lecrapaud 0.20.0__py3-none-any.whl → 0.20.2__py3-none-any.whl

{lecrapaud-0.20.0.dist-info → lecrapaud-0.20.2.dist-info}/RECORD

@@ -1,6 +1,6 @@
 lecrapaud/__init__.py,sha256=oCxbtw_nk8rlOXbXbWo0RRMlsh6w-hTiZ6e5PRG_wp0,28
-lecrapaud/api.py,sha256=xPa8GG5o9ngjJaGgBWhojzGzRq1tbFL5nsCv5U1Ehjw,22681
-lecrapaud/config.py,sha256=QK1MxWsEddXii02Rme31tCGDyMFsfHHF2Zy-lLIOuSY,1218
+lecrapaud/api.py,sha256=IQlH3wcSzxYgvlamfICNMwNsQGoaNxBJUPTlC9M0kBk,20321
+lecrapaud/config.py,sha256=0NEg61QdLxQ97bVFDDXa6OwlWFEo_z8VIhX5KrD1ik0,1170
 lecrapaud/db/__init__.py,sha256=82o9fMfaqKXPh2_rt44EzNRVZV1R4LScEnQYvj_TjK0,34
 lecrapaud/db/alembic/README,sha256=MVlc9TYmr57RbhXET6QxgyCcwWP7w-vLkEsirENqiIQ,38
 lecrapaud/db/alembic/env.py,sha256=RvTTBa3bDVBxmDtapAfzUoeWBgmVQU3s9U6HmQCAP84,2421
@@ -14,10 +14,11 @@ lecrapaud/db/alembic/versions/2025_08_28_1516-c36e9fee22b9_add_avg_precision_to_
 lecrapaud/db/alembic/versions/2025_08_28_1622-8b11c1ba982e_change_name_column.py,sha256=g6H2Z9MwB6UEiqdGlBoHBXpO9DTaWkwHt8FS6joVOm0,1191
 lecrapaud/db/alembic/versions/2025_10_25_0635-07e303521594_add_unique_constraint_to_score.py,sha256=FshOF1t-NWXrBtXT3wMNGFslJ4sWUxzvBEXSymu05cI,1043
 lecrapaud/db/alembic/versions/2025_10_26_1727-033e0f7eca4f_merge_score_and_model_trainings_into_.py,sha256=htHUD4zPJr-0z_DQfTi8r9RsFVe9m7SL0f7oRIvLIcQ,10999
+lecrapaud/db/alembic/versions/2025_10_28_2006-0a8fb7826e9b_add_number_of_targets_and_remove_other_.py,sha256=o3TNHq1GTFjxfk2zHWaUbq91khMJi6Xy6HToO9i54AU,2051
 lecrapaud/db/alembic.ini,sha256=Zw2rdwsKV6c7J1SPtoFIPDX08_oTP3MuUKnNxBDiY8I,3796
 lecrapaud/db/models/__init__.py,sha256=-XoCN1eeLihnNxBMl90lXrgrTSDkMbeqgienMqFi5f4,702
 lecrapaud/db/models/base.py,sha256=0548x4ftd6Oim9BJmtD7Er4izM6u0QCrlTG5560384w,9458
-lecrapaud/db/models/experiment.py,sha256=BOQzaAkEuR_ZA9tleUCB8m3RRLAuCKwlrF5BVAvOMNo,15562
+lecrapaud/db/models/experiment.py,sha256=aDvSgbE0n-gUHLrz3NNYkeeSp-KkAZ5nbF9WxaxXawM,15029
 lecrapaud/db/models/feature.py,sha256=5o77O2FyRObnLOCGNj8kaPSGM3pLv1Ov6mXXHYkmnYY,1136
 lecrapaud/db/models/feature_selection.py,sha256=PBNWk9QaLb7-_xyrLlOUfab0y2xEj3agAIzt1gxssZQ,3172
 lecrapaud/db/models/feature_selection_rank.py,sha256=POo-OLdaxU3eaH6fC6fTOj7Fnv0ujvTXgYZMzjjwTfE,1773
@@ -28,9 +29,9 @@ lecrapaud/db/models/target.py,sha256=DKnfeaLU8eT8J_oh_vuFo5-o1CaoXR13xBbswme6Bgk
 lecrapaud/db/models/utils.py,sha256=-a-nWWmpJ2XzidIxo2COVUTrGZIPYCfBzjhcszJj_bM,1109
