb0670b554d10b1e693a8b9"}, 1041 | {file = "scipy-1.13.0-cp310-cp310-win_amd64.whl", hash = "sha256:1d2f7bb14c178f8b13ebae93f67e42b0a6b0fc50eba1cd8021c9b6e08e8fb1cd"}, 1042 | {file = "scipy-1.13.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:0fbcf8abaf5aa2dc8d6400566c1a727aed338b5fe880cde64907596a89d576fa"}, 1043 | {file = "scipy-1.13.0-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:5e4a756355522eb60fcd61f8372ac2549073c8788f6114449b37e9e8104f15a5"}, 1044 | {file = "scipy-1.13.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b5acd8e1dbd8dbe38d0004b1497019b2dbbc3d70691e65d69615f8a7292865d7"}, 1045 | {file = "scipy-1.13.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9ff7dad5d24a8045d836671e082a490848e8639cabb3dbdacb29f943a678683d"}, 1046 | {file = "scipy-1.13.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:4dca18c3ffee287ddd3bc8f1dabaf45f5305c5afc9f8ab9cbfab855e70b2df5c"}, 1047 | {file = "scipy-1.13.0-cp311-cp311-win_amd64.whl", hash = "sha256:a2f471de4d01200718b2b8927f7d76b5d9bde18047ea0fa8bd15c5ba3f26a1d6"}, 1048 | {file = "scipy-1.13.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:d0de696f589681c2802f9090fff730c218f7c51ff49bf252b6a97ec4a5d19e8b"}, 1049 | {file = "scipy-1.13.0-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:b2a3ff461ec4756b7e8e42e1c681077349a038f0686132d623fa404c0bee2551"}, 1050 | {file = "scipy-1.13.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6bf9fe63e7a4bf01d3645b13ff2aa6dea023d38993f42aaac81a18b1bda7a82a"}, 1051 | {file = "scipy-1.13.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1e7626dfd91cdea5714f343ce1176b6c4745155d234f1033584154f60ef1ff42"}, 1052 | {file = "scipy-1.13.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:109d391d720fcebf2fbe008621952b08e52907cf4c8c7efc7376822151820820"}, 1053 | {file = "scipy-1.13.0-cp312-cp312-win_amd64.whl", hash = "sha256:8930ae3ea371d6b91c203b1032b9600d69c568e537b7988a3073dfe4d4774f21"}, 1054 | {file = "scipy-1.13.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:5407708195cb38d70fd2d6bb04b1b9dd5c92297d86e9f9daae1576bd9e06f602"}, 1055 | {file = "scipy-1.13.0-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:ac38c4c92951ac0f729c4c48c9e13eb3675d9986cc0c83943784d7390d540c78"}, 1056 | {file = "scipy-1.13.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:09c74543c4fbeb67af6ce457f6a6a28e5d3739a87f62412e4a16e46f164f0ae5"}, 1057 | {file = "scipy-1.13.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:28e286bf9ac422d6beb559bc61312c348ca9b0f0dae0d7c5afde7f722d6ea13d"}, 1058 | {file = "scipy-1.13.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:33fde20efc380bd23a78a4d26d59fc8704e9b5fd9b08841693eb46716ba13d86"}, 1059 | {file = "scipy-1.13.0-cp39-cp39-win_amd64.whl", hash = "sha256:45c08bec71d3546d606989ba6e7daa6f0992918171e2a6f7fbedfa7361c2de1e"}, 1060 | {file = "scipy-1.13.0.tar.gz", hash = "sha256:58569af537ea29d3f78e5abd18398459f195546bb3be23d16677fb26616cc11e"}, 1061 | ] 1062 | 1063 | [package.dependencies] 1064 | numpy = ">=1.22.4,<2.3" 1065 | 1066 | [package.extras] 1067 | dev = ["cython-lint (>=0.12.2)", "doit (>=0.36.0)", "mypy", "pycodestyle", "pydevtool", "rich-click", "ruff", "types-psutil", "typing_extensions"] 1068 | doc = ["jupyterlite-pyodide-kernel", "jupyterlite-sphinx (>=0.12.0)", "jupytext", "matplotlib (>=3.5)", "myst-nb", "numpydoc", "pooch", "pydata-sphinx-theme (>=0.15.2)", "sphinx (>=5.0.0)", "sphinx-design (>=0.4.0)"] 1069 | test = ["array-api-strict", "asv", "gmpy2", "hypothesis (>=6.30)", "mpmath", "pooch", "pytest", "pytest-cov", "pytest-timeout", "pytest-xdist", "scikit-umfpack", "threadpoolctl"] 1070 | 1071 | [[package]] 1072 | name = "sentencepiece" 1073 | version = "0.2.0" 1074 | description = "SentencePiece python wrapper" 1075 | optional = false 1076 | python-versions = "*" 1077 | files = [ 1078 | {file = "sentencepiece-0.2.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:188779e1298a1c8b8253c7d3ad729cb0a9891e5cef5e5d07ce4592c54869e227"}, 1079 | {file = "sentencepiece-0.2.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:bed9cf85b296fa2b76fc2547b9cbb691a523864cebaee86304c43a7b4cb1b452"}, 1080 | {file = "sentencepiece-0.2.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:d7b67e724bead13f18db6e1d10b6bbdc454af574d70efbb36f27d90387be1ca3"}, 1081 | {file = "sentencepiece-0.2.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2fde4b08cfe237be4484c6c7c2e2c75fb862cfeab6bd5449ce4caeafd97b767a"}, 1082 | {file = "sentencepiece-0.2.0-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4c378492056202d1c48a4979650981635fd97875a00eabb1f00c6a236b013b5e"}, 1083 | {file = "sentencepiece-0.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1380ce6540a368de2ef6d7e6ba14ba8f3258df650d39ba7d833b79ee68a52040"}, 1084 | {file = "sentencepiece-0.2.0-cp310-cp310-win32.whl", hash = "sha256:a1151d6a6dd4b43e552394aed0edfe9292820272f0194bd56c7c1660a0c06c3d"}, 1085 | {file = "sentencepiece-0.2.0-cp310-cp310-win_amd64.whl", hash = "sha256:d490142b0521ef22bc1085f061d922a2a6666175bb6b42e588ff95c0db6819b2"}, 1086 | {file = "sentencepiece-0.2.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:17982700c4f6dbb55fa3594f3d7e5dd1c8659a274af3738e33c987d2a27c9d5c"}, 1087 | {file = "sentencepiece-0.2.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:7c867012c0e8bcd5bdad0f791609101cb5c66acb303ab3270218d6debc68a65e"}, 1088 | {file = "sentencepiece-0.2.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:7fd6071249c74f779c5b27183295b9202f8dedb68034e716784364443879eaa6"}, 1089 | {file = "sentencepiece-0.2.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:27f90c55a65013cbb8f4d7aab0599bf925cde4adc67ae43a0d323677b5a1c6cb"}, 1090 | {file = "sentencepiece-0.2.0-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b293734059ef656dcd65be62ff771507bea8fed0a711b6733976e1ed3add4553"}, 1091 | {file = "sentencepiece-0.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e58b47f933aca74c6a60a79dcb21d5b9e47416256c795c2d58d55cec27f9551d"}, 1092 | {file = "sentencepiece-0.2.0-cp311-cp311-win32.whl", hash = "sha256:c581258cf346b327c62c4f1cebd32691826306f6a41d8c4bec43b010dee08e75"}, 1093 | {file = "sentencepiece-0.2.0-cp311-cp311-win_amd64.whl", hash = "sha256:0993dbc665f4113017892f1b87c3904a44d0640eda510abcacdfb07f74286d36"}, 1094 | {file = "sentencepiece-0.2.0-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:ea5f536e32ea8ec96086ee00d7a4a131ce583a1b18d130711707c10e69601cb2"}, 1095 | {file = "sentencepiece-0.2.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:d0cb51f53b6aae3c36bafe41e86167c71af8370a039f542c43b0cce5ef24a68c"}, 1096 | {file = "sentencepiece-0.2.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:3212121805afc58d8b00ab4e7dd1f8f76c203ddb9dc94aa4079618a31cf5da0f"}, 1097 | {file = "sentencepiece-0.2.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2a3149e3066c2a75e0d68a43eb632d7ae728c7925b517f4c05c40f6f7280ce08"}, 1098 | {file = "sentencepiece-0.2.0-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:632f3594d3e7ac8b367bca204cb3fd05a01d5b21455acd097ea4c0e30e2f63d7"}, 1099 | {file = "sentencepiece-0.2.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f295105c6bdbb05bd5e1b0cafbd78ff95036f5d3641e7949455a3f4e5e7c3109"}, 1100 | {file = "sentencepiece-0.2.0-cp312-cp312-win32.whl", hash = "sha256:fb89f811e5efd18bab141afc3fea3de141c3f69f3fe9e898f710ae7fe3aab251"}, 1101 | {file = "sentencepiece-0.2.0-cp312-cp312-win_amd64.whl", hash = "sha256:7a673a72aab81fef5ebe755c6e0cc60087d1f3a4700835d40537183c1703a45f"}, 1102 | {file = "sentencepiece-0.2.0-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:4547683f330289ec4f093027bfeb87f9ef023b2eb6f879fdc4a8187c7e0ffb90"}, 1103 | {file = "sentencepiece-0.2.0-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7cd6175f7eaec7142d2bf6f6597ce7db4c9ac89acf93fcdb17410c3a8b781eeb"}, 1104 | {file = "sentencepiece-0.2.0-cp36-cp36m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:859ba1acde782609a0910a26a60e16c191a82bf39b5621107552c0cd79fad00f"}, 1105 | {file = "sentencepiece-0.2.0-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bcbbef6cc277f8f18f36959e305f10b1c620442d75addc79c21d7073ae581b50"}, 1106 | {file = "sentencepiece-0.2.0-cp36-cp36m-win32.whl", hash = "sha256:536b934e244829e3fe6c4f198652cd82da48adb9aa145c9f00889542726dee3d"}, 1107 | {file = "sentencepiece-0.2.0-cp36-cp36m-win_amd64.whl", hash = "sha256:0a91aaa3c769b52440df56fafda683b3aa48e3f2169cf7ee5b8c8454a7f3ae9b"}, 1108 | {file = "sentencepiece-0.2.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:787e480ca4c1d08c9985a7eb1eae4345c107729c99e9b5a9a00f2575fc7d4b4b"}, 1109 | {file = "sentencepiece-0.2.0-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f4d158189eb2ecffea3a51edf6d25e110b3678ec47f1a40f2d541eafbd8f6250"}, 1110 | {file = "sentencepiece-0.2.0-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d1e5ca43013e8935f25457a4fca47e315780172c3e821b4b13a890668911c792"}, 1111 | {file = "sentencepiece-0.2.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7140d9e5a74a0908493bb4a13f1f16a401297bd755ada4c707e842fbf6f0f5bf"}, 1112 | {file = "sentencepiece-0.2.0-cp37-cp37m-win32.whl", hash = "sha256:6cf333625234f247ab357b0bd9836638405ea9082e1543d5b8408f014979dcbf"}, 1113 | {file = "sentencepiece-0.2.0-cp37-cp37m-win_amd64.whl", hash = "sha256:ff88712338b01031910e8e61e7239aff3ce8869ee31a47df63cb38aadd591bea"}, 1114 | {file = "sentencepiece-0.2.0-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:20813a68d4c221b1849c62c30e1281ea81687894d894b8d4a0f4677d9311e0f5"}, 1115 | {file = "sentencepiece-0.2.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:926ef920ae2e8182db31d3f5d081ada57804e3e1d3a8c4ef8b117f9d9fb5a945"}, 1116 | {file = "sentencepiece-0.2.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:89f65f69636b7e9c015b79dff9c9985a9bc7d19ded6f79ef9f1ec920fdd73ecf"}, 1117 | {file = "sentencepiece-0.2.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0f67eae0dbe6f2d7d6ba50a354623d787c99965f068b81e145d53240198021b0"}, 1118 | {file = "sentencepiece-0.2.0-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:98501e075f35dd1a1d5a20f65be26839fcb1938752ec61539af008a5aa6f510b"}, 1119 | {file = "sentencepiece-0.2.