lecrapaud 0.1.0__py3-none-any.whl → 0.2.1__py3-none-any.whl

lecrapaud/config.py

@@ -22,4 +22,5 @@ DB_PASSWORD = (
 DB_HOST = os.getenv("TEST_DB_HOST") if PYTHON_ENV == "Test" else os.getenv("DB_HOST")
 DB_PORT = os.getenv("TEST_DB_PORT") if PYTHON_ENV == "Test" else os.getenv("DB_PORT")
 DB_NAME = os.getenv("TEST_DB_NAME") if PYTHON_ENV == "Test" else os.getenv("DB_NAME")
+DB_URI = os.getenv("DB_URI", None)
 OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")

lecrapaud/db/session.py

@@ -3,20 +3,30 @@
 from contextlib import contextmanager
 from sqlalchemy import create_engine, text
 from sqlalchemy.orm import sessionmaker
-from lecrapaud.config import DB_USER, DB_PASSWORD, DB_HOST, DB_PORT, DB_NAME
+from urllib.parse import urlparse
+
+from lecrapaud.config import DB_USER, DB_PASSWORD, DB_HOST, DB_PORT, DB_NAME, DB_URI
 
 _engine = None
 _SessionLocal = None
-DATABASE_URL = f"mysql+pymysql://{DB_USER}:{DB_PASSWORD}@{DB_HOST}:{DB_PORT}/{DB_NAME}"
+DATABASE_URL = (
+    f"mysql+pymysql://{DB_USER}:{DB_PASSWORD}@{DB_HOST}:{DB_PORT}/{DB_NAME}" or DB_URI
+)
 
 
 def init_db(uri: str = None):
     global _engine, _SessionLocal
 
+    uri = uri if uri else DATABASE_URL
+    # Extract DB name from URI to connect without it
+    parsed = urlparse(uri)
+    db_name = parsed.path.lstrip("/")  # remove leading slash
+
+    # Build root engine (no database in URI)
+    root_uri = uri.replace(f"/{db_name}", "/")
+
     # Step 1: Connect to MySQL without a database
-    root_engine = create_engine(
-        uri if uri else f"mysql+pymysql://{DB_USER}:{DB_PASSWORD}@{DB_HOST}:{DB_PORT}/"
-    )
+    root_engine = create_engine(root_uri)
 
     # Step 2: Create database if it doesn't exist
     with root_engine.connect() as conn:
@@ -24,7 +34,7 @@ def init_db(uri: str = None):
         conn.commit()
 
     # Step 3: Connect to the newly created database
-    _engine = create_engine(DATABASE_URL, echo=False)
+    _engine = create_engine(uri, echo=False)
 
     # Step 4: Create session factory
     _SessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=_engine)

lecrapaud/feature_engineering.py

@@ -589,7 +589,6 @@ class PreprocessFeature:
 
         if transformer:
             transformed = transformer.transform(X)
-            print(len(transformed), len(transformed[0]))
         else:
             transformer = ColumnTransformer(
                 transformers=[

lecrapaud/feature_selection.py

@@ -811,12 +811,10 @@ class PreprocessModel:
         if duplicates:
             raise ValueError(f"Doublons détectés dans columns_to_keep: {duplicates}")
 
-        logger.info(self.all_features)
-
         self.train = train[columns_to_keep]
-        if val:
+        if isinstance(val, pd.DataFrame):
             self.val = val[columns_to_keep]
-        if test:
+        if isinstance(test, pd.DataFrame):
             self.test = test[columns_to_keep]
 
     def run(self):

lecrapaud/model_selection.py

@@ -894,12 +894,9 @@ class ModelSelectionEngine:
             # instantiate model
             model = ModelEngine(
                 model_name=model_name,
-                recurrent=recurrent,
-                need_scaling=need_scaling,
                 search_params=config["search_params"],
                 target_type=self.target_type,
                 create_model=config["create_model"],
-                scaler_y=self.scaler_y,
                 plot=self.plot,
                 log_dir=log_dir,
             )

