From 8a7b93e25ed6b1eceed8cdcf4991dba236a49bf3 Mon Sep 17 00:00:00 2001 From: Ha Nguyen Date: Fri, 6 Feb 2026 23:40:34 +0100 Subject: [PATCH] Solved lab --- lab7.ipynb | 576 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 576 insertions(+) create mode 100644 lab7.ipynb diff --git a/lab7.ipynb b/lab7.ipynb new file mode 100644 index 0000000..c02f7bc --- /dev/null +++ b/lab7.ipynb @@ -0,0 +1,576 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "id": "dfb724b8", + "metadata": {}, + "outputs": [], + "source": [ + "import pandas as pd\n", + "import numpy as np\n", + "import pymysql\n", + "from sqlalchemy import create_engine\n", + "import getpass # To get the password without showing the input\n", + "password = getpass.getpass()" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "bcac7947", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "Engine(mysql+pymysql://root:***@localhost/sakila)" + ] + }, + "execution_count": 9, + "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": 52, + "id": "4fb3a6ba", + "metadata": {}, + "outputs": [], + "source": [ + "from sqlalchemy import text\n", + "\n", + "def get_rental_info(engine,month,year):\n", + " with engine.connect() as connection:\n", + " query = text(\"\"\"SELECT * FROM rental\n", + " WHERE MONTH(rental_date) = :month AND YEAR(rental_date) = :year;\n", + " \"\"\")\n", + " result = connection.execute(query, {\n", + " \"month\": month,\n", + " \"year\": year\n", + " })\n", + " df = pd.DataFrame(result.all())\n", + " return df\n", + "df = get_rental_info(engine,5,2005)\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 53, + "id": "8f0b4a99", + "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", + " \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", + " \n", + " \n", + " \n", + " \n", + " \n", + "
rental_idrental_dateinventory_idcustomer_idreturn_datestaff_idlast_update
012005-05-24 22:53:303671302005-05-26 22:04:3012006-02-15 21:30:53
122005-05-24 22:54:3315254592005-05-28 19:40:3312006-02-15 21:30:53
232005-05-24 23:03:3917114082005-06-01 22:12:3912006-02-15 21:30:53
342005-05-24 23:04:4124523332005-06-03 01:43:4122006-02-15 21:30:53
452005-05-24 23:05:2120792222005-06-02 04:33:2112006-02-15 21:30:53
........................
115111532005-05-31 21:36:4427255062005-06-10 01:26:4422006-02-15 21:30:53
115211542005-05-31 21:42:092732592005-06-08 16:40:0912006-02-15 21:30:53
115311552005-05-31 22:17:1120482512005-06-04 20:27:1122006-02-15 21:30:53
115411562005-05-31 22:37:344601062005-06-01 23:02:3422006-02-15 21:30:53
115511572005-05-31 22:47:451449612005-06-02 18:01:4512006-02-15 21:30:53
\n", + "