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e3d1d2cc4882e8d6a1adf9d5927d7716f80617fc693385661caff21888972269"}, 1120 | {file = "sentencepiece-0.2.0-cp38-cp38-win32.whl", hash = "sha256:b99a308a2e5e569031ab164b74e6fab0b6f37dfb493c32f7816225f4d411a6dd"}, 1121 | {file = "sentencepiece-0.2.0-cp38-cp38-win_amd64.whl", hash = "sha256:cdb701eec783d3ec86b7cd4c763adad8eaf6b46db37ee1c36e5e6c44b3fe1b5f"}, 1122 | {file = "sentencepiece-0.2.0-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:1e0f9c4d0a6b0af59b613175f019916e28ade076e21242fd5be24340d8a2f64a"}, 1123 | {file = "sentencepiece-0.2.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:298f21cc1366eb60311aedba3169d30f885c363ddbf44214b0a587d2908141ad"}, 1124 | {file = "sentencepiece-0.2.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:3f1ec95aa1e5dab11f37ac7eff190493fd87770f7a8b81ebc9dd768d1a3c8704"}, 1125 | {file = "sentencepiece-0.2.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7b06b70af54daa4b4904cbb90b4eb6d35c9f3252fdc86c9c32d5afd4d30118d8"}, 1126 | {file = "sentencepiece-0.2.0-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:22e37bac44dd6603388cb598c64ff7a76e41ca774646f21c23aadfbf5a2228ab"}, 1127 | {file = "sentencepiece-0.2.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0461324897735512a32d222e3d886e24ad6a499761952b6bda2a9ee6e4313ea5"}, 1128 | {file = "sentencepiece-0.2.0-cp39-cp39-win32.whl", hash = "sha256:38aed822fb76435fa1f12185f10465a94ab9e51d5e8a9159e9a540ce926f0ffd"}, 1129 | {file = "sentencepiece-0.2.0-cp39-cp39-win_amd64.whl", hash = "sha256:d8cf876516548b5a1d6ac4745d8b554f5c07891d55da557925e5c13ff0b4e6ad"}, 1130 | {file = "sentencepiece-0.2.0.tar.gz", hash = "sha256:a52c19171daaf2e697dc6cbe67684e0fa341b1248966f6aebb541de654d15843"}, 1131 | ] 1132 | 1133 | [[package]] 1134 | name = "six" 1135 | version = "1.16.0" 1136 | description = "Python 2 and 3 compatibility utilities" 1137 | optional = false 1138 | python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*" 1139 | files = [ 1140 | {file = "six-1.16.0-py2.py3-none-any.whl", hash = "sha256:8abb2f1d86890a2dfb989f9a77cfcfd3e47c2a354b01111771326f8aa26e0254"}, 1141 | {file = "six-1.16.0.tar.gz", hash = "sha256:1e61c37477a1626458e36f7b1d82aa5c9b094fa4802892072e49de9c60c4c926"}, 1142 | ] 1143 | 1144 | [[package]] 1145 | name = "sudachidict-core" 1146 | version = "20240409" 1147 | description = "Sudachi Dictionary for SudachiPy - Core Edition" 1148 | optional = false 1149 | python-versions = "*" 1150 | files = [ 1151 | {file = "SudachiDict-core-20240409.tar.gz", hash = "sha256:341eb2fdf1ce3a0db329213b01e0dea2f0e3db26ea1f5244c43c4a1cd739d41e"}, 1152 | {file = "SudachiDict_core-20240409-py3-none-any.whl", hash = "sha256:99b165574f9fe7a42c9caee2f4f274d22f8c99602eaba2863575bbc09020a2fb"}, 1153 | ] 1154 | 1155 | [package.dependencies] 1156 | SudachiPy = ">=0.5,<0.7" 1157 | 1158 | [[package]] 1159 | name = "sudachipy" 1160 | version = "0.6.8" 1161 | description = "Python version of Sudachi, the Japanese Morphological Analyzer" 1162 | optional = false 1163 | python-versions = "*" 1164 | files = [ 1165 | {file = "SudachiPy-0.6.8-cp310-cp310-macosx_10_12_universal2.whl", hash = "sha256:85f91a6ac347d2fbf478ae96e0e08efe7b8e47fb7cdfb770e90611be5669cabb"}, 1166 | {file = "SudachiPy-0.6.8-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:361ef3e3333ef4165b517668878dd80fbed6d3c443659b9dc3236132ea8f7fbb"}, 1167 | {file = "SudachiPy-0.6.8-cp310-cp310-win_amd64.whl", hash = "sha256:081c52918bdae35f564637db146389f0a48b3b5263f215859b4d1ae311a7a474"}, 1168 | {file = "SudachiPy-0.6.8-cp311-cp311-macosx_10_12_universal2.whl", hash = "sha256:0a6cb506e402933023ea07035fc3e81d65880392afcdb2f09676027882b09e73"}, 1169 | {file = "SudachiPy-0.6.8-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d19db58be100b05362d00d0ad5cd29aff6da31807967b302f35bd43dd59e141f"}, 1170 | {file = "SudachiPy-0.6.8-cp311-cp311-win_amd64.whl", hash = "sha256:27833ae472220dc46f934edd9a8839b0134279c0113f7da01d67e424bfe2d0ab"}, 1171 | {file = "SudachiPy-0.6.8-cp312-cp312-macosx_10_12_universal2.whl", hash = "sha256:7f75d4627fa141bc02951c5ce17ec7055faf2e9424d10c697e923c27b7936369"}, 1172 | {file = "SudachiPy-0.6.8-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:33afa2efa4d98ae3cbea0ab8cc09c71b0405d188074d0c4cef2b2080a51caafe"}, 1173 | {file = "SudachiPy-0.6.8-cp312-cp312-win_amd64.whl", hash = "sha256:2a2f22605093ed7994eb7edced2a21c8ac71b9ecc9877e94539414b1a60d172a"}, 1174 | {file = "SudachiPy-0.6.8-cp37-cp37m-macosx_10_12_universal2.whl", hash = "sha256:6ab54826d151dcf69dfd168e784887d2701c553cf3f455d28b171e64584a404d"}, 1175 | {file = "SudachiPy-0.6.8-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9d9aa1890b3f43af0ff691f6de8f770ab9ea58506d9e1ee3c8bb9aae460c58d2"}, 1176 | {file = "SudachiPy-0.6.8-cp37-cp37m-win_amd64.whl", hash = "sha256:686a890a376589e78b606548f9d5427a43ce8492edc46bcd09c104d9df594f7c"}, 1177 | {file = "SudachiPy-0.6.8-cp38-cp38-macosx_10_12_universal2.whl", hash = "sha256:8d19395daf8c96e4a14df18c4df634e1f7caa7790917ab089c174ffcbdcaf4c0"}, 1178 | {file = "SudachiPy-0.6.8-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d9cae943138ef2e9d0126a5a4110dca5d6e5d8f35dc3f909e3ef1aeff3aa565b"}, 1179 | {file = "SudachiPy-0.6.8-cp38-cp38-win_amd64.whl", hash = "sha256:e8de107715dcd1d566837c91c6a10572efc171d4969a505176ecb37efe65cb48"}, 1180 | {file = "SudachiPy-0.6.8-cp39-cp39-macosx_10_12_universal2.whl", hash = "sha256:d52ddc5001b0125375419409adee012f8957b15ad1a4017e18f30c54ba69f9b7"}, 1181 | {file = "SudachiPy-0.6.8-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c2a7c98f75567bd8488a1597c83f8f6abb4c15c577d0b5f92fa0c31c8304dae4"}, 1182 | {file = "SudachiPy-0.6.8-cp39-cp39-win_amd64.whl", hash = "sha256:1ae6e533f98e510e751d7355ec512aff3a7dac73539abb61c731cdcc316a183f"}, 1183 | {file = "SudachiPy-0.6.8.tar.gz", hash = "sha256:3d1c9086ff09afacc34d02fdb2112aab7cff1d78f0d4b81f78b9ba01c36d4888"}, 1184 | ] 1185 | 1186 | [package.extras] 1187 | tests = ["sudachidict-core", "tokenizers"] 1188 | 1189 | [[package]] 1190 | name = "sympy" 1191 | version = "1.12" 1192 | description = "Computer algebra system (CAS) in Python" 1193 | optional = false 1194 | python-versions = ">=3.8" 1195 | files = [ 1196 | {file = "sympy-1.12-py3-none-any.whl", hash = "sha256:c3588cd4295d0c0f603d0f2ae780587e64e2efeedb3521e46b9bb1d08d184fa5"}, 1197 | {file = "sympy-1.12.tar.gz", hash = "sha256:ebf595c8dac3e0fdc4152c51878b498396ec7f30e7a914d6071e674d49420fb8"}, 1198 | ] 1199 | 1200 | [package.dependencies] 1201 | mpmath = ">=0.19" 1202 | 1203 | [[package]] 1204 | name = "threadpoolctl" 1205 | version = "3.4.0" 1206 | description = "threadpoolctl" 1207 | optional = false 1208 | python-versions = ">=3.8" 1209 | files = [ 1210 | {file = "threadpoolctl-3.4.0-py3-none-any.whl", hash = "sha256:8f4c689a65b23e5ed825c8436a92b818aac005e0f3715f6a1664d7c7ee29d262"}, 1211 | {file = "threadpoolctl-3.4.0.tar.gz", hash = "sha256:f11b491a03661d6dd7ef692dd422ab34185d982466c49c8f98c8f716b5c93196"}, 1212 | ] 1213 | 1214 | [[package]] 1215 | name = "tokenizers" 1216 | version = "0.19.1" 1217 | description = "" 1218 | optional = false 1219 | python-versions = ">=3.7" 1220 | files = [ 1221 | {file = "tokenizers-0.19.1-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:952078130b3d101e05ecfc7fc3640282d74ed26bcf691400f872563fca15ac97"}, 1222 | {file = "tokenizers-0.19.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:82c8b8063de6c0468f08e82c4e198763e7b97aabfe573fd4cf7b33930ca4df77"}, 1223 | {file = "tokenizers-0.19.1-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:f03727225feaf340ceeb7e00604825addef622d551cbd46b7b775ac834c1e1c4"}, 1224 | {file = "tokenizers-0.19.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:453e4422efdfc9c6b6bf2eae00d5e323f263fff62b29a8c9cd526c5003f3f642"}, 1225 | {file = "tokenizers-0.19.1-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:02e81bf089ebf0e7f4df34fa0207519f07e66d8491d963618252f2e0729e0b46"}, 1226 | {file = "tokenizers-0.19.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b07c538ba956843833fee1190cf769c60dc62e1cf934ed50d77d5502194d63b1"}, 1227 | {file = "tokenizers-0.19.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:e28cab1582e0eec38b1f38c1c1fb2e56bce5dc180acb1724574fc5f47da2a4fe"}, 1228 | {file = "tokenizers-0.19.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8b01afb7193d47439f091cd8f070a1ced347ad0f9144952a30a41836902fe09e"}, 1229 | {file = "tokenizers-0.19.1-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:7fb297edec6c6841ab2e4e8f357209519188e4a59b557ea4fafcf4691d1b4c98"}, 1230 | {file = "tokenizers-0.19.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:2e8a3dd055e515df7054378dc9d6fa8c8c34e1f32777fb9a01fea81496b3f9d3"}, 1231 | {file = "tokenizers-0.19.1-cp310-none-win32.whl", hash = "sha256:7ff898780a155ea053f5d934925f3902be2ed1f4d916461e1a93019cc7250837"}, 1232 | {file = "tokenizers-0.19.1-cp310-none-win_amd64.whl", hash = "sha256:bea6f9947e9419c2fda21ae6c32871e3d398cba549b93f4a65a2d369662d9403"}, 1233 | {file = "tokenizers-0.19.1-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:5c88d1481f1882c2e53e6bb06491e474e420d9ac7bdff172610c4f9ad3898059"}, 1234 | {file = "tokenizers-0.19.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:ddf672ed719b4ed82b51499100f5417d7d9f6fb05a65e232249268f35de5ed14"}, 1235 | {file = "tokenizers-0.19.1-cp311-cp311-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:dadc509cc8a9fe460bd274c0e16ac4184d0958117cf026e0ea8b32b438171594"}, 1236 | {file = "tokenizers-0.19.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:dfedf31824ca4915b511b03441784ff640378191918264268e6923da48104acc"}, 1237 | {file = "tokenizers-0.19.1-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:ac11016d0a04aa6487b1513a3a36e7bee7eec0e5d30057c9c0408067345c48d2"}, 1238 | {file = "tokenizers-0.19.