Python sklearn.metrics 模块，zero_one_loss() 实例源码

def test_mdr_custom_score(): 
    """Ensure that the MDR 'score' function outputs the right custom score passed in from the user"""
    features = np.array([[2,    0],
                         [0,    0],
                         [0,    1],
                         [0,    0],
                         [0,    0],
                         [0,    0],
                         [0,    1],
                         [0,    0],
                         [0,    0],
                         [0,    1],
                         [0,    0],
                         [0,    0],
                         [0,    0],
                         [1,    1],
                         [1,    1]])

    classes = np.array([1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0])

    mdr = MDRClassifier() 
    mdr.fit(features, classes)
    assert mdr.score(features = features, class_labels = classes, scoring_function = accuracy_score) == 12. / 15
    assert mdr.score(features = features, class_labels = classes, scoring_function = zero_one_loss) == 1 - 12. / 15
    assert mdr.score(features = features, class_labels = classes, scoring_function = zero_one_loss, normalize=False) == 15 - 12

def test_milboost_musk_fitting_lse():
    c = MILBoostClassifier(
        base_estimator=DecisionTreeClassifier(max_depth=1),
        softmax=LogSumExponential(5.0),
        n_estimators=30,
        learning_rate=1.0
    )

    data = MUSK1()
    c.fit(data.data, data.labels)
    assert_array_less(c.estimator_errors_, 0.5)
    assert zero_one_loss(np.sign(data.labels), c.predict(data.data)) < 0.30

def test_milboost_hastie_fitting():
    c = MILBoostClassifier(
        base_estimator=DecisionTreeClassifier(max_depth=1),
        softmax=LogSumExponential(5.0),
        n_estimators=30,
        learning_rate=1.0
    )

    data = Hastie_10_2()
    c.fit(data.data, data.labels)
    assert_array_less(c.estimator_errors_, 0.5)
    assert zero_one_loss(np.sign(data.labels), c.predict(data.data)) < 0.40

def test_logitboost_musk_fitting():
    c = LogitBoostClassifier(
            base_estimator=DecisionTreeRegressor(max_depth=1),
            n_estimators=30,
            learning_rate=1.0
    )
    data = MUSK1()
    c.fit(data.data, np.sign(data.labels))
    assert_array_less(c.estimator_errors_, 0.6)
    assert zero_one_loss(np.sign(data.labels), c.predict(data.data)) < 0.05

def test_logitboost_hastie_fitting():
    c = LogitBoostClassifier(
            base_estimator=DecisionTreeRegressor(max_depth=1),
            n_estimators=30,
            learning_rate=1.0
    )
    data = Hastie_10_2()
    c.fit(data.data, np.sign(data.labels))
    assert_array_less(c.estimator_errors_, 0.5)
    assert zero_one_loss(np.sign(data.labels), c.predict(data.data)) < 0.2

def test_gentleboost_musk_fitting():
    c = GentleBoostClassifier(
        base_estimator=DecisionTreeRegressor(max_depth=1),
        n_estimators=30,
        learning_rate=1.0
    )
    data = MUSK1()
    c.fit(data.data, np.sign(data.labels))
    assert_array_less(c.estimator_errors_, 0.5)
    assert zero_one_loss(np.sign(data.labels), c.predict(data.data)) < 0.1

def clf_bias_var(clf, X, y, n_replicas):

    roc_auc_scorer = get_scorer("roc_auc")
    # roc_auc_scorer(clf, X_test, y_test)
    auc_scores = []
    error_scores = []
    counts = np.zeros(X.shape[0], dtype = np.float64)
    sum_preds = np.zeros(X.shape[0], dtype = np.float64)
    for it in xrange(n_replicas):
        # generate train sets and test sets
        train_indices = np.random.randint(X.shape[0], size = X.shape[0])
        # get test sets
        in_train = np.unique(train_indices)
        mask = np.ones(X.shape[0], dtype = np.bool)
        mask[in_train] = False
        test_indices = np.arange(X.shape[0])[mask]

        clf.fit(X[train_indices], y[train_indices])

        auc_scores.append(roc_auc_scorer(clf, X[test_indices], y[test_indices]))
        error_scores.append(zero_one_loss(y[test_indices], clf.predict(X[test_indices])))

        preds = clf.predict(X)
        for index in test_indices:
            counts[index] += 1
            sum_preds[index] += preds[index]

