# Drop unnecccessary features and split into training/test sets features = titanic.drop(['PassengerId', 'Ticket', 'Name', 'Survived'], axis=1) labels = titanic['Survived'] X_train, X_test, y_train, y_test = train_test_split(features, labels, test_size=0.4, random_state=42) X_val, X_test, y_val, y_test = train_test_split(X_test, y_test, test_size=0.5, random_state=42) X_train.head() # Store it to local X_train.to_csv('train_features.csv', index=False) X_val.to_csv('val_features.csv', index=False) X_test.to_csv('test_features.csv', index=False) y_train.to_csv('train_labels.csv', index=False) y_val.to_csv('val_labels.csv', index=False) y_test.to_csv('test_labels.csv', index=False)
Preview:
downloadDownload PNG
downloadDownload JPEG
downloadDownload SVG
Tip: You can change the style, width & colours of the snippet with the inspect tool before clicking Download!
Click to optimize width for Twitter