Solved lab

lab-sql-python-connection.ipynb

@@ -0,0 +1,97 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "2c392e84",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sqlalchemy import create_engine\n",
+    "\n",
+    "# Replace the following with your actual database URI\n",
+    "DATABASE_URI = 'mysql+pymysql://username:password@localhost:3306/sakila'\n",
+    "\n",
+    "# Create engine\n",
+    "engine = create_engine(DATABASE_URI)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "3acedc81",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "def rentals_month(engine, month, year):\n",
+    "    query = f\"\"\"\n",
+    "    SELECT \n",
+    "        customer_id, \n",
+    "        COUNT(rental_id) AS rentals\n",
+    "    FROM \n",
+    "        sakila.rental\n",
+    "    WHERE \n",
+    "        MONTH(rental_date) = {month} AND YEAR(rental_date) = {year}\n",
+    "    GROUP BY \n",
+    "        customer_id;\n",
+    "    \"\"\"\n",
+    "    \n",
+    "    # Retrieve data using pandas\n",
+    "    df = pd.read_sql(query, con=engine)\n",
+    "    return df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "1a7162c2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def rental_count_month(rental_df, month, year):\n",
+    "    column_name = f'rentals_{str(month).zfill(2)}_{year}'\n",
+    "    rental_df = rental_df.rename(columns={'rentals': column_name})\n",
+    "    return rental_df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "b26328f9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def compare_rentals(df1, df2):\n",
+    "    # Merge the two DataFrames on customer_id\n",
+    "    combined_df = pd.merge(df1, df2, on='customer_id', how='outer').fillna(0)\n",
+    "    \n",
+    "    # Create 'difference' column\n",
+    "    combined_df['difference'] = combined_df.iloc[:, 1] - combined_df.iloc[:, 2]\n",
+    "    return combined_df"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "base",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.13.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}