From 4cd7db1ca8e1381d2f01d503f0ff138038e90b72 Mon Sep 17 00:00:00 2001
From: Ou Hai <yumiou0703@gmail.com>
Date: Sat, 6 Dec 2025 21:04:41 +0100
Subject: [PATCH] Solved Lab

---
 lab-sql-python-connection.ipynb | 177 ++++++++++++++++++++++++++++++++
 1 file changed, 177 insertions(+)
 create mode 100644 lab-sql-python-connection.ipynb

diff --git a/lab-sql-python-connection.ipynb b/lab-sql-python-connection.ipynb
new file mode 100644
index 0000000..7331474
--- /dev/null
+++ b/lab-sql-python-connection.ipynb
@@ -0,0 +1,177 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "e63e6101",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import pymysql\n",
+    "from sqlalchemy import create_engine\n",
+    "import getpass\n",
+    "import urllib.parse\n",
+    "password = getpass.getpass()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "3faf64c3",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Engine(mysql+pymysql://root:***@localhost:3306/sakila)"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "bd = \"sakila\"\n",
+    "\n",
+    "password_encoded = urllib.parse.quote(password)\n",
+    "\n",
+    "\n",
+    "connection_string = f\"mysql+pymysql://root:{password_encoded}@localhost:3306/{bd}\"\n",
+    "\n",
+    "engine = create_engine(connection_string)\n",
+    "\n",
+    "engine"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "e67bca96",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def rentals_month(engine, month: int, year: int) -> pd.DataFrame:\n",
+    "    query = text(\"\"\"\n",
+    "        SELECT\n",
+    "            rental_id,\n",
+    "            rental_date,\n",
+    "            inventory_id,\n",
+    "            customer_id,\n",
+    "            staff_id\n",
+    "        FROM rental\n",
+    "        WHERE EXTRACT(MONTH FROM rental_date) = :month\n",
+    "          AND EXTRACT(YEAR  FROM rental_date) = :year\n",
+    "    \"\"\")\n",
+    "\n",
+    "    df = pd.read_sql(query, engine, params={\"month\": month, \"year\": year})\n",
+    "    return df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "41097caf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def rental_count_month(df: pd.DataFrame, month: int, year: int) -> pd.DataFrame:\n",
+    "    col_name = f\"rentals_{month:02d}_{year}\"\n",
+    "    \n",
+    "    counts = (\n",
+    "        df.groupby(\"customer_id\")\n",
+    "          .size()\n",
+    "          .reset_index(name=col_name)\n",
+    "    )\n",
+    "\n",
+    "    return counts"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "c9719ccb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def compare_rentals(df1: pd.DataFrame, df2: pd.DataFrame) -> pd.DataFrame:\n",
+    "    merged = pd.merge(df1, df2, on=\"customer_id\", how=\"outer\")\n",
+    "\n",
+    "    merged = merged.fillna(0)\n",
+    "    count_cols = [c for c in merged.columns if c != \"customer_id\"]\n",
+    "    if len(count_cols) != 2:\n",
+    "        raise ValueError(\n",
+    "            f\"Expected two rental count columns, but got：{count_cols}\"\n",
+    "        )\n",
+    "\n",
+    "    col1, col2 = count_cols\n",
+    "\n",
+    "    merged[\"difference\"] = merged[col2] - merged[col1]\n",
+    "\n",
+    "    return merged"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "9260daa4",
+   "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": [
+    "\n",
+    "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",
+    "print(comparison.head())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "afc86b70",
+   "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": "3.13.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}