lecrapaud-0.2.1.dist-info/METADATA

@@ -0,0 +1,171 @@
+Metadata-Version: 2.3
+Name: lecrapaud
+Version: 0.2.1
+Summary: Framework for machine and deep learning, with regression, classification and time series analysis
+License: Apache 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: backoff (>=2.2.1)
+Requires-Dist: category-encoders (>=2.8.1)
+Requires-Dist: celery (>=5.5.1)
+Requires-Dist: curl-cffi (>=0.11.1)
+Requires-Dist: deep-translator (>=1.11.4)
+Requires-Dist: degiro-connector (>=3.0.26)
+Requires-Dist: fake-useragent (>=2.1.0)
+Requires-Dist: ftfy (>=6.3.1)
+Requires-Dist: honeybadger (>=0.21)
+Requires-Dist: joblib (>=1.4.2)
+Requires-Dist: keras (>=3.9.0)
+Requires-Dist: keras-tcn (>=3.1.2)
+Requires-Dist: lightgbm (>=4.6.0)
+Requires-Dist: matplotlib (>=3.10.1)
+Requires-Dist: mlxtend (>=0.23.4)
+Requires-Dist: numpy (>=2.1.3)
+Requires-Dist: openai (>=1.86.0)
+Requires-Dist: pandas (>=2.2.3)
+Requires-Dist: pandas-market-calendars (>=4.6.1)
+Requires-Dist: playwright (>=1.52.0)
+Requires-Dist: pydantic (>=2.10.6)
+Requires-Dist: python-dotenv (>=1.0.1)
+Requires-Dist: pytz (>=2025.1)
+Requires-Dist: ratelimit (>=2.2.1)
+Requires-Dist: scikit-learn (>=1.6.1)
+Requires-Dist: scipy (>=1.15.2)
+Requires-Dist: seaborn (>=0.13.2)
+Requires-Dist: sentence-transformers (>=3.4.1)
+Requires-Dist: sqlalchemy (>=2.0.39)
+Requires-Dist: tensorboardx (>=2.6.2.2)
+Requires-Dist: tensorflow (>=2.19.0)
+Requires-Dist: tf-keras (>=2.19.0)
+Requires-Dist: tiktoken (>=0.9.0)
+Requires-Dist: tqdm (>=4.67.1)
+Requires-Dist: xgboost (>=3.0.0)
+Requires-Dist: yahoo-fin (>=0.8.9.1)
+Requires-Dist: yfinance (>=0.2.55)
+Description-Content-Type: text/markdown
+
+<div align="center">
+
+<div style="font-size:50rem;">🐸</div>
+
+## Welcome to LeCrapaud
+
+**An all-in-one machine learning framework**
+
+</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()
+
+# 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)
+```
+
+### 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)
+```
+
+## 🤝 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-0.1.0.dist-info → lecrapaud-0.2.1.dist-info}/RECORD