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:76951121890fea8330d3a0df9a954b3f2a37e3ec20e5b0530e9a0044ca2e11fe"}, 1239 | {file = "tokenizers-0.19.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b342d2ce8fc8d00f376af068e3274e2e8649562e3bc6ae4a67784ded6b99428d"}, 1240 | {file = "tokenizers-0.19.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d16ff18907f4909dca9b076b9c2d899114dd6abceeb074eca0c93e2353f943aa"}, 1241 | {file = "tokenizers-0.19.1-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:706a37cc5332f85f26efbe2bdc9ef8a9b372b77e4645331a405073e4b3a8c1c6"}, 1242 | {file = "tokenizers-0.19.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:16baac68651701364b0289979ecec728546133e8e8fe38f66fe48ad07996b88b"}, 1243 | {file = "tokenizers-0.19.1-cp311-none-win32.whl", hash = "sha256:9ed240c56b4403e22b9584ee37d87b8bfa14865134e3e1c3fb4b2c42fafd3256"}, 1244 | {file = "tokenizers-0.19.1-cp311-none-win_amd64.whl", hash = "sha256:ad57d59341710b94a7d9dbea13f5c1e7d76fd8d9bcd944a7a6ab0b0da6e0cc66"}, 1245 | {file = "tokenizers-0.19.1-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:621d670e1b1c281a1c9698ed89451395d318802ff88d1fc1accff0867a06f153"}, 1246 | {file = "tokenizers-0.19.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:d924204a3dbe50b75630bd16f821ebda6a5f729928df30f582fb5aade90c818a"}, 1247 | {file = "tokenizers-0.19.1-cp312-cp312-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:4f3fefdc0446b1a1e6d81cd4c07088ac015665d2e812f6dbba4a06267d1a2c95"}, 1248 | {file = "tokenizers-0.19.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9620b78e0b2d52ef07b0d428323fb34e8ea1219c5eac98c2596311f20f1f9266"}, 1249 | {file = "tokenizers-0.19.1-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:04ce49e82d100594715ac1b2ce87d1a36e61891a91de774755f743babcd0dd52"}, 1250 | {file = "tokenizers-0.19.1-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c5c2ff13d157afe413bf7e25789879dd463e5a4abfb529a2d8f8473d8042e28f"}, 1251 | {file = "tokenizers-0.19.1-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:3174c76efd9d08f836bfccaca7cfec3f4d1c0a4cf3acbc7236ad577cc423c840"}, 1252 | {file = "tokenizers-0.19.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7c9d5b6c0e7a1e979bec10ff960fae925e947aab95619a6fdb4c1d8ff3708ce3"}, 1253 | {file = "tokenizers-0.19.1-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:a179856d1caee06577220ebcfa332af046d576fb73454b8f4d4b0ba8324423ea"}, 1254 | {file = "tokenizers-0.19.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:952b80dac1a6492170f8c2429bd11fcaa14377e097d12a1dbe0ef2fb2241e16c"}, 1255 | {file = "tokenizers-0.19.1-cp312-none-win32.whl", hash = "sha256:01d62812454c188306755c94755465505836fd616f75067abcae529c35edeb57"}, 1256 | {file = "tokenizers-0.19.1-cp312-none-win_amd64.whl", hash = "sha256:b70bfbe3a82d3e3fb2a5e9b22a39f8d1740c96c68b6ace0086b39074f08ab89a"}, 1257 | {file = "tokenizers-0.19.1-cp37-cp37m-macosx_10_12_x86_64.whl", hash = "sha256:bb9dfe7dae85bc6119d705a76dc068c062b8b575abe3595e3c6276480e67e3f1"}, 1258 | {file = "tokenizers-0.19.1-cp37-cp37m-macosx_11_0_arm64.whl", hash = "sha256:1f0360cbea28ea99944ac089c00de7b2e3e1c58f479fb8613b6d8d511ce98267"}, 1259 | {file = "tokenizers-0.19.1-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:71e3ec71f0e78780851fef28c2a9babe20270404c921b756d7c532d280349214"}, 1260 | {file = "tokenizers-0.19.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b82931fa619dbad979c0ee8e54dd5278acc418209cc897e42fac041f5366d626"}, 1261 | {file = "tokenizers-0.19.1-cp37-cp37m-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:e8ff5b90eabdcdaa19af697885f70fe0b714ce16709cf43d4952f1f85299e73a"}, 1262 | {file = "tokenizers-0.19.1-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e742d76ad84acbdb1a8e4694f915fe59ff6edc381c97d6dfdd054954e3478ad4"}, 1263 | {file = "tokenizers-0.19.1-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d8c5d59d7b59885eab559d5bc082b2985555a54cda04dda4c65528d90ad252ad"}, 1264 | {file = "tokenizers-0.19.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6b2da5c32ed869bebd990c9420df49813709e953674c0722ff471a116d97b22d"}, 1265 | {file = "tokenizers-0.19.1-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:638e43936cc8b2cbb9f9d8dde0fe5e7e30766a3318d2342999ae27f68fdc9bd6"}, 1266 | {file = "tokenizers-0.19.1-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:78e769eb3b2c79687d9cb0f89ef77223e8e279b75c0a968e637ca7043a84463f"}, 1267 | {file = "tokenizers-0.19.1-cp37-none-win32.whl", hash = "sha256:72791f9bb1ca78e3ae525d4782e85272c63faaef9940d92142aa3eb79f3407a3"}, 1268 | {file = "tokenizers-0.19.1-cp37-none-win_amd64.whl", hash = "sha256:f3bbb7a0c5fcb692950b041ae11067ac54826204318922da754f908d95619fbc"}, 1269 | {file = "tokenizers-0.19.1-cp38-cp38-macosx_10_12_x86_64.whl", hash = "sha256:07f9295349bbbcedae8cefdbcfa7f686aa420be8aca5d4f7d1ae6016c128c0c5"}, 1270 | {file = "tokenizers-0.19.1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:10a707cc6c4b6b183ec5dbfc5c34f3064e18cf62b4a938cb41699e33a99e03c1"}, 1271 | {file = "tokenizers-0.19.1-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:6309271f57b397aa0aff0cbbe632ca9d70430839ca3178bf0f06f825924eca22"}, 1272 | {file = "tokenizers-0.19.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4ad23d37d68cf00d54af184586d79b84075ada495e7c5c0f601f051b162112dc"}, 1273 | {file = "tokenizers-0.19.1-cp38-cp38-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:427c4f0f3df9109314d4f75b8d1f65d9477033e67ffaec4bca53293d3aca286d"}, 1274 | {file = "tokenizers-0.19.1-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e83a31c9cf181a0a3ef0abad2b5f6b43399faf5da7e696196ddd110d332519ee"}, 1275 | {file = "tokenizers-0.19.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c27b99889bd58b7e301468c0838c5ed75e60c66df0d4db80c08f43462f82e0d3"}, 1276 | {file = "tokenizers-0.19.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bac0b0eb952412b0b196ca7a40e7dce4ed6f6926489313414010f2e6b9ec2adf"}, 1277 | {file = "tokenizers-0.19.1-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:8a6298bde623725ca31c9035a04bf2ef63208d266acd2bed8c2cb7d2b7d53ce6"}, 1278 | {file = "tokenizers-0.19.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:08a44864e42fa6d7d76d7be4bec62c9982f6f6248b4aa42f7302aa01e0abfd26"}, 1279 | {file = "tokenizers-0.19.1-cp38-none-win32.whl", hash = "sha256:1de5bc8652252d9357a666e609cb1453d4f8e160eb1fb2830ee369dd658e8975"}, 1280 | {file = "tokenizers-0.19.1-cp38-none-win_amd64.whl", hash = "sha256:0bcce02bf1ad9882345b34d5bd25ed4949a480cf0e656bbd468f4d8986f7a3f1"}, 1281 | {file = "tokenizers-0.19.1-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:0b9394bd204842a2a1fd37fe29935353742be4a3460b6ccbaefa93f58a8df43d"}, 1282 | {file = "tokenizers-0.19.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:4692ab92f91b87769d950ca14dbb61f8a9ef36a62f94bad6c82cc84a51f76f6a"}, 1283 | {file = "tokenizers-0.19.1-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:6258c2ef6f06259f70a682491c78561d492e885adeaf9f64f5389f78aa49a051"}, 1284 | {file = "tokenizers-0.19.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c85cf76561fbd01e0d9ea2d1cbe711a65400092bc52b5242b16cfd22e51f0c58"}, 1285 | {file = "tokenizers-0.19.1-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:670b802d4d82bbbb832ddb0d41df7015b3e549714c0e77f9bed3e74d42400fbe"}, 1286 | {file = "tokenizers-0.19.1-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:85aa3ab4b03d5e99fdd31660872249df5e855334b6c333e0bc13032ff4469c4a"}, 1287 | {file = "tokenizers-0.19.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:cbf001afbbed111a79ca47d75941e9e5361297a87d186cbfc11ed45e30b5daba"}, 1288 | {file = "tokenizers-0.19.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b4c89aa46c269e4e70c4d4f9d6bc644fcc39bb409cb2a81227923404dd6f5227"}, 1289 | {file = "tokenizers-0.19.1-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:39c1ec76ea1027438fafe16ecb0fb84795e62e9d643444c1090179e63808c69d"}, 1290 | {file = "tokenizers-0.19.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:c2a0d47a89b48d7daa241e004e71fb5a50533718897a4cd6235cb846d511a478"}, 1291 | {file = "tokenizers-0.19.1-cp39-none-win32.whl", hash = "sha256:61b7fe8886f2e104d4caf9218b157b106207e0f2a4905c9c7ac98890688aabeb"}, 1292 | {file = "tokenizers-0.19.1-cp39-none-win_amd64.whl", hash = "sha256:f97660f6c43efd3e0bfd3f2e3e5615bf215680bad6ee3d469df6454b8c6e8256"}, 1293 | {file = "tokenizers-0.19.1-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:3b11853f17b54c2fe47742c56d8a33bf49ce31caf531e87ac0d7d13d327c9334"}, 1294 | {file = "tokenizers-0.19.1-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:d26194ef6c13302f446d39972aaa36a1dda6450bc8949f5eb4c27f51191375bd"}, 1295 | {file = "tokenizers-0.19.1-pp310-pypy310_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:e8d1ed93beda54bbd6131a2cb363a576eac746d5c26ba5b7556bc6f964425594"}, 1296 | {file = "tokenizers-0.19.1-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ca407133536f19bdec44b3da117ef0d12e43f6d4b56ac4c765f37eca501c7bda"}, 1297 | {file = "tokenizers-0.19.1-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ce05fde79d2bc2e46ac08aacbc142bead21614d937aac950be88dc79f9db9022"}, 1298 | {file = "tokenizers-0.19.1-pp310-pypy310_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:35583cd46d16f07c054efd18b5d46af4a2f070a2dd0a47914e66f3ff5efb2b1e"}, 1299 | {file = "tokenizers-0.19.1-pp310-pypy310_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:43350270bfc16b06ad3f6f07eab21f089adb835544417afda0f83256a8bf8b75"}, 1300 | {file = "tokenizers-0.19.1-pp37-pypy37_pp73-macosx_10_12_x86_64.whl", hash = "sha256:b4399b59d1af5645bcee2072a463318114c39b8547437a7c2d6a186a1b5a0e2d"}, 1301 | {file = "tokenizers-0.19.1-pp37-pypy37_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:6852c5b2a853b8b0ddc5993cd4f33bfffdca4fcc5d52f89dd4b8eada99379285"}, 1302 | {file = "tokenizers-0.19.1-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:bcd266ae85c3d39df2f7e7d0e07f6c41a55e9a3123bb11f854412952deacd828"}, 1303 | {file = "tokenizers-0.19.1-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ecb2651956eea2aa0a2d099434134b1b68f1c31f9a5084d6d53f08ed43d45ff2"}, 1304 | {file = "tokenizers-0.19.1-pp37-pypy37_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:b279ab506ec4445166ac476fb4d3cc383accde1ea152998509a94d82547c8e2a"}, 1305 | {file = "tokenizers-0.19.1-pp37-pypy37_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:89183e55fb86e61d848ff83753f64cded119f5d6e1f553d14ffee3700d0a4a49"}, 1306 | {file = "tokenizers-0.19.1-pp38-pypy38_pp73-macosx_10_12_x86_64.whl", hash = "sha256:b2edbc75744235eea94d595a8b70fe279dd42f3296f76d5a86dde1d46e35f574"}, 1307 | {file = "tokenizers-0.19.1-pp38-pypy38_pp73-macosx_11_0_arm64.whl", hash = "sha256:0e64bfde9a723274e9a71630c3e9494ed7b4c0f76a1faacf7fe294cd26f7ae7c"}, 1308 | {file = "tokenizers-0.19.1-pp38-pypy38_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:0b5ca92bfa717759c052e345770792d02d1f43b06f9e790ca0a1db62838816f3"}, 1309 | {file = "tokenizers-0.19.1-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6f8a20266e695ec9d7a946a019c1d5ca4eddb6613d4f466888eee04f16eedb85"}, 1310 | {file = "tokenizers-0.19.1-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:63c38f45d8f2a2ec0f3a20073cccb335b9f99f73b3c69483cd52ebc75369d8a1"}, 1311 | {file = "tokenizers-0.19.1-pp38-pypy38_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:dd26e3afe8a7b61422df3176e06664503d3f5973b94f45d5c45987e1cb711876"}, 1312 | {file = "tokenizers-0.19.1-pp38-pypy38_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:eddd5783a4a6309ce23432353cdb36220e25cbb779bfa9122320666508b44b88"}, 1313 | {file = "tokenizers-0.19.1-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:56ae39d4036b753994476a1b935584071093b55c7a72e3b8288e68c313ca26e7"}, 1314 | {file = "tokenizers-0.19.1-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:f9939ca7e58c2758c01b40324a59c034ce0cebad18e0d4563a9b1beab3018243"}, 1315 | {file = "tokenizers-0.19.1-pp39-pypy39_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:6c330c0eb815d212893c67a032e9dc1b38a803eccb32f3e8172c19cc69fbb439"}, 1316 | {file = "tokenizers-0.19.1-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ec11802450a2487cdf0e634b750a04cbdc1c4d066b97d94ce7dd2cb51ebb325b"}, 1317 | {file = "tokenizers-0.19.1-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a2b718f316b596f36e1dae097a7d5b91fc5b85e90bf08b01ff139bd8953b25af"}, 1318 | {file = "tokenizers-0.19.1-pp39-pypy39_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:ed69af290c2b65169f0ba9034d1dc39a5db9459b32f1dd8b5f3f32a3fcf06eab"}, 1319 | {file = "tokenizers-0.19.1-pp39-pypy39_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:f8a9c828277133af13f3859d1b6bf1c3cb6e9e1637df0e45312e6b7c2e622b1f"}, 1320 | {file = "tokenizers-0.19.1.tar.gz", hash = "sha256:ee59e6680ed0fdbe6b724cf38bd70400a0c1dd623b07ac729087270caeac88e3"}, 1321 | ] 1322 | 1323 | [package.dependencies] 1324 | huggingface-hub = ">=0.16.4,<1.0" 1325 | 1326 | [package.extras] 1327 | dev = ["tokenizers[testing]"] 1328 | docs = ["setuptools-rust", "sphinx", "sphinx-rtd-theme"] 1329 | testing = ["black (==22.3)", "datasets", "numpy", "pytest", "requests", "ruff"] 1330 | 1331 | [[package]] 1332 | name = "torch" 1333 | version = "2.0.1+cu118" 1334 | description = "Tensors and Dynamic neural networks in Python with strong GPU acceleration" 1335 | optional = false 1336 | python-versions = ">=3.8.0" 1337 | files = [ 1338 | {file = "torch-2.0.1+cu118-cp310-cp310-linux_x86_64.whl", hash = "sha256:a7a49d459bf4862f64f7bc1a68beccf8881c2fa9f3e0569608e16ba6f85ebf7b"}, 1339 | ] 1340 | 1341 | [package.dependencies] 1342 | filelock = "*" 1343 | jinja2 = "*" 1344 | networkx = "*" 1345 | sympy = "*" 1346 | triton = {version = "2.0.0", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} 1347 | typing-extensions = "*" 1348 | 1349 | [package.extras] 1350 | opt-einsum = ["opt-einsum (>=3.3)"] 1351 | 1352 | [package.source] 1353 | type = "url" 1354 | url = "https://download.pytorch.org/whl/cu118/torch-2.0.1%2Bcu118-cp310-cp310-linux_x86_64.whl" 1355 | 1356 | [[package]] 1357 | name = "tqdm" 1358 | version = "4.66.2" 1359 | description = "Fast, Extensible Progress Meter" 1360 | optional = false 1361 | python-versions = ">=3.7" 1362 | files = [ 1363 | {file = "tqdm-4.66.2-py3-none-any.whl", hash = "sha256:1ee4f8a893eb9bef51c6e35730cebf234d5d0b6bd112b0271e10ed7c24a02bd9"}, 1364 | {file = "tqdm-4.66.2.tar.gz", hash = "sha256:6cd52cdf0fef0e0f543299cfc96fec90d7b8a7e88745f411ec33eb44d5ed3531"}, 1365 | ] 1366 | 1367 | [package.dependencies] 1368 | colorama = {version = "*", markers = "platform_system == \"Windows\""} 1369 | 1370 | [package.extras] 1371 | dev = ["pytest (>=6)", "pytest-cov", "pytest-timeout", "pytest-xdist"] 1372 | notebook = ["ipywidgets (>=6)"] 1373 | slack = ["slack-sdk"] 1374 | telegram = ["requests"] 1375 | 1376 | [[package]] 1377 | name = "transformers" 1378 | version = "4.40.1" 1379 | description = "State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow" 1380 | optional = false 1381 | python-versions = ">=3.8.0" 1382 | files = [ 1383 | {file = "transformers-4.40.1-py3-none-any.whl", hash = "sha256:9d5ee0c8142a60501faf9e49a0b42f8e9cb8611823bce4f195a9325a6816337e"}, 1384 | {file = "transformers-4.40.1.tar.gz", hash = "sha256:55e1697e6f18b58273e7117bb469cdffc11be28995462d8d5e422fef38d2de36"}, 1385 | ] 1386 | 1387 | [package.dependencies] 1388 | filelock = "*" 1389 | fugashi = {version = ">=1.0", optional = true, markers = "extra == \"ja\""} 1390 | huggingface-hub = ">=0.19.3,<1.0" 1391 | ipadic = {version = ">=1.0.0,<2.0", optional = true, markers = "extra == \"ja\""} 1392 | numpy = ">=1.17" 1393 | packaging = ">=20.0" 1394 | protobuf = {version = "*", optional = true, markers = "extra == \"sentencepiece\""} 1395 | pyyaml = ">=5.1" 1396 | regex = "!=2019.12.17" 1397 | requests = "*" 1398 | rhoknp = {version = ">=1.1.0,<1.3.1", optional = true, markers = "extra == \"ja\""} 1399 | safetensors = ">=0.4.1" 1400 | sentencepiece = {version = ">=0.1.91,<0.1.92 || >0.1.92", optional = true, markers = "extra == \"sentencepiece\""} 1401 | sudachidict-core = {version = ">=20220729", optional = true, markers = "extra == \"ja\""} 1402 | sudachipy = {version = ">=0.6.6", optional = true, markers = "extra == \"ja\""} 1403 | tokenizers = ">=0.19,<0.20" 1404 | tqdm = ">=4.27" 1405 | unidic = {version = ">=1.0.2", optional = true, markers = "extra == \"ja\""} 1406 | unidic-lite = {version = ">=1.0.7", optional = true, markers = "extra == \"ja\""} 1407 | 1408 | [package.extras] 1409 | accelerate = ["accelerate (>=0.21.0)"] 1410 | agents = ["Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "datasets (!=2.5.0)", "diffusers", "opencv-python", "sentencepiece (>=0.1.91,!=0.1.92)", "torch"] 1411 | all = ["Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "av (==9.2.0)", "codecarbon (==1.2.0)", "decord (==0.6.0)", "flax (>=0.4.1,<=0.7.0)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "phonemizer", "protobuf", "pyctcdecode (>=0.4.0)", "ray[tune] (>=2.7.0)", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "tensorflow (>=2.6,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timm", "tokenizers (>=0.19,<0.20)", "torch", "torchaudio", "torchvision"] 1412 | audio = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"] 1413 | codecarbon = ["codecarbon (==1.2.0)"] 1414 | deepspeed = ["accelerate (>=0.21.0)", "deepspeed (>=0.9.3)"] 1415 | deepspeed-testing = ["GitPython (<3.1.19)", "accelerate (>=0.21.0)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "deepspeed (>=0.9.3)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "hf-doc-builder (>=0.3.0)", "nltk", "optuna", "parameterized", "protobuf", "psutil", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorboard", "timeout-decorator"] 1416 | dev = ["GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "av (==9.2.0)", "beautifulsoup4", "codecarbon (==1.2.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "decord (==0.6.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "flax (>=0.4.1,<=0.7.0)", "fugashi (>=1.0)", "hf-doc-builder", "hf-doc-builder (>=0.3.0)", "ipadic (>=1.0.0,<2.0)", "isort (>=5.5.4)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "nltk", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-timeout", "pytest-xdist", "ray[tune] (>=2.7.0)", "rhoknp (>=1.1.0,<1.3.1)", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "tensorboard", "tensorflow (>=2.6,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timeout-decorator", "timm", "tokenizers (>=0.19,<0.20)", "torch", "torchaudio", "torchvision", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)", "urllib3 (<2.0.0)"] 1417 | dev-tensorflow = ["GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "hf-doc-builder", "hf-doc-builder (>=0.3.0)", "isort (>=5.5.4)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "nltk", "onnxconverter-common", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorboard", "tensorflow (>=2.6,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timeout-decorator", "tokenizers (>=0.19,<0.20)", "urllib3 (<2.0.0)"] 1418 | dev-torch = ["GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "beautifulsoup4", "codecarbon (==1.2.