 lecrapaud/db/session.py,sha256=u9NCwUoV5VbtScRb6HOSQr4oTEjIwj0waP5mGlc1qJg,3735
 lecrapaud/directories.py,sha256=0LrANuDgbuneSLker60c6q2hmGnQ3mKHIztTGzTx6Gw,826
-lecrapaud/experiment.py,sha256=S9qdhSTFX8M7Fxjnlsl0PsPBTuexF-7Ogto2rWb46yM,2607
-lecrapaud/feature_engineering.py,sha256=a1B4AbACZZiIxCmxyyfjekyWi6qTBt1E77cd36O89yI,39209
-lecrapaud/feature_selection.py,sha256=-uk3Wi2bwPEO-_rOz-TQceMB5uxN9El16EWn5f-gdIM,43536
+lecrapaud/experiment.py,sha256=hhi6NdVKtxoyx_AGBB4iNEZZpd9b3rKs23qiLPf-mUk,2384
+lecrapaud/feature_engineering.py,sha256=UM-EIOsgYWedqsR9uA-09eaWSb9FofVxoE0rRcDelQ8,39173
+lecrapaud/feature_selection.py,sha256=Q9xWVmZsvRjX9mJHB_PY_KLXsEAYNLX7txSe0cniY4A,47529
 lecrapaud/integrations/openai_integration.py,sha256=hHLF3fk5Bps8KNbNrEL3NUFa945jwClE6LrLpuMZOd4,7459
 lecrapaud/jobs/__init__.py,sha256=ZkrsyTOR21c_wN7RY8jPhm8jCrL1oCEtTsf3VFIlQiE,292
 lecrapaud/jobs/config.py,sha256=AmO0j3RFjx8H66dfKw_7vnshaOJb9Ox5BAZ9cwwLFMY,377
@@ -40,10 +41,10 @@ lecrapaud/misc/tabpfn_tests.ipynb,sha256=VkgsCUJ30d8jaL2VaWtQAgb8ngHPNtPgnXLs7QQ
 lecrapaud/misc/test-gpu-bilstm.ipynb,sha256=4nLuZRJVe2kn6kEmauhRiz5wkWT9AVrYhI9CEk_dYUY,9608
 lecrapaud/misc/test-gpu-resnet.ipynb,sha256=27Vu7nYwujYeh3fOxBNCnKJn3MXNPKZU-U8oDDUbymg,4944
 lecrapaud/misc/test-gpu-transformers.ipynb,sha256=k6MBSs_Um1h4PykvE-LTBcdpbWLbIFST_xl_AFW2jgI,8444
-lecrapaud/model_selection.py,sha256=6VYwrvneA6qsRTewaHzXLXV4AGCwwEtaDfQja_AX2Wo,87856
+lecrapaud/model_selection.py,sha256=o4_hOEp91_33HtMatVHU7YPc71KZ2hK7wucN63xqWkA,88017
 lecrapaud/search_space.py,sha256=caCehJklD3-sgmlisJj_GmuB7LJiVvTF71gEjPGDvV4,36336
-lecrapaud/utils.py,sha256=vsNBd2Nnhpjo65Ugz2GFJaRhq3U3_eWERfofpevo5Ls,8884
-lecrapaud-0.20.0.dist-info/METADATA,sha256=DpCGcnGtDcnOdO_tgulp24kUSMfJ4ApxReIjIJ_-9qs,11137
-lecrapaud-0.20.0.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
-lecrapaud-0.20.0.dist-info/licenses/LICENSE,sha256=MImCryu0AnqhJE_uAZD-PIDKXDKb8sT7v0i1NOYeHTM,11350
-lecrapaud-0.20.0.dist-info/RECORD,,
+lecrapaud/utils.py,sha256=0k76HFETO0_NgCYUv8b3RTBLgry6MsDBaHJfpAplxCY,8855
+lecrapaud-0.20.2.dist-info/METADATA,sha256=FUXEVYVCJAoat8HUtsupISlRbK56YVxezYwCH6j4kBE,14239
+lecrapaud-0.20.2.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
+lecrapaud-0.20.2.dist-info/licenses/LICENSE,sha256=MImCryu0AnqhJE_uAZD-PIDKXDKb8sT7v0i1NOYeHTM,11350
+lecrapaud-0.20.2.dist-info/RECORD,,

lecrapaud-0.20.0.dist-info/METADATA

@@ -1,250 +0,0 @@
-Metadata-Version: 2.4