@@ -1,6 +1,6 @@
 lecrapaud/__init__.py,sha256=oCxbtw_nk8rlOXbXbWo0RRMlsh6w-hTiZ6e5PRG_wp0,28
 lecrapaud/api.py,sha256=VpVj6zRanLzHo2bwbkar-HcOKsJPEDghWhxbrqDOxp4,9749
-lecrapaud/config.py,sha256=NMHQw98wqnva9uVaheJH1Peq6QmssvGkFECwi0tYb90,992
+lecrapaud/config.py,sha256=Jf7kknumJ9NudVoLugOxqLqB7zTSl67IVV2VVWA0Pv4,1027
 lecrapaud/db/__init__.py,sha256=82o9fMfaqKXPh2_rt44EzNRVZV1R4LScEnQYvj_TjK0,34
 lecrapaud/db/alembic/README,sha256=MVlc9TYmr57RbhXET6QxgyCcwWP7w-vLkEsirENqiIQ,38
 lecrapaud/db/alembic/env.py,sha256=OwO56oeL7o3XQe2pnhMxK9C3Yeoz-ZCnGUSnXkNU-rg,2164
@@ -32,17 +32,17 @@ lecrapaud/db/models/model_selection.py,sha256=Lj2WZBWvaVpJeDjdiAs8wvkoI-XrWv2IIj
 lecrapaud/db/models/model_training.py,sha256=2xv9SOh8IUV1ROSsKlooAGanl9G8nBdmr7vaV4GAWtw,1618
 lecrapaud/db/models/score.py,sha256=I6kA55ZQhReo9dA_JEgeRSqDoFKmYyL3l-zCffwsofs,1719
 lecrapaud/db/models/target.py,sha256=scEtXVO3oysEvg9uwm_ncsS3-4o2A6z6XiDVGrg5WHE,1644
-lecrapaud/db/session.py,sha256=lk_H-oCWgvK8HKahyk96HBgWp0SLw7PCeaOgCgg8aPc,1387
+lecrapaud/db/session.py,sha256=eD3zNodgC_ZEiNrSnhooMsaMiyccK9xgeReABWrbAuk,1629
 lecrapaud/directory_management.py,sha256=wrHmAJ-cBKb0GhJifxrb_RoLhZJX8xdkeirrWs7jQHk,791
 lecrapaud/experiment.py,sha256=8Y7HX5MGifrcquOML1lYXG-q40Wn4WBBRqLfPs1tLuk,1994
-lecrapaud/feature_engineering.py,sha256=jlqqUeRj4SnCpklZdnXkEpwFGaz3S-fy8frAuDOFcpc,30384
-lecrapaud/feature_selection.py,sha256=N8yRhx544hk__rJV-MFq28IetVwhev4iKHruBalYpjU,43011
+lecrapaud/feature_engineering.py,sha256=zia2qxe_KLBUZV2KYVPqGd2K55AjHiyeeCm_GhobJHE,30327
+lecrapaud/feature_selection.py,sha256=2h3S_c0hYZM-EKenpVRYTFFqT4T7fg2lJ5pY2gUDalk,43023
 lecrapaud/integrations/openai_integration.py,sha256=hHLF3fk5Bps8KNbNrEL3NUFa945jwClE6LrLpuMZOd4,7459
 lecrapaud/jobs/__init__.py,sha256=ZkrsyTOR21c_wN7RY8jPhm8jCrL1oCEtTsf3VFIlQiE,292
 lecrapaud/jobs/config.py,sha256=AmO0j3RFjx8H66dfKw_7vnshaOJb9Ox5BAZ9cwwLFMY,377
 lecrapaud/jobs/scheduler.py,sha256=SiYWPxokpKnR8V6btLOO6gbK0PEjSRoeG0kCbQvYPf4,990
 lecrapaud/jobs/tasks.py,sha256=evzhOHpgp6Gvoz__jUipi-_HSNny7bWgAauHv2Hpxyk,1640
-lecrapaud/model_selection.py,sha256=500OZaZ2hRfn54WES0uVijbGedJzXMxiE_4Gp5Lpvp4,61273
+lecrapaud/model_selection.py,sha256=3BGp9mM9pZECcEcxLvm5YBJZ9Q7CJxZEC2zVWOm9g2o,61153
 lecrapaud/predictions.py,sha256=Uw6Ghm05KcoZIB1m9YLBe4v7sV42_Hv1oPgYfKsF2iY,10754
 lecrapaud/preprocessing.py,sha256=GfOTdVpubf9w13bbgKjcx12oP3mefaTgm1HK1V3tVeQ,34424
 lecrapaud/search_space.py,sha256=6kVXDSmvpTuLKTlqQkKIzrJOM2P7HpqRiO3PR37VrsM,34123
@@ -57,7 +57,7 @@ lecrapaud/speed_tests/tests.ipynb,sha256=RjI7LDHSsbadUkea_hT14sD7ivljtIQk4NB5McX
 lecrapaud/speed_tests/trash.py,sha256=E4zrrRyVqeNEumWg8rYKquR9VTIULN52eCRqjmv_s58,1647
 lecrapaud/training.py,sha256=a-p-06-h-oRj5A728-xwekHZ7mxTnrPnKjAjoZhNZME,8071
 lecrapaud/utils.py,sha256=J2lMRo8J1CoZ1AYIPcdbFWXg-PxtQTs8qmeINioXWfk,8107
-lecrapaud-0.1.0.dist-info/LICENSE,sha256=MImCryu0AnqhJE_uAZD-PIDKXDKb8sT7v0i1NOYeHTM,11350
-lecrapaud-0.1.0.dist-info/METADATA,sha256=k3hj1_rsu1xXKg5wQIWtgpIVEzvxOQ3lnJRkvS08fOw,2519
-lecrapaud-0.1.0.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-lecrapaud-0.1.0.dist-info/RECORD,,
+lecrapaud-0.2.1.dist-info/LICENSE,sha256=MImCryu0AnqhJE_uAZD-PIDKXDKb8sT7v0i1NOYeHTM,11350
+lecrapaud-0.2.1.dist-info/METADATA,sha256=g2qZx1kl3Qf1GT7LE-NNmTOwJluyZel0tgL1FCSYmt4,4460
+lecrapaud-0.2.1.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+lecrapaud-0.2.1.dist-info/RECORD,,

