From b198ba43591c0d02621a43d665c055b5546e12c1 Mon Sep 17 00:00:00 2001 From: roizherrerapilar-hub Date: Sun, 3 May 2026 18:11:21 +0200 Subject: [PATCH] Create connecting_python_sql.ipynb --- connecting_python_sql.ipynb | 967 ++++++++++++++++++++++++++++++++++++ 1 file changed, 967 insertions(+) create mode 100644 connecting_python_sql.ipynb diff --git a/connecting_python_sql.ipynb b/connecting_python_sql.ipynb new file mode 100644 index 0000000..59ca977 --- /dev/null +++ b/connecting_python_sql.ipynb @@ -0,0 +1,967 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "id": "b977b013", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Requirement already satisfied: pymysql in c:\\Users\\pilir\\AppData\\Local\\Python\\pythoncore-3.14-64\\Lib\\site-packages (1.1.2)\n", + "Note: you may need to restart the kernel to use updated packages.\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "\n", + "[notice] A new release of pip is available: 26.0.1 -> 26.1\n", + "[notice] To update, run: python.exe -m pip install --upgrade pip\n" + ] + } + ], + "source": [ + "pip install pymysql" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "id": "2188bad9", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Requirement already satisfied: sqlalchemy in c:\\Users\\pilir\\AppData\\Local\\Python\\pythoncore-3.14-64\\Lib\\site-packages (2.0.49)\n", + "Requirement already satisfied: greenlet>=1 in c:\\Users\\pilir\\AppData\\Local\\Python\\pythoncore-3.14-64\\Lib\\site-packages (from sqlalchemy) (3.5.0)\n", + "Requirement already satisfied: typing-extensions>=4.6.0 in c:\\Users\\pilir\\AppData\\Local\\Python\\pythoncore-3.14-64\\Lib\\site-packages (from sqlalchemy) (4.15.0)\n", + "Note: you may need to restart the kernel to use updated packages.\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "\n", + "[notice] A new release of pip is available: 26.0.1 -> 26.1\n", + "[notice] To update, run: python.exe -m pip install --upgrade pip\n" + ] + } + ], + "source": [ + "pip install sqlalchemy" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "6369d9e5", + "metadata": {}, + "outputs": [], + "source": [ + "import pandas as pd \n", + "import numpy as np\n", + "import pymysql\n", + "from sqlalchemy import create_engine\n", + "import getpass \n", + "password = getpass.getpass()" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "d993576a", + "metadata": {}, + "outputs": [], + "source": [ + "password = \"27021999\"" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "id": "809a3321", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "Engine(mysql+pymysql://root:***@localhost/sakila)" + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "bd = \"sakila\" \n", + "connection_string = 'mysql+pymysql://root:' + \"27021999\" + '@localhost/'+bd \n", + "engine = create_engine(connection_string)\n", + "\n", + "engine" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "id": "d75c2dac", + "metadata": {}, + "outputs": [], + "source": [ + "from sqlalchemy import text" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "id": "72795c59", + "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
........................
16039160452005-08-23 22:25:26772142005-08-25 23:54:2612006-02-15 21:30:53
16040160462005-08-23 22:26:474364742005-08-27 18:02:4722006-02-15 21:30:53
16041160472005-08-23 22:42:4820881142005-08-25 02:48:4822006-02-15 21:30:53
16042160482005-08-23 22:43:0720191032005-08-31 21:33:0712006-02-15 21:30:53
16043160492005-08-23 22:50:1226663932005-08-30 01:01:1222006-02-15 21:30:53
\n", + "