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "fugashi (>=1.0)", "hf-doc-builder", "hf-doc-builder (>=0.3.0)", "ipadic (>=1.0.0,<2.0)", "isort (>=5.5.4)", "kenlm", "librosa", "nltk", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "optuna", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-timeout", "pytest-xdist", "ray[tune] (>=2.7.0)", "rhoknp (>=1.1.0,<1.3.1)", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "tensorboard", "timeout-decorator", "timm", "tokenizers (>=0.19,<0.20)", "torch", "torchaudio", "torchvision", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)", "urllib3 (<2.0.0)"] 1419 | docs = ["Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "av (==9.2.0)", "codecarbon (==1.2.0)", "decord (==0.6.0)", "flax (>=0.4.1,<=0.7.0)", "hf-doc-builder", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "phonemizer", "protobuf", "pyctcdecode (>=0.4.0)", "ray[tune] (>=2.7.0)", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "tensorflow (>=2.6,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timm", "tokenizers (>=0.19,<0.20)", "torch", "torchaudio", "torchvision"] 1420 | docs-specific = ["hf-doc-builder"] 1421 | flax = ["flax (>=0.4.1,<=0.7.0)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "optax (>=0.0.8,<=0.1.4)"] 1422 | flax-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"] 1423 | ftfy = ["ftfy"] 1424 | integrations = ["optuna", "ray[tune] (>=2.7.0)", "sigopt"] 1425 | ja = ["fugashi (>=1.0)", "ipadic (>=1.0.0,<2.0)", "rhoknp (>=1.1.0,<1.3.1)", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)"] 1426 | modelcreation = ["cookiecutter (==1.7.3)"] 1427 | natten = ["natten (>=0.14.6,<0.15.0)"] 1428 | onnx = ["onnxconverter-common", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "tf2onnx"] 1429 | onnxruntime = ["onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)"] 1430 | optuna = ["optuna"] 1431 | quality = ["GitPython (<3.1.19)", "datasets (!=2.5.0)", "hf-doc-builder (>=0.3.0)", "isort (>=5.5.4)", "ruff (==0.1.5)", "urllib3 (<2.0.0)"] 1432 | ray = ["ray[tune] (>=2.7.0)"] 1433 | retrieval = ["datasets (!=2.5.0)", "faiss-cpu"] 1434 | sagemaker = ["sagemaker (>=2.31.0)"] 1435 | sentencepiece = ["protobuf", "sentencepiece (>=0.1.91,!=0.1.92)"] 1436 | serving = ["fastapi", "pydantic", "starlette", "uvicorn"] 1437 | sigopt = ["sigopt"] 1438 | sklearn = ["scikit-learn"] 1439 | speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)", "torchaudio"] 1440 | testing = ["GitPython (<3.1.19)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "hf-doc-builder (>=0.3.0)", "nltk", "parameterized", "protobuf", "psutil", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorboard", "timeout-decorator"] 1441 | tf = ["keras-nlp (>=0.3.1)", "onnxconverter-common", "tensorflow (>=2.6,<2.16)", "tensorflow-text (<2.16)", "tf2onnx"] 1442 | tf-cpu = ["keras-nlp (>=0.3.1)", "onnxconverter-common", "tensorflow-cpu (>=2.6,<2.16)", "tensorflow-text (<2.16)", "tf2onnx"] 1443 | tf-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"] 1444 | timm = ["timm"] 1445 | tokenizers = ["tokenizers (>=0.19,<0.20)"] 1446 | torch = ["accelerate (>=0.21.0)", "torch"] 1447 | torch-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)", "torchaudio"] 1448 | torch-vision = ["Pillow (>=10.0.1,<=15.0)", "torchvision"] 1449 | torchhub = ["filelock", "huggingface-hub (>=0.19.3,<1.0)", "importlib-metadata", "numpy (>=1.17)", "packaging (>=20.0)", "protobuf", "regex (!=2019.12.17)", "requests", "sentencepiece (>=0.1.91,!=0.1.92)", "tokenizers (>=0.19,<0.20)", "torch", "tqdm (>=4.27)"] 1450 | video = ["av (==9.2.0)", "decord (==0.6.0)"] 1451 | vision = ["Pillow (>=10.0.1,<=15.0)"] 1452 | 1453 | [[package]] 1454 | name = "triton" 1455 | version = "2.0.0" 1456 | description = "A language and compiler for custom Deep Learning operations" 1457 | optional = false 1458 | python-versions = "*" 1459 | files = [ 1460 | {file = "triton-2.0.0-1-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:38806ee9663f4b0f7cd64790e96c579374089e58f49aac4a6608121aa55e2505"}, 1461 | {file = "triton-2.0.0-1-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:226941c7b8595219ddef59a1fdb821e8c744289a132415ddd584facedeb475b1"}, 1462 | {file = "triton-2.0.0-1-cp36-cp36m-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:4c9fc8c89874bc48eb7e7b2107a9b8d2c0bf139778637be5bfccb09191685cfd"}, 1463 | {file = "triton-2.0.0-1-cp37-cp37m-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:d2684b6a60b9f174f447f36f933e9a45f31db96cb723723ecd2dcfd1c57b778b"}, 1464 | {file = "triton-2.0.0-1-cp38-cp38-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:9d4978298b74fcf59a75fe71e535c092b023088933b2f1df933ec32615e4beef"}, 1465 | {file = "triton-2.0.0-1-cp39-cp39-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:74f118c12b437fb2ca25e1a04759173b517582fcf4c7be11913316c764213656"}, 1466 | {file = "triton-2.0.0-1-pp37-pypy37_pp73-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:9618815a8da1d9157514f08f855d9e9ff92e329cd81c0305003eb9ec25cc5add"}, 1467 | {file = "triton-2.0.0-1-pp38-pypy38_pp73-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:1aca3303629cd3136375b82cb9921727f804e47ebee27b2677fef23005c3851a"}, 1468 | {file = "triton-2.0.0-1-pp39-pypy39_pp73-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:e3e13aa8b527c9b642e3a9defcc0fbd8ffbe1c80d8ac8c15a01692478dc64d8a"}, 1469 | {file = "triton-2.0.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8f05a7e64e4ca0565535e3d5d3405d7e49f9d308505bb7773d21fb26a4c008c2"}, 1470 | {file = "triton-2.0.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bb4b99ca3c6844066e516658541d876c28a5f6e3a852286bbc97ad57134827fd"}, 1471 | {file = "triton-2.0.0-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:47b4d70dc92fb40af553b4460492c31dc7d3a114a979ffb7a5cdedb7eb546c08"}, 1472 | {file = "triton-2.0.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fedce6a381901b1547e0e7e1f2546e4f65dca6d91e2d8a7305a2d1f5551895be"}, 1473 | {file = "triton-2.0.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:75834f27926eab6c7f00ce73aaf1ab5bfb9bec6eb57ab7c0bfc0a23fac803b4c"}, 1474 | {file = "triton-2.0.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0117722f8c2b579cd429e0bee80f7731ae05f63fe8e9414acd9a679885fcbf42"}, 1475 | {file = "triton-2.0.0-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bcd9be5d0c2e45d2b7e6ddc6da20112b6862d69741576f9c3dbaf941d745ecae"}, 1476 | {file = "triton-2.0.0-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:42a0d2c3fc2eab4ba71384f2e785fbfd47aa41ae05fa58bf12cb31dcbd0aeceb"}, 1477 | {file = "triton-2.0.0-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:52c47b72c72693198163ece9d90a721299e4fb3b8e24fd13141e384ad952724f"}, 1478 | ] 1479 | 1480 | [package.dependencies] 1481 | cmake = "*" 1482 | filelock = "*" 1483 | lit = "*" 1484 | torch = "*" 1485 | 1486 | [package.extras] 1487 | tests = ["autopep8", "flake8", "isort", "numpy", "pytest", "scipy (>=1.7.1)"] 1488 | tutorials = ["matplotlib", "pandas", "tabulate"] 1489 | 1490 | [[package]] 1491 | name = "typed-argument-parser" 1492 | version = "1.10.0" 1493 | description = "Typed Argument Parser" 1494 | optional = false 1495 | python-versions = ">=3.8" 1496 | files = [ 1497 | {file = "typed-argument-parser-1.10.0.tar.gz", hash = "sha256:d0e463511549f2951df2968b181b856c2e281be1ab1f4471437de08eb4113ef2"}, 1498 | ] 1499 | 1500 | [package.dependencies] 1501 | docstring-parser = ">=0.15" 1502 | typing-inspect = ">=0.7.1" 1503 | 1504 | [package.extras] 1505 | dev = ["flake8", "pydantic (>=2.5.0)", "pytest", "pytest-cov"] 1506 | dev-no-pydantic = ["flake8", "pytest", "pytest-cov"] 1507 | 1508 | [[package]] 1509 | name = "typing-extensions" 1510 | version = "4.11.0" 1511 | description = "Backported and Experimental Type Hints for Python 3.8+" 1512 | optional = false 1513 | python-versions = ">=3.8" 1514 | files = [ 1515 | {file = "typing_extensions-4.11.0-py3-none-any.whl", hash = "sha256:c1f94d72897edaf4ce775bb7558d5b79d8126906a14ea5ed1635921406c0387a"}, 1516 | {file = "typing_extensions-4.11.0.tar.gz", hash = "sha256:83f085bd5ca59c80295fc2a82ab5dac679cbe02b9f33f7d83af68e241bea51b0"}, 1517 | ] 1518 | 1519 | [[package]] 1520 | name = "typing-inspect" 1521 | version = "0.9.0" 1522 | description = "Runtime inspection utilities for typing module." 1523 | optional = false 1524 | python-versions = "*" 1525 | files = [ 1526 | {file = "typing_inspect-0.9.0-py3-none-any.whl", hash = "sha256:9ee6fc59062311ef8547596ab6b955e1b8aa46242d854bfc78f4f6b0eff35f9f"}, 1527 | {file = "typing_inspect-0.9.0.tar.gz", hash = "sha256:b23fc42ff6f6ef6954e4852c1fb512cdd18dbea03134f91f856a95ccc9461f78"}, 1528 | ] 1529 | 1530 | [package.dependencies] 1531 | mypy-extensions = ">=0.3.0" 1532 | typing-extensions = ">=3.7.4" 1533 | 1534 | [[package]] 1535 | name = "tzdata" 1536 | version = "2024.1" 1537 | description = "Provider of IANA time zone data" 1538 | optional = false 1539 | python-versions = ">=2" 1540 | files = [ 1541 | {file = "tzdata-2024.1-py2.py3-none-any.whl", hash = "sha256:9068bc196136463f5245e51efda838afa15aaeca9903f49050dfa2679db4d252"}, 1542 | {file = "tzdata-2024.1.tar.gz", hash = "sha256:2674120f8d891909751c38abcdfd386ac0a5a1127954fbc332af6b5ceae07efd"}, 1543 | ] 1544 | 1545 | [[package]] 1546 | name = "unidic" 1547 | version = "1.1.0" 1548 | description = "UniDic packaged for Python" 1549 | optional = false 1550 | python-versions = ">=3.5" 1551 | files = [ 1552 | {file = "unidic-1.1.0.tar.gz", hash = "sha256:0ab91c05de342c84d2a6314901fd3afb9061ecd7534dd4a0431dccbb87d921b7"}, 1553 | ] 1554 | 1555 | [package.dependencies] 1556 | plac = ">=1.1.3,<2.0.0" 1557 | requests = ">=2.22.0,<3.0.0" 1558 | tqdm = ">=4.41.1,<5.0.0" 1559 | wasabi = ">=0.6.0,<1.0.0" 1560 | 1561 | [[package]] 1562 | name = "unidic-lite" 1563 | version = "1.0.8" 1564 | description = "A small version of UniDic packaged for Python" 1565 | optional = false 1566 | python-versions = "*" 1567 | files = [ 1568 | {file = "unidic-lite-1.0.8.tar.gz", hash = "sha256:db9d4572d9fdd4d00a97949d4b0741ec480ee05a7e7e2e32f547500dae27b245"}, 1569 | ] 1570 | 1571 | [[package]] 1572 | name = "urllib3" 1573 | version = "2.2.1" 1574 | description = "HTTP library with thread-safe connection pooling, file post, and more." 1575 | optional = false 1576 | python-versions = ">=3.8" 1577 | files = [ 1578 | {file = "urllib3-2.2.1-py3-none-any.whl", hash = "sha256:450b20ec296a467077128bff42b73080516e71b56ff59a60a02bef2232c4fa9d"}, 1579 | {file = "urllib3-2.2.1.tar.gz", hash = "sha256:d0570876c61ab9e520d776c38acbbb5b05a776d3f9ff98a5c8fd5162a444cf19"}, 1580 | ] 1581 | 1582 | [package.extras] 1583 | brotli = ["brotli (>=1.0.9)", "brotlicffi (>=0.8.0)"] 1584 | h2 = ["h2 (>=4,<5)"] 1585 | socks = ["pysocks (>=1.5.6,!