solved lab

lab_connecting_python_to_SQL.ipynb

@@ -0,0 +1,155 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "5ab0d189-4a68-4007-b822-42ef49caa122",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Requirement already satisfied: pymysql in c:\\users\\leysu\\anaconda3\\envs\\anaconda-2025.12-py3.13\\lib\\site-packages (1.2.0)\n",
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# install pymsql\n",
+    "%pip install pymysql"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "dc4405f4-4fff-4fc6-8ded-498645eedf85",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Step 1: Import Required Libraries\n",
+    "from sqlalchemy import create_engine\n",
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "0ffa6320-3fd7-41cf-aa6c-f6a1054fd2a8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# STEP 2: Establish a connection between python and sakila database\n",
+    "engine = create_engine(\"mysql+pymysql://root:BABYb@22@localhost/sakila\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "5e7425de-8f94-4f5a-be6d-d5f358faf5ba",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# STEP 3: write the rentals_month function\n",
+    "def rentals_month(engine, month: int, year: int) -> pd.DataFrame:\n",
+    "    \"\"\"Retrieves raw rental records for a designated month and year.\"\"\"\n",
+    "    # Write the SQL query\n",
+    "    query = f\"\"\"\n",
+    "    SELECT\n",
+    "    r.rental_id,\n",
+    "    r.rental_date,\n",
+    "    r.inventory_id,\n",
+    "    r.customer_id,\n",
+    "    r.staff_id\n",
+    "    FROM rental AS r\n",
+    "    WHERE MONTH(r.rental_date) = {month}\n",
+    "    AND YEAR(r.rental_date) = {year};\n",
+    "    \"\"\"\n",
+    "    # Executing the query and loading results directly into a DataFrame\n",
+    "    df_rentals = pd.read_sql(query, con=engine)\n",
+    "    return df_rentals"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "ce941b11-da46-44a1-829d-e5eff29373e5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# STEP 4: Develop the rental_count_month function\n",
+    "def rental_count_month(df_rentalas: pd.DataFrame, month: int, year: int) -> pd.DataFrame:\n",
+    "    \"\"\"Aggregates rental data by customer_id and dynamically titles the count column.\"\"\"\n",
+    "\n",
+    "    # Grouping by customer_id and counting the number of records per group\n",
+    "    df_counts = df_rentals.groupby(\"customer_id\").size().reset_index(name=\"rental_count\")\n",
+    "    \n",
+    "    # Formatting strings to match the requested pattern\n",
+    "    column_name = f\"rentals_{month:02d}_{year}\"\n",
+    "\n",
+    "    # Renaming the generic count column to the custom dynamic name\n",
+    "    df_counts = df_counts.raname(columns={\"rental_count\": column_name})\n",
+    "\n",
+    "    return df_counts\n",
+    "    "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "b0a162fb-b387-4459-b77c-d81d4ec13a80",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# STEP 5: Create the compare_rentals function\n",
+    "def compare_rentals(df_month1: pd.DataFrame, df_month2: pd.DataFrame) -> pd.DataFrame:\n",
+    "    \"\"\"Merges two monthly datasets and calculates individual customer rental volume differences.\"\"\"\n",
+    "    \n",
+    "    # Identifying the custom dynamic column names to perform calculations later\n",
+    "    col_m1 = df_month1.columns[1]\n",
+    "    col_m2 = df_month2.columns[1]\n",
+    "    \n",
+    "    # Performing an outer join on customer_id so no customer data is left out\n",
+    "    df_merged = pd.merge(df_month1, df_month2, on=\"customer_id\", how=\"outer\")\n",
+    "    \n",
+    "    # Replacing NaN values with 0 for customers who didn't rent during a specific month\n",
+    "    df_merged[col_m1] = df_merged[col_m1].fillna(0).astype(int)\n",
+    "    df_merged[col_m2] = df_merged[col_m2].fillna(0).astype(int)\n",
+    "    \n",
+    "    # Creating the derived 'difference' field by subtracting Month 1 from Month 2\n",
+    "    df_merged[\"difference\"] = df_merged[col_m2] - df_merged[col_m1]\n",
+    "    \n",
+    "    return df_merged"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ced5f6e9-29b6-49f1-9a22-28934157618a",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "anaconda-2025.12-py3.13",
+   "language": "python",
+   "name": "conda-env-anaconda-2025.12-py3.13"
+  },
+  "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
+}