lecrapaud 0.20.1__tar.gz → 0.20.2__tar.gz

lecrapaud-0.20.2/PKG-INFO

@@ -0,0 +1,344 @@
+Metadata-Version: 2.4
+Name: lecrapaud
+Version: 0.20.2
+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
+
+The experiment context is a dictionary containing all configuration parameters for your ML pipeline. Parameters are stored in the experiment's database record and automatically retrieved when loading an existing experiment.
+
+#### Required Parameters
+
+| Parameter         | Type      | Description                                          | Example                |
+|-------------------|-----------|------------------------------------------------------|------------------------|
+| `data`           | DataFrame | Input dataset (required for new experiments only)    | `pd.DataFrame(...)`    |
+| `experiment_name`| str       | Unique name for the experiment                      | `'stock_prediction'`   |
+| `date_column`    | str       | Name of the date column (required for time series)  | `'DATE'`              |
+| `group_column`   | str       | Name of the group column (required for panel data)  | `'STOCK'`             |
+
+#### Feature Engineering Parameters
+
+| Parameter             | Type  | Default | Description                                                              |
+|-----------------------|-------|---------|--------------------------------------------------------------------------|
+| `columns_drop`        | list  | `[]`    | Columns to drop during feature engineering                              |
+| `columns_boolean`     | list  | `[]`    | Columns to convert to boolean features                                  |
+| `columns_date`        | list  | `[]`    | Date columns for cyclic encoding                                        |
+| `columns_te_groupby`  | list  | `[]`    | Groupby columns for target encoding                                     |
+| `columns_te_target`   | list  | `[]`    | Target columns for target encoding                                      |
+
+#### Preprocessing Parameters
+
+| Parameter               | Type  | Default | Description                                                           |
+|-------------------------|-------|---------|-----------------------------------------------------------------------|
+| `time_series`           | bool  | `False` | Whether data is time series                                          |
+| `val_size`              | float | `0.2`   | Validation set size (fraction)                                       |
+| `test_size`             | float | `0.2`   | Test set size (fraction)                                             |
+| `columns_pca`           | list  | `[]`    | Columns for PCA transformation                                       |
+| `pca_temporal`          | list  | `[]`    | Temporal PCA config (e.g., lag features)                            |
+| `pca_cross_sectional`   | list  | `[]`    | Cross-sectional PCA config (e.g., market regime)                    |
+| `columns_onehot`        | list  | `[]`    | Columns for one-hot encoding                                         |
+| `columns_binary`        | list  | `[]`    | Columns for binary encoding                                          |
+| `columns_ordinal`       | list  | `[]`    | Columns for ordinal encoding                                         |
+| `columns_frequency`     | list  | `[]`    | Columns for frequency encoding                                       |
+
+#### Feature Selection Parameters
+
+| Parameter                   | Type  | Default | Description                                                      |
+|-----------------------------|-------|---------|------------------------------------------------------------------|
+| `percentile`                | float | `20`    | Percentage of features to keep per selection method             |
+| `corr_threshold`            | float | `80`    | Maximum correlation threshold (%) between features              |
+| `max_features`              | int   | `50`    | Maximum number of final features                                |
