Python svm.LinearSVC方法代码示例

# 需要导入模块: from sklearn import svm [as 别名]
# 或者: from sklearn.svm import LinearSVC [as 别名]
def proxy_a_distance(source_X, target_X):
    """
    Compute the Proxy-A-Distance of a source/target representation
    """
    nb_source = np.shape(source_X)[0]
    nb_target = np.shape(target_X)[0]

    train_X = np.vstack((source_X, target_X))
    train_Y = np.hstack((np.zeros(nb_source, dtype=int),
                         np.ones(nb_target, dtype=int)))

    clf = svm.LinearSVC(random_state=0)
    clf.fit(train_X, train_Y)
    y_pred = clf.predict(train_X)
    error = metrics.mean_absolute_error(train_Y, y_pred)
    dist = 2 * (1 - 2 * error)
    return dist 

# 需要导入模块: from sklearn import svm [as 别名]
# 或者: from sklearn.svm import LinearSVC [as 别名]
def __init__(self, vocab=None, idxlabelmap=None, clf=None):
        """ Initialization
        
        :type vocab: dict
        :param vocab: mappint from feature templates to feature indices

        :type idxrelamap: dict
        :param idxrelamap: mapping from parsing action indices to
                           parsing actions

        :type clf: LinearSVC
        :param clf: an multiclass classifier from sklearn
        """
        self.vocab = vocab
        # print labelmap
        self.labelmap = idxlabelmap
        if clf is None:
            self.clf = LinearSVC() 

# 需要导入模块: from sklearn import svm [as 别名]
# 或者: from sklearn.svm import LinearSVC [as 别名]
def test_random_hasher():
    # test random forest hashing on circles dataset
    # make sure that it is linearly separable.
    # even after projected to two SVD dimensions
    # Note: Not all random_states produce perfect results.
    hasher = RandomTreesEmbedding(n_estimators=30, random_state=1)
    X, y = datasets.make_circles(factor=0.5)
    X_transformed = hasher.fit_transform(X)

    # test fit and transform:
    hasher = RandomTreesEmbedding(n_estimators=30, random_state=1)
    assert_array_equal(hasher.fit(X).transform(X).toarray(),
                       X_transformed.toarray())

    # one leaf active per data point per forest
    assert_equal(X_transformed.shape[0], X.shape[0])
    assert_array_equal(X_transformed.sum(axis=1), hasher.n_estimators)
    svd = TruncatedSVD(n_components=2)
    X_reduced = svd.fit_transform(X_transformed)
    linear_clf = LinearSVC()
    linear_clf.fit(X_reduced, y)
    assert_equal(linear_clf.score(X_reduced, y), 1.) 

# 需要导入模块: from sklearn import svm [as 别名]
# 或者: from sklearn.svm import LinearSVC [as 别名]
def test_check_scoring_gridsearchcv():
    # test that check_scoring works on GridSearchCV and pipeline.
    # slightly redundant non-regression test.

    grid = GridSearchCV(LinearSVC(), param_grid={'C': [.1, 1]})
    scorer = check_scoring(grid, "f1")
    assert isinstance(scorer, _PredictScorer)

    pipe = make_pipeline(LinearSVC())
    scorer = check_scoring(pipe, "f1")
    assert isinstance(scorer, _PredictScorer)

    # check that cross_val_score definitely calls the scorer
    # and doesn't make any assumptions about the estimator apart from having a
    # fit.
    scores = cross_val_score(EstimatorWithFit(), [[1], [2], [3]], [1, 0, 1],
                             scoring=DummyScorer())
    assert_array_equal(scores, 1) 

# 需要导入模块: from sklearn import svm [as 别名]
# 或者: from sklearn.svm import LinearSVC [as 别名]
def test_linearsvc():
    # Similar to test_SVC
    clf = svm.LinearSVC(random_state=0).fit(X, Y)
    sp_clf = svm.LinearSVC(random_state=0).fit(X_sp, Y)

    assert sp_clf.fit_intercept

    assert_array_almost_equal(clf.coef_, sp_clf.coef_, decimal=4)
    assert_array_almost_equal(clf.intercept_, sp_clf.intercept_, decimal=4)

    assert_array_almost_equal(clf.predict(X), sp_clf.predict(X_sp))

    clf.fit(X2, Y2)
    sp_clf.fit(X2_sp, Y2)

    assert_array_almost_equal(clf.coef_, sp_clf.coef_, decimal=4)
    assert_array_almost_equal(clf.intercept_, sp_clf.intercept_, decimal=4) 

# 需要导入模块: from sklearn import svm [as 别名]
# 或者: from sklearn.svm import LinearSVC [as 别名]
def test_linearsvc_iris():
    # Test the sparse LinearSVC with the iris dataset

    sp_clf = svm.LinearSVC(random_state=0).fit(iris.data, iris.target)
    clf = svm.LinearSVC(random_state=0).fit(iris.data.toarray(), iris.target)

    assert_equal(clf.fit_intercept, sp_clf.fit_intercept)

    assert_array_almost_equal(clf.coef_, sp_clf.coef_, decimal=1)
    assert_array_almost_equal(clf.intercept_, sp_clf.intercept_, decimal=1)
    assert_array_almost_equal(
        clf.predict(iris.data.toarray()), sp_clf.predict(iris.data))