-Name: lecrapaud
-Version: 0.20.0
-Summary: Framework for machine and deep learning, with regression, classification and time series analysis
-License: Apache License
-License-File: LICENSE
-Author: Pierre H. Gallet
-Requires-Python: ==3.12.*
-Classifier: License :: Other/Proprietary License
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.12
-Requires-Dist: catboost (>=1.2.8)
-Requires-Dist: category-encoders (>=2.8.1)
-Requires-Dist: celery (>=5.5.3)
-Requires-Dist: ftfy (>=6.3.1)
-Requires-Dist: joblib (>=1.5.1)
-Requires-Dist: keras (>=3.10.0)
-Requires-Dist: lightgbm (>=4.6.0)
-Requires-Dist: matplotlib (>=3.10.3)
-Requires-Dist: mlxtend (>=0.23.4)
-Requires-Dist: numpy (>=2.1.3)
-Requires-Dist: openai (>=1.88.0)
-Requires-Dist: pandas (>=2.3.0)
-Requires-Dist: pydantic (>=2.9.2)
-Requires-Dist: python-dotenv (>=1.1.0)
-Requires-Dist: scikit-learn (>=1.6.1)
-Requires-Dist: scipy (<1.14.0)
-Requires-Dist: seaborn (>=0.13.2)
-Requires-Dist: sqlalchemy (>=2.0.41)
-Requires-Dist: tensorboardx (>=2.6.4)
-Requires-Dist: tensorflow (>=2.19.0)
-Requires-Dist: tiktoken (>=0.9.0)
-Requires-Dist: tqdm (>=4.67.1)
-Requires-Dist: xgboost (>=3.0.2)
-Description-Content-Type: text/markdown
-
-<div align="center">
-
-<img src="https://s3.amazonaws.com/pix.iemoji.com/images/emoji/apple/ios-12/256/frog-face.png" width=120 alt="crapaud"/>
-
-## Welcome to LeCrapaud
-
-**An all-in-one machine learning framework**
-
-[![GitHub stars](https://img.shields.io/github/stars/pierregallet/lecrapaud.svg?style=flat&logo=github&colorB=blue&label=stars)](https://github.com/pierregallet/lecrapaud/stargazers)
-[![PyPI version](https://badge.fury.io/py/lecrapaud.svg)](https://badge.fury.io/py/lecrapaud)
-[![Python versions](https://img.shields.io/pypi/pyversions/lecrapaud.svg)](https://pypi.org/project/lecrapaud)
-[![License](https://img.shields.io/github/license/pierregallet/lecrapaud.svg)](https://github.com/pierregallet/lecrapaud/blob/main/LICENSE)
-[![codecov](https://codecov.io/gh/pierregallet/lecrapaud/branch/main/graph/badge.svg)](https://codecov.io/gh/pierregallet/lecrapaud)
-
-</div>
-
-## 🚀 Introduction
-
-LeCrapaud is a high-level Python library for end-to-end machine learning workflows on tabular data, with a focus on financial and stock datasets. It provides a simple API to handle feature engineering, model selection, training, and prediction, all in a reproducible and modular way.