+| `max_p_value_categorical`   | float | `0.05`  | Maximum p-value for categorical feature selection (Chi2)        |
+
+#### Model Selection Parameters
+
+| Parameter              | Type  | Default | Description                                                           |
+|------------------------|-------|---------|-----------------------------------------------------------------------|
+| `target_numbers`       | list  | `[]`    | List of target indices to predict                                     |
+| `target_clf`           | list  | `[]`    | Classification target indices                                         |
+| `models_idx`           | list  | `[]`    | Model indices or names to use (e.g., `[1, 'xgb', 'lgb']`)           |
+| `max_timesteps`        | int   | `120`   | Maximum timesteps for recurrent models                               |
+| `perform_hyperopt`     | bool  | `True`  | Whether to perform hyperparameter optimization                       |
+| `number_of_trials`     | int   | `20`    | Number of hyperopt trials                                            |
+| `perform_crossval`     | bool  | `False` | Whether to use cross-validation during hyperopt                      |
+| `plot`                 | bool  | `True`  | Whether to generate plots                                            |
+| `preserve_model`       | bool  | `True`  | Whether to save the best model                                       |
+| `target_clf_thresholds`| dict  | `{}`    | Classification thresholds per target                                 |
+
+#### Example Context Configuration
+
+```python
+context = {
+    # Required parameters
+    "experiment_name": f"stock_{datetime.now().strftime('%Y%m%d_%H%M%S')}",
+    "date_column": "DATE",
+    "group_column": "STOCK",
+    
+    # Feature selection
+    "corr_threshold": 80,
+    "max_features": 20,
+    "percentile": 20,
+    "max_p_value_categorical": 0.05,
+    
+    # Feature engineering
+    "columns_drop": ["SECURITY", "ISIN", "ID"],
+    "columns_boolean": [],
+    "columns_date": ["DATE"],
+    "columns_te_groupby": [["SECTOR", "DATE"]],
+    "columns_te_target": ["RET", "VOLUME"],
+    
+    # Preprocessing
+    "time_series": True,
+    "val_size": 0.2,
+    "test_size": 0.2,
+    "pca_temporal": [
+        {"name": "LAST_20_RET", "columns": [f"RET_-{i}" for i in range(1, 21)]},
+    ],
+    "pca_cross_sectional": [
+        {
+            "name": "MARKET_REGIME",
+            "index": "DATE",
+            "columns": "STOCK",
+            "value": "RET",
+        }
+    ],
+    "columns_onehot": ["BUY_SIGNAL"],
+    "columns_binary": ["SECTOR", "LOCATION"],
+    "columns_ordinal": ["STOCK"],
+    
+    # Model selection
+    "target_numbers": [1, 2, 3],
+    "target_clf": [1],
+    "models_idx": ["xgb", "lgb", "catboost"],
+    "max_timesteps": 120,
+    "perform_hyperopt": True,
+    "number_of_trials": 50,
+    "perform_crossval": True,
+    "plot": True,
+    "preserve_model": True,
+    "target_clf_thresholds": {1: {"precision": 0.80}},
+}
+
+# Create experiment
+experiment = app.create_experiment(data=your_dataframe, **context)
+```
+
+#### Important Notes
+
+1. **Context Persistence**: All context parameters are saved in the database when creating an experiment and automatically restored when loading it.
+
+2. **Parameter Precedence**: When loading an existing experiment, the stored context takes precedence over any parameters passed to the constructor.
+
+3. **PCA Time Series**: For time series data with `pca_cross_sectional` where index equals `date_column`, the system automatically uses an expanding window approach to prevent data leakage.
+
+4. **OpenAI Embeddings**: If using `columns_pca` with text columns, ensure `OPENAI_API_KEY` is set as an environment variable.
+
+5. **Model Indices**: The `models_idx` parameter accepts both integer indices and string names (e.g., `'xgb'`, `'lgb'`, `'catboost'`).
+
+
+
+### 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