=1.5.7,<2.0)"] 1586 | zstd = ["zstandard (>=0.18.0)"] 1587 | 1588 | [[package]] 1589 | name = "wasabi" 1590 | version = "0.10.1" 1591 | description = "A lightweight console printing and formatting toolkit" 1592 | optional = false 1593 | python-versions = "*" 1594 | files = [ 1595 | {file = "wasabi-0.10.1-py3-none-any.whl", hash = "sha256:fe862cc24034fbc9f04717cd312ab884f71f51a8ecabebc3449b751c2a649d83"}, 1596 | {file = "wasabi-0.10.1.tar.gz", hash = "sha256:c8e372781be19272942382b14d99314d175518d7822057cb7a97010c4259d249"}, 1597 | ] 1598 | 1599 | [metadata] 1600 | lock-version = "2.0" 1601 | python-versions = "3.10.x" 1602 | content-hash = "24f331eba5c36f8fbfaa97ce99f3d9f45efc84e73f95a98cc9f93d5bbd423aa6" 1603 | -------------------------------------------------------------------------------- /poetry.toml: -------------------------------------------------------------------------------- 1 | [virtualenvs] 2 | in-project = true 3 | prefer-active-python = true 4 | -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- 1 | [tool.poetry] 2 | name = "bert-classification-tutorial" 3 | version = "0.2.0" 4 | description = "" 5 | authors = ["hppRC "] 6 | readme = "README.md" 7 | packages = [{ include = "src" }] 8 | 9 | [tool.poetry.dependencies] 10 | python = "3.10.x" 11 | torch = { url = "https://download.pytorch.org/whl/cu118/torch-2.0.1%2Bcu118-cp310-cp310-linux_x86_64.whl" } 12 | transformers = { extras = ["ja", "sentencepiece"], version = "^4.30.0" } 13 | numpy = "^1.25.0" 14 | pandas = "^2.0.3" 15 | more-itertools = "^9.1.0" 16 | scikit-learn = "^1.2.2" 17 | tqdm = "^4.65.0" 18 | typed-argument-parser = "^1.8.1" 19 | 20 | 21 | [build-system] 22 | requires = ["poetry-core"] 23 | build-backend = "poetry.core.masonry.api" 24 | -------------------------------------------------------------------------------- /results/all.csv: -------------------------------------------------------------------------------- 1 | model_name,lr,best-val-epoch,best-val-f1,loss,accuracy,precision,recall,f1 2 | studio-ousia/luke-japanese-large-lite,3e-05,13,0.9803307153306133,1.0117710664179986e-05,0.9782608695652174,0.9781845081015911,0.9721837335852859,0.974666386510519 3 | cl-tohoku/bert-large-japanese,3e-05,10,0.9623007426615955,1.3588468351846803e-05,0.9769021739130435,0.9752889944289515,0.9743804670186093,0.9745718695194223 4 | studio-ousia/luke-japanese-large-lite,5e-05,17,0.9716851424735443,0.0019995424410571222,0.9769021739130435,0.9750356067064866,0.972172760983891,0.9733810284873314 5 | cl-tohoku/bert-base-japanese-v3,1e-05,16,0.965857470358343,2.7869671137760516e-05,0.9755434782608695,0.9741442452343865,0.9700223416102411,0.9717839483791343 6 | cl-tohoku/bert-large-japanese,5e-05,16,0.9691338127571516,4.4329594263968906e-06,0.9755434782608695,0.971268708753331,0.9710024409536481,0.9710252631500842 7 | cl-tohoku/bert-base-japanese-v3,3e-05,15,0.9691015887210997,7.329005039418521e-06,0.9728260869565217,0.969695205944551,0.9685780081751972,0.9688998388633822 8 | xlm-roberta-large,1e-05,3,0.9721218673483413,0.0005663783168015273,0.9714673913043478,0.9736291125269076,0.9649464572349067,0.9683345666416806 9 | studio-ousia/mluke-large-lite,5e-05,14,0.9694460346550713,4.861095753174437e-06,0.9728260869565217,0.9725267620345418,0.9655621507784667,0.9682639977822115 10 | bert-base-multilingual-cased,3e-05,17,0.9612447795788788,1.9436233940169863e-05,0.9714673913043478,0.968936588217098,0.9676290961283907,0.96813936933821 11 | cl-tohoku/bert-large-japanese-v2,5e-05,11,0.9715665344423188,4.899185454553884e-05,0.9741847826086957,0.9706415957614758,0.965598929930874,0.9676653237078823 12 | studio-ousia/luke-japanese-base-lite,3e-05,5,0.9648968201786197,0.0001528384366437145,0.970108695652174,0.969090673825161,0.9656991271844912,0.9671426262493132 13 | cl-tohoku/bert-large-japanese-v2,3e-05,10,0.9717731438474253,3.141069622791332e-05,0.9728260869565217,0.9683687407120058,0.9663689795953572,0.9670916798917983 14 | studio-ousia/luke-japanese-base-lite,1e-05,11,0.9708808393837598,0.0007912645359402118,0.970108695652174,0.9689741516058051,0.9645054467781975,0.9663920648129523 15 | xlm-roberta-base,3e-05,15,0.9760026180244464,0.0004802491191936576,0.9714673913043478,0.9671245841194211,0.9658355923326999,0.9663132481207993 16 | studio-ousia/mluke-base-lite,3e-05,17,0.969131791255312,0.0023548831434353538,0.970108695652174,0.9661274433019381,0.9662882959764959,0.9660215446218198 17 | studio-ousia/mluke-base-lite,5e-05,18,0.9681537757423995,0.0033546054492826047,0.96875,0.9648774946140539,0.9647618081883983,0.9646811231870799 18 | studio-ousia/luke-japanese-base-lite,5e-05,13,0.9731860115903948,0.01046712955702906,0.970108695652174,0.9671712874191836,0.9628725028120493,0.9646175059058673 19 | cl-tohoku/bert-base-japanese-whole-word-masking,5e-05,9,0.9654032528282558,4.343916257114514e-05,0.96875,0.9658907778511323,0.963746490123714,0.9644600326795809 20 | cl-tohoku/bert-base-japanese-v2,5e-05,9,0.9672144444978882,1.587970030453542e-05,0.96875,0.9641995015208553,0.9645619070518967,0.9642857487777206 21 | cl-tohoku/bert-large-japanese,1e-05,14,0.9613073812131732,8.425286859678833e-06,0.970108695652174,0.9677074058019275,0.9620579209850821,0.9642466437675318 22 | studio-ousia/luke-japanese-large-lite,1e-05,9,0.9727597738641758,0.0005273388536727947,0.970108695652174,0.9656332324090893,0.9629835356644159,0.9640365538555593 23 | cl-tohoku/bert-base-japanese-v3,5e-05,13,0.9715090487864061,0.00021241182137442672,0.96875,0.9658555512470703,0.9627886451858235,0.9639172275240635 24 | cl-tohoku/bert-base-japanese-v2,3e-05,7,0.9618507864110506,0.001678766439790311,0.967391304347826,0.964752029246868,0.9629136610433748,0.9633427120676732 25 | cl-tohoku/bert-large-japanese-v2,1e-05,5,0.9738005698083073,0.0001132118961085444,0.967391304347826,0.9656746194737741,0.9609654714470326,0.9626031688833093 26 | cl-tohoku/bert-large-japanese-char-v2,3e-05,16,0.9592427785466501,0.014843723048334536,0.967391304347826,0.9663115069555209,0.959849892028046,0.962350909916791 27 | studio-ousia/mluke-large-lite,3e-05,17,0.9657439662039291,0.0002081041305285433,0.96875,0.9629213890280524,0.9607069333238749,0.96160130937943 28 | cl-tohoku/bert-base-japanese,3e-05,6,0.966716985736648,0.0038873838341754417,0.967391304347826,0.9620198298847006,0.9615802535669135,0.9615671825196155 29 | cl-tohoku/bert-base-japanese-v2,1e-05,6,0.9615521017965963,0.0010342133919829907,0.967391304347826,0.962000095675056,0.9618281998167263,0.9615263189795206 30 | bert-base-multilingual-cased,5e-05,15,0.9620682725123305,1.92398134538013e-05,0.9660326086956522,0.9625054039683284,0.9606018764758684,0.961195554917367 31 | xlm-roberta-base,5e-05,10,0.9648023564108895,0.001497434209222379,0.9660326086956522,0.9613782334015709,0.960417665785215,0.9607809075604544 32 | xlm-roberta-base,1e-05,15,0.9643574063783069,7.998038832422183e-05,0.9646739130434783,0.959440927052358,0.9622811646105518,0.9606843988864041 33 | cl-tohoku/bert-base-japanese-char-v2,5e-05,14,0.9523335103601279,0.004338460124057272,0.9646739130434783,0.9611414387393956,0.9602471394499614,0.9602451845135932 34 | cl-tohoku/bert-large-japanese-char-v2,1e-05,19,0.956036437040095,0.0001474128044007913,0.9646739130434783,0.9588824391170727,0.9598192204182762,0.9591458686216965 35 | studio-ousia/mluke-large-lite,1e-05,9,0.9690493411535984,0.001147434925255568,0.9646739130434783,0.9633268348805074,0.9560683892362977,0.9587025258220265 36 | cl-tohoku/bert-base-japanese-whole-word-masking,3e-05,9,0.9642480077902632,0.0033488668825315394,0.9646739130434783,0.9595812778107172,0.9584384904580612,0.958665409639662 37 | xlm-roberta-large,5e-05,6,0.9565019896250944,0.000861010716661163,0.9633152173913043,0.9619913105140072,0.9551443103435999,0.9579193305040508 38 | cl-tohoku/bert-base-japanese,5e-05,19,0.9643157540453551,4.0935777613650196e-05,0.9646739130434783,0.9594055501333799,0.956915164455549,0.9578999960748765 39 | studio-ousia/mluke-base-lite,1e-05,10,0.9667572871317063,0.005579081566437431,0.9646739130434783,0.9573873338649075,0.9587910759615581,0.9578659717250706 40 | cl-tohoku/bert-base-japanese,1e-05,7,0.9654186261994657,0.0023639608660469885,0.9646739130434783,0.9576922862452952,0.9571652663952638,0.9571578861809498 41 | cl-tohoku/bert-base-japanese-char-v3,5e-05,15,0.9654906407904633,0.001314284684865371,0.9633152173913043,0.956945163400538,0.9574516862693796,0.9569830403755406 42 | cl-tohoku/bert-base-japanese-char-v3,3e-05,7,0.9615379895363129,8.218494021212277e-05,0.9633152173913043,0.9598001955473221,0.954523921817737,0.9564948976705107 43 | bert-base-multilingual-cased,1e-05,10,0.9564020914958681,0.009866498086763464,0.9619565217391305,0.9546019083939563,0.956258396222996,0.9552070307742978 44 | cl-tohoku/bert-base-japanese-char-v2,3e-05,11,0.9568366619053356,8.497648346035376e-05,0.9605978260869565,0.9561816474467076,0.9526441303255991,0.9539286102000774 45 | cl-tohoku/bert-large-japanese-char-v2,5e-05,16,0.9651988359021085,7.712019040532734e-06,0.9592391304347826,0.9572504445386034,0.9517143433359815,0.9537508210462886 46 | xlm-roberta-large,3e-05,5,0.9579736422370438,0.004672625790471616,0.9578804347826086,0.9550130784825994,0.9508563237249342,0.9526776766461121 47 | cl-tohoku/bert-base-japanese-whole-word-masking,1e-05,7,0.9666119485671791,0.0011994586852581604,0.9578804347826086,0.9523627260241978,0.9525066751864468,0.9521039782651941 48 | cl-tohoku/bert-base-japanese-char,3e-05,12,0.9566941967581258,0.0016382696188014486,0.9592391304347826,0.9515871365788402,0.9527599020454743,0.951924201422291 49 | cl-tohoku/bert-base-japanese-char-v3,1e-05,14,0.9600248121269725,0.0005949993577340375,0.9578804347826086,0.9523474955646672,0.9502281176258516,0.9510685646296887 50 | cl-tohoku/bert-base-japanese-char,5e-05,19,0.9554789880930016,0.0012592360701249993,0.9578804347826086,0.9501014505396714,0.9518947067392869,0.9507663804828831 51 | cl-tohoku/bert-base-japanese-char,1e-05,7,0.9577310424962108,0.00023697964523149574,0.9510869565217391,0.9491478786293794,0.938180169213655,0.941705850419144 52 | cl-tohoku/bert-base-japanese-char-v2,1e-05,3,0.9491936263417937,0.003155147251875504,0.9429347826086957,0.9345902733615247,0.9327626582166272,0.9326712072522574 53 | -------------------------------------------------------------------------------- /results/best.csv: -------------------------------------------------------------------------------- 1 | model_name,lr,best-val-epoch,best-val-f1,loss,accuracy,precision,recall,f1 2 | studio-ousia/luke-japanese-large-lite,3e-05,13,0.9803307153306133,1.0117710664179986e-05,0.9782608695652174,0.9781845081015911,0.9721837335852859,0.974666386510519 3 | cl-tohoku/bert-large-japanese,5e-05,16,0.9691338127571516,4.4329594263968906e-06,0.9755434782608695,0.971268708753331,0.9710024409536481,0.9710252631500842 4 | xlm-roberta-large,1e-05,3,0.9721218673483413,0.0005663783168015273,0.9714673913043478,0.9736291125269076,0.9649464572349067,0.9683345666416806 5 | studio-ousia/mluke-large-lite,5e-05,14,0.9694460346550713,4.861095753174437e-06,0.9728260869565217,0.9725267620345418,0.9655621507784667,0.9682639977822115 6 | xlm-roberta-base,3e-05,15,0.9760026180244464,0.0004802491191936576,0.9714673913043478,0.9671245841194211,0.9658355923326999,0.9663132481207993 7 | studio-ousia/mluke-base-lite,3e-05,17,0.969131791255312,0.0023548831434353538,0.970108695652174,0.9661274433019381,0.9662882959764959,0.9660215446218198 8 | studio-ousia/luke-japanese-base-lite,5e-05,13,0.9731860115903948,0.01046712955702906,0.970108695652174,0.9671712874191836,0.9628725028120493,0.9646175059058673 9 | cl-tohoku/bert-base-japanese-v2,5e-05,9,0.9672144444978882,1.587970030453542e-05,0.96875,0.9641995015208553,0.9645619070518967,0.9642857487777206 10 | cl-tohoku/bert-base-japanese-v3,5e-05,13,0.9715090487864061,0.00021241182137442672,0.96875,0.9658555512470703,0.9627886451858235,0.9639172275240635 11 | cl-tohoku/bert-large-japanese-v2,1e-05,5,0.9738005698083073,0.0001132118961085444,0.967391304347826,0.9656746194737741,0.9609654714470326,0.9626031688833093 12 | cl-tohoku/bert-base-japanese,3e-05,6,0.966716985736648,0.0038873838341754417,0.967391304347826,0.9620198298847006,0.9615802535669135,0.9615671825196155 13 | bert-base-multilingual-cased,5e-05,15,0.9620682725123305,1.92398134538013e-05,0.9660326086956522,0.9625054039683284,0.9606018764758684,0.961195554917367 14 | cl-tohoku/bert-base-japanese-char-v3,5e-05,15,0.9654906407904633,0.001314284684865371,0.9633152173913043,0.956945163400538,0.9574516862693796,0.9569830403755406 15 | cl-tohoku/bert-base-japanese-char-v2,3e-05,11,0.9568366619053356,8.497648346035376e-05,0.9605978260869565,0.9561816474467076,0.9526441303255991,0.9539286102000774 16 | cl-tohoku/bert-large-japanese-char-v2,5e-05,16,0.9651988359021085,7.712019040532734e-06,0.9592391304347826,0.9572504445386034,0.9517143433359815,0.9537508210462886 17 | cl-tohoku/bert-base-japanese-whole-word-masking,1e-05,7,0.9666119485671791,0.0011994586852581604,0.9578804347826086,0.9523627260241978,0.9525066751864468,0.9521039782651941 18 | cl-tohoku/bert-base-japanese-char,1e-05,7,0.9577310424962108,0.00023697964523149574,0.9510869565217391,0.9491478786293794,0.938180169213655,0.941705850419144 19 | -------------------------------------------------------------------------------- /src/aggregate.py: -------------------------------------------------------------------------------- 1 | from pathlib import Path 2 | 3 | import pandas as pd 4 | import torch.nn as nn 5 | from tap import Tap 6 | from transformers import AutoModel 7 | 8 | import src.utils as utils 9 | 10 | 11 | class Args(Tap): 12 | input_dir: Path = "./outputs" 13 | output_dir: Path = "./results" 14 | 15 | 16 | def calc_num_params(model: nn.Module) -> int: 17 | params = 0 18 | for p in model.parameters(): 19 | params += p.numel() 20 | return params 21 | 22 | 23 | def main(args: Args): 24 | data = [] 25 | for path in args.input_dir.glob("**/test-metrics.json"): 26 | test_metrics = utils.load_json(path) 27 | val_metrics = utils.load_json(path.parent / "val-metrics.json") 28 | config = utils.load_json(path.parent / "config.json") 29 | 30 | data.append( 31 | { 32 | "model_name": config["model_name"], 33 | "lr": config["lr"], 34 | "best-val-epoch": val_metrics["best-epoch"], 35 | "best-val-f1": val_metrics["f1"], 36 | **test_metrics, 37 | } 38 | ) 39 | 40 | args.output_dir.mkdir(parents=True, exist_ok=True) 41 | df = pd.DataFrame(data).sort_values("f1", ascending=False) 42 | df.to_csv(str(args.output_dir / "all.csv"), index=False) 43 | 44 | best_df = ( 45 | df.groupby("model_name", as_index=False) 46 | .apply(lambda x: x.nlargest(1, "best-val-f1").reset_index(drop=True)) 47 | .reset_index(drop=True) 48 | ).sort_values("f1", ascending=False) 49 | 50 | best_df.to_csv(str(args.output_dir / "best.csv"), index=False) 51 | 52 | for row in best_df.to_dict("records"): 53 | model = AutoModel.from_pretrained(row["model_name"]) 54 | params = calc_num_params(model) // 1_000_000 55 | 56 | print( 57 | f'|[{row["model_name"]}](https://huggingface.co/{row["model_name"]})|{params} M|{row["lr"]}|{row["accuracy"]*100:.2f}|{row["precision"]*100:.2f}|{row["recall"]*100:.2f}|{row["f1"]*100:.2f}|' 58 | ) 59 | 60 | 61 | if __name__ == "__main__": 62 | args = Args().parse_args() 63 | main(args) 64 | -------------------------------------------------------------------------------- /src/download.sh: -------------------------------------------------------------------------------- 1 | mkdir -p data 2 | 3 | wget https://www.rondhuit.com/download/ldcc-20140209.tar.gz 4 | mv ./ldcc-20140209.tar.gz ./data/ 5 | cd data 6 | tar -zxvf ./ldcc-20140209.tar.gz 7 | cd .. 8 | -------------------------------------------------------------------------------- /src/prepare.py: -------------------------------------------------------------------------------- 1 | import random 2 | import unicodedata 3 | from pathlib import Path 4 | 5 | from more_itertools import divide, flatten 6 | from tap import Tap 7 | from tqdm import tqdm 8 | 9 | import src.utils as utils 10 | 11 | 12 | class Args(Tap): 13 | input_dir: Path = "./data/text" 14 | output_dir: Path = "./datasets/livedoor" 15 | seed: int = 42 16 | 17 | 18 | def process_title(title: str) -> str: 19 | title = unicodedata.normalize("NFKC", title) 20 | title = title.strip("　").strip() 21 | return title 22 | 23 | 24 | # 記事本文の前処理 25 | # 重複した改行の削除、文頭の全角スペースの削除、NFKC正規化を実施 26 | def process_body(body: list[str]) -> str: 27 | body = [unicodedata.normalize("NFKC", line) for line in body] 28 | body = [line.strip("　").strip() for line in body] 29 | body = [line for line in body if line] 30 | body = "\n".join(body) 31 | return body 32 | 33 | 34 | def main(args: Args): 35 | random.seed(args.seed) 36 | 37 | data = [] 38 | labels = set() 39 | 40 | for path in tqdm(list(args.input_dir.glob("*/*.txt"))): 41 | if path.name == "LICENSE.txt": 42 | continue 43 | category = path.parent.name 44 | labels.add(category) 45 | 46 | # データフォーマット 47 | # １行目：記事のURL 48 | # ２行目：記事の日付 49 | # ３行目：記事のタイトル 50 | # ４行目以降：記事の本文 51 | lines = path.read_text().splitlines() 52 | 53 | data.append( 54 | { 55 | "category": category, 56 | "category-id": path.stem, 57 | "url": lines[0].strip(), 58 | "date": lines[1].strip(), 59 | "title": process_title(lines[2].strip()), 60 | "body": process_body(lines[3:]), 61 | } 62 | ) 63 | random.shuffle(data) 64 | 65 | label2id = {label: i for i, label in enumerate(sorted(labels))} 66 | data = [ 67 | { 68 | "id": idx, 69 | "label": label2id[d["category"]], 70 | **d, 71 | } 72 | for idx, d in enumerate(data) 73 | ] 74 | 75 | utils.save_jsonl(data, args.output_dir / "all.jsonl") 76 | utils.save_json(label2id, args.output_dir / "label2id.json") 77 | 78 | portions = list(divide(10, data)) 79 | train, val, test = list(flatten(portions[:-2])), portions[-2], portions[-1] 80 | utils.save_jsonl(train, args.output_dir / "train.jsonl") 81 | utils.save_jsonl(val, args.output_dir / "val.jsonl") 82 | utils.save_jsonl(test, args.output_dir / "test.jsonl") 83 | 84 | 85 | if __name__ == "__main__": 86 | args = Args().parse_args() 87 | main(args) 88 | -------------------------------------------------------------------------------- /src/train.py: -------------------------------------------------------------------------------- 1 | from datetime import datetime 2 | from pathlib import Path 3 | 4 | import torch 5 | from sklearn.metrics import accuracy_score, precision_recall_fscore_support 6 | from tap import Tap 7 | from torch.utils.data import DataLoader 8 | from tqdm import tqdm, trange 9 | from transformers import ( 10 | AutoModelForSequenceClassification, 11 | AutoTokenizer, 12 | PreTrainedModel, 13 | ) 14 | from transformers.modeling_outputs import SequenceClassifierOutput 15 | from transformers.optimization import get_linear_schedule_with_warmup 16 | from transformers.tokenization_utils import BatchEncoding, PreTrainedTokenizer 17 | 18 | import src.utils as utils 19 | 20 | 21 | class Args(Tap): 22 | model_name: str = "cl-tohoku/bert-base-japanese-v3" 23 | dataset_dir: Path = "./datasets/livedoor" 24 | 25 | batch_size: int = 16 26 | epochs: int = 20 27 | lr: float = 3e-5 28 | num_warmup_epochs: int = 2 29 | max_seq_len: int = 512 30 | weight_decay: float = 0.01 31 | gradient_checkpointing: bool = False 32 | 33 | device: str = "cuda:0" 34 | seed: int = 42 35 | 36 | def process_args(self): 37 | self.label2id: dict[str, int] = utils.load_json(self.dataset_dir / "label2id.json") 38 | self.labels: list[int] = list(self.label2id.values()) 39 | 40 | date, time = datetime.now().strftime("%Y-%m-%d/%H-%M-%S.