python类Perceptron()的实例源码

def test_classification():
    # Check classification for various parameter settings.
    rng = check_random_state(0)
    X_train, X_test, y_train, y_test = train_test_split(iris.data,
                                                        iris.target,
                                                        random_state=rng)
    grid = ParameterGrid({"max_samples": [0.5, 1.0],
                          "max_features": [1, 2, 4],
                          "bootstrap": [True, False],
                          "bootstrap_features": [True, False]})

    for base_estimator in [None,
                           DummyClassifier(),
                           Perceptron(),
                           DecisionTreeClassifier(),
                           KNeighborsClassifier(),
                           SVC()]:
        for params in grid:
            BaggingClassifier(base_estimator=base_estimator,
                              random_state=rng,
                              **params).fit(X_train, y_train).predict(X_test)

def test_base():
    # Check BaseEnsemble methods.
    ensemble = BaggingClassifier(base_estimator=Perceptron(), n_estimators=3)

    iris = load_iris()
    ensemble.fit(iris.data, iris.target)
    ensemble.estimators_ = []  # empty the list and create estimators manually

    ensemble._make_estimator()
    ensemble._make_estimator()
    ensemble._make_estimator()
    ensemble._make_estimator(append=False)

    assert_equal(3, len(ensemble))
    assert_equal(3, len(ensemble.estimators_))

    assert_true(isinstance(ensemble[0], Perceptron))

def test_nested_circles():
    # Test the linear separability of the first 2D KPCA transform
    X, y = make_circles(n_samples=400, factor=.3, noise=.05,
                        random_state=0)

    # 2D nested circles are not linearly separable
    train_score = Perceptron().fit(X, y).score(X, y)
    assert_less(train_score, 0.8)

    # Project the circles data into the first 2 components of a RBF Kernel
    # PCA model.
    # Note that the gamma value is data dependent. If this test breaks
    # and the gamma value has to be updated, the Kernel PCA example will
    # have to be updated too.
    kpca = KernelPCA(kernel="rbf", n_components=2,
                     fit_inverse_transform=True, gamma=2.)
    X_kpca = kpca.fit_transform(X)

    # The data is perfectly linearly separable in that space
    train_score = Perceptron().fit(X_kpca, y).score(X_kpca, y)
    assert_equal(train_score, 1.0)

def train_classifier(self, trainvectors, labels, alpha='', iterations=50, jobs=10):
        iterations = int(iterations)
        jobs = int(jobs)
        if alpha == '':
            paramsearch = GridSearchCV(estimator=Perceptron(), param_grid=dict(alpha=numpy.linspace(0,2,20)[1:],n_iter=[iterations]), n_jobs=jobs)
            paramsearch.fit(trainvectors,self.label_encoder.transform(labels))
            selected_alpha = paramsearch.best_estimator_.alpha
        elif alpha == 'default':
            selected_alpha = 1.0
        else:
            selected_alpha = alpha
        # train a perceptron with the settings that led to the best performance
        self.model = Perceptron(alpha=selected_alpha,n_iter=iterations,n_jobs=jobs)
        self.model.fit(trainvectors, self.label_encoder.transform(labels))

def test_basic(self, single_chunk_classification):
        X, y = single_chunk_classification
        a = PartialPerceptron(classes=[0, 1], max_iter=1000, tol=1e-3)
        b = Perceptron(max_iter=1000, tol=1e-3)
        a.fit(X, y)
        b.partial_fit(X, y, classes=[0, 1])
        assert_estimator_equal(a.coef_, b.coef_)

def __init__(self, isTrain, isOutlierRemoval=0):
        super(ClassificationPLA, self).__init__(isTrain, isOutlierRemoval)

        # data preprocessing
        self.dataPreprocessing()

        # PLA object
        self.clf = Perceptron()

def estimate(X_train, y_train, X_test, y_test):
    clf = Perceptron(random_state=241)
    clf.fit(X_train, y_train)
    prediciton = clf.predict(X_test)
    return accuracy_score(y_test, prediciton)

def _init_model(self):
        return Perceptron()

def __init__(self, genres, data, type='knn', name='', clf_kwargs=None):
        self.logger = get_logger('classifier')
        self.display_name = name

        self.genres = genres
        self.m_genres = { genre:i for i, genre in enumerate(genres) }
        self.randstate = np.random.RandomState()
        self.scaler = StandardScaler()

        clf_kwargs = { } if not clf_kwargs else clf_kwargs
        if type in ['svm', 'mlp']:
            clf_kwargs['random_state'] = self.randstate

        if type == 'knn':
            self.proto_clf = KNeighborsClassifier(**clf_kwargs)
        elif type == 'svm':
            self.proto_clf = SVC(**clf_kwargs)
        elif type == 'dtree':
            self.proto_clf = DecisionTreeClassifier(**clf_kwargs)
        elif type == 'gnb':
            self.proto_clf = GaussianNB(**clf_kwargs)
        elif type == 'perc':
            self.proto_clf = Perceptron(**clf_kwargs)
        elif type == 'mlp':
            self.proto_clf = MLPClassifier(**clf_kwargs)
        elif type == 'ada':
            self.proto_clf = AdaBoostClassifier(**clf_kwargs)
        else:
            raise LookupError('Classifier type "{}" is invalid'.format(type))

        self._convert_data(data)

        self.logger.info('Classifier: {} (params={})'.format(
            self.proto_clf.__class__.__name__,
            clf_kwargs
        ))

def test_base_zero_n_estimators():
    # Check that instantiating a BaseEnsemble with n_estimators<=0 raises
    # a ValueError.
    ensemble = BaggingClassifier(base_estimator=Perceptron(), n_estimators=0)
    iris = load_iris()
    assert_raise_message(ValueError,
                         "n_estimators must be greater than zero, got 0.",
                         ensemble.fit, iris.data, iris.target)