1156 rows × 7 columns

\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", + "1151 1153 2005-05-31 21:36:44 2725 506 \n", + "1152 1154 2005-05-31 21:42:09 2732 59 \n", + "1153 1155 2005-05-31 22:17:11 2048 251 \n", + "1154 1156 2005-05-31 22:37:34 460 106 \n", + "1155 1157 2005-05-31 22:47:45 1449 61 \n", + "\n", + " return_date staff_id last_update \n", + "0 2005-05-26 22:04:30 1 2006-02-15 21:30:53 \n", + "1 2005-05-28 19:40:33 1 2006-02-15 21:30:53 \n", + "2 2005-06-01 22:12:39 1 2006-02-15 21:30:53 \n", + "3 2005-06-03 01:43:41 2 2006-02-15 21:30:53 \n", + "4 2005-06-02 04:33:21 1 2006-02-15 21:30:53 \n", + "... ... ... ... \n", + "1151 2005-06-10 01:26:44 2 2006-02-15 21:30:53 \n", + "1152 2005-06-08 16:40:09 1 2006-02-15 21:30:53 \n", + "1153 2005-06-04 20:27:11 2 2006-02-15 21:30:53 \n", + "1154 2005-06-01 23:02:34 2 2006-02-15 21:30:53 \n", + "1155 2005-06-02 18:01:45 1 2006-02-15 21:30:53 \n", + "\n", + "[1156 rows x 7 columns]" + ] + }, + "execution_count": 53, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df" + ] + }, + { + "cell_type": "code", + "execution_count": 54, + "id": "9872bf03", + "metadata": {}, + "outputs": [], + "source": [ + "\n", + "\n", + "def get_rental_info_customer_id(engine,month,year):\n", + " with engine.connect() as connection:\n", + " query = text(\"\"\"SELECT * FROM rental\n", + " WHERE MONTH(rental_date) = :month AND YEAR(rental_date) = :year;\n", + " \"\"\")\n", + " result = connection.execute(query, {\n", + " \"month\": month,\n", + " \"year\": year\n", + " })\n", + " df = pd.DataFrame(result.all())\n", + "\n", + " column_name = \"rentals_\" + f\"{int(month):02d}\" + \"_\" + str(year)\n", + "\n", + " df =df.groupby(\"customer_id\").size().reset_index(name=column_name)\n", + " return df\n", + "df = get_rental_info_customer_id(engine,5,2005)" + ] + }, + { + "cell_type": "code", + "execution_count": 55, + "id": "3b719d6a", + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
customer_idrentals_05_2005
012
121
232
353
463
.........
5155944
5165951
5175966
5185972
5195991
\n", + "

520 rows × 2 columns

\n", + "
" + ], + "text/plain": [ + " customer_id rentals_05_2005\n", + "0 1 2\n", + "1 2 1\n", + "2 3 2\n", + "3 5 3\n", + "4 6 3\n", + ".. ... ...\n", + "515 594 4\n", + "516 595 1\n", + "517 596 6\n", + "518 597 2\n", + "519 599 1\n", + "\n", + "[520 rows x 2 columns]" + ] + }, + "execution_count": 55, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df" + ] + }, + { + "cell_type": "code", + "execution_count": 56, + "id": "ed15b1d0", + "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", + " \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", + "
customer_idrentals_05_2005rentals_06_2005difference
012.07.0-5.0
121.01.00.0
232.04.0-2.0
340.06.0-6.0
453.05.0-2.0
...............
5935951.02.0-1.0
5945966.02.04.0
5955972.03.0-1.0
5965980.01.0-1.0
5975991.04.0-3.0
\n", + "

598 rows × 4 columns

\n", + "
" + ], + "text/plain": [ + " customer_id rentals_05_2005 rentals_06_2005 difference\n", + "0 1 2.0 7.0 -5.0\n", + "1 2 1.0 1.0 0.0\n", + "2 3 2.0 4.0 -2.0\n", + "3 4 0.0 6.0 -6.0\n", + "4 5 3.0 5.0 -2.0\n", + ".. ... ... ... ...\n", + "593 595 1.0 2.0 -1.0\n", + "594 596 6.0 2.0 4.0\n", + "595 597 2.0 3.0 -1.0\n", + "596 598 0.0 1.0 -1.0\n", + "597 599 1.0 4.0 -3.0\n", + "\n", + "[598 rows x 4 columns]" + ] + }, + "execution_count": 56, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "def compare_rental_info(engine,month1,year1,month2,year2):\n", + " df1 = get_rental_info_customer_id(engine,month1,year1)\n", + " df2 = get_rental_info_customer_id(engine,month2,year2)\n", + "\n", + " merged_df = pd.merge(df1, df2, on='customer_id', how='outer').fillna(0)\n", + "\n", + " merged_df['difference'] = merged_df.iloc[:, 1] - merged_df.iloc[:, 2]\n", + "\n", + " return merged_df\n", + "comparison_df = compare_rental_info(engine,5,2005,6,2005)\n", + "comparison_df" + ] + } + ], + "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 +}