Python sklearn.datasets.load_digits() Examples

def split_train_test(n_classes):
    from sklearn.datasets import load_digits

    n_labeled = 5
    digits = load_digits(n_class=n_classes)  # consider binary case
    X = digits.data
    y = digits.target
    print(np.shape(X))

    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33)
    while len(np.unique(y_train[:n_labeled])) < n_classes:
        X_train, X_test, y_train, y_test = train_test_split(
            X, y, test_size=0.33)

    trn_ds = Dataset(X_train, np.concatenate(
        [y_train[:n_labeled], [None] * (len(y_train) - n_labeled)]))
    tst_ds = Dataset(X_test, y_test)

    return trn_ds, tst_ds, digits 

def test_pca_score_with_different_solvers(self):
        digits = datasets.load_digits()
        X_digits = mt.tensor(digits.data)

        pca_dict = {svd_solver: PCA(n_components=30, svd_solver=svd_solver,
                                    random_state=0)
                    for svd_solver in self.solver_list}

        for pca in pca_dict.values():
            pca.fit(X_digits)
            # Sanity check for the noise_variance_. For more details see
            # https://github.com/scikit-learn/scikit-learn/issues/7568
            # https://github.com/scikit-learn/scikit-learn/issues/8541
            # https://github.com/scikit-learn/scikit-learn/issues/8544
            assert mt.all((pca.explained_variance_ - pca.noise_variance_) >= 0).to_numpy()

        # Compare scores with different svd_solvers
        score_dict = {svd_solver: pca.score(X_digits).to_numpy()
                      for svd_solver, pca in pca_dict.items()}
        assert_almost_equal(score_dict['full'], score_dict['randomized'],
                            decimal=3) 

def get_mnist_data():
    """Loads the MNIST data set into memory.

    Returns
    -------
    X : array-like, shape=[n_samples, n_features]
        Training data for the MNIST data set.
        
    y : array-like, shape=[n_samples,]
        Labels for the MNIST data set.
    """
    digits = load_digits()
    X, y = digits.data, digits.target
    y = LabelBinarizer().fit_transform(y)

    return X, y 

def _get_mnist_data(seed=None):

    digits = load_digits()["images"]

    if seed is not None:
        rnd = np.random.RandomState(seed=seed)
    else:
        rnd = np.random.RandomState()

    no_img, rows, cols = digits.shape
    X = digits.reshape((no_img, rows * cols))
    X = np.ascontiguousarray(X)
    rnd.shuffle(X)

    X_test = X[:100]
    X_train = X[100:]

    return X_train, X_test 

def digits_reduced():
    data=load_digits()
    XX = data['data']
    y = data['target']
    nn,dd = XX.shape
    XX = XX.reshape([nn,8,8])

    X = np.empty([nn,3])
    for i in xrange(nn):
        X[i,0] = simetria_hor(XX[i,:,:])
        X[i,1] = simetria_ver(XX[i,:,:])
        X[i,2] = np.mean(XX[i,:])
    
    return X,y

### ARFF dataframes ### 

def digits_reduced():
    data=load_digits()
    XX = data['data']
    y = data['target']
    nn,dd = XX.shape
    XX = XX.reshape([nn,8,8])

    X = np.empty([nn,3])
    for i in xrange(nn):
        X[i,0] = simetria_hor(XX[i,:,:])
        X[i,1] = simetria_ver(XX[i,:,:])
        X[i,2] = np.mean(XX[i,:])
    
    return X,y

### ARFF dataframes ### 

def test_pca_default_int_randomised(self):
        data = load_digits()
        X_train, X_test, *_ = train_test_split(
            data.data, data.target, test_size=0.2, random_state=42)
        model = PCA(random_state=42, svd_solver='randomized',
                    iterated_power=3).fit(X_train)
        model_onnx = convert_sklearn(
            model,
            initial_types=[("input",
                            Int64TensorType([None, X_test.shape[1]]))],
        )
        self.assertTrue(model_onnx is not None)
        dump_data_and_model(
            X_test.astype(np.int64),
            model,
            model_onnx,
            basename="SklearnPCADefaultIntRandomised",
            allow_failure="StrictVersion("
            "onnxruntime.__version__)"
            "<= StrictVersion('0.2.1')",
        ) 

def test_dummy_identity(self):

        digits = datasets.load_digits(n_class=6)
        Xd = digits.data[:20]
        yd = digits.target[:20]
        n_samples, n_features = Xd.shape

        idtr = make_pipeline(IdentityTransformer(), identity())
        idtr.fit(Xd, yd)

        update_registered_converter(IdentityTransformer, "IdentityTransformer",
                                    dummy_shape_calculator, dummy_converter)
        update_registered_converter(identity, "identity",
                                    dummy_shape_calculator, dummy_converter)

        model_onnx = convert_sklearn(
            idtr,
            "idtr",
            [("input", FloatTensorType([None, Xd.shape[1]]))],
            target_opset=TARGET_OPSET)

        idnode = [node for node in model_onnx.graph.node
                  if node.op_type == "Identity"]
        assert len(idnode) == 2 

def test_kmeans_clustering_int(self):
        data = load_digits()
        X = data.data
        model = KMeans(n_clusters=4)
        model.fit(X)
        model_onnx = convert_sklearn(model, "kmeans",
                                     [("input", Int64TensorType([None,
                                      X.shape[1]]))],
                                     target_opset=TARGET_OPSET)
        self.assertIsNotNone(model_onnx)
        dump_data_and_model(
            X.astype(numpy.int64)[40:60],
            model,
            model_onnx,
            basename="SklearnKMeansInt-Dec4",
            # Operator gemm is not implemented in onnxruntime
            allow_failure="StrictVersion(onnx.__version__)"
                          " < StrictVersion('1.2') or "
                          "StrictVersion(onnxruntime.__version__) "
                          "<= StrictVersion('0.2.1')",
        ) 

def test_batchkmeans_clustering_int(self):
        data = load_digits()
        X = data.data
        model = MiniBatchKMeans(n_clusters=4)
        model.fit(X)
        model_onnx = convert_sklearn(model, "kmeans",
                                     [("input", Int64TensorType([None,
                                      X.shape[1]]))],
                                     target_opset=TARGET_OPSET)
        self.assertIsNotNone(model_onnx)
        dump_data_and_model(
            X.astype(numpy.int64)[40:60],
            model,
            model_onnx,
            basename="SklearnBatchKMeansInt-Dec4",
            allow_failure="StrictVersion(onnx.__version__)"
                          " < StrictVersion('1.2') or "
                          "StrictVersion(onnxruntime.__version__) "
                          "<= StrictVersion('0.2.1')",
        ) 

def test_model_calibrated_classifier_cv_int(self):
        data = load_digits()
        X, y = data.data, data.target
        clf = MultinomialNB().fit(X, y)
        model = CalibratedClassifierCV(clf, cv=2, method="sigmoid").fit(X, y)
        model_onnx = convert_sklearn(
            model,
            "scikit-learn CalibratedClassifierCVMNB",
            [("input", Int64TensorType([None, X.shape[1]]))],
            target_opset=TARGET_OPSET
        )
        self.assertTrue(model_onnx is not None)
        dump_data_and_model(
            X.astype(np.int64),
            model,
            model_onnx,
            basename="SklearnCalibratedClassifierCVInt-Dec4",
            allow_failure="StrictVersion(onnxruntime.__version__)"
            "<= StrictVersion('0.2.1')",
        ) 

def test_feature_union_transformer_weights_1(self):
        data = load_digits()
        X, y = data.data, data.target
        X = X.astype(np.int64)
        X_train, X_test, *_ = train_test_split(X, y, test_size=0.5,
                                               random_state=42)
        model = FeatureUnion([('pca', PCA()),
                              ('svd', TruncatedSVD())],
                             transformer_weights={'pca': 10, 'svd': 3}
                             ).fit(X_train)
        model_onnx = convert_sklearn(
            model, 'feature union',
            [('input', Int64TensorType([None, X_test.shape[1]]))])
        self.assertTrue(model_onnx is not None)
        dump_data_and_model(
            X_test,
            model,
            model_onnx,
            basename="SklearnFeatureUnionTransformerWeights1-Dec4",
            allow_failure="StrictVersion("
            "onnxruntime.__version__)"
            "<= StrictVersion('0.2.1')",
        ) 