    # check decision_function
    pred = np.argmax(sp_clf.decision_function(iris.data), 1)
    assert_array_almost_equal(pred, clf.predict(iris.data.toarray()))

    # sparsify the coefficients on both models and check that they still
    # produce the same results
    clf.sparsify()
    assert_array_equal(pred, clf.predict(iris.data))
    sp_clf.sparsify()
    assert_array_equal(pred, sp_clf.predict(iris.data)) 

# 需要导入模块: from sklearn import svm [as 别名]
# 或者: from sklearn.svm import LinearSVC [as 别名]
def check_l1_min_c(X, y, loss, fit_intercept=True, intercept_scaling=None):
    min_c = l1_min_c(X, y, loss, fit_intercept, intercept_scaling)

    clf = {
        'log': LogisticRegression(penalty='l1', solver='liblinear',
                                  multi_class='ovr'),
        'squared_hinge': LinearSVC(loss='squared_hinge',
                                   penalty='l1', dual=False),
    }[loss]

    clf.fit_intercept = fit_intercept
    clf.intercept_scaling = intercept_scaling

    clf.C = min_c
    clf.fit(X, y)
    assert (np.asarray(clf.coef_) == 0).all()
    assert (np.asarray(clf.intercept_) == 0).all()

    clf.C = min_c * 1.01
    clf.fit(X, y)
    assert ((np.asarray(clf.coef_) != 0).any() or
            (np.asarray(clf.intercept_) != 0).any()) 

# 需要导入模块: from sklearn import svm [as 别名]
# 或者: from sklearn.svm import LinearSVC [as 别名]
def test_weight():
    # Test class weights
    clf = svm.SVC(gamma='scale', class_weight={1: 0.1})
    # we give a small weights to class 1
    clf.fit(X, Y)
    # so all predicted values belong to class 2
    assert_array_almost_equal(clf.predict(X), [2] * 6)

    X_, y_ = make_classification(n_samples=200, n_features=10,
                                 weights=[0.833, 0.167], random_state=2)

    for clf in (linear_model.LogisticRegression(),
                svm.LinearSVC(random_state=0), svm.SVC(gamma="scale")):
        clf.set_params(class_weight={0: .1, 1: 10})
        clf.fit(X_[:100], y_[:100])
        y_pred = clf.predict(X_[100:])
        assert f1_score(y_[100:], y_pred) > .3 

# 需要导入模块: from sklearn import svm [as 别名]
# 或者: from sklearn.svm import LinearSVC [as 别名]
def test_liblinear_set_coef():
    # multi-class case
    clf = svm.LinearSVC().fit(iris.data, iris.target)
    values = clf.decision_function(iris.data)
    clf.coef_ = clf.coef_.copy()
    clf.intercept_ = clf.intercept_.copy()
    values2 = clf.decision_function(iris.data)
    assert_array_almost_equal(values, values2)

    # binary-class case
    X = [[2, 1],
         [3, 1],
         [1, 3],
         [2, 3]]
    y = [0, 0, 1, 1]

    clf = svm.LinearSVC().fit(X, y)
    values = clf.decision_function(X)
    clf.coef_ = clf.coef_.copy()
    clf.intercept_ = clf.intercept_.copy()
    values2 = clf.decision_function(X)
    assert_array_equal(values, values2) 

# 需要导入模块: from sklearn import svm [as 别名]
# 或者: from sklearn.svm import LinearSVC [as 别名]
def test_grid_search_no_score():
    # Test grid-search on classifier that has no score function.
    clf = LinearSVC(random_state=0)
    X, y = make_blobs(random_state=0, centers=2)
    Cs = [.1, 1, 10]
    clf_no_score = LinearSVCNoScore(random_state=0)
    grid_search = GridSearchCV(clf, {'C': Cs}, scoring='accuracy')
    grid_search.fit(X, y)

    grid_search_no_score = GridSearchCV(clf_no_score, {'C': Cs},
                                        scoring='accuracy')
    # smoketest grid search
    grid_search_no_score.fit(X, y)

    # check that best params are equal
    assert_equal(grid_search_no_score.best_params_, grid_search.best_params_)
    # check that we can call score and that it gives the correct result
    assert_equal(grid_search.score(X, y), grid_search_no_score.score(X, y))

    # giving no scoring function raises an error
    grid_search_no_score = GridSearchCV(clf_no_score, {'C': Cs})
    assert_raise_message(TypeError, "no scoring", grid_search_no_score.fit,
                         [[1]]) 

