Python discriminant_analysis.LinearDiscriminantAnalysis方法代码示例

# 需要导入模块: from sklearn import discriminant_analysis [as 别名]
# 或者: from sklearn.discriminant_analysis import LinearDiscriminantAnalysis [as 别名]
def _tested_estimators():
    for name, Estimator in all_estimators():
        if issubclass(Estimator, BiclusterMixin):
            continue
        if name.startswith("_"):
            continue
        # FIXME _skip_test should be used here (if we could)

        required_parameters = getattr(Estimator, "_required_parameters", [])
        if len(required_parameters):
            if required_parameters in (["estimator"], ["base_estimator"]):
                if issubclass(Estimator, RegressorMixin):
                    estimator = Estimator(Ridge())
                else:
                    estimator = Estimator(LinearDiscriminantAnalysis())
            else:
                warnings.warn("Can't instantiate estimator {} which requires "
                              "parameters {}".format(name,
                                                     required_parameters),
                              SkipTestWarning)
                continue
        else:
            estimator = Estimator()
        yield name, estimator 

# 需要导入模块: from sklearn import discriminant_analysis [as 别名]
# 或者: from sklearn.discriminant_analysis import LinearDiscriminantAnalysis [as 别名]
def test_lda_priors():
    # Test priors (negative priors)
    priors = np.array([0.5, -0.5])
    clf = LinearDiscriminantAnalysis(priors=priors)
    msg = "priors must be non-negative"
    assert_raise_message(ValueError, msg, clf.fit, X, y)

    # Test that priors passed as a list are correctly handled (run to see if
    # failure)
    clf = LinearDiscriminantAnalysis(priors=[0.5, 0.5])
    clf.fit(X, y)

    # Test that priors always sum to 1
    priors = np.array([0.5, 0.6])
    prior_norm = np.array([0.45, 0.55])
    clf = LinearDiscriminantAnalysis(priors=priors)
    assert_warns(UserWarning, clf.fit, X, y)
    assert_array_almost_equal(clf.priors_, prior_norm, 2) 

# 需要导入模块: from sklearn import discriminant_analysis [as 别名]
# 或者: from sklearn.discriminant_analysis import LinearDiscriminantAnalysis [as 别名]
def test_lda_explained_variance_ratio():
    # Test if the sum of the normalized eigen vectors values equals 1,
    # Also tests whether the explained_variance_ratio_ formed by the
    # eigen solver is the same as the explained_variance_ratio_ formed
    # by the svd solver

    state = np.random.RandomState(0)
    X = state.normal(loc=0, scale=100, size=(40, 20))
    y = state.randint(0, 3, size=(40,))

    clf_lda_eigen = LinearDiscriminantAnalysis(solver="eigen")
    clf_lda_eigen.fit(X, y)
    assert_almost_equal(clf_lda_eigen.explained_variance_ratio_.sum(), 1.0, 3)
    assert_equal(clf_lda_eigen.explained_variance_ratio_.shape, (2,),
                 "Unexpected length for explained_variance_ratio_")

    clf_lda_svd = LinearDiscriminantAnalysis(solver="svd")
    clf_lda_svd.fit(X, y)
    assert_almost_equal(clf_lda_svd.explained_variance_ratio_.sum(), 1.0, 3)
    assert_equal(clf_lda_svd.explained_variance_ratio_.shape, (2,),
                 "Unexpected length for explained_variance_ratio_")

    assert_array_almost_equal(clf_lda_svd.explained_variance_ratio_,
                              clf_lda_eigen.explained_variance_ratio_) 

# 需要导入模块: from sklearn import discriminant_analysis [as 别名]
# 或者: from sklearn.discriminant_analysis import LinearDiscriminantAnalysis [as 别名]
def test_lda_scaling():
    # Test if classification works correctly with differently scaled features.
    n = 100
    rng = np.random.RandomState(1234)
    # use uniform distribution of features to make sure there is absolutely no
    # overlap between classes.
    x1 = rng.uniform(-1, 1, (n, 3)) + [-10, 0, 0]
    x2 = rng.uniform(-1, 1, (n, 3)) + [10, 0, 0]
    x = np.vstack((x1, x2)) * [1, 100, 10000]
    y = [-1] * n + [1] * n

    for solver in ('svd', 'lsqr', 'eigen'):
        clf = LinearDiscriminantAnalysis(solver=solver)
        # should be able to separate the data perfectly
        assert_equal(clf.fit(x, y).score(x, y), 1.0,
                     'using covariance: %s' % solver) 

