lecrapaud 0.1.0__py3-none-any.whl

lecrapaud/db/session.py

@@ -0,0 +1,45 @@
+"""Database session management and initialization module."""
+
+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
+
+_engine = None
+_SessionLocal = None
+DATABASE_URL = f"mysql+pymysql://{DB_USER}:{DB_PASSWORD}@{DB_HOST}:{DB_PORT}/{DB_NAME}"
+
+
+def init_db(uri: str = None):
+    global _engine, _SessionLocal
+
+    # 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}/"
+    )
+
+    # Step 2: Create database if it doesn't exist
+    with root_engine.connect() as conn:
+        conn.execute(text(f"CREATE DATABASE IF NOT EXISTS {DB_NAME}"))
+        conn.commit()
+
+    # Step 3: Connect to the newly created database
+    _engine = create_engine(DATABASE_URL, echo=False)
+
+    # Step 4: Create session factory
+    _SessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=_engine)
+
+
+# Dependency to get a session instance
+@contextmanager
+def get_db():
+    if _SessionLocal is None:
+        raise RuntimeError("Database not initialized. Call `init_db()` first.")
+    db = _SessionLocal()
+    try:
+        yield db
+    except Exception as e:
+        db.rollback()
+        raise Exception(e) from e
+    finally:
+        db.close()

lecrapaud/directory_management.py

@@ -0,0 +1,28 @@
+import os, shutil
+from pathlib import Path
+
+cwd = os.getcwd()
+tmp_dir = cwd + "/tmp"
+data_dir = tmp_dir + "/data"
+logger_dir = cwd + "/log"
+
+os.makedirs(tmp_dir, exist_ok=True)
+os.makedirs(data_dir, exist_ok=True)
+os.makedirs(logger_dir, exist_ok=True)
+
+
+def clean_directories():
+    clean_directory(tmp_dir)
+
+
+def clean_directory(dir_path: str):
+    if os.path.exists(dir_path):
+        for root, dirs, files in os.walk(dir_path, topdown=False):
+            for file in files:
+                file_path = os.path.join(root, file)
+                os.remove(file_path)
+            for dir in dirs:
+                dir_path = os.path.join(root, dir)
+                shutil.rmtree(dir_path)  # Recursively remove directories
+    else:
+        Exception(f"Directory {dir_path} does not exist.")

lecrapaud/experiment.py

@@ -0,0 +1,64 @@
+import pandas as pd
+import os
+from pathlib import Path
+
+os.environ["COVERAGE_FILE"] = str(Path(".coverage").resolve())
+
+# Internal
+from lecrapaud.directory_management import tmp_dir
+from lecrapaud.utils import logger
+from lecrapaud.config import PYTHON_ENV
+from lecrapaud.db import (
+    Dataset,
+    Target,
+)
+from lecrapaud.db.session import get_db
+
+
+def create_dataset(
+    data: pd.DataFrame,
+    corr_threshold,
+    percentile,
+    max_features,
+    date_column,
+    group_column,
+    **kwargs,
+):
+    dates = {}
+    if date_column:
+        dates["start_date"] = pd.to_datetime(data[date_column].iat[0])
+        dates["end_date"] = pd.to_datetime(data[date_column].iat[-1])
+
+    groups = {}
+    if group_column:
+        groups["number_of_groups"] = data[group_column].nunique()
+        groups["list_of_groups"] = data[group_column].unique().tolist()
+
+    with get_db() as db:
+        all_targets = Target.get_all(db=db)
+        targets = [target for target in all_targets if target.name in data.columns]
+        dataset_name = f"data_{groups["number_of_groups"] if group_column else 'ng'}_{corr_threshold}_{percentile}_{max_features}_{dates['start_date'].date() if date_column else 'nd'}_{dates['end_date'].date() if date_column else 'nd'}"
+
+        dataset_dir = f"{tmp_dir}/{dataset_name}"
+        preprocessing_dir = f"{dataset_dir}/preprocessing"
+        data_dir = f"{dataset_dir}/data"
+        os.makedirs(dataset_dir, exist_ok=True)
+        os.makedirs(preprocessing_dir, exist_ok=True)
+        os.makedirs(data_dir, exist_ok=True)
+
+        dataset = Dataset.upsert(
+            match_fields=["name"],
+            db=db,
+            name=dataset_name,
+            path=Path(dataset_dir).resolve(),
+            type="training",
+            size=data.shape[0],
+            corr_threshold=corr_threshold,
+            percentile=percentile,
+            max_features=max_features,
+            **groups,
+            **dates,
+            targets=targets,
+        )
+
+        return dataset