def test_feature_union_transformer_weights_2(self):
        data = load_digits()
        X, y = data.data, data.target
        X = X.astype(np.float32)
        X_train, X_test, *_ = train_test_split(X, y, test_size=0.5,
                                               random_state=42)
        model = FeatureUnion([('pca', PCA()),
                              ('svd', TruncatedSVD())],
                             transformer_weights={'pca1': 10, 'svd2': 3}
                             ).fit(X_train)
        model_onnx = convert_sklearn(
            model, 'feature union',
            [('input', FloatTensorType([None, X_test.shape[1]]))])
        self.assertTrue(model_onnx is not None)
        dump_data_and_model(
            X_test,
            model,
            model_onnx,
            basename="SklearnFeatureUnionTransformerWeights2-Dec4",
            allow_failure="StrictVersion("
            "onnxruntime.__version__)"
            "<= StrictVersion('0.2.1')",
        ) 

def setup_method(self):
        import sklearn.svm as svm
        digits = datasets.load_digits()
        self.data = digits.data
        self.target = digits.target
        self.df = pdml.ModelFrame(digits)

        estimator1 = self.df.svm.LinearSVC(C=1.0, random_state=self.random_state)
        self.df.fit(estimator1)

        estimator2 = svm.LinearSVC(C=1.0, random_state=self.random_state)
        estimator2.fit(self.data, self.target)
        self.pred = estimator2.predict(self.data)
        self.decision = estimator2.decision_function(self.data)

        # argument for classification reports
        self.labels = np.array([9, 8, 7, 6, 5, 4, 3, 2, 1, 0]) 

def test_train_test_split(self):

        df = pdml.ModelFrame(datasets.load_digits())
        self.assertIsInstance(df, pdml.ModelFrame)

        train_df, test_df = df.model_selection.train_test_split()
        tm.assert_index_equal(df.columns, train_df.columns)
        tm.assert_index_equal(df.columns, test_df.columns)

        self.assertEqual(len(df), len(train_df) + len(test_df))
        self.assertEqual(df.shape[1], train_df.shape[1])
        self.assertEqual(df.shape[1], test_df.shape[1])

        tm.assert_index_equal(df.columns, train_df.columns)
        tm.assert_index_equal(df.columns, test_df.columns)

        df = pdml.ModelFrame(datasets.load_digits())
        df.target_name = 'xxx'

        train_df, test_df = df.model_selection.train_test_split()
        tm.assert_index_equal(df.columns, train_df.columns)
        tm.assert_index_equal(df.columns, test_df.columns)
        self.assertEqual(train_df.target_name, 'xxx')
        self.assertEqual(test_df.target_name, 'xxx') 

def test_validation_curve(self):
        digits = datasets.load_digits()
        df = pdml.ModelFrame(digits)

        param_range = np.logspace(-2, -1, 2)

        svc = df.svm.SVC(random_state=self.random_state)
        result = df.model_selection.validation_curve(svc, 'gamma',
                                                     param_range)
        expected = ms.validation_curve(svm.SVC(random_state=self.random_state),
                                       digits.data, digits.target,
                                       'gamma', param_range)

        self.assertEqual(len(result), 2)
        self.assert_numpy_array_almost_equal(result[0], expected[0])
        self.assert_numpy_array_almost_equal(result[1], expected[1]) 

def main():
    data = datasets.load_digits()
    X = normalize(data.data)
    y = data.target

    # Convert the nominal y values to binary
    y = to_categorical(y)

    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4, seed=1)

    # MLP
    clf = MultilayerPerceptron(n_hidden=16,
        n_iterations=1000,
        learning_rate=0.01)

    clf.fit(X_train, y_train)
    y_pred = np.argmax(clf.predict(X_test), axis=1)
    y_test = np.argmax(y_test, axis=1)

    accuracy = accuracy_score(y_test, y_pred)
    print ("Accuracy:", accuracy)

    # Reduce dimension to two using PCA and plot the results
    Plot().plot_in_2d(X_test, y_pred, title="Multilayer Perceptron", accuracy=accuracy, legend_labels=np.unique(y)) 

def main():
    data = datasets.load_digits()
    X = data.data
    y = data.target

