You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
152 lines
6.9 KiB
152 lines
6.9 KiB
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"source": [
|
|
"Copyright (c) Microsoft Corporation. All rights reserved.\r\n",
|
|
"\r\n",
|
|
"Licensed under the MIT License."
|
|
],
|
|
"metadata": {}
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"source": [
|
|
"# Exploring NYC Taxi data in Winter and Summer"
|
|
],
|
|
"metadata": {}
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"source": [
|
|
"Install azureml-opendatasets package"
|
|
],
|
|
"metadata": {}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"source": [
|
|
"!pip install pandas"
|
|
],
|
|
"outputs": [],
|
|
"metadata": {
|
|
"scrolled": true
|
|
}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 19,
|
|
"source": [
|
|
"import pandas as pd\r\n",
|
|
"import glob\r\n",
|
|
"\r\n",
|
|
"# print(pd.read_csv('../../data/Taxi/yellow_tripdata_2019-01.csv'))\r\n",
|
|
"all_files = glob.glob('../../data/Taxi/*.csv')\r\n",
|
|
"\r\n",
|
|
"df = pd.concat((pd.read_csv(f) for f in all_files))\r\n",
|
|
"print(df)"
|
|
],
|
|
"outputs": [
|
|
{
|
|
"output_type": "stream",
|
|
"name": "stdout",
|
|
"text": [
|
|
" VendorID tpep_pickup_datetime tpep_dropoff_datetime passenger_count \\\n",
|
|
"0 1.0 2019-01-01 00:46:40 2019-01-01 00:53:20 1.0 \n",
|
|
"1 1.0 2019-01-01 00:59:47 2019-01-01 01:18:59 1.0 \n",
|
|
"2 2.0 2018-12-21 13:48:30 2018-12-21 13:52:40 3.0 \n",
|
|
"3 2.0 2018-11-28 15:52:25 2018-11-28 15:55:45 5.0 \n",
|
|
"4 2.0 2018-11-28 15:56:57 2018-11-28 15:58:33 5.0 \n",
|
|
"... ... ... ... ... \n",
|
|
"6896312 NaN 2019-12-31 00:07:00 2019-12-31 00:46:00 NaN \n",
|
|
"6896313 NaN 2019-12-31 00:20:00 2019-12-31 00:47:00 NaN \n",
|
|
"6896314 NaN 2019-12-31 00:50:00 2019-12-31 01:21:00 NaN \n",
|
|
"6896315 NaN 2019-12-31 00:38:19 2019-12-31 01:19:37 NaN \n",
|
|
"6896316 NaN 2019-12-31 00:21:00 2019-12-31 00:56:00 NaN \n",
|
|
"\n",
|
|
" trip_distance RatecodeID store_and_fwd_flag PULocationID \\\n",
|
|
"0 1.50 1.0 N 151 \n",
|
|
"1 2.60 1.0 N 239 \n",
|
|
"2 0.00 1.0 N 236 \n",
|
|
"3 0.00 1.0 N 193 \n",
|
|
"4 0.00 2.0 N 193 \n",
|
|
"... ... ... ... ... \n",
|
|
"6896312 12.78 NaN NaN 230 \n",
|
|
"6896313 18.52 NaN NaN 219 \n",
|
|
"6896314 13.13 NaN NaN 161 \n",
|
|
"6896315 14.51 NaN NaN 230 \n",
|
|
"6896316 -17.16 NaN NaN 193 \n",
|
|
"\n",
|
|
" DOLocationID payment_type fare_amount extra mta_tax tip_amount \\\n",
|
|
"0 239 1.0 7.00 0.50 0.5 1.65 \n",
|
|
"1 246 1.0 14.00 0.50 0.5 1.00 \n",
|
|
"2 236 1.0 4.50 0.50 0.5 0.00 \n",
|
|
"3 193 2.0 3.50 0.50 0.5 0.00 \n",
|
|
"4 193 2.0 52.00 0.00 0.5 0.00 \n",
|
|
"... ... ... ... ... ... ... \n",
|
|
"6896312 72 NaN 32.32 2.75 0.5 0.00 \n",
|
|
"6896313 32 NaN 51.63 2.75 0.5 0.00 \n",
|
|
"6896314 76 NaN 38.02 2.75 0.5 0.00 \n",
|
|
"6896315 21 NaN 41.86 2.75 0.0 0.00 \n",
|
|
"6896316 219 NaN 44.62 2.75 0.5 0.00 \n",
|
|
"\n",
|
|
" tolls_amount improvement_surcharge total_amount \\\n",
|
|
"0 0.00 0.3 9.95 \n",
|
|
"1 0.00 0.3 16.30 \n",
|
|
"2 0.00 0.3 5.80 \n",
|
|
"3 0.00 0.3 7.55 \n",
|
|
"4 0.00 0.3 55.55 \n",
|
|
"... ... ... ... \n",
|
|
"6896312 6.12 0.3 41.99 \n",
|
|
"6896313 6.12 0.3 61.30 \n",
|
|
"6896314 6.12 0.3 47.69 \n",
|
|
"6896315 6.12 0.3 51.03 \n",
|
|
"6896316 0.00 0.3 48.17 \n",
|
|
"\n",
|
|
" congestion_surcharge \n",
|
|
"0 NaN \n",
|
|
"1 NaN \n",
|
|
"2 NaN \n",
|
|
"3 NaN \n",
|
|
"4 NaN \n",
|
|
"... ... \n",
|
|
"6896312 0.0 \n",
|
|
"6896313 0.0 \n",
|
|
"6896314 0.0 \n",
|
|
"6896315 0.0 \n",
|
|
"6896316 0.0 \n",
|
|
"\n",
|
|
"[40908284 rows x 18 columns]\n"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {}
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"name": "python3",
|
|
"display_name": "Python 3.9.7 64-bit ('venv': venv)"
|
|
},
|
|
"language_info": {
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"version": "3.9.7",
|
|
"nbconvert_exporter": "python",
|
|
"file_extension": ".py"
|
|
},
|
|
"name": "04-nyc-taxi-join-weather-in-pandas",
|
|
"notebookId": 1709144033725344,
|
|
"interpreter": {
|
|
"hash": "6b9b57232c4b57163d057191678da2030059e733b8becc68f245de5a75abe84e"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 2
|
|
} |