16044 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", + "16039 16045 2005-08-23 22:25:26 772 14 \n", + "16040 16046 2005-08-23 22:26:47 4364 74 \n", + "16041 16047 2005-08-23 22:42:48 2088 114 \n", + "16042 16048 2005-08-23 22:43:07 2019 103 \n", + "16043 16049 2005-08-23 22:50:12 2666 393 \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", + "16039 2005-08-25 23:54:26 1 2006-02-15 21:30:53 \n", + "16040 2005-08-27 18:02:47 2 2006-02-15 21:30:53 \n", + "16041 2005-08-25 02:48:48 2 2006-02-15 21:30:53 \n", + "16042 2005-08-31 21:33:07 1 2006-02-15 21:30:53 \n", + "16043 2005-08-30 01:01:12 2 2006-02-15 21:30:53 \n", + "\n", + "[16044 rows x 7 columns]" + ] + }, + "execution_count": 7, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "with engine.connect() as connection:\n", + " query = text('SELECT * FROM rental') \n", + " result = connection.execute(query)\n", + " df = pd.DataFrame(result.all())\n", + " \n", + "df" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "id": "62a53155", + "metadata": {}, + "outputs": [], + "source": [ + "def rentals_month(engine, month, year):\n", + " query = text(\"\"\"\n", + " SELECT *\n", + " FROM rental\n", + " WHERE MONTH(rental_date) = :month\n", + " AND YEAR(rental_date) = :year\n", + " \"\"\")\n", + "\n", + " with engine.connect() as connection:\n", + " result = connection.execute(query, {\"month\": month, \"year\": year})\n", + " df = pd.DataFrame(result.all())\n", + "\n", + " return df" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "4a364ed3", + "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": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "rentals_may = rentals_month(engine, 5, 2005) #Alquileres de mayo de 2005\n", + "rentals_may" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "id": "341020b5", + "metadata": {}, + "outputs": [], + "source": [ + "#Alquileres por cliente en el mes de mayo de 2005. \n", + "def rental_count_month(df, month, year):\n", + " counts = df.groupby(\"customer_id\").size().reset_index(name=f\"rentals_{month}_{year}\")\n", + " return counts" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "id": "16794655", + "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_5_2005
012
121
232
353
463
.........
5155944
5165951
5175966
5185972
5195991
\n", + "

520 rows × 2 columns

\n", + "
" + ], + "text/plain": [ + " customer_id rentals_5_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": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "rentals_may_count = rental_count_month(rentals_may, 5, 2005)\n", + "rentals_may_count" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "id": "d9d8fdb5", + "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_6_2005
017
121
234
346
455
.........
5855952
5865962
5875973
5885981
5895994
\n", + "

590 rows × 2 columns

\n", + "
" + ], + "text/plain": [ + " customer_id rentals_6_2005\n", + "0 1 7\n", + "1 2 1\n", + "2 3 4\n", + "3 4 6\n", + "4 5 5\n", + ".. ... ...\n", + "585 595 2\n", + "586 596 2\n", + "587 597 3\n", + "588 598 1\n", + "589 599 4\n", + "\n", + "[590 rows x 2 columns]" + ] + }, + "execution_count": 12, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#Vamos a sacar junio y contar los alquileres por cliente.\n", + "rentals_june = rentals_month(engine, 6, 2005)\n", + "rentals_june_count = rental_count_month(rentals_june, 6, 2005)\n", + "\n", + "rentals_june_count" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "id": "04e2a9aa", + "metadata": {}, + "outputs": [], + "source": [ + "def compare_rentals(df_may, df_june):\n", + " df = pd.merge(df_may, df_june, on=\"customer_id\", how=\"outer\")\n", + " df = df.fillna(0)\n", + "\n", + " df[\"difference\"] = df[\"rentals_6_2005\"] - df[\"rentals_5_2005\"]\n", + "\n", + " return df" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "id": "ce94c487", + "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_5_2005rentals_6_2005difference
012.07.05.0
121.01.00.0
232.04.02.0
340.06.06.0
453.05.02.0
...............
5935951.02.01.0
5945966.02.0-4.0
5955972.03.01.0
5965980.01.01.0
5975991.04.03.0
\n", + "

598 rows × 4 columns

\n", + "
" + ], + "text/plain": [ + " customer_id rentals_5_2005 rentals_6_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": 16, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#Comparar alquileres de los meses de mayo y junio de 2005. \n", + "result= compare_rentals(rentals_may_count, rentals_june_count)\n", + "result" + ] + } + ], + "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": "3.14.4" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +}