scripts/insert_dataset.py

import os
import pandas as pd
from dotenv import load_dotenv
from sqlalchemy import create_engine

load_dotenv()

BASE_DIR = os.path.dirname(os.path.abspath(__file__))
csv_path = os.path.join(BASE_DIR, "dataset_final.csv")

df = pd.read_csv(csv_path, encoding="latin-1")

DB_USER = os.getenv("DB_USER")
DB_PASSWORD = os.getenv("DB_PASSWORD")
DB_HOST = os.getenv("DB_HOST")
DB_PORT = os.getenv("DB_PORT")
DB_NAME = os.getenv("DB_NAME")

DATABASE_URL = (f"postgresql+psycopg2://{DB_USER}:{DB_PASSWORD}"f"@{DB_HOST}:{DB_PORT}/{DB_NAME}")

engine = create_engine(DATABASE_URL)

df.to_sql("employees_dataset", engine, if_exists="replace", index=False)

print("Dataset inséré dans PostgreSQL")