diff --git a/lab-sql-python-connection.ipynb b/lab-sql-python-connection.ipynb new file mode 100644 index 0000000..eab2c36 --- /dev/null +++ b/lab-sql-python-connection.ipynb @@ -0,0 +1,344 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "id": "47ed2e29", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Requirement already satisfied: pymysql in /opt/anaconda3/lib/python3.13/site-packages (1.1.2)\n", + "Note: you may need to restart the kernel to use updated packages.\n" + ] + } + ], + "source": [ + "%pip install pymysql" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "id": "c5060bba", + "metadata": {}, + "outputs": [], + "source": [ + "import pandas as pd\n", + "import numpy as np\n", + "import pymysql\n", + "from sqlalchemy import create_engine, text\n", + "import getpass\n", + "password=getpass.getpass()" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "4582723a", + "metadata": {}, + "outputs": [], + "source": [ + "bd= \"sakila\"\n", + "connection_string= ''" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "494b90ff", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "Engine(mysql+pymysql://root:***@localhost/sakila)" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "bd = \"sakila\"\n", + "connection_string = 'mysql+pymysql://root:' + password + '@localhost/'+bd\n", + "engine = create_engine(connection_string)\n", + "engine" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "id": "6b47e247", + "metadata": {}, + "outputs": [], + "source": [ + "def rentals_month(engine, month, year):\n", + " query = f\"\"\"\n", + " SELECT \n", + " rental_id,\n", + " rental_date,\n", + " inventory_id,\n", + " customer_id,\n", + " return_date,\n", + " staff_id\n", + " FROM rental\n", + " WHERE MONTH(rental_date) = {month}\n", + " AND YEAR(rental_date) = {year};\n", + " \"\"\"\n", + " df = pd.read_sql_query(query, engine)\n", + " return df" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "id": "4ad87897", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
rental_idrental_dateinventory_idcustomer_idreturn_datestaff_id
012005-05-24 22:53:303671302005-05-26 22:04:301
122005-05-24 22:54:3315254592005-05-28 19:40:331
232005-05-24 23:03:3917114082005-06-01 22:12:391
342005-05-24 23:04:4124523332005-06-03 01:43:412
452005-05-24 23:05:2120792222005-06-02 04:33:211
\n", + "
" + ], + "text/plain": [ + " rental_id rental_date inventory_id customer_id \\\n", + "0 1 2005-05-24 22:53:30 367 130 \n", + "1 2 2005-05-24 22:54:33 1525 459 \n", + "2 3 2005-05-24 23:03:39 1711 408 \n", + "3 4 2005-05-24 23:04:41 2452 333 \n", + "4 5 2005-05-24 23:05:21 2079 222 \n", + "\n", + " return_date staff_id \n", + "0 2005-05-26 22:04:30 1 \n", + "1 2005-05-28 19:40:33 1 \n", + "2 2005-06-01 22:12:39 1 \n", + "3 2005-06-03 01:43:41 2 \n", + "4 2005-06-02 04:33:21 1 " + ] + }, + "execution_count": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df_rentals = rentals_month(engine, 5, 2005)\n", + "df_rentals.head()\n" + ] + }, + { + "cell_type": "markdown", + "id": "c5a4eeef", + "metadata": {}, + "source": [ + "Develop a Python function called rental_count_month that takes the DataFrame provided by rentals_month as input along with the month and year and returns a new DataFrame containing the number of rentals made by each customer_id during the selected month and year." + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "id": "9d6101c4", + "metadata": {}, + "outputs": [], + "source": [ + "def rental_count_month(df, month, year):\n", + " result = (\n", + " df.groupby(\"customer_id\")\n", + " .agg(rental_count=(\"rental_id\", \"count\"))\n", + " .reset_index()\n", + " )\n", + " result[\"month\"] = month\n", + " result[\"year\"] = year\n", + " return result" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "id": "3702dc53", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " customer_id rental_count month year\n", + "0 1 2 5 2005\n", + "1 2 1 5 2005\n", + "2 3 2 5 2005\n", + "3 5 3 5 2005\n", + "4 6 3 5 2005\n" + ] + } + ], + "source": [ + "df_rentals = rentals_month(engine, 5, 2005)\n", + "df_counts = rental_count_month(df_rentals, 5, 2005)\n", + "print(df_counts.head())\n" + ] + }, + { + "cell_type": "markdown", + "id": "ff3dd271", + "metadata": {}, + "source": [ + "Create a Python function called compare_rentals that takes two DataFrames as input containing the number of rentals made by each customer in different months and years. The function should return a combined DataFrame with a new 'difference' column, which is the difference between the number of rentals in the two months." + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "id": "a5a57a25", + "metadata": {}, + "outputs": [], + "source": [ + "\n", + "def compare_rentals(df1, df2):\n", + " merged = pd.merge(df1, df2, on=\"customer_id\", suffixes=(\"_1\", \"_2\"), how=\"outer\").fillna(0)\n", + " merged[\"difference\"] = merged[\"rental_count_2\"] - merged[\"rental_count_1\"]\n", + " return merged" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "id": "47fccace", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " customer_id rental_count_1 month_1 year_1 rental_count_2 month_2 \\\n", + "0 1 2.0 5.0 2005.0 7.0 6.0 \n", + "1 2 1.0 5.0 2005.0 1.0 6.0 \n", + "2 3 2.0 5.0 2005.0 4.0 6.0 \n", + "3 4 0.0 0.0 0.0 6.0 6.0 \n", + "4 5 3.0 5.0 2005.0 5.0 6.0 \n", + "\n", + " year_2 difference \n", + "0 2005.0 5.0 \n", + "1 2005.0 0.0 \n", + "2 2005.0 2.0 \n", + "3 2005.0 6.0 \n", + "4 2005.0 2.0 \n" + ] + } + ], + "source": [ + "df_may = rental_count_month(rentals_month(engine, 5, 2005), 5, 2005)\n", + "df_june = rental_count_month(rentals_month(engine, 6, 2005), 6, 2005)\n", + "\n", + "comparison = compare_rentals(df_may, df_june)\n", + "print(comparison.head())\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "1c2a4eef", + "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 +}