-
-## ✨ Key Features
-
-- 🧩 Modular pipeline: Feature engineering, preprocessing, selection, and modeling as independent steps
-- 🤖 Automated model selection and hyperparameter optimization
-- 📊 Easy integration with pandas DataFrames
-- 🔬 Supports both regression and classification tasks
-- 🛠️ Simple API for both full pipeline and step-by-step usage
-- 📦 Ready for production and research workflows
-
-## ⚡ Quick Start
-
-
-### Install the package
-
-```sh
-pip install lecrapaud
-```
-
-### How it works
-
-This package provides a high-level API to manage experiments for feature engineering, model selection, and prediction on tabular data (e.g. stock data).
-
-### Typical workflow
-
-```python
-from lecrapaud import LeCrapaud
-
-# 1. Create the main app
-app = LeCrapaud(uri=uri)
-
-# 2. Define your experiment context (see your notebook or api.py for all options)
-context = {
-    "data": your_dataframe,
-    "columns_drop": [...],
-    "columns_date": [...],
-    # ... other config options
-}
-
-# 3. Create an experiment
-experiment = app.create_experiment(**context)
-
-# 4. Run the full training pipeline
-experiment.train(your_dataframe)
-
-# 5. Make predictions on new data
-predictions = experiment.predict(new_data)
-```
-
-### Database Configuration (Required)
-
-LeCrapaud requires access to a MySQL database to store experiments and results. You must either:
-
-- Pass a valid MySQL URI to the `LeCrapaud` constructor:
-  ```python
-  app = LeCrapaud(uri="mysql+pymysql://user:password@host:port/dbname")
-  ```
-- **OR** set the following environment variables before using the package:
-  - `DB_USER`, `DB_PASSWORD`, `DB_HOST`, `DB_PORT`, `DB_NAME`
-  - Or set `DB_URI` directly with your full connection string.
-
-If neither is provided, database operations will not work.
-
-### Using OpenAI Embeddings (Optional)
-
-If you want to use the `columns_pca` embedding feature (for advanced feature engineering), you must set the `OPENAI_API_KEY` environment variable with your OpenAI API key:
-
-```sh
-export OPENAI_API_KEY=sk-...
-```
-
-If this variable is not set, features relying on OpenAI embeddings will not be available.
-
-### Experiment Context Arguments
-
-Below are the main arguments you can pass to `create_experiment` (or the `Experiment` class):
-
-| Argument             | Type      | Description                                                                              | Example/Default    |
-| -------------------- | --------- | ---------------------------------------------------------------------------------------- | ------------------ |
-| `columns_binary`     | list      | Columns to treat as binary                                                               | `['flag']`         |
-| `columns_boolean`    | list      | Columns to treat as boolean                                                              | `['is_active']`    |
-| `columns_date`       | list      | Columns to treat as dates                                                                | `['date']`         |
-| `columns_drop`       | list      | Columns to drop during feature engineering                                               | `['col1', 'col2']` |
-| `columns_frequency`  | list      | Columns to frequency encode                                                              | `['category']`     |
-| `columns_onehot`     | list      | Columns to one-hot encode                                                                | `['sector']`       |
-| `columns_ordinal`    | list      | Columns to ordinal encode                                                                | `['grade']`        |
-| `columns_pca`        | list      | Columns to use for PCA/embeddings (requires `OPENAI_API_KEY` if using OpenAI embeddings) | `['text_col']`     |
-| `columns_te_groupby` | list      | Columns for target encoding groupby                                                      | `['sector']`       |
-| `columns_te_target`  | list      | Columns for target encoding target                                                       | `['target']`       |
-| `data`               | DataFrame | Your main dataset (required for new experiment)                                          | `your_dataframe`   |
-| `date_column`        | str       | Name of the date column                                                                  | `'date'`           |
-| `experiment_name`    | str       | Name for the training session                                                            | `'my_session'`     |
-| `group_column`       | str       | Name of the group column                                                                 | `'stock_id'`       |
-| `max_timesteps`      | int       | Max timesteps for time series models                                                     | `30`               |
-| `models_idx`         | list      | Indices of models to use for model selection                                             | `[0, 1, 2]`        |
-| `number_of_trials`   | int       | Number of trials for hyperparameter optimization                                         | `20`               |
-| `perform_crossval`   | bool      | Whether to perform cross-validation                                                      | `True`/`False`     |
-| `perform_hyperopt`   | bool      | Whether to perform hyperparameter optimization                                           | `True`/`False`     |
-| `plot`               | bool      | Whether to plot results                                                                  | `True`/`False`     |
-| `preserve_model`     | bool      | Whether to preserve the best model                                                       | `True`/`False`     |
-| `target_clf`         | list      | List of classification target column indices/names                                       | `[1, 2, 3]`        |
-| `target_mclf`        | list      | Multi-class classification targets (not yet implemented)                                 | `[11]`             |
-| `target_numbers`     | list      | List of regression target column indices/names                                           | `[1, 2, 3]`        |
-| `test_size`          | int/float | Test set size (count or fraction)                                                        | `0.2`              |
-| `time_series`        | bool      | Whether the data is time series                                                          | `True`/`False`     |
-| `val_size`           | int/float | Validation set size (count or fraction)                                                  | `0.2`              |
-
-**Note:**
-- Not all arguments are required; defaults may exist for some.
-- For `columns_pca` with OpenAI embeddings, you must set the `OPENAI_API_KEY` environment variable.
-
-
-
-### Modular usage
-
-You can also use each step independently:
-
-```python
-data_eng = experiment.feature_engineering(data)
-train, val, test = experiment.preprocess_feature(data_eng)
-features = experiment.feature_selection(train)
-std_data, reshaped_data = experiment.preprocess_model(train, val, test)
-experiment.model_selection(std_data, reshaped_data)
-```
-
-## ⚠️ Using Alembic in Your Project (Important for Integrators)
-
-If you use Alembic for migrations in your own project and you share the same database with LeCrapaud, you must ensure that Alembic does **not** attempt to drop or modify LeCrapaud tables (those prefixed with `{LECRAPAUD_TABLE_PREFIX}_`).
-
-By default, Alembic's autogenerate feature will propose to drop any table that exists in the database but is not present in your project's models. To prevent this, add the following filter to your `env.py`:
-
-```python
-def include_object(object, name, type_, reflected, compare_to):
-    if type_ == "table" and name.startswith(f"{LECRAPAUD_TABLE_PREFIX}_"):
-        return False  # Ignore LeCrapaud tables
-    return True
-
-context.configure(
-    # ... other options ...
-    include_object=include_object,
-)
-```
-
-This will ensure that Alembic ignores all tables created by LeCrapaud when generating migrations for your own project.
-
----
-
-## 🤝 Contributing
-
-### Reminders for Github usage
-
-1. Creating Github repository
-
-```sh
-$ brew install gh
-$ gh auth login
-$ gh repo create
-```
-
-2. Initializing git and first commit to distant repository
-
-```sh
-$ git init
-$ git add .
-$ git commit -m 'first commit'
-$ git remote add origin <YOUR_REPO_URL>
-$ git push -u origin master
-```
-
-3. Use conventional commits  
-https://www.conventionalcommits.org/en/v1.0.0/#summary
-
-4. Create environment
-
-```sh
-$ pip install virtualenv
-$ python -m venv .venv
-$ source .venv/bin/activate
-```
-
-5. Install dependencies
-
-```sh
-$ make install
-```
-
-6. Deactivate virtualenv (if needed)
-
-```sh
-$ deactivate
-```
-
----
-
-Pierre Gallet © 2025