Python sklearn.model_selection 模块，ShuffleSplit() 实例源码

我们从Python开源项目中，提取了以下50个代码示例，用于说明如何使用sklearn.model_selection.ShuffleSplit()。

项目：cnn_basics 作者：kootenpv | 项目源码 | 文件源码

def validate(model, X, y, nb_epoch=25, batch_size=128,
             stop_early=True, folds=10, test_size=None, shuffle=True, verbose=True):
    early_stopping = EarlyStopping(monitor='val_loss', patience=3, verbose=0, mode='auto')

    total_score = []
    if test_size is None:
        if folds == 1:
            test_size = 0.25
        else:
            test_size = 1 - (1. / folds)
    kf = ShuffleSplit(n_splits=folds, test_size=test_size)
    for fold, (train_index, test_index) in enumerate(kf.split(X, y)):
        shuffle_weights(model)
        if fold > 0:
            print("FOLD:", fold)
            print("-" * 40)
            model.reset_states()
            callbacks = [early_stopping] if True else None
        hist = model.fit(X[train_index], y[train_index], batch_size=batch_size, shuffle=shuffle,
                         validation_data=(X[test_index], y[test_index]),
                         callbacks=[early_stopping], verbose=verbose)
        total_score.append(hist.history["val_acc"][-1])
    return np.mean(total_score)

项目：deeppavlov 作者：deepmipt | 项目源码 | 文件源码

def train_test_split(inpath, train, test, split, random_seed):
    """
    RuCor doesn't provide train/test data splitting, it makes random splitting.
    Args:
        inpath: path to data
        train: path to train folder
        test: path to test folder
        split: int, split ratio
        random_seed: seed for random module

    Returns:

    """
    print('Start train-test splitting ...')
    z = os.listdir(inpath)
    doc_split = ShuffleSplit(1, test_size=split, random_state=random_seed)
    for train_indeses, test_indeses in doc_split.split(z): 
        train_set = [z[i] for i in sorted(list(train_indeses))]
        test_set = [z[i] for i in sorted(list(test_indeses))]
    for x in train_set:
        build_data.move(os.path.join(inpath, x), os.path.join(train, x))
    for x in test_set:
        build_data.move(os.path.join(inpath, x), os.path.join(test, x))
    print('End train-test splitts.')
    return None

项目：pythonml 作者：nicholastoddsmith | 项目源码 | 文件源码

def TestPerformance(self, df = None):
        #If no dataframe is provided, use the currently learned one
        if(df is None):
            D = self.D
        else:
            D = self.S.transform(df.copy())
        #Get features from the data frame
        A = self._ExtractFeat(D)
        #Get the target values and their corresponding column names
        y, _ = self._ExtractTarg(D)
        #Begin cross validation
        ss = ShuffleSplit(n_splits = 1)
        for trn, tst in ss.split(A):
            s1 = self.R.score(A, y)
            s2 = self.R.score(A[tst], y[tst])
            s3 = self.R.score(A[trn], y[trn])
            print('C-V:\t' + str(s1) + '\nTst:\t' + str(s2) + '\nTrn:\t' + str(s3))

项目：poeai 作者：nicholastoddsmith | 项目源码 | 文件源码

def Train(self, C, A, Y, SF):
        '''
        Train the classifier using the sample matrix A and target matrix Y
        '''
        C.fit(A, Y)
        YH = np.zeros(Y.shape, dtype = np.object)
        for i in np.array_split(np.arange(A.shape[0]), 32):   #Split up verification into chunks to prevent out of memory
            YH[i] = C.predict(A[i])
        s1 = SF(Y, YH)
        print('All:{:8.6f}'.format(s1))
        '''
        ss = ShuffleSplit(random_state = 1151)  #Use fixed state for so training can be repeated later
        trn, tst = next(ss.split(A, Y))         #Make train/test split
        mi = [8] * 1                            #Maximum number of iterations at each iter
        YH = np.zeros((A.shape[0]), dtype = np.object)
        for mic in mi:                                      #Chunk size to split dataset for CV results
            #C.SetMaxIter(mic)                               #Set the maximum number of iterations to run
            #C.fit(A[trn], Y[trn])                           #Perform training iterations
        '''

项目：Parallel-SGD 作者：angadgill | 项目源码 | 文件源码

def test_safe_split_with_precomputed_kernel():
    clf = SVC()
    clfp = SVC(kernel="precomputed")

    X, y = iris.data, iris.target
    K = np.dot(X, X.T)

    cv = ShuffleSplit(test_size=0.25, random_state=0)
    tr, te = list(cv.split(X))[0]

    X_tr, y_tr = _safe_split(clf, X, y, tr)
    K_tr, y_tr2 = _safe_split(clfp, K, y, tr)
    assert_array_almost_equal(K_tr, np.dot(X_tr, X_tr.T))

    X_te, y_te = _safe_split(clf, X, y, te, tr)
    K_te, y_te2 = _safe_split(clfp, K, y, te, tr)
    assert_array_almost_equal(K_te, np.dot(X_te, X_tr.T))

