Lab solved

lab_sql_python_connection.ipynb

@@ -0,0 +1,138 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "ee78eee4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sqlalchemy import create_engine\n",
+    "import pandas as pd \n",
+    "import getpass \n",
+    "password = getpass.getpass()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "aaefef7f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "engine = create_engine(\"mysql+pymysql://root:\" + password + \"@localhost:3306/sakila\")\n",
+    "\n",
+    "def rentals_month(engine,month,year):\n",
+    "    query = '''\n",
+    "    SELECT\n",
+    "        rental_id,\n",
+    "        rental_date,\n",
+    "        customer_id\n",
+    "    FROM rental\n",
+    "    WHERE MONTH(rental_date) =%s\n",
+    "    AND YEAR(rental_date) =%s\n",
+    "    '''\n",
+    "    df = pd.read_sql(query,engine, params =(month, year))\n",
+    "    return df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "d056b7b5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def rental_count_month(df, month, year):\n",
+    "    column_name = f\"rentals_{month:02d}_{year}\"\n",
+    "    \n",
+    "    result = (\n",
+    "        df.groupby(\"customer_id\")\n",
+    "          .size()\n",
+    "          .reset_index(name=column_name)\n",
+    "    )\n",
+    "    \n",
+    "    return result\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "bfaa16f3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def compare_rentals(df1, df2):\n",
+    "    combined = pd.merge(df1, df2, on=\"customer_id\", how=\"outer\")\n",
+    "    \n",
+    "    combined = combined.fillna(0)\n",
+    "    \n",
+    "    rental_cols = combined.columns.drop(\"customer_id\")\n",
+    "    \n",
+    "    combined[\"difference\"] = combined[rental_cols[1]] - combined[rental_cols[0]]\n",
+    "    \n",
+    "    return combined"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "06b7874e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "   customer_id  rentals_05_2005  rentals_06_2005  difference\n",
+      "0            1              2.0              7.0         5.0\n",
+      "1            2              1.0              1.0         0.0\n",
+      "2            3              2.0              4.0         2.0\n",
+      "3            4              0.0              6.0         6.0\n",
+      "4            5              3.0              5.0         2.0\n"
+     ]
+    }
+   ],
+   "source": [
+    "may_df = rentals_month(engine, 5, 2005)\n",
+    "june_df = rentals_month(engine, 6, 2005)\n",
+    "\n",
+    "may_counts = rental_count_month(may_df, 5, 2005)\n",
+    "june_counts = rental_count_month(june_df, 6, 2005)\n",
+    "\n",
+    "comparison = compare_rentals(may_counts, june_counts)\n",
+    "\n",
+    "print(comparison.head())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8b931f46",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "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
+}