Gabriel_lab_sql_python_connection.ipynb

lab_sql_python_connection.ipynb

@@ -0,0 +1,190 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "83bcd4b9",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>customer_id</th>\n",
+       "      <th>rentals_05_2005</th>\n",
+       "      <th>rentals_06_2005</th>\n",
+       "      <th>difference</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>2</td>\n",
+       "      <td>7</td>\n",
+       "      <td>5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3</td>\n",
+       "      <td>2</td>\n",
+       "      <td>4</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>5</td>\n",
+       "      <td>3</td>\n",
+       "      <td>5</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>6</td>\n",
+       "      <td>3</td>\n",
+       "      <td>4</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   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"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "from sqlalchemy import create_engine\n",
+    "from urllib.parse import quote_plus\n",
+    "\n",
+    "password = quote_plus(\"Gazeb@85\")\n",
+    "\n",
+    "engine = create_engine(\n",
+    "    f\"mysql+pymysql://root:{password}@localhost:3306/sakila\"\n",
+    ")\n",
+    "\n",
+    "def rentals_month(engine, month, year):\n",
+    "    query = \"\"\"\n",
+    "    SELECT *\n",
+    "    FROM rental\n",
+    "    WHERE MONTH(rental_date) = %(month)s\n",
+    "      AND YEAR(rental_date) = %(year)s;\n",
+    "    \"\"\"\n",
+    "    \n",
+    "    return pd.read_sql(\n",
+    "        query,\n",
+    "        engine,\n",
+    "        params={\"month\": month, \"year\": year}\n",
+    "    )\n",
+    "\n",
+    "\n",
+    "def rental_count_month(rentals_df, month, year):\n",
+    "    column_name = f\"rentals_{month:02d}_{year}\"\n",
+    "    \n",
+    "    rental_count = (\n",
+    "        rentals_df\n",
+    "        .groupby(\"customer_id\")\n",
+    "        .size()\n",
+    "        .reset_index(name=column_name)\n",
+    "    )\n",
+    "    \n",
+    "    return rental_count\n",
+    "\n",
+    "\n",
+    "def compare_rentals(df_month_1, df_month_2):\n",
+    "    comparison = pd.merge(\n",
+    "        df_month_1,\n",
+    "        df_month_2,\n",
+    "        on=\"customer_id\",\n",
+    "        how=\"inner\"\n",
+    "    )\n",
+    "    \n",
+    "    rental_columns = [\n",
+    "        col for col in comparison.columns \n",
+    "        if col.startswith(\"rentals_\")\n",
+    "    ]\n",
+    "    \n",
+    "    comparison[\"difference\"] = (\n",
+    "        comparison[rental_columns[1]] - comparison[rental_columns[0]]\n",
+    "    )\n",
+    "    \n",
+    "    return comparison\n",
+    "\n",
+    "\n",
+    "rentals_may = rentals_month(engine, 5, 2005)\n",
+    "rentals_june = rentals_month(engine, 6, 2005)\n",
+    "\n",
+    "rentals_may_count = rental_count_month(rentals_may, 5, 2005)\n",
+    "rentals_june_count = rental_count_month(rentals_june, 6, 2005)\n",
+    "\n",
+    "comparison_df = compare_rentals(rentals_may_count, rentals_june_count)\n",
+    "\n",
+    "comparison_df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1929046c",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.9.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}