    test_mask = (counts > 0) # indices of samples that have been tested

    # print('counts mean: {}'.format(np.mean(counts)))
    # print('counts standard derivation: {}'.format(np.std(counts)))

    bias, var = bias_var(y[test_mask], sum_preds[test_mask], counts[test_mask], n_replicas)

    return auc_scores, error_scores, bias, var

def test_zero_one_loss():
    '''
    test 0-1 loss function
    :return: None
    '''
    y_true=[1,1,1,1,1,0,0,0,0,0]
    y_pred=[0,0,0,1,1,1,1,1,0,0]
    print("zero_one_loss<fraction>:",zero_one_loss(y_true,y_pred,normalize=True))
    print("zero_one_loss<num>:",zero_one_loss(y_true,y_pred,normalize=False))

def test_multilabel_zero_one_loss_subset():
    # Dense label indicator matrix format
    y1 = np.array([[0, 1, 1], [1, 0, 1]])
    y2 = np.array([[0, 0, 1], [1, 0, 1]])

    assert_equal(zero_one_loss(y1, y2), 0.5)
    assert_equal(zero_one_loss(y1, y1), 0)
    assert_equal(zero_one_loss(y2, y2), 0)
    assert_equal(zero_one_loss(y2, np.logical_not(y2)), 1)
    assert_equal(zero_one_loss(y1, np.logical_not(y1)), 1)
    assert_equal(zero_one_loss(y1, np.zeros(y1.shape)), 1)
    assert_equal(zero_one_loss(y2, np.zeros(y1.shape)), 1)

def test_rfecv():
    generator = check_random_state(0)
    iris = load_iris()
    X = np.c_[iris.data, generator.normal(size=(len(iris.data), 6))]
    y = list(iris.target)   # regression test: list should be supported

    # Test using the score function
    rfecv = RFECV(estimator=SVC(kernel="linear"), step=1, cv=5)
    rfecv.fit(X, y)
    # non-regression test for missing worst feature:
    assert_equal(len(rfecv.grid_scores_), X.shape[1])
    assert_equal(len(rfecv.ranking_), X.shape[1])
    X_r = rfecv.transform(X)

    # All the noisy variable were filtered out
    assert_array_equal(X_r, iris.data)

    # same in sparse
    rfecv_sparse = RFECV(estimator=SVC(kernel="linear"), step=1, cv=5)
    X_sparse = sparse.csr_matrix(X)
    rfecv_sparse.fit(X_sparse, y)
    X_r_sparse = rfecv_sparse.transform(X_sparse)
    assert_array_equal(X_r_sparse.toarray(), iris.data)

    # Test using a customized loss function
    scoring = make_scorer(zero_one_loss, greater_is_better=False)
    rfecv = RFECV(estimator=SVC(kernel="linear"), step=1, cv=5,
                  scoring=scoring)
    ignore_warnings(rfecv.fit)(X, y)
    X_r = rfecv.transform(X)
    assert_array_equal(X_r, iris.data)

    # Test using a scorer
    scorer = get_scorer('accuracy')
    rfecv = RFECV(estimator=SVC(kernel="linear"), step=1, cv=5,
                  scoring=scorer)
    rfecv.fit(X, y)
    X_r = rfecv.transform(X)
    assert_array_equal(X_r, iris.data)

    # Test fix on grid_scores
    def test_scorer(estimator, X, y):
        return 1.0
    rfecv = RFECV(estimator=SVC(kernel="linear"), step=1, cv=5,
                  scoring=test_scorer)
    rfecv.fit(X, y)
    assert_array_equal(rfecv.grid_scores_, np.ones(len(rfecv.grid_scores_)))

    # Same as the first two tests, but with step=2
    rfecv = RFECV(estimator=SVC(kernel="linear"), step=2, cv=5)
    rfecv.fit(X, y)
    assert_equal(len(rfecv.grid_scores_), 6)
    assert_equal(len(rfecv.ranking_), X.shape[1])
    X_r = rfecv.transform(X)
    assert_array_equal(X_r, iris.data)

    rfecv_sparse = RFECV(estimator=SVC(kernel="linear"), step=2, cv=5)
    X_sparse = sparse.csr_matrix(X)
    rfecv_sparse.fit(X_sparse, y)
    X_r_sparse = rfecv_sparse.transform(X_sparse)
    assert_array_equal(X_r_sparse.toarray(), iris.data)