a function to split train validation and test set

train_test_valid_split.py

#from https://stackoverflow.com/questions/38250710/how-to-split-data-into-3-sets-train-validation-and-test
def train_validate_test_split(df, train_percent=.6, validate_percent=.2, seed=None):
    np.random.seed(seed)
    perm = np.random.permutation(df.index)
    m = len(df.index)
    train_end = int(train_percent * m)
    validate_end = int(validate_percent * m) + train_end
    train = df.ix[perm[:train_end]]
    validate = df.ix[perm[train_end:validate_end]]
    test = df.ix[perm[validate_end:]]
    return train, validate, test