doneconnection

python_connection.ipynb

@@ -0,0 +1,117 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6611acf4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sqlalchemy import create_engine\n",
+    "import pandas as pd\n",
+    "\n",
+    "def create_db_engine(user, password, host=\"localhost\", port=3306, database=\"sakila\"):\n",
+    "    connection_string = f\"mysql+pymysql://{user}:{password}@{host}:{port}/{database}\"\n",
+    "    engine = create_engine(connection_string)\n",
+    "    return engine\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "743212f6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "engine = create_db_engine(\"root\", \"your_password\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bda56806",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def rentals_month(engine, month, year):\n",
+    "    query = f\"\"\"\n",
+    "        SELECT\n",
+    "            rental_id,\n",
+    "            customer_id,\n",
+    "            rental_date\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": null,
+   "id": "ab263820",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def rental_count_month(df, month, year):\n",
+    "    \n",
+    "    column_name = f\"rentals_{month:02d}_{year}\"\n",
+    "    \n",
+    "    rental_count = (\n",
+    "        df.groupby(\"customer_id\")\n",
+    "          .size()\n",
+    "          .reset_index(name=column_name)\n",
+    "    )\n",
+    "    \n",
+    "    return rental_count\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "33d006c3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def compare_rentals(df1, df2):\n",
+    "    \n",
+    "    combined = pd.merge(\n",
+    "        df1,\n",
+    "        df2,\n",
+    "        on=\"customer_id\",\n",
+    "        how=\"outer\"\n",
+    "    ).fillna(0)\n",
+    "    \n",
+    "    # Identificar automaticamente colunas de rentals\n",
+    "    rental_cols = [col for col in combined.columns if col.startswith(\"rentals_\")]\n",
+    "    \n",
+    "    combined[\"difference\"] = combined[rental_cols[1]] - combined[rental_cols[0]]\n",
+    "    \n",
+    "    return combined\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "167c84eb",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "base",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python",
+   "version": "3.13.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}