10 examples of 'train test split sklearn' in Python

33
def train_test_split_result(clf, X, y):
34
    print("This is Random and Percentaged Spilt Result ... ")
35
    X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y)
36
    clf = clf.fit(X_train, y_train)
37
    report_result(clf, X_test, y_test, y_train)

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

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

134
def test_split(self):
135
    """
136
    Apply split to the sample described in the docstring of prepare_time_inhomogeneous_cv_object, with n_splits = 4
137
    and n_test_splits = 2. The folds are [0 : 6], [6 : 11], [11 : 16], [16 : 21]. We use an embargo of zero.
138
    Inspection shows that the pairs test-train sets should respectively be
139
    [...]
140
    3. Train: folds 1 and 4, samples [0, 1, 2, 3, 4, 16, 17, 18, 19, 20]. Test: folds 2 and 3, samples [6, 7, 8, 9,
141
     10, 11, 12, 13, 14, 15]. Sample 5 is purged from the train set.
142
    4. Train: folds 2 and 3, samples [7, 8, 9, 10, 11, 12, 13, 14, 15]. Test: folds 1 and 4, samples [0, 1, 2, 3, 4,
143
     5, 16, 17, 18, 19, 20]. Sample 6 is embargoed.
144
    [...]
145
    """
146
    cv = CombPurgedKFoldCV(n_splits=4, n_test_splits=2)
147
    prepare_time_inhomogeneous_cv_object(cv)
148
    count = 0
149
    for train_set, test_set in cv.split(cv.X, pred_times=cv.pred_times, eval_times=cv.eval_times):
150
        count += 1
151
        if count == 3:
152
            result_train = np.array([0, 1, 2, 3, 4, 16, 17, 18, 19, 20])
153
            result_test = np.array([6, 7, 8, 9, 10, 11, 12, 13, 14, 15])
154
            self.assertTrue(np.array_equal(result_train, train_set))
155
            self.assertTrue(np.array_equal(result_test, test_set))
156
        if count == 4:
157
            result_train = np.array([7, 8, 9, 10, 11, 12, 13, 14, 15])
158
            result_test = np.array([0, 1, 2, 3, 4, 5, 16, 17, 18, 19, 20])
159
            self.assertTrue(np.array_equal(result_train, train_set))
160
            self.assertTrue(np.array_equal(result_test, test_set))

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)

158
def train_test(self, train_path, test_path=None):
159
    # load train and (maybe) test data
160
    metadata = MetaData(label_column=self.label_column,
161
                        train_path=train_path,
162
                        test_path=test_path)
163
    self.num_classes = metadata.k_classes
164
    self.num_features = metadata.d_features
165
166
    # if necessary, cast judgment metric into its binary/multiary equivalent
167
    if self.num_classes == 2:
168
        if self.judgment_metric in [Metrics.F1_MICRO, Metrics.F1_MACRO]:
169
            self.judgment_metric = Metrics.F1
170
        elif self.judgment_metric in [Metrics.ROC_AUC_MICRO,
171
                                      Metrics.ROC_AUC_MACRO]:
172
            self.judgment_metric = Metrics.ROC_AUC
173
    else:
174
        if self.judgment_metric == Metrics.F1:
175
            self.judgment_metric = Metrics.F1_MACRO
176
        elif self.judgment_metric == Metrics.ROC_AUC:
177
            self.judgment_metric = Metrics.ROC_AUC_MACRO
178
179
    # load training data
180
    train_data = self.load_data(train_path)
181
182
    # if necessary, generate permanent train/test split
183
    if test_path is not None:
184
        test_data = self.load_data(test_path)
185
    else:
186
        train_data, test_data = train_test_split(train_data,
187
                                                 test_size=self.testing_ratio,
188
                                                 random_state=self.random_state)
189
190
    # extract feature matrix and labels from raw data
191
    self.encoder = DataEncoder(label_column=self.label_column)
192
    X_train, y_train = self.encoder.fit_transform(train_data)
193
    X_test, y_test = self.encoder.transform(test_data)
194
195
    # create and cross-validate pipeline
196
    self.make_pipeline()
197
    cv_scores = self.cross_validate(X_train, y_train)
198
199
    # train and test the final model
200
    self.pipeline.fit(X_train, y_train)
201
    test_scores = self.test_final_model(X_test, y_test)
202
    return {'cv': cv_scores, 'test': test_scores}

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)

167
@staticmethod
168
def _get_split(X, y):
169
    split = ShuffleSplit(y.shape[0], n_iter=1)
170
    train, validate = list(split)[0]
171
    X_train, X_validate, y_train, y_validate = X[train], X[validate], y[train], y[validate]
172
    return X_train, X_validate, y_train, y_validate

24
def split_train_evaluate(self, X, Y, train_precent, seed=0):
25
    state = np.random.get_state()
26
    training_size = int(train_precent * len(X))
27
    shuffle_indices = np.random.permutation(np.arange(len(X)))
28
    X_train = [X[shuffle_indices[i]] for i in range(training_size)]
29
    Y_train = [Y[shuffle_indices[i]] for i in range(training_size)]
30
    X_test = [X[shuffle_indices[i]] for i in range(training_size, len(X))]
31
    Y_test = [Y[shuffle_indices[i]] for i in range(training_size, len(X))]
32
33
    self.train(X_train, Y_train, Y)
34
    np.random.set_state(state)
35
    return self.evaluate(X_test, Y_test)

423
def _train_val_split(df, validation):
424
    train_df = df
425
    val_df = None
426
    validation_ratio = 0.0
427
428
    if isinstance(validation, float) and validation > 0:
429
        train_df, val_df = train_df.randomSplit([1.0 - validation, validation])
430
        validation_ratio = validation
431
    elif isinstance(validation, str):
432
        dtype = [field.dataType for field in df.schema.fields if field.name == validation][0]
433
        bool_dtype = isinstance(dtype, BooleanType)
434
        val_df = train_df.filter(
435
            f.col(validation) if bool_dtype else f.col(validation) > 0).drop(validation)
436
        train_df = train_df.filter(
437
            ~f.col(validation) if bool_dtype else f.col(validation) == 0).drop(validation)
438
439
        # Approximate ratio of validation data to training data for proportionate scale
440
        # of partitions
441
        timeout_ms = 1000
442
        confidence = 0.90
443
        train_rows = train_df.rdd.countApprox(timeout=timeout_ms, confidence=confidence)
444
        val_rows = val_df.rdd.countApprox(timeout=timeout_ms, confidence=confidence)
445
        validation_ratio = val_rows / (val_rows + train_rows)
446
    elif validation:
447
        raise ValueError('Unrecognized validation type: {}'.format(type(validation)))
448
449
    return train_df, val_df, validation_ratio