# 需要导入模块: from sklearn import discriminant_analysis [as 别名]
# 或者: from sklearn.discriminant_analysis import LinearDiscriminantAnalysis [as 别名]
def test_11_lda(self):
        print("\ntest 11 (LDA with preprocessing) [multi-class]\n")
        X, X_test, y, features, target, test_file = self.data_utility.get_data_for_multi_class_classification()

        model = LinearDiscriminantAnalysis()
        pipeline_obj = Pipeline([
            ("scaler", MaxAbsScaler()),
            ("model", model)
        ])
        pipeline_obj.fit(X,y)
        file_name = 'test11sklearn.pmml'
        
        skl_to_pmml(pipeline_obj, features, target, file_name)
        model_name  = self.adapa_utility.upload_to_zserver(file_name)
        predictions, probabilities = self.adapa_utility.score_in_zserver(model_name, test_file)
        model_pred = pipeline_obj.predict(X_test)
        model_prob = pipeline_obj.predict_proba(X_test)
        self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
        self.assertEqual(self.adapa_utility.compare_probability(probabilities, model_prob), True) 

# 需要导入模块: from sklearn import discriminant_analysis [as 别名]
# 或者: from sklearn.discriminant_analysis import LinearDiscriminantAnalysis [as 别名]
def test_12_lda(self):
        print("\ntest 12 (LDA with preprocessing) [binary-class]\n")
        X, X_test, y, features, target, test_file = self.data_utility.get_data_for_binary_classification()

        model = LinearDiscriminantAnalysis()
        pipeline_obj = Pipeline([
            ("scaler", StandardScaler()),
            ("model", model)
        ])
        pipeline_obj.fit(X,y)
        file_name = 'test12sklearn.pmml'
        
        skl_to_pmml(pipeline_obj, features, target, file_name)
        model_name  = self.adapa_utility.upload_to_zserver(file_name)
        predictions, probabilities = self.adapa_utility.score_in_zserver(model_name, test_file)
        model_pred = pipeline_obj.predict(X_test)
        model_prob = pipeline_obj.predict_proba(X_test)
        self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True)
        self.assertEqual(self.adapa_utility.compare_probability(probabilities, model_prob), True) 

# 需要导入模块: from sklearn import discriminant_analysis [as 别名]
# 或者: from sklearn.discriminant_analysis import LinearDiscriminantAnalysis [as 别名]
def main():
	# prepare data
	trainingSet=[]
	testSet=[]
	accuracy = 0.0
	split = 0.25
	loadDataset('../Dataset/LDAdata.csv', split, trainingSet, testSet)
	print('Train set: ' + repr(len(trainingSet)))
	print('Test set: ' + repr(len(testSet)))
	trainData = np.array(trainingSet)[:,0:np.array(trainingSet).shape[1] - 1]
	columns = trainData.shape[1] 
	X = np.array(trainData)
	y = np.array(trainingSet)[:,columns]
	clf = BaggingClassifier(LDA())
	clf.fit(X, y)
	testData = np.array(testSet)[:,0:np.array(trainingSet).shape[1] - 1]
	X_test = np.array(testData)
	y_test = np.array(testSet)[:,columns]
	accuracy = clf.score(X_test,y_test)
	accuracy *= 100
	print("Accuracy %:",accuracy) 

# 需要导入模块: from sklearn import discriminant_analysis [as 别名]
# 或者: from sklearn.discriminant_analysis import LinearDiscriminantAnalysis [as 别名]
def lda_selection(X,y,n_components):
	"""
	Performs the Fisher's Linear Discrimination Analysis keeps the most discriminative features

	Keyword arguments:
	X -- The feature vectors
	y -- The target vector
	n_components -- Number of features to keep
	"""

	if verbose:
		print '\nPerforming Linear Discrimination Analysis ...'