%f").split("/") 41 | self.output_dir = self.make_output_dir( 42 | "outputs", 43 | self.model_name, 44 | date, 45 | time, 46 | ) 47 | 48 | def make_output_dir(self, *args) -> Path: 49 | args = [str(a).replace("/", "__") for a in args] 50 | output_dir = Path(*args) 51 | output_dir.mkdir(parents=True, exist_ok=True) 52 | return output_dir 53 | 54 | 55 | class Experiment: 56 | def __init__(self, args: Args): 57 | self.args: Args = args 58 | 59 | self.tokenizer: PreTrainedTokenizer = AutoTokenizer.from_pretrained( 60 | args.model_name, 61 | model_max_length=args.max_seq_len, 62 | ) 63 | 64 | self.model: PreTrainedModel = ( 65 | AutoModelForSequenceClassification.from_pretrained( 66 | args.model_name, 67 | num_labels=len(args.labels), 68 | ) 69 | .eval() 70 | .to(args.device, non_blocking=True) 71 | ) 72 | 73 | # gradient_checkpointingとtorch.compileは相性が悪いことが多いので排他的に使用 74 | if args.gradient_checkpointing: 75 | self.model.gradient_checkpointing_enable() 76 | else: 77 | self.model = torch.compile(self.model) 78 | 79 | self.train_dataloader: DataLoader = self.load_dataset(split="train", shuffle=True) 80 | self.val_dataloader: DataLoader = self.load_dataset(split="val") 81 | self.test_dataloader: DataLoader = self.load_dataset(split="test") 82 | 83 | self.optimizer, self.lr_scheduler = self.create_optimizer() 84 | 85 | def load_dataset( 86 | self, 87 | split: str, 88 | shuffle: bool = False, 89 | ) -> DataLoader: 90 | path: Path = self.args.dataset_dir / f"{split}.jsonl" 91 | dataset: list[dict] = utils.load_jsonl(path).to_dict(orient="records") 92 | return self.create_loader(dataset, shuffle=shuffle) 93 | 94 | def collate_fn(self, data_list: list[dict]) -> BatchEncoding: 95 | title = [d["title"] for d in data_list] 96 | body = [d["body"] for d in data_list] 97 | 98 | inputs: BatchEncoding = self.tokenizer( 99 | title, 100 | body, 101 | padding=True, 102 | truncation="only_second", 103 | return_tensors="pt", 104 | max_length=args.max_seq_len, 105 | ) 106 | 107 | labels = torch.LongTensor([d["label"] for d in data_list]) 108 | return BatchEncoding({**inputs, "labels": labels}) 109 | 110 | def create_loader( 111 | self, 112 | dataset, 113 | batch_size=None, 114 | shuffle=False, 115 | ): 116 | return DataLoader( 117 | dataset, 118 | collate_fn=self.collate_fn, 119 | batch_size=batch_size or args.batch_size, 120 | shuffle=shuffle, 121 | num_workers=4, 122 | pin_memory=True, 123 | ) 124 | 125 | def create_optimizer(self) -> tuple[torch.optim.Optimizer, torch.optim.lr_scheduler.LambdaLR]: 126 | # see: https://tma15.github.io/blog/2021/09/17/deep-learningbert%E5%AD%A6%E7%BF%92%E6%99%82%E3%81%ABbias%E3%82%84layer-normalization%E3%82%92weight-decay%E3%81%97%E3%81%AA%E3%81%84%E7%90%86%E7%94%B1/ 127 | no_decay = {"bias", "LayerNorm.weight"} 128 | optimizer_grouped_parameters = [ 129 | { 130 | "params": [ 131 | param for name, param in self.model.named_parameters() if not name in no_decay 132 | ], 133 | "weight_decay": self.args.weight_decay, 134 | }, 135 | { 136 | "params": [ 137 | param for name, param in self.model.named_parameters() if name in no_decay 138 | ], 139 | "weight_decay": 0.0, 140 | }, 141 | ] 142 | 143 | optimizer = torch.optim.AdamW(optimizer_grouped_parameters, lr=self.args.lr) 144 | 145 | lr_scheduler = get_linear_schedule_with_warmup( 146 | optimizer=optimizer, 147 | num_warmup_steps=len(self.train_dataloader) * args.num_warmup_epochs, 148 | num_training_steps=len(self.train_dataloader) * args.epochs, 149 | ) 150 | 151 | return optimizer, lr_scheduler 152 | 153 | @torch.cuda.amp.autocast(dtype=torch.bfloat16 if torch.cuda.is_bf16_supported() else None) 154 | def run(self): 155 | val_metrics = {"epoch": None, **self.evaluate(self.val_dataloader)} 156 | best_epoch, best_val_f1 = None, val_metrics["f1"] 157 | best_state_dict = self.clone_state_dict() 158 | self.log(val_metrics) 159 | 160 | scaler = torch.cuda.amp.GradScaler() 161 | 162 | for epoch in trange(args.epochs, dynamic_ncols=True): 163 | self.model.train() 164 | 165 | for batch in tqdm( 166 | self.train_dataloader, 167 | total=len(self.train_dataloader), 168 | dynamic_ncols=True, 169 | leave=False, 170 | ): 171 | out: SequenceClassifierOutput = self.model(**batch.to(args.device)) 172 | loss: torch.FloatTensor = out.loss 173 | 174 | self.optimizer.zero_grad() 175 | scaler.scale(loss).backward() 176 | scaler.step(self.optimizer) 177 | 178 | scale = scaler.get_scale() 179 | scaler.update() 180 | if scale <= scaler.get_scale(): 181 | self.lr_scheduler.step() 182 | 183 | self.model.eval() 184 | val_metrics = {"epoch": epoch, **self.evaluate(self.val_dataloader)} 185 | self.log(val_metrics) 186 | 187 | # 開発セットでのF値最良時のモデルを保存 188 | if val_metrics["f1"] > best_val_f1: 189 | best_val_f1 = val_metrics["f1"] 190 | best_epoch = epoch 191 | best_state_dict = self.clone_state_dict() 192 | 193 | self.model.load_state_dict(best_state_dict) 194 | self.model.eval().to(args.device, non_blocking=True) 195 | 196 | val_metrics = {"best-epoch": best_epoch, **self.evaluate(self.val_dataloader)} 197 | test_metrics = self.evaluate(self.test_dataloader) 198 | 199 | return val_metrics, test_metrics 200 | 201 | @torch.no_grad() 202 | @torch.cuda.amp.autocast(dtype=torch.bfloat16 if torch.cuda.is_bf16_supported() else None) 203 | def evaluate(self, dataloader: DataLoader) -> dict[str, float]: 204 | self.model.eval() 205 | total_loss, gold_labels, pred_labels = 0, [], [] 206 | 207 | for batch in tqdm(dataloader, total=len(dataloader), dynamic_ncols=True, leave=False): 208 | out: SequenceClassifierOutput = self.model(**batch.to(self.args.device)) 209 | 210 | batch_size: int = batch.input_ids.size(0) 211 | loss = out.loss.item() * batch_size 212 | total_loss += loss 213 | 214 | pred_labels += out.logits.argmax(dim=-1).tolist() 215 | gold_labels += batch.labels.tolist() 216 | 217 | accuracy: float = accuracy_score(gold_labels, pred_labels) 218 | precision, recall, f1, _ = precision_recall_fscore_support( 219 | gold_labels, 220 | pred_labels, 221 | average="macro", 222 | zero_division=0, 223 | labels=args.labels, 224 | ) 225 | 226 | return { 227 | "loss": loss / len(dataloader.dataset), 228 | "accuracy": accuracy, 229 | "precision": precision, 230 | "recall": recall, 231 | "f1": f1, 232 | } 233 | 234 | def log(self, metrics: dict) -> None: 235 | utils.log(metrics, self.args.output_dir / "log.csv") 236 | tqdm.write( 237 | f"epoch: {metrics['epoch']} \t" 238 | f"loss: {metrics['loss']:2.6f} \t" 239 | f"accuracy: {metrics['accuracy']:.4f} \t" 240 | f"precision: {metrics['precision']:.4f} \t" 241 | f"recall: {metrics['recall']:.4f} \t" 242 | f"f1: {metrics['f1']:.4f}" 243 | ) 244 | 245 | def clone_state_dict(self) -> dict: 246 | return {k: v.detach().clone().cpu() for k, v in self.model.state_dict().items()} 247 | 248 | 249 | def main(args: Args): 250 | exp = Experiment(args=args) 251 | val_metrics, test_metrics = exp.run() 252 | 253 | utils.save_json(val_metrics, args.output_dir / "val-metrics.json") 254 | utils.save_json(test_metrics, args.output_dir / "test-metrics.json") 255 | utils.save_config(args, args.output_dir / "config.json") 256 | 257 | 258 | if __name__ == "__main__": 259 | args = Args().parse_args() 260 | utils.init(seed=args.seed) 261 | main(args) 262 | -------------------------------------------------------------------------------- /src/utils.py: -------------------------------------------------------------------------------- 1 | import json 2 | import random 3 | from collections.abc import Iterable 4 | from inspect import ismethod 5 | from pathlib import Path 6 | from typing import Any 7 | 8 | import numpy as np 9 | import pandas as pd 10 | import torch 11 | 12 | 13 | def save_jsonl(data: pd.DataFrame | Iterable[dict] | dict[Any, Iterable], path: Path | str) -> None: 14 | path = Path(path) 15 | path.parent.mkdir(parents=True, exist_ok=True) 16 | 17 | if type(data) != pd.DataFrame: 18 | data = pd.DataFrame(data) 19 | data.to_json( 20 | path, 21 | orient="records", 22 | lines=True, 23 | force_ascii=False, 24 | ) 25 | 26 | 27 | def save_json(data: dict[Any, Any], path: Path | str) -> None: 28 | path = Path(path) 29 | path.parent.mkdir(parents=True, exist_ok=True) 30 | 31 | with path.open("w") as f: 32 | json.dump(data, f, indent=2, ensure_ascii=False) 33 | 34 | 35 | def load_jsonl(path: Path | str) -> pd.DataFrame: 36 | path = Path(path) 37 | return pd.read_json(path, lines=True) 38 | 39 | 40 | def load_json(path: Path | str) -> dict: 41 | path = Path(path) 42 | with path.open() as f: 43 | data = json.load(f) 44 | return data 45 | 46 | 47 | def log(data: dict, path: Path | str) -> None: 48 | path = Path(path) 49 | path.parent.mkdir(parents=True, exist_ok=True) 50 | 51 | if path.exists(): 52 | df: pd.DataFrame = pd.read_csv(path) 53 | df = pd.DataFrame(df.to_dict("records") + [data]) 54 | df.to_csv(path, index=False) 55 | else: 56 | pd.DataFrame([data]).to_csv(path, index=False) 57 | 58 | 59 | def save_config(data, path: Path | str) -> None: 60 | path = Path(path) 61 | path.parent.mkdir(parents=True, exist_ok=True) 62 | 63 | try: 64 | data: dict = data.as_dict() 65 | except: 66 | try: 67 | data: dict = data.to_dict() 68 | except: 69 | pass 70 | 71 | if type(data) != dict: 72 | data: dict = vars(data) 73 | 74 | data = {k: v for k, v in data.items() if not ismethod(v)} 75 | data = {k: v if type(v) in [int, float, bool, None] else str(v) for k, v in data.items()} 76 | 77 | save_json(data, path) 78 | 79 | 80 | def set_seed(seed: int = None) -> None: 81 | if seed is None: 82 | return 83 | 84 | random.seed(seed) 85 | np.random.seed(seed) 86 | torch.manual_seed(seed) 87 | torch.cuda.manual_seed_all(seed) 88 | 89 | 90 | def dict_average(dicts: Iterable[dict]) -> dict: 91 | dicts: list[dict] = list(dicts) 92 | averaged = {} 93 | 94 | for k, v in dicts[0].items(): 95 | try: 96 | v = v.item() 97 | except: 98 | pass 99 | if type(v) in [int, float]: 100 | averaged[k] = v / len(dicts) 101 | else: 102 | averaged[k] = [v] 103 | 104 | for d in dicts[1:]: 105 | for k, v in d.items(): 106 | try: 107 | v = v.item() 108 | except: 109 | pass 110 | if type(v) in [int, float]: 111 | averaged[k] += v / len(dicts) 112 | else: 113 | averaged[k].append(v) 114 | 115 | return averaged 116 | 117 | 118 | def init( 119 | seed: int, 120 | float32_matmul_precision: str = "high", 121 | ): 122 | import torch._inductor.config as inductor_config 123 | 124 | inductor_config.fallback_random = True 125 | 126 | set_seed(seed) 127 | torch.set_float32_matmul_precision(float32_matmul_precision) 128 | --------------------------------------------------------------------------------