项目：MLClass 作者：bm2-lab | 项目源码 | 文件源码

def split_testing_data_r(y):
    ss = ShuffleSplit(n_splits=1, test_size=0.2)
    tri = None
    tei = None
    for itr, ite in ss.split(y):
        tri = itr
        tei = ite
    return tri, tei

项目：pydl 作者：rafaeltg | 项目源码 | 文件源码

def get_cv_method(method, **kwargs):

    if method == 'kfold':
        return KFold(**kwargs)
    elif method == 'skfold':
        return StratifiedKFold(**kwargs)
    elif method == 'loo':
        return LeaveOneOut()
    elif method == 'shuffle_split':
        return ShuffleSplit(**kwargs)
    elif method == 'split':
        return TrainTestSplit(**kwargs)
    elif method == 's_shuffle_split':
        return StratifiedShuffleSplit(**kwargs)
    elif method == 'time_series':
        return TimeSeriesSplit(**kwargs)
    else:
        raise AttributeError('Invalid CV method - %s!' % method)

项目：Spam-Message-Classifier-sklearn 作者：ZPdesu | 项目源码 | 文件源码

def cross_validation(self):
        cv = ShuffleSplit(n_splits=5, test_size=0.2, random_state=20)
        scores = cross_val_score(self.clf, self.training_data, self.training_target, cv=cv, scoring='f1_macro')
        print scores
        print("Accuracy: %0.2f (+/- %0.2f)" % (scores.mean(), scores.std() * 2))

项目：Spam-Message-Classifier-sklearn 作者：ZPdesu | 项目源码 | 文件源码

def cross_validation(self):
        cv = ShuffleSplit(n_splits=5, test_size=0.2, random_state=20)
        scores = cross_val_score(self.clf, self.training_data, self.training_target, cv=cv, scoring='f1_macro')
        print scores
        print("Accuracy: %0.2f (+/- %0.2f)" % (scores.mean(), scores.std() * 2))

项目：Spam-Message-Classifier-sklearn 作者：ZPdesu | 项目源码 | 文件源码

def cross_validation(self):
        cv = ShuffleSplit(n_splits=5, test_size=0.2, random_state=20)
        scores = cross_val_score(self.clf, self.training_data, self.training_target, cv=cv, scoring='f1_macro')
        print scores
        print("Accuracy: %0.2f (+/- %0.2f)" % (scores.mean(), scores.std() * 2))

项目：yellowbrick 作者：DistrictDataLabs | 项目源码 | 文件源码

def test_learning_curve_comprehensive(self):
        """
        Test learning curve with all parameters with visual unit test.
        """

        try:
            visualizer = LearningCurveVisualizer(LinearSVC(random_state=0), train_sizes=np.linspace(.1, 1.0, 5), 
                cv=ShuffleSplit(n_splits=100, test_size=0.2, random_state=0), 
                n_jobs=4)
            visualizer.fit(X, y)
            visualizer.poof()
        except Exception as e:
            self.fail("error during learning curve: {}".format(e))

        self.assert_images_similar(visualizer)

项目：yellowbrick 作者：DistrictDataLabs | 项目源码 | 文件源码

def test_learning_curve_model_cv_only(self):
        """
        Test learning curve with inputting model and cv only.
        """

        try:
            visualizer = LearningCurveVisualizer(LinearSVC(),
                cv=ShuffleSplit(n_splits=100, test_size=0.2, random_state=0))
            visualizer.fit(X, y)
            visualizer.poof()
        except Exception as e:
            self.fail("error during learning curve: {}".format(e))

项目：yellowbrick 作者：DistrictDataLabs | 项目源码 | 文件源码

def test_learning_curve_model_trainsize_cv_only(self):
        """
        Test learning curve with inputting model, training size, and cv only.
        """

        try:
            visualizer = LearningCurveVisualizer(LinearSVC(), 
                train_sizes=np.linspace(.1, 1.0, 5),
                cv=ShuffleSplit(n_splits=100, test_size=0.2, random_state=0))
            visualizer.fit(X, y)
            visualizer.poof()
        except Exception as e:
            self.fail("error during learning curve: {}".format(e))

项目：yellowbrick 作者：DistrictDataLabs | 项目源码 | 文件源码

def test_learning_curve_bad_trainsize(self):
        """
        Test learning curve with bad input for training size.
        """

        with self.assertRaises(YellowbrickError):
            visualizer = LearningCurveVisualizer(LinearSVC(), 
                train_sizes=10000,
                cv=ShuffleSplit(n_splits=100, test_size=0.2, random_state=0))
            visualizer.fit(X, y)
            visualizer.poof()

项目：ramp-workflow 作者：paris-saclay-cds | 项目源码 | 文件源码

def get_cv(self, X, y):
        unique_event_ids = np.unique(y[:, 0])
        event_cv = ShuffleSplit(
            n_splits=self.n_cv, test_size=self.cv_test_size,
            random_state=self.random_state)
        for train_event_is, test_event_is in event_cv.split(unique_event_ids):
            train_is = np.where(
                np.in1d(y[:, 0], unique_event_ids[train_event_is]))[0]
            test_is = np.where(
                np.in1d(y[:, 0], unique_event_ids[test_event_is]))[0]
            yield train_is, test_is