	lda = LDA(n_components = n_components,solver='eigen')
	discriminative_attributes = lda.fit(X, y).transform(X)
	return discriminative_attributes

#Random Forest Classifier with an additional attribute coef_, in order to be usable by the Recursive Feature Elimination method 

# 需要导入模块: from sklearn import discriminant_analysis [as 别名]
# 或者: from sklearn.discriminant_analysis import LinearDiscriminantAnalysis [as 别名]
def __init__(self, **kwargs):
        """Initializes a ShrinkingLDA classifier.

        Additional arguments will be forwarded to the underlying classifier
        instantiation, which is
        ``sklearn.discriminant_analysis.LinearDiscriminantAnalysis`` here.

        Keyword Arguments
        -----------------
        solver: string, default = lsqr
            Solver used in LDA
        shrinkage: string, default = 'auto'

        """
        super(ShrinkingLDA, self).__init__()
        self.solver = kwargs.pop('solver', 'lsqr')
        self.shrinkage = kwargs.pop('shrinkage', 'auto')
        self.clf = _LinearDiscriminantAnalysis(solver=self.solver, shrinkage=self.shrinkage, **kwargs) 

# 需要导入模块: from sklearn import discriminant_analysis [as 别名]
# 或者: from sklearn.discriminant_analysis import LinearDiscriminantAnalysis [as 别名]
def rdm_lda_kfold(x, labels):
    from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
    from sklearn.model_selection import RepeatedStratifiedKFold
    from sklearn.model_selection import cross_val_score
    lda = LinearDiscriminantAnalysis(solver='lsqr', shrinkage='auto')
    folding = RepeatedStratifiedKFold(n_splits=3, n_repeats=3)

    objects = numpy.unique(labels)
    pairs = list(itertools.combinations(objects, 2))
    npairs = len(pairs)
    utv = numpy.full([npairs,], numpy.nan)
    for p in trange(npairs, desc='pairs', leave=False, ascii=True):
        pair = pairs[p]
        pair_mask = numpy.isin(labels, pair)
        x_pair = x[pair_mask, :]
        labels_pair = labels[pair_mask]
        scores = cross_val_score(lda, x_pair, labels_pair, cv=folding)
        utv[p] = scores.mean()
    return utv 

# 需要导入模块: from sklearn import discriminant_analysis [as 别名]
# 或者: from sklearn.discriminant_analysis import LinearDiscriminantAnalysis [as 别名]
def test_model_logistic_linear_discriminant_analysis(self):
        X = np.array([[-1, -1], [-2, -1], [-3, -2], [1, 1], [2, 1], [3, 2]])
        y = np.array([1, 1, 1, 2, 2, 2])
        X_test = np.array([[-0.8, -1], [-2, -1]], dtype=np.float32)
        model = LinearDiscriminantAnalysis().fit(X, y)
        model_onnx = convert_sklearn(
            model, "linear model",
            [("input", FloatTensorType([None, X_test.shape[1]]))])
        self.assertIsNotNone(model_onnx)
        dump_data_and_model(
            X_test,
            model,
            model_onnx,
            basename="SklearnLinearDiscriminantAnalysisBin-Dec3",
            # Operator cast-1 is not implemented in onnxruntime
            allow_failure="StrictVersion(onnx.__version__)"
                          " < StrictVersion('1.3') or "
                          "StrictVersion(onnxruntime.__version__)"
                          " <= StrictVersion('0.2.1')",
        ) 

