def train_test_split(data, test_size=0.3, shuffle=True, random_state=None):
"""Split DataFrame into random train and test subsets
Parameters
----------
data : pandas dataframe, need to split dataset.
test_size : float
If float, should be between 0.0 and 1.0 and represent the
proportion of the dataset to include in the train split.
random_state : int, RandomState instance or None, optional (default=None)
If int, random_state is the seed used by the random number generator;
If RandomState instance, random_state is the random number generator;
If None, the random number generator is the RandomState instance used
by `np.random`.
shuffle : boolean, optional (default=None)
Whether or not to shuffle the data before splitting. If shuffle=False
then stratify must be None.
"""
if shuffle:
data = reset(data, random_state=random_state)
train_size = 1 - test_size
test_dataset = data[int(len(data) * train_size):].reset_index(drop=True)
train_dataset = data[:int(len(data) * train_size)].reset_index(drop=True)
return train_dataset, test_dataset
def train_test_split(df, test_size=0.3, shuffle=False, random_state=None):
if shuffle:
df = reset(df, random_state=random_state)
traindf = df[int(len(df) * test_size):]
testdf = df[:int(len(df) * test_size)]
return traindf, testdf
def train_test_split(data_df, test_size=0.2, shuffle=True, random_state=None):
if shuffle:
data_df = reset(data_df, random_state=random_state)
train = data_df[int(len(data_df) * test_size):].reset_index(drop=True)
test = data_df[: int(len(data_df) * test_size)].reset_index(drop=True)
return train, test