Solved lab

.gitignore

@@ -0,0 +1 @@
+.venv/

main.py

@@ -0,0 +1,63 @@
+import os
+import pandas as pd
+from sqlalchemy import create_engine, text
+
+
+def get_engine():
+    user = os.getenv("MYSQL_USER", "root")
+    password = os.getenv("MYSQL_PASSWORD","Kalamarhs1997")
+    host = os.getenv("MYSQL_HOST", "127.0.0.1")
+    port = os.getenv("MYSQL_PORT", "3306")
+    db = os.getenv("MYSQL_DB", "sakila")
+
+    if not password:
+        raise ValueError("MYSQL_PASSWORD not set")
+
+    url = f"mysql+pymysql://{user}:{password}@{host}:{port}/{db}"
+    return create_engine(url)
+
+
+def rentals_month(engine, month, year):
+    query = text("""
+        SELECT rental_id, rental_date, inventory_id, customer_id, return_date, staff_id
+        FROM rental
+        WHERE YEAR(rental_date) = :year
+          AND MONTH(rental_date) = :month
+    """)
+    return pd.read_sql(query, engine, params={"year": year, "month": month})
+
+
+def rental_count_month(df, month, year):
+    col = f"rentals_{month:02d}_{year}"
+    return df.groupby("customer_id").size().reset_index(name=col)
+
+
+def compare_rentals(df1, df2):
+    col1 = [c for c in df1.columns if c.startswith("rentals_")][0]
+    col2 = [c for c in df2.columns if c.startswith("rentals_")][0]
+
+    merged = df1.merge(df2, on="customer_id", how="inner")
+    merged["difference"] = merged[col2] - merged[col1]
+
+    return merged.sort_values("difference", ascending=False)
+
+
+def main():
+    engine = get_engine()
+
+    may = rentals_month(engine, 5, 2005)
+    june = rentals_month(engine, 6, 2005)
+
+    may_counts = rental_count_month(may, 5, 2005)
+    june_counts = rental_count_month(june, 6, 2005)
+
+    comparison = compare_rentals(may_counts, june_counts)
+
+    print(comparison.head(20))
+
+    comparison.to_csv("may_vs_june_rentals.csv", index=False)
+    print("Saved to may_vs_june_rentals.csv")
+
+
+if __name__ == "__main__":
+    main()