lecrapaud-0.20.2/README.md

@@ -0,0 +1,308 @@
+<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
+
+The experiment context is a dictionary containing all configuration parameters for your ML pipeline. Parameters are stored in the experiment's database record and automatically retrieved when loading an existing experiment.
+
+#### Required Parameters
+
+| Parameter         | Type      | Description                                          | Example                |
+|-------------------|-----------|------------------------------------------------------|------------------------|
+| `data`           | DataFrame | Input dataset (required for new experiments only)    | `pd.DataFrame(...)`    |
+| `experiment_name`| str       | Unique name for the experiment                      | `'stock_prediction'`   |
+| `date_column`    | str       | Name of the date column (required for time series)  | `'DATE'`              |
+| `group_column`   | str       | Name of the group column (required for panel data)  | `'STOCK'`             |
+
+#### Feature Engineering Parameters
+
+| Parameter             | Type  | Default | Description                                                              |
+|-----------------------|-------|---------|--------------------------------------------------------------------------|
+| `columns_drop`        | list  | `[]`    | Columns to drop during feature engineering                              |
+| `columns_boolean`     | list  | `[]`    | Columns to convert to boolean features                                  |
+| `columns_date`        | list  | `[]`    | Date columns for cyclic encoding                                        |
+| `columns_te_groupby`  | list  | `[]`    | Groupby columns for target encoding                                     |
+| `columns_te_target`   | list  | `[]`    | Target columns for target encoding                                      |
+
+#### Preprocessing Parameters
+
+| Parameter               | Type  | Default | Description                                                           |
+|-------------------------|-------|---------|-----------------------------------------------------------------------|
+| `time_series`           | bool  | `False` | Whether data is time series                                          |
+| `val_size`              | float | `0.2`   | Validation set size (fraction)                                       |
+| `test_size`             | float | `0.2`   | Test set size (fraction)                                             |
+| `columns_pca`           | list  | `[]`    | Columns for PCA transformation                                       |
+| `pca_temporal`          | list  | `[]`    | Temporal PCA config (e.g., lag features)                            |
+| `pca_cross_sectional`   | list  | `[]`    | Cross-sectional PCA config (e.g., market regime)                    |
+| `columns_onehot`        | list  | `[]`    | Columns for one-hot encoding                                         |
+| `columns_binary`        | list  | `[]`    | Columns for binary encoding                                          |
+| `columns_ordinal`       | list  | `[]`    | Columns for ordinal encoding                                         |
+| `columns_frequency`     | list  | `[]`    | Columns for frequency encoding                                       |
+
+#### Feature Selection Parameters
+
+| Parameter                   | Type  | Default | Description                                                      |
+|-----------------------------|-------|---------|------------------------------------------------------------------|
+| `percentile`                | float | `20`    | Percentage of features to keep per selection method             |
+| `corr_threshold`            | float | `80`    | Maximum correlation threshold (%) between features              |
+| `max_features`              | int   | `50`    | Maximum number of final features                                |
+| `max_p_value_categorical`   | float | `0.05`  | Maximum p-value for categorical feature selection (Chi2)        |
+
+#### Model Selection Parameters
+
+| Parameter              | Type  | Default | Description                                                           |
+|------------------------|-------|---------|-----------------------------------------------------------------------|
+| `target_numbers`       | list  | `[]`    | List of target indices to predict                                     |
+| `target_clf`           | list  | `[]`    | Classification target indices                                         |
+| `models_idx`           | list  | `[]`    | Model indices or names to use (e.g., `[1, 'xgb', 'lgb']`)           |
+| `max_timesteps`        | int   | `120`   | Maximum timesteps for recurrent models                               |
+| `perform_hyperopt`     | bool  | `True`  | Whether to perform hyperparameter optimization                       |
+| `number_of_trials`     | int   | `20`    | Number of hyperopt trials                                            |
+| `perform_crossval`     | bool  | `False` | Whether to use cross-validation during hyperopt                      |
+| `plot`                 | bool  | `True`  | Whether to generate plots                                            |
+| `preserve_model`       | bool  | `True`  | Whether to save the best model                                       |
+| `target_clf_thresholds`| dict  | `{}`    | Classification thresholds per target                                 |
+
+#### Example Context Configuration
+
+```python
+context = {
+    # Required parameters
+    "experiment_name": f"stock_{datetime.now().strftime('%Y%m%d_%H%M%S')}",
+    "date_column": "DATE",
+    "group_column": "STOCK",
+    
+    # Feature selection
+    "corr_threshold": 80,
+    "max_features": 20,
+    "percentile": 20,
+    "max_p_value_categorical": 0.05,
+    
+    # Feature engineering
+    "columns_drop": ["SECURITY", "ISIN", "ID"],
+    "columns_boolean": [],
+    "columns_date": ["DATE"],
+    "columns_te_groupby": [["SECTOR", "DATE"]],
+    "columns_te_target": ["RET", "VOLUME"],
+    
+    # Preprocessing
+    "time_series": True,
+    "val_size": 0.2,
+    "test_size": 0.2,
+    "pca_temporal": [
+        {"name": "LAST_20_RET", "columns": [f"RET_-{i}" for i in range(1, 21)]},
+    ],
+    "pca_cross_sectional": [
+        {
+            "name": "MARKET_REGIME",
+            "index": "DATE",
+            "columns": "STOCK",
+            "value": "RET",
+        }
+    ],
+    "columns_onehot": ["BUY_SIGNAL"],
+    "columns_binary": ["SECTOR", "LOCATION"],
+    "columns_ordinal": ["STOCK"],
+    
+    # Model selection
+    "target_numbers": [1, 2, 3],
+    "target_clf": [1],
+    "models_idx": ["xgb", "lgb", "catboost"],
+    "max_timesteps": 120,
+    "perform_hyperopt": True,
+    "number_of_trials": 50,
+    "perform_crossval": True,
+    "plot": True,
+    "preserve_model": True,
+    "target_clf_thresholds": {1: {"precision": 0.80}},
+}
+
+# Create experiment
+experiment = app.create_experiment(data=your_dataframe, **context)
+```
+
+#### Important Notes
+
+1. **Context Persistence**: All context parameters are saved in the database when creating an experiment and automatically restored when loading it.
+
+2. **Parameter Precedence**: When loading an existing experiment, the stored context takes precedence over any parameters passed to the constructor.
+
+3. **PCA Time Series**: For time series data with `pca_cross_sectional` where index equals `date_column`, the system automatically uses an expanding window approach to prevent data leakage.
+
+4. **OpenAI Embeddings**: If using `columns_pca` with text columns, ensure `OPENAI_API_KEY` is set as an environment variable.
+
+5. **Model Indices**: The `models_idx` parameter accepts both integer indices and string names (e.g., `'xgb'`, `'lgb'`, `'catboost'`).
+
+
+
+### 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