# 需要导入模块: from sklearn import svm [as 别名]
# 或者: from sklearn.svm import LinearSVC [as 别名]
def test_classes__property():
    # Test that classes_ property matches best_estimator_.classes_
    X = np.arange(100).reshape(10, 10)
    y = np.array([0] * 5 + [1] * 5)
    Cs = [.1, 1, 10]

    grid_search = GridSearchCV(LinearSVC(random_state=0), {'C': Cs})
    grid_search.fit(X, y)
    assert_array_equal(grid_search.best_estimator_.classes_,
                       grid_search.classes_)

    # Test that regressors do not have a classes_ attribute
    grid_search = GridSearchCV(Ridge(), {'alpha': [1.0, 2.0]})
    grid_search.fit(X, y)
    assert not hasattr(grid_search, 'classes_')

    # Test that the grid searcher has no classes_ attribute before it's fit
    grid_search = GridSearchCV(LinearSVC(random_state=0), {'C': Cs})
    assert not hasattr(grid_search, 'classes_')

    # Test that the grid searcher has no classes_ attribute without a refit
    grid_search = GridSearchCV(LinearSVC(random_state=0),
                               {'C': Cs}, refit=False)
    grid_search.fit(X, y)
    assert not hasattr(grid_search, 'classes_') 

# 需要导入模块: from sklearn import svm [as 别名]
# 或者: from sklearn.svm import LinearSVC [as 别名]
def test_grid_search_sparse():
    # Test that grid search works with both dense and sparse matrices
    X_, y_ = make_classification(n_samples=200, n_features=100, random_state=0)

    clf = LinearSVC()
    cv = GridSearchCV(clf, {'C': [0.1, 1.0]})
    cv.fit(X_[:180], y_[:180])
    y_pred = cv.predict(X_[180:])
    C = cv.best_estimator_.C

    X_ = sp.csr_matrix(X_)
    clf = LinearSVC()
    cv = GridSearchCV(clf, {'C': [0.1, 1.0]})
    cv.fit(X_[:180].tocoo(), y_[:180])
    y_pred2 = cv.predict(X_[180:])
    C2 = cv.best_estimator_.C

    assert np.mean(y_pred == y_pred2) >= .9
    assert_equal(C, C2) 

# 需要导入模块: from sklearn import svm [as 别名]
# 或者: from sklearn.svm import LinearSVC [as 别名]
def test_refit_callable_out_bound(out_bound_value, search_cv):
    """
    Test implementation catches the errors when 'best_index_' returns an
    out of bound result.
    """
    def refit_callable_out_bound(cv_results):
        """
        A dummy function tests when returned 'best_index_' is out of bounds.
        """
        return out_bound_value

    X, y = make_classification(n_samples=100, n_features=4,
                               random_state=42)

    clf = search_cv(LinearSVC(random_state=42), {'C': [0.1, 1]},
                    scoring='precision', refit=refit_callable_out_bound, cv=5)
    with pytest.raises(IndexError, match='best_index_ index out of range'):
        clf.fit(X, y) 

# 需要导入模块: from sklearn import svm [as 别名]
# 或者: from sklearn.svm import LinearSVC [as 别名]
def test_refit_callable_multi_metric():
    """
    Test refit=callable in multiple metric evaluation setting
    """
    def refit_callable(cv_results):
        """
        A dummy function tests `refit=callable` interface.
        Return the index of a model that has the least
        `mean_test_prec`.
        """
        assert 'mean_test_prec' in cv_results
        return cv_results['mean_test_prec'].argmin()

    X, y = make_classification(n_samples=100, n_features=4,
                               random_state=42)
    scoring = {'Accuracy': make_scorer(accuracy_score), 'prec': 'precision'}
    clf = GridSearchCV(LinearSVC(random_state=42), {'C': [0.01, 0.1, 1]},
                       scoring=scoring, refit=refit_callable, cv=5)
    clf.fit(X, y)

    assert clf.best_index_ == 0
    # Ensure `best_score_` is disabled when using `refit=callable`
    assert not hasattr(clf, 'best_score_') 

# 需要导入模块: from sklearn import svm [as 别名]
# 或者: from sklearn.svm import LinearSVC [as 别名]
def test_search_cv_timing():
    svc = LinearSVC(random_state=0)

    X = [[1, ], [2, ], [3, ], [4, ]]
    y = [0, 1, 1, 0]

    gs = GridSearchCV(svc, {'C': [0, 1]}, cv=2, error_score=0)
    rs = RandomizedSearchCV(svc, {'C': [0, 1]}, cv=2, error_score=0, n_iter=2)

    for search in (gs, rs):
        search.fit(X, y)
        for key in ['mean_fit_time', 'std_fit_time']:
            # NOTE The precision of time.time in windows is not high
            # enough for the fit/score times to be non-zero for trivial X and y
            assert np.all(search.cv_results_[key] >= 0)
            assert np.all(search.cv_results_[key] < 1)

        for key in ['mean_score_time', 'std_score_time']:
            assert search.cv_results_[key][1] >= 0
            assert search.cv_results_[key][0] == 0.0
            assert np.all(search.cv_results_[key] < 1)

        assert hasattr(search, "refit_time_")
        assert isinstance(search.refit_time_, float)
        assert_greater_equal(search.refit_time_, 0)