Download Kaggle Datasets on Google Colab

In [0]:

! pip install -q kaggle

In [0]:

from google.colab import files

In [ ]:

files.upload()

In [0]:

! mkdir ~/.kaggle

In [0]:

! cp kaggle.json ~/.kaggle/

In [0]:

! chmod 600 ~/.kaggle/kaggle.json

In [7]:

! kaggle datasets list

ref                                                          title                                                size  lastUpdated          downloadCount  
-----------------------------------------------------------  --------------------------------------------------  -----  -------------------  -------------  
russellyates88/suicide-rates-overview-1985-to-2016           Suicide Rates Overview 1985 to 2016                 396KB  2018-12-01 19:18:25          12009  
ronitf/heart-disease-uci                                     Heart Disease UCI                                     3KB  2018-06-25 11:33:56          16139  
karangadiya/fifa19                                           FIFA 19 complete player dataset                       2MB  2018-12-21 03:52:59          13725  
mohansacharya/graduate-admissions                            Graduate Admissions                                   9KB  2018-12-28 10:07:14          13531  
lava18/google-play-store-apps                                Google Play Store Apps                                2MB  2019-02-03 13:55:47          42229  
bigquery/crypto-ethereum-classic                             Ethereum Classic Blockchain                          69GB  2019-03-04 14:57:33              0  
iarunava/cell-images-for-detecting-malaria                   Malaria Cell Images Dataset                         337MB  2018-12-05 05:40:21           2806  
vjchoudhary7/customer-segmentation-tutorial-in-python        Mall Customer Segmentation Data                       2KB  2018-08-11 07:23:02           4391  
jessicali9530/celeba-dataset                                 CelebFaces Attributes (CelebA) Dataset                1GB  2018-06-01 20:08:48           5050  
noriuk/us-education-datasets-unification-project             U.S. Education Datasets: Unification Project         85MB  2019-03-02 18:41:52           2086  
jessicali9530/stanford-dogs-dataset                          Stanford Dogs Dataset                               735MB  2019-02-13 05:45:25           1230  
safegraph/census-block-group-american-community-survey-data  Census Block Group American Community Survey Data     2GB  2018-12-22 00:29:56            465  
safegraph/visit-patterns-by-census-block-group               Consumer & Visitor Insights For Neighborhoods        66MB  2018-12-19 21:31:50            798  
cityofLA/los-angeles-parking-citations                       Los Angeles Parking Citations                       253MB  2019-03-15 22:11:26           2286  
jutrera/stanford-car-dataset-by-classes-folder               Stanford Car Dataset by classes folder                2GB  2018-07-02 07:35:45           2172  
pavansanagapati/urban-sound-classification                   Urban Sound Classification                            6GB  2018-06-16 13:44:36           1765  
rmisra/news-headlines-dataset-for-sarcasm-detection          News Headlines Dataset For Sarcasm Detection          2MB  2018-06-09 22:14:56           1800  
fivethirtyeight/fivethirtyeight-comic-characters-dataset     FiveThirtyEight Comic Characters Dataset            577KB  2019-02-01 15:02:23           1578  
anokas/kuzushiji                                             Kuzushiji-MNIST                                     318MB  2018-12-17 01:19:31            596  
mdhrumil/top-5000-youtube-channels-data-from-socialblade     Top 5000 Youtube channels data from Socialblade.    128KB  2018-09-09 14:05:54           4998  

In [8]:

! kaggle competitions download -c 'santander-customer-transaction-prediction'

Downloading train.csv.zip to /content
 89% 109M/122M [00:01<00:00, 62.5MB/s] 
100% 122M/122M [00:01<00:00, 76.7MB/s]
Downloading sample_submission.csv.zip to /content
  0% 0.00/463k [00:00<?, ?B/s]
100% 463k/463k [00:00<00:00, 148MB/s]
Downloading test.csv.zip to /content
 95% 116M/122M [00:01<00:00, 75.8MB/s]
100% 122M/122M [00:01<00:00, 82.0MB/s]

In [9]:

import os
os.listdir()

Out[9]:

['.config',
 'kaggle.json',
 'train.csv.zip',
 'sample_submission.csv.zip',
 'test.csv.zip',
 'sample_data']

In [10]:

!pwd

/content

In [0]:

!mkdir train
!mkdir test
!mkdir sub

In [12]:

! unzip train.csv.zip -d train

Archive:  train.csv.zip
  inflating: train/train.csv         

In [13]:

! unzip test.csv.zip -d test

Archive:  test.csv.zip
  inflating: test/test.csv           

In [14]:

! unzip sample_submission.csv.zip -d sub

Archive:  sample_submission.csv.zip
  inflating: sub/sample_submission.csv  

In [15]:

os.listdir("train")

Out[15]:

['train.csv']

In [0]:

import pandas as pd

In [0]:

train = pd.read_csv("train/train.csv")

In [22]:

train.head()

Out[22]:

	ID_code	target	var_0	var_1	var_2	var_3	var_4	var_5	var_6	var_7	...	var_190	var_191	var_192	var_193	var_194	var_195	var_196	var_197	var_198	var_199
0	train_0	0	8.9255	-6.7863	11.9081	5.0930	11.4607	-9.2834	5.1187	18.6266	...	4.4354	3.9642	3.1364	1.6910	18.5227	-2.3978	7.8784	8.5635	12.7803	-1.0914
1	train_1	0	11.5006	-4.1473	13.8588	5.3890	12.3622	7.0433	5.6208	16.5338	...	7.6421	7.7214	2.5837	10.9516	15.4305	2.0339	8.1267	8.7889	18.3560	1.9518
2	train_2	0	8.6093	-2.7457	12.0805	7.8928	10.5825	-9.0837	6.9427	14.6155	...	2.9057	9.7905	1.6704	1.6858	21.6042	3.1417	-6.5213	8.2675	14.7222	0.3965
3	train_3	0	11.0604	-2.1518	8.9522	7.1957	12.5846	-1.8361	5.8428	14.9250	...	4.4666	4.7433	0.7178	1.4214	23.0347	-1.2706	-2.9275	10.2922	17.9697	-8.9996
4	train_4	0	9.8369	-1.4834	12.8746	6.6375	12.2772	2.4486	5.9405	19.2514	...	-1.4905	9.5214	-0.1508	9.1942	13.2876	-1.5121	3.9267	9.5031	17.9974	-8.8104

5 rows × 202 columns

In [23]:

train.shape

Out[23]:

(200000, 202)