{lecrapaud-0.20.1 → lecrapaud-0.20.2}/lecrapaud/config.py

@@ -32,6 +32,7 @@ DB_URI: str = (
 )
 OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
 LECRAPAUD_LOGFILE = os.getenv("LECRAPAUD_LOGFILE")
-LECRAPAUD_LOCAL = os.getenv("LECRAPAUD_LOCAL", False)
 LECRAPAUD_TABLE_PREFIX = os.getenv("LECRAPAUD_TABLE_PREFIX", "lecrapaud")
-LECRAPAUD_OPTIMIZATION_BACKEND = os.getenv("LECRAPAUD_OPTIMIZATION_BACKEND", "ray").lower()
+LECRAPAUD_OPTIMIZATION_BACKEND = os.getenv(
+    "LECRAPAUD_OPTIMIZATION_BACKEND", "ray"
+).lower()

{lecrapaud-0.20.1 → lecrapaud-0.20.2}/lecrapaud/experiment.py

@@ -16,15 +16,18 @@ from lecrapaud.db.session import get_db
 
 def create_experiment(
     data: pd.DataFrame | str,
-    date_column,
-    group_column,
     experiment_name,
+    date_column=None,
+    group_column=None,
     **kwargs,
 ):
     if isinstance(data, str):
         path = f"{data}/data/full.pkl"
         data = joblib.load(path)
 
+    if kwargs.get("time_series") and not date_column:
+        raise ValueError("date_column must be provided for time series experiments")
+
     dates = {}
     if date_column:
         dates["start_date"] = pd.to_datetime(data[date_column].iat[0])