7 examples of 'import train test split' in Python

9
def train_test_split(fileName,type=1):
10
    header = ['user_id', 'item_id', 'rating', 'timestamp']
11
    if(type==1):
12
        df = pd.read_csv(fileName, sep='\t', names=header)
13
    else:
14
        df = pd.read_csv(fileName, sep='::', names=header,engine = 'python')
15
    n_users = df.user_id.unique().shape[0]
16
    users = df.user_id.max()
17
    n_items = df.item_id.unique().shape[0]
18
    items = df.item_id.max()
19
20
    print 'Number of users = ' + str(n_users) + ' | Number of movies = ' + str(n_items)
21
    print 'The biggest ID of users = ' + str(users) + ' | The biggest ID of movies = ' + str(items)
22
    #
23
    train_data, test_data = cv.train_test_split(df, test_size=0.1)
24
    train_data = pd.DataFrame(train_data)
25
    test_data = pd.DataFrame(test_data)
26
    #Create two user-item matrices, one for training and another for testing
27
    train_data_matrix = np.zeros((users, items))
28
    for line in train_data.itertuples():
29
        train_data_matrix[line[1]-1, line[2]-1] = line[3]
30
31
    test_data_matrix = np.zeros((users, items))
32
    for line in test_data.itertuples():
33
        test_data_matrix[line[1]-1, line[2]-1] = line[3]
34
    return train_data_matrix,test_data_matrix

23
def train_valid_test_split(SOURCE_DATA_DIR, TARGET_DATA_DIR, train_size=0.8, valid_size=0.1, 
24
                           COMBINE_FOLDERS=None, SELECT_FOLDERS=None):
25
    """
26
    Usage:
27
        SOURCE_DATA_DIR = "data/ClothingAttributeDataset/images/"
28
        TARGET_DATA_DIR = "data/"
29
30
        train_valid_test_split(SOURCE_DATA_DIR, TARGET_DATA_DIR)
31
    """
32
    if COMBINE_FOLDERS is None:
33
        COMBINE_FOLDERS = dict()
34
    for folder_name in ["train", "test", "valid"]:
35
        rmtree(os.path.join(TARGET_DATA_DIR, folder_name), ignore_errors=True)
36
        os.makedirs(os.path.join(TARGET_DATA_DIR, folder_name))
37
38
    # Split records by 80-20 between Train and Validation Set
39
    filenames = np.random.permutation(glob(os.path.join(SOURCE_DATA_DIR, "*.jpg")))
40
41
    train_idx = int(len(filenames) * train_size)
42
    test_idx = int(len(filenames) * (train_size+valid_size))
43
    for idx, filename in enumerate(filenames):
44
        target_name = filename.split("/")[-1]
45
        if idx < train_idx:
46
            target_filepath = os.path.join(TARGET_DATA_DIR, "train", target_name)
47
        elif idx < test_idx:
48
            target_filepath = os.path.join(TARGET_DATA_DIR, "valid", target_name)
49
        else:
50
            target_filepath = os.path.join(TARGET_DATA_DIR, "test", target_name)            
51
        copyfile(filenames[idx], target_filepath)

75
def _get_adapted_dataset(split):
76
    """ Gets the adapted dataset for the experiments
77
78
    Args :
79
            split (str): train or test
80
    Returns :
81
            (tuple):  images and labels
82
    """
83
    dataset = _get_dataset()
84
    key_img = 'x_' + split
85
    key_lbl = 'y_' + split
86
87
    if split != 'train':
88
        dataset[key_img], dataset[key_lbl] = _adapt(dataset[key_img],
89
                                                    dataset[key_lbl])
90
91
    return (dataset[key_img], dataset[key_lbl])

36
def prepare_data():
37
    data = io.loadmat(raw_filename)
38
    df = pd.DataFrame(dict(
39
        spectra=data['Int_ABQR'].tolist(),
40
        solute=data['Gamme_ABQR'].ravel(),
41
        vial=data['Vial_ABQR'].ravel(),
42
        concentration=data['Conc_ABQR'].ravel(),
43
        molecule=data['Molecule_ABQR'].ravel()))
44
    skf = ShuffleSplit(n_splits=2, test_size=held_out_test_size,
45
                       random_state=random_state)
46
    train_is, test_is = list(skf.split(df))[0]
47
    df_train = df.iloc[train_is]
48
    df_test = df.iloc[test_is]
49
    df_train.to_csv(train_filename, index=False)
50
    df_test.to_csv(test_filename, index=False)

9
def train_test_split(X, y, train_percentage=0.8):
10
    '''
11
    Very simple splitting into train and test data. Works for
12
    any input shape without dependencies, but is a bit restricted.
13
    '''
14
    cut_idx = int(floor(X.shape[0] * 0.80))
15
    X_train, X_test = X[:cut_idx], X[cut_idx:]
16
    y_train, y_test = y[:cut_idx], y[cut_idx:]
17
    print("Number of train samples", X_train.shape[0])
18
    print("Number of test samples", X_test.shape[0])
19
20
    return (X_train, y_train), (X_test, y_test)

82
def my_train_split(ds, y):
83
    return ds, skorch.dataset.Dataset(corpus.valid[:200], y=None)

35
def split_data(df):
36
    X = df.drop('Y', axis=1).values
37
    y = df['Y'].values
38
39
    X_train, X_test, y_train, y_test = train_test_split(
40
        X, y, test_size=0.2, random_state=0)
41
    data = {"train": {"X": X_train, "y": y_train},
42
            "test": {"X": X_test, "y": y_test}}
43
    return data