# 需要导入模块: from sklearn import discriminant_analysis [as 别名]
# 或者: from sklearn.discriminant_analysis import LinearDiscriminantAnalysis [as 别名]
def test_model_logistic_linear_discriminant_analysis_decfunc(self):
        X = np.array([[-1, -1], [-2, -1], [-3, -2], [1, 1], [2, 1], [3, 2]])
        y = np.array([1, 1, 1, 2, 2, 2])
        X_test = np.array([[-0.8, -1], [0, 1]], dtype=np.float32)
        model = LinearDiscriminantAnalysis().fit(X, y)
        model_onnx = convert_sklearn(
            model, "linear model",
            [("input", FloatTensorType([None, X_test.shape[1]]))],
            options={id(model): {'raw_scores': True}})
        self.assertIsNotNone(model_onnx)
        dump_data_and_model(
            X_test, model, model_onnx,
            basename="SklearnLinearDiscriminantAnalysisBinRawScore-Out0",
            # Operator cast-1 is not implemented in onnxruntime
            allow_failure="StrictVersion(onnx.__version__)"
                          " < StrictVersion('1.3') or "
                          "StrictVersion(onnxruntime.__version__)"
                          " <= StrictVersion('0.2.1')",
            methods=['predict', 'decision_function']
        ) 

# 需要导入模块: from sklearn import discriminant_analysis [as 别名]
# 或者: from sklearn.discriminant_analysis import LinearDiscriminantAnalysis [as 别名]
def test_model_logistic_linear_discriminant_analysis_decfunc3(self):
        X = np.array([[-1, -1], [-2, -1], [-3, -2], [1, 1], [2, 1], [3, 2]])
        y = np.array([1, 1, 1, 2, 2, 3])
        X_test = np.array([[-0.8, -1], [0, 1]], dtype=np.float32)
        model = LinearDiscriminantAnalysis().fit(X, y)
        model_onnx = convert_sklearn(
            model, "linear model",
            [("input", FloatTensorType([None, X_test.shape[1]]))],
            options={id(model): {'raw_scores': True}})
        self.assertIsNotNone(model_onnx)
        dump_data_and_model(
            X_test, model, model_onnx,
            basename="SklearnLinearDiscriminantAnalysisBinRawScore3-Out0",
            # Operator cast-1 is not implemented in onnxruntime
            allow_failure="StrictVersion(onnx.__version__)"
                          " < StrictVersion('1.3') or "
                          "StrictVersion(onnxruntime.__version__)"
                          " <= StrictVersion('0.2.1')",
            methods=['predict', 'decision_function']
        ) 

# 需要导入模块: from sklearn import discriminant_analysis [as 别名]
# 或者: from sklearn.discriminant_analysis import LinearDiscriminantAnalysis [as 别名]
def test_lda_coefs():
    # Test if the coefficients of the solvers are approximately the same.
    n_features = 2
    n_classes = 2
    n_samples = 1000
    X, y = make_blobs(n_samples=n_samples, n_features=n_features,
                      centers=n_classes, random_state=11)

    clf_lda_svd = LinearDiscriminantAnalysis(solver="svd")
    clf_lda_lsqr = LinearDiscriminantAnalysis(solver="lsqr")
    clf_lda_eigen = LinearDiscriminantAnalysis(solver="eigen")

    clf_lda_svd.fit(X, y)
    clf_lda_lsqr.fit(X, y)
    clf_lda_eigen.fit(X, y)

    assert_array_almost_equal(clf_lda_svd.coef_, clf_lda_lsqr.coef_, 1)
    assert_array_almost_equal(clf_lda_svd.coef_, clf_lda_eigen.coef_, 1)
    assert_array_almost_equal(clf_lda_eigen.coef_, clf_lda_lsqr.coef_, 1) 

# 需要导入模块: from sklearn import discriminant_analysis [as 别名]
# 或者: from sklearn.discriminant_analysis import LinearDiscriminantAnalysis [as 别名]
def plot_lda(self, group_ids, channels, sample=None, ax=None):
        """
        Reduce dimensionality using LDA and plot data
        """
        ax = plt if ax is None else ax

        scores, labels = self.scores_for_groups(group_ids, channels)

        lda = LDA(n_components=2)
        reduced = lda.fit_transform(scores, labels)

        for color in np.unique(group_ids).astype('int'):
            x = reduced[labels == color, 0]
            y = reduced[labels == color, 1]

            if sample:
                x = np.random.choice(x, size=int(sample*len(x)), replace=False)
                y = np.random.choice(x, size=int(sample*len(y)), replace=False)

            ax.scatter(x, y, label='Group {}'.format(color), alpha=0.7)

        ax.legend()