diff --git a/Lab sql-python.ipynb b/Lab sql-python.ipynb new file mode 100644 index 0000000..2b0a7ee --- /dev/null +++ b/Lab sql-python.ipynb @@ -0,0 +1,918 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 5, + "id": "c9565b2f", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Note: you may need to restart the kernel to use updated packages.\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "'grep' is not recognized as an internal or external command,\n", + "operable program or batch file.\n" + ] + } + ], + "source": [ + "pip show sqlalchemy | grep Version" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "id": "31ae5d94", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Requirement already satisfied: sqlalchemy in c:\\users\\igrav\\anaconda3\\lib\\site-packages (2.0.44)\n", + "Requirement already satisfied: greenlet>=1 in c:\\users\\igrav\\anaconda3\\lib\\site-packages (from sqlalchemy) (3.0.1)\n", + "Requirement already satisfied: typing-extensions>=4.6.0 in c:\\users\\igrav\\anaconda3\\lib\\site-packages (from sqlalchemy) (4.11.0)\n", + "Note: you may need to restart the kernel to use updated packages.\n" + ] + } + ], + "source": [ + "pip install --upgrade sqlalchemy" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "id": "275b44ce", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Requirement already satisfied: pymysql in c:\\users\\igrav\\anaconda3\\lib\\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": 8, + "id": "b9dbb092", + "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()\n" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "id": "556e42cf", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "Engine(mysql+pymysql://root:***@localhost/sakila)" + ] + }, + "execution_count": 15, + "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": 16, + "id": "f3003f80", + "metadata": {}, + "outputs": [], + "source": [ + "password = 'H87ch25M03'" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "id": "730c6de8", + "metadata": {}, + "outputs": [], + "source": [ + "from sqlalchemy import text" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "id": "4dae3205", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 17, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "with engine.connect() as connection:\n", + " txt = 'select * from rental'\n", + " query = text(txt)\n", + " result = connection.execute(query)\n", + " \n", + "result " + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "30807f6a", + "metadata": {}, + "outputs": [], + "source": [ + "row= result.first()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "e86a33a9", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "{'rental_id': 1, 'rental_date': datetime.datetime(2005, 5, 24, 22, 53, 30), 'inventory_id': 367, 'customer_id': 130, 'return_date': datetime.datetime(2005, 5, 26, 22, 4, 30), 'staff_id': 1, 'last_update': datetime.datetime(2006, 2, 15, 21, 30, 53)}" + ] + }, + "execution_count": 16, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "row._mapping" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "id": "f1168d39", + "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": 18, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "with engine.connect() as connection:\n", + " txt = 'select * from rental'\n", + " query = text(txt)\n", + " result = connection.execute(query)\n", + " df = pd.DataFrame(result.all())\n", + "\n", + "df" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "id": "cd9baf3d", + "metadata": {}, + "outputs": [], + "source": [ + "def rental_month(engine, month, year):\n", + " with engine.connect() as connection:\n", + " \n", + " query = text('''\n", + " SELECT * FROM rental\n", + " WHERE EXTRACT(MONTH FROM rental_date) = :month\n", + " AND EXTRACT(YEAR FROM rental_date) = :year\n", + " ''')\n", + " result = connection.execute(query, {\"month\": month, \"year\": year})\n", + " rental_df = pd.DataFrame(result.fetchall(), columns=result.keys())\n", + "\n", + " return rental_df" + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "id": "2055b225", + "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": 27, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "rental_month(engine, 5, 2005)" + ] + }, + { + "cell_type": "code", + "execution_count": 31, + "id": "84e3d4c9", + "metadata": {}, + "outputs": [], + "source": [ + "#Develop a Python function called `rental_count_month` that takes the DataFrame provided by `rentals_month` \n", + "# as input along with the month and year and returns a new DataFrame containing the number of \n", + "# rentals made by each customer_id during the selected month and year. \n", + "\n", + "#The function should also include the month and year as parameters and use them to name the new column according to the month and year, \n", + "# for example, if the input month is 05 and the year is 2005, the column name should be \"rentals_05_2005\".\n", + "\n", + "\n", + "# *Hint: Consider making use of pandas [groupby()\n", + "\n", + "\n", + "\n", + "def rental_count_month(rental_df, month, year):\n", + " column_name = f'rentals_{month:02d}_{year}'\n", + " rental_counts = rental_df.groupby('customer_id').size().reset_index(name = column_name)\n", + " return rental_counts" + ] + }, + { + "cell_type": "code", + "execution_count": 30, + "id": "ed386023", + "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": 30, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "rental_count_month(rental_month(engine, 5, 2005), 5, 2005)" + ] + }, + { + "cell_type": "code", + "execution_count": 32, + "id": "5a093b2e", + "metadata": {}, + "outputs": [], + "source": [ + "# 4. Create a Python function called compare_rentals that takes two DataFrames as input containing the number of rentals made by each\n", + "# customer in different months and years. The function should return a combined DataFrame with a new 'difference' column, which is the\n", + "# difference between the number of rentals in the two months.\n", + "\n", + "def compare_rentals(df1, df2):\n", + " combined = pd.merge(df1, df2, on=\"customer_id\", suffixes=(\"_may\", \"_jun\"))\n", + " combined[\"difference\"] = combined[\"rentals_05_2005\"] - combined[\"rentals_06_2005\"]\n", + " return combined" + ] + }, + { + "cell_type": "code", + "execution_count": 35, + "id": "6d1be0e2", + "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
0127-5
12110
2324-2
3535-2
4634-1
...............
50759446-2
50859512-1
509596624
51059723-1
51159914-3
\n", + "

512 rows × 4 columns

\n", + "
" + ], + "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\n", + ".. ... ... ... ...\n", + "507 594 4 6 -2\n", + "508 595 1 2 -1\n", + "509 596 6 2 4\n", + "510 597 2 3 -1\n", + "511 599 1 4 -3\n", + "\n", + "[512 rows x 4 columns]" + ] + }, + "execution_count": 35, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "compare_rentals(rental_count_month(rental_month(engine,5, 2005),5 ,2005), rental_count_month(rental_month(engine,6, 2005),6, 2005))" + ] + } + ], + "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": "3.12.3" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +}