Lab Notebook: Connecting Python to SQL

Connecting Python to SQL.ipynb

@@ -0,0 +1,196 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "f9878474",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sqlalchemy import create_engine\n",
+    "\n",
+    "engine = create_engine(\n",
+    "    \"mysql+mysqlconnector://root:Reynold451!!@localhost/sakila\"\n",
+    ")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "b8eddb12",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "from sqlalchemy import text\n",
+    "\n",
+    "# 2. rentals_month(engine, month, year)\n",
+    "def rentals_month(engine, month: int, year: int) -> pd.DataFrame:\n",
+    "    \"\"\"\n",
+    "    Return all rentals for a given month/year from sakila.rental as a DataFrame.\n",
+    "    \"\"\"\n",
+    "    query = text(\n",
+    "        \"\"\"\n",
+    "        SELECT\n",
+    "            rental_id,\n",
+    "            rental_date,\n",
+    "            inventory_id,\n",
+    "            customer_id,\n",
+    "            return_date,\n",
+    "            staff_id,\n",
+    "            last_update\n",
+    "        FROM rental\n",
+    "        WHERE\n",
+    "            MONTH(rental_date) = :month\n",
+    "            AND YEAR(rental_date) = :year\n",
+    "        \"\"\"\n",
+    "    )\n",
+    "    df = pd.read_sql(query, con=engine, params={\"month\": month, \"year\": year})\n",
+    "    return df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "2428798c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 3. rental_count_month(df_rentals, month, year)\n",
+    "def rental_count_month(df_rentals: pd.DataFrame, month: int, year: int) -> pd.DataFrame:\n",
+    "    \"\"\"\n",
+    "    From a rentals DataFrame, return a DataFrame with number of rentals\n",
+    "    per customer_id for the given month/year.\n",
+    "    Column name should be rentals_MM_YYYY.\n",
+    "    \"\"\"\n",
+    "    col_name = f\"rentals_{month:02d}_{year}\"\n",
+    "\n",
+    "    # group by customer_id and count rentals\n",
+    "    counts = (\n",
+    "        df_rentals.groupby(\"customer_id\")[\"rental_id\"]\n",
+    "        .count()\n",
+    "        .reset_index()\n",
+    "        .rename(columns={\"rental_id\": col_name})\n",
+    "    )\n",
+    "    return counts\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "4b9bead9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd \n",
+    "from sqlalchemy import create_engine, text\n",
+    "import getpass\n",
+    "import urllib.parse\n",
+    "\n",
+    "# 1. Create SQLAlchemy engine (prompt for user/password/host/db)\n",
+    "# Example for local MYSQL + Sakila:\n",
+    "# pip install sqlalchemy mysql-connector-python\n",
+    "\n",
+    "# Prompt for credentials so you don't hard-code invalid credentials in the notebook.\n",
+    "# Enter the correct username/password for your MySQL instance.\n",
+    "user = input(\"MySQL user (e.g. 'root' or your user'): \").strip()\n",
+    "host = input(\"MySQL host (default 'localhost'): \").strip() or \"localhost\"\n",
+    "db = input(\"Database name (default 'sakila'): \").strip() or \"sakila\"\n",
+    "password = getpass.getpass(f\"Password for {user}@{host}: \")\n",
+    "\n",
+    "# escape password to be safe in a URL\n",
+    "password_esc = urllib.parse.quote_plus(password)\n",
+    "\n",
+    "engine = create_engine(f\"mysql+mysqlconnector://{user}:{password_esc}@{host}/{db}\")\n",
+    "\n",
+    "# quick connection test with helpful error message\n",
+    "try:\n",
+    "    with engine.connect() as conn:\n",
+    "        conn.execute(text(\"SELECT 1\"))\n",
+    "except Exception as e:\n",
+    "    print(\"Failed to connect to the database. Check username/password/host/database.\")\n",
+    "    print(\"Connection error:\", e)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0c4b1703",
+   "metadata": {},
+   "source": [
+    "# Create compare_rentals to compare between two months "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "a50f45cd",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Empty DataFrame\n",
+      "Columns: [customer_id, rentals_05_2005, rentals_06_2005, difference]\n",
+      "Index: []\n"
+     ]
+    }
+   ],
+   "source": [
+    "# 4. compare_rentals(df1, df2)\n",
+    "def compare_rentals(df1: pd.DataFrame, df2: pd.DataFrame) -> pd.DataFrame:\n",
+    "    \"\"\"\n",
+    "    Merge two DataFrames (counts per customer) and compute a 'difference' column\n",
+    "    = rentals in df2 minus rentals in df1.\n",
+    "    Assumes both have 'customer_id' and one rentals_* column each.\n",
+    "    \"\"\"\n",
+    "    # Inner or outer join depending on requirement; lab usually wants\n",
+    "    # customers active in both months -> inner join:\n",
+    "    df_merged = df1.merge(df2, on=\"customer_id\", how=\"inner\")\n",
+    "\n",
+    "    # Identify the two rentals columns\n",
+    "    rental_cols = [c for c in df_merged.columns if c.startswith(\"rentals_\")]\n",
+    "    if len(rental_cols) != 2:\n",
+    "        raise ValueError(\"Each input DataFrame must have exactly one rentals_* column.\")\n",
+    "\n",
+    "    col1, col2 = rental_cols\n",
+    "    df_merged[\"difference\"] = df_merged[col2] - df_merged[col1]\n",
+    "    return df_merged\n",
+    "\n",
+    "\n",
+    "if __name__ == \"__main__\":\n",
+    "    # Example usage for May and June 2005\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())"
+   ]
+  }
+ ],
+ "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": "3.9.20"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}