titanic-prep-12.py

# Split full dataset into train and test sets
train = titanic_full[:889]; train.name='titanic_train_clean'
test = titanic_full[889:]; test.name='titanic_test_clean'
test.drop(['Survived'], axis=1, inplace=True)

def validate_test_split(df, validate_percent=.25, seed=42):
    np.random.seed(seed)
    perm = np.random.permutation(df.index)
    m = len(df.index)
    validate_end = int(validate_percent * m)
    validate = df.ix[perm[:validate_end]]
    test = df.ix[perm[validate_end:]]
    return validate, test

validate, test = validate_test_split(test)