lecrapaud-0.1.0.dist-info/METADATA

@@ -1,105 +0,0 @@
-Metadata-Version: 2.3
-Name: lecrapaud
-Version: 0.1.0
-Summary: Framework for machine and deep learning, with regression, classification and time series analysis
-License: Apache 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: backoff (>=2.2.1)
-Requires-Dist: category-encoders (>=2.8.1)
-Requires-Dist: celery (>=5.5.1)
-Requires-Dist: curl-cffi (>=0.11.1)
-Requires-Dist: deep-translator (>=1.11.4)
-Requires-Dist: degiro-connector (>=3.0.26)
-Requires-Dist: fake-useragent (>=2.1.0)
-Requires-Dist: ftfy (>=6.3.1)
-Requires-Dist: honeybadger (>=0.21)
-Requires-Dist: joblib (>=1.4.2)
-Requires-Dist: keras (>=3.9.0)
-Requires-Dist: keras-tcn (>=3.1.2)
-Requires-Dist: lightgbm (>=4.6.0)
-Requires-Dist: matplotlib (>=3.10.1)
-Requires-Dist: mlxtend (>=0.23.4)
-Requires-Dist: numpy (>=2.1.3)
-Requires-Dist: openai (>=1.86.0)
-Requires-Dist: pandas (>=2.2.3)
-Requires-Dist: pandas-market-calendars (>=4.6.1)
-Requires-Dist: playwright (>=1.52.0)
-Requires-Dist: pydantic (>=2.10.6)
-Requires-Dist: python-dotenv (>=1.0.1)
-Requires-Dist: pytz (>=2025.1)
-Requires-Dist: ratelimit (>=2.2.1)
-Requires-Dist: scikit-learn (>=1.6.1)
-Requires-Dist: scipy (>=1.15.2)
-Requires-Dist: seaborn (>=0.13.2)
-Requires-Dist: sentence-transformers (>=3.4.1)
-Requires-Dist: sqlalchemy (>=2.0.39)
-Requires-Dist: tensorboardx (>=2.6.2.2)
-Requires-Dist: tensorflow (>=2.19.0)
-Requires-Dist: tf-keras (>=2.19.0)
-Requires-Dist: tiktoken (>=0.9.0)
-Requires-Dist: tqdm (>=4.67.1)
-Requires-Dist: xgboost (>=3.0.0)
-Requires-Dist: yahoo-fin (>=0.8.9.1)
-Requires-Dist: yfinance (>=0.2.55)
-Description-Content-Type: text/markdown
-
-# Stock
-
-## Overview
-
-## Project description
-
-## Quick Start
-
-1. Create environment
-
-```sh
-$ pip install virtualenv
-$ python -m venv .venv
-$ source .venv/bin/activate
-```
-
-2. Install dependencies
-
-```sh
-$ pip install -r requirements.txt
-$ pip freeze > requirements.txt
-```
-
-3. Deactivate virtualenv (if needed)
-
-```sh
-$ deactivate
-```
-
-## 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
-
-
-***
-
-Pierre Gallet © 2024