def test_perceptron_accuracy():
    for data in (X, X_csr):
        clf = Perceptron(n_iter=30, shuffle=False)
        clf.fit(data, y)
        score = clf.score(data, y)
        assert_true(score >= 0.7)

def test_undefined_methods():
    clf = Perceptron()
    for meth in ("predict_proba", "predict_log_proba"):
        assert_raises(AttributeError, lambda x: getattr(clf, x), meth)

def test_gridsearch_pipeline():
    # Test if we can do a grid-search to find parameters to separate
    # circles with a perceptron model.
    X, y = make_circles(n_samples=400, factor=.3, noise=.05,
                        random_state=0)
    kpca = KernelPCA(kernel="rbf", n_components=2)
    pipeline = Pipeline([("kernel_pca", kpca), ("Perceptron", Perceptron())])
    param_grid = dict(kernel_pca__gamma=2. ** np.arange(-2, 2))
    grid_search = GridSearchCV(pipeline, cv=3, param_grid=param_grid)
    grid_search.fit(X, y)
    assert_equal(grid_search.best_score_, 1)

def test_gridsearch_pipeline_precomputed():
    # Test if we can do a grid-search to find parameters to separate
    # circles with a perceptron model using a precomputed kernel.
    X, y = make_circles(n_samples=400, factor=.3, noise=.05,
                        random_state=0)
    kpca = KernelPCA(kernel="precomputed", n_components=2)
    pipeline = Pipeline([("kernel_pca", kpca), ("Perceptron", Perceptron())])
    param_grid = dict(Perceptron__n_iter=np.arange(1, 5))
    grid_search = GridSearchCV(pipeline, cv=3, param_grid=param_grid)
    X_kernel = rbf_kernel(X, gamma=2.)
    grid_search.fit(X_kernel, y)
    assert_equal(grid_search.best_score_, 1)

def __init__(self, isTrain, isOutlierRemoval=0):
        super(ClassificationUniformBlending, self).__init__(isTrain, isOutlierRemoval)
        # data preprocessing
        self.dataPreprocessing()

        # create logistic regression object
        self.logreg = linear_model.LogisticRegression(tol=1e-6, penalty='l1', C=0.0010985411419875584)

        # create adaboost object
        self.dt_stump = DecisionTreeClassifier(max_depth=10)
        self.ada = AdaBoostClassifier(
            base_estimator=self.dt_stump,
            learning_rate=1,
            n_estimators=5,
            algorithm="SAMME.R")

        # create knn object
        self.knn = neighbors.KNeighborsClassifier(2, weights='uniform')

        # create decision tree object
        self.decisiontree = DecisionTreeClassifier(max_depth=45, max_features='log2')

        # create neural network object
        self.net1 = NeuralNet(
                        layers=[  # three layers: one hidden layer
                            ('input', layers.InputLayer),
                            ('hidden', layers.DenseLayer),
                            #('hidden2', layers.DenseLayer),
                            ('output', layers.DenseLayer),
                            ],
                        # layer parameters:
                        input_shape=(None, 12),  # inut dimension is 12
                        hidden_num_units=6,  # number of units in hidden layer
                        #hidden2_num_units=3,  # number of units in hidden layer
                        output_nonlinearity=lasagne.nonlinearities.sigmoid,  # output layer uses sigmoid function
                        output_num_units=1,  # output dimension is 1

                        # optimization method:
                        update=nesterov_momentum,
                        update_learning_rate=0.002,
                        update_momentum=0.9,

                        regression=True,  # flag to indicate we're dealing with regression problem
                        max_epochs=25,  # we want to train this many epochs
                        verbose=0,
                        )

        # create PLA object
        self.pla = Perceptron()

        # create random forest object
        self.rf = RandomForestClassifier(max_features='log2', n_estimators=20, max_depth=30)

def test_base_estimator():
    # Check base_estimator and its default values.
    rng = check_random_state(0)

    # Classification
    X_train, X_test, y_train, y_test = train_test_split(iris.data,
                                                        iris.target,
                                                        random_state=rng)

    ensemble = BaggingClassifier(None,
                                 n_jobs=3,
                                 random_state=0).fit(X_train, y_train)

    assert_true(isinstance(ensemble.base_estimator_, DecisionTreeClassifier))

    ensemble = BaggingClassifier(DecisionTreeClassifier(),
                                 n_jobs=3,
                                 random_state=0).fit(X_train, y_train)

    assert_true(isinstance(ensemble.base_estimator_, DecisionTreeClassifier))

    ensemble = BaggingClassifier(Perceptron(),
                                 n_jobs=3,
                                 random_state=0).fit(X_train, y_train)

    assert_true(isinstance(ensemble.base_estimator_, Perceptron))

    # Regression
    X_train, X_test, y_train, y_test = train_test_split(boston.data,
                                                        boston.target,
                                                        random_state=rng)

    ensemble = BaggingRegressor(None,
                                n_jobs=3,
                                random_state=0).fit(X_train, y_train)

    assert_true(isinstance(ensemble.base_estimator_, DecisionTreeRegressor))

    ensemble = BaggingRegressor(DecisionTreeRegressor(),
                                n_jobs=3,
                                random_state=0).fit(X_train, y_train)

    assert_true(isinstance(ensemble.base_estimator_, DecisionTreeRegressor))

    ensemble = BaggingRegressor(SVR(),
                                n_jobs=3,
                                random_state=0).fit(X_train, y_train)
    assert_true(isinstance(ensemble.base_estimator_, SVR))