    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4, seed=2)

    clf = RandomForest(n_estimators=100)
    clf.fit(X_train, y_train)
    y_pred = clf.predict(X_test)

    accuracy = accuracy_score(y_test, y_pred)

    print ("Accuracy:", accuracy)

    Plot().plot_in_2d(X_test, y_pred, title="Random Forest", accuracy=accuracy, legend_labels=data.target_names) 

def main():
    data = datasets.load_digits()
    X = normalize(data.data)
    y = data.target

    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4)

    clf = NaiveBayes()
    clf.fit(X_train, y_train)
    y_pred = clf.predict(X_test)

    accuracy = accuracy_score(y_test, y_pred)

    print ("Accuracy:", accuracy)

    # Reduce dimension to two using PCA and plot the results
    Plot().plot_in_2d(X_test, y_pred, title="Naive Bayes", accuracy=accuracy, legend_labels=data.target_names) 

def get_sample_dataset(dataset_properties):
    """Returns sample dataset

    Args:
        dataset_properties (dict): Dictionary corresponding to the properties of the dataset
            used to verify the estimator and metric generators.

    Returns:
        X (array-like): Features array

        y (array-like): Labels array

        splits (iterator): This is an iterator that returns train test splits for
            cross-validation purposes on ``X`` and ``y``.
    """
    kwargs = dataset_properties.copy()
    data_type = kwargs.pop('type')
    if data_type == 'multiclass':
        try:
            X, y = datasets.make_classification(random_state=8, **kwargs)
            splits = model_selection.StratifiedKFold(n_splits=2, random_state=8).split(X, y)
        except Exception as e:
            raise exceptions.UserError(repr(e))
    elif data_type == 'iris':
        X, y = datasets.load_iris(return_X_y=True)
        splits = model_selection.StratifiedKFold(n_splits=2, random_state=8).split(X, y)
    elif data_type == 'mnist':
        X, y = datasets.load_digits(return_X_y=True)
        splits = model_selection.StratifiedKFold(n_splits=2, random_state=8).split(X, y)
    elif data_type == 'breast_cancer':
        X, y = datasets.load_breast_cancer(return_X_y=True)
        splits = model_selection.StratifiedKFold(n_splits=2, random_state=8).split(X, y)
    elif data_type == 'boston':
        X, y = datasets.load_boston(return_X_y=True)
        splits = model_selection.KFold(n_splits=2, random_state=8).split(X)
    elif data_type == 'diabetes':
        X, y = datasets.load_diabetes(return_X_y=True)
        splits = model_selection.KFold(n_splits=2, random_state=8).split(X)
    else:
        raise exceptions.UserError('Unknown dataset type {}'.format(dataset_properties['type']))
    return X, y, splits 

def extract_main_dataset():
    X, y = load_digits(return_X_y=True)
    return X, y 

def test_correct_dataset(self):
        X, y = load_digits(return_X_y=True)
        verification_dict = functions.verify_dataset(X, y)
        assert verification_dict['features_shape'] == (1797,64)
        assert verification_dict['labels_shape'] == (1797,) 

def setUp(self):
		data = load_digits()
		self.Xtr, self.Xte, Ytr, Yte = train_test_split(data.data, data.target, shuffle=True, train_size=.15)
		self.Xtr_numpy = self.Xtr.copy()
		self.Xte_numpy = self.Xte.copy()
		self.Xtr = preprocessing.normalization(self.Xtr)
		self.Xte = preprocessing.normalization(self.Xte)
		self.Ytr = torch.Tensor(Ytr)
		self.Yte = torch.Tensor(Yte)
		self.KLtr = [pairwise_mk.homogeneous_polynomial_kernel(self.Xtr, degree=d) for d in range(1,11)]
		self.KLte = [pairwise_mk.homogeneous_polynomial_kernel(self.Xte, self.Xtr, degree=d) for d in range(1,11)] 

def test_scikit_learn(df):

    sklearn = import_module('sklearn')  # noqa
    from sklearn import svm, datasets

    digits = datasets.load_digits()
    clf = svm.SVC(gamma=0.001, C=100.)
    clf.fit(digits.data[:-1], digits.target[:-1])
    clf.predict(digits.data[-1:])


