SagemakerAutoPilotDataPreparationCourse

video Link : https://www.youtube.com/watch?v=qMEtqJPhqpA
Julien Simon
-----

import pandas as pd

data = pd.read_csv('Your CSV File')
pd.set_option('display.max_columns', 500)     # Make sure we can see all of the columns
pd.set_option('display.max_rows', 50)         # Keep the output on one page
data[:10]
-----
Split The Dataset
-----
import numpy as np

train_data, test_data, _ = np.split(data.sample(frac=1, random_state=123), 
                                                  [int(0.95 * len(data)), int(len(data))])  

# Save to CSV files
train_data.to_csv('automl-train.csv', index=False, header=True, sep=',') # Need to keep column names
test_data.to_csv('automl-test.csv', index=False, header=True, sep=',')
------
 %%sh

ls -l *.csv
-----
Upload Data to S3
----
import sagemaker

prefix = 'sagemaker/DEMO-automl-dm/input'
sess   = sagemaker.Session()

uri = sess.upload_data(path="automl-train.csv", key_prefix=prefix)
print(uri)
---