DataAnalist_PT_NOV25_MiguelFlorindo

Connecting Python to SQL.ipynb

@@ -0,0 +1,172 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "521d4783",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sqlalchemy import create_engine\n",
+    "import pandas as pd\n",
+    "\n",
+    "# Example connection string (adjust as needed)\n",
+    "# MySQL Sakila database running locally\n",
+    "engine = create_engine('mysql+pymysql://root:#Safeguard100@localhost/sakila')\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "2ab775b4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def rentals_month(engine, month, year):\n",
+    "    \"\"\"\n",
+    "    Retrieves rental data for a specific month and year from the Sakila database.\n",
+    "    \n",
+    "    Parameters:\n",
+    "        engine : SQLAlchemy engine object\n",
+    "        month  : int, month number (e.g., 5 for May)\n",
+    "        year   : int, year number (e.g., 2005)\n",
+    "        \n",
+    "    Returns:\n",
+    "        pandas DataFrame with rental data for that month and year\n",
+    "    \"\"\"\n",
+    "    query = f\"\"\"\n",
+    "        SELECT \n",
+    "            rental_id,\n",
+    "            rental_date,\n",
+    "            customer_id\n",
+    "        FROM rental\n",
+    "        WHERE MONTH(rental_date) = {month}\n",
+    "          AND YEAR(rental_date) = {year};\n",
+    "    \"\"\"\n",
+    "    \n",
+    "    df = pd.read_sql(query, engine)\n",
+    "    return df\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "8a9e7496",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def rental_count_month(df, month, year):\n",
+    "    \"\"\"\n",
+    "    Counts number of rentals per customer for a given month/year.\n",
+    "    \n",
+    "    Parameters:\n",
+    "        df    : pandas DataFrame from rentals_month()\n",
+    "        month : int\n",
+    "        year  : int\n",
+    "        \n",
+    "    Returns:\n",
+    "        pandas DataFrame with columns [customer_id, rentals_MM_YYYY]\n",
+    "    \"\"\"\n",
+    "    col_name = f\"rentals_{month:02d}_{year}\"\n",
+    "    \n",
+    "    rental_counts = (\n",
+    "        df.groupby('customer_id')\n",
+    "          .size()\n",
+    "          .reset_index(name=col_name)\n",
+    "    )\n",
+    "    \n",
+    "    return rental_counts\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "99229755",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def compare_rentals(df1, df2):\n",
+    "    \"\"\"\n",
+    "    Compares rental activity between two months.\n",
+    "    \n",
+    "    Parameters:\n",
+    "        df1, df2 : DataFrames from rental_count_month()\n",
+    "        \n",
+    "    Returns:\n",
+    "        Combined DataFrame with rental counts for both months and a 'difference' column.\n",
+    "    \"\"\"\n",
+    "    merged = pd.merge(df1, df2, on='customer_id', how='inner')\n",
+    "    \n",
+    "    # Identify column names dynamically (the two rental count columns)\n",
+    "    cols = [c for c in merged.columns if c.startswith('rentals_')]\n",
+    "    \n",
+    "    merged['difference'] = merged[cols[1]] - merged[cols[0]]\n",
+    "    \n",
+    "    return merged\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "e1db19d4",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "   customer_id  rentals_05_2005  rentals_06_2005  difference\n",
+      "0            1                2                7           5\n",
+      "1            2                1                1           0\n",
+      "2            3                2                4           2\n",
+      "3            5                3                5           2\n",
+      "4            6                3                4           1\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Get data for May and June 2005\n",
+    "may_df = rentals_month(engine, 5, 2005)\n",
+    "june_df = rentals_month(engine, 6, 2005)\n",
+    "\n",
+    "# Count rentals per customer\n",
+    "may_counts = rental_count_month(may_df, 5, 2005)\n",
+    "june_counts = rental_count_month(june_df, 6, 2005)\n",
+    "\n",
+    "# Compare customer activity\n",
+    "comparison = compare_rentals(may_counts, june_counts)\n",
+    "\n",
+    "print(comparison.head())\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1c1caa42",
+   "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
+}