# Cython import warning and traitlets 

def digits_dataload():
    from sklearn import datasets
    Digits=datasets.load_digits()
    Data=Digits.data/16.
    label=Digits.target
    return Data,label 

def test_scikit_learn(df):

    sklearn = import_module('sklearn')  # noqa
    from sklearn import svm, datasets

    digits = datasets.load_digits()
    clf = svm.SVC(gamma=0.001, C=100.)
    clf.fit(digits.data[:-1], digits.target[:-1])
    clf.predict(digits.data[-1:]) 

def test_unsorted_indices():
    # test that the result with sorted and unsorted indices in csr is the same
    # we use a subset of digits as iris, blobs or make_classification didn't
    # show the problem
    digits = load_digits()
    X, y = digits.data[:50], digits.target[:50]
    X_test = sparse.csr_matrix(digits.data[50:100])

    X_sparse = sparse.csr_matrix(X)
    coef_dense = svm.SVC(kernel='linear', probability=True,
                         random_state=0).fit(X, y).coef_
    sparse_svc = svm.SVC(kernel='linear', probability=True,
                         random_state=0).fit(X_sparse, y)
    coef_sorted = sparse_svc.coef_
    # make sure dense and sparse SVM give the same result
    assert_array_almost_equal(coef_dense, coef_sorted.toarray())

    # reverse each row's indices
    def scramble_indices(X):
        new_data = []
        new_indices = []
        for i in range(1, len(X.indptr)):
            row_slice = slice(*X.indptr[i - 1: i + 1])
            new_data.extend(X.data[row_slice][::-1])
            new_indices.extend(X.indices[row_slice][::-1])
        return sparse.csr_matrix((new_data, new_indices, X.indptr),
                                 shape=X.shape)

    X_sparse_unsorted = scramble_indices(X_sparse)
    X_test_unsorted = scramble_indices(X_test)

    assert not X_sparse_unsorted.has_sorted_indices
    assert not X_test_unsorted.has_sorted_indices

    unsorted_svc = svm.SVC(kernel='linear', probability=True,
                           random_state=0).fit(X_sparse_unsorted, y)
    coef_unsorted = unsorted_svc.coef_
    # make sure unsorted indices give same result
    assert_array_almost_equal(coef_unsorted.toarray(), coef_sorted.toarray())
    assert_array_almost_equal(sparse_svc.predict_proba(X_test_unsorted),
                              sparse_svc.predict_proba(X_test)) 

def test_check_accuracy_on_digits():
    # Non regression test to make sure that any further refactoring / optim
    # of the NB models do not harm the performance on a slightly non-linearly
    # separable dataset
    digits = load_digits()
    X, y = digits.data, digits.target
    binary_3v8 = np.logical_or(digits.target == 3, digits.target == 8)
    X_3v8, y_3v8 = X[binary_3v8], y[binary_3v8]

    # Multinomial NB
    scores = cross_val_score(MultinomialNB(alpha=10), X, y, cv=10)
    assert_greater(scores.mean(), 0.86)

    scores = cross_val_score(MultinomialNB(alpha=10), X_3v8, y_3v8, cv=10)
    assert_greater(scores.mean(), 0.94)

    # Bernoulli NB
    scores = cross_val_score(BernoulliNB(alpha=10), X > 4, y, cv=10)
    assert_greater(scores.mean(), 0.83)

    scores = cross_val_score(BernoulliNB(alpha=10), X_3v8 > 4, y_3v8, cv=10)
    assert_greater(scores.mean(), 0.92)

    # Gaussian NB
    scores = cross_val_score(GaussianNB(), X, y, cv=10)
    assert_greater(scores.mean(), 0.77)

    scores = cross_val_score(GaussianNB(var_smoothing=0.1), X, y, cv=10)
    assert_greater(scores.mean(), 0.89)

    scores = cross_val_score(GaussianNB(), X_3v8, y_3v8, cv=10)
    assert_greater(scores.mean(), 0.86) 

def test_load_digits():
    digits = load_digits()
    assert_equal(digits.data.shape, (1797, 64))
    assert_equal(numpy.unique(digits.target).size, 10)

    # test return_X_y option
    check_return_X_y(digits, partial(load_digits)) 

def test_load_digits_n_class_lt_10():
    digits = load_digits(9)
    assert_equal(digits.data.shape, (1617, 64))
    assert_equal(numpy.unique(digits.target).size, 9)