Python MultiOutputClassifier.predict方法代码示例

# 需要导入模块: from sklearn.multioutput import MultiOutputClassifier [as 别名]
# 或者: from sklearn.multioutput.MultiOutputClassifier import predict [as 别名]
def test_multi_output_classification_partial_fit():
    # test if multi_target initializes correctly with base estimator and fit
    # assert predictions work as expected for predict

    sgd_linear_clf = SGDClassifier(loss='log', random_state=1)
    multi_target_linear = MultiOutputClassifier(sgd_linear_clf)

    # train the multi_target_linear and also get the predictions.
    half_index = X.shape[0] // 2
    multi_target_linear.partial_fit(
        X[:half_index], y[:half_index], classes=classes)

    first_predictions = multi_target_linear.predict(X)
    assert_equal((n_samples, n_outputs), first_predictions.shape)

    multi_target_linear.partial_fit(X[half_index:], y[half_index:])
    second_predictions = multi_target_linear.predict(X)
    assert_equal((n_samples, n_outputs), second_predictions.shape)

    # train the linear classification with each column and assert that
    # predictions are equal after first partial_fit and second partial_fit
    for i in range(3):
        # create a clone with the same state
        sgd_linear_clf = clone(sgd_linear_clf)
        sgd_linear_clf.partial_fit(
            X[:half_index], y[:half_index, i], classes=classes[i])
        assert_array_equal(sgd_linear_clf.predict(X), first_predictions[:, i])
        sgd_linear_clf.partial_fit(X[half_index:], y[half_index:, i])
        assert_array_equal(sgd_linear_clf.predict(X), second_predictions[:, i])

# 需要导入模块: from sklearn.multioutput import MultiOutputClassifier [as 别名]
# 或者: from sklearn.multioutput.MultiOutputClassifier import predict [as 别名]
def test_multi_output_classification():
    # test if multi_target initializes correctly with base estimator and fit
    # assert predictions work as expected for predict, prodict_proba and score

    forest = RandomForestClassifier(n_estimators=10, random_state=1)
    multi_target_forest = MultiOutputClassifier(forest)

    # train the multi_target_forest and also get the predictions.
    multi_target_forest.fit(X, y)

    predictions = multi_target_forest.predict(X)
    assert_equal((n_samples, n_outputs), predictions.shape)

    predict_proba = multi_target_forest.predict_proba(X)

    assert len(predict_proba) == n_outputs
    for class_probabilities in predict_proba:
        assert_equal((n_samples, n_classes), class_probabilities.shape)

    assert_array_equal(np.argmax(np.dstack(predict_proba), axis=1),
                       predictions)

    # train the forest with each column and assert that predictions are equal
    for i in range(3):
        forest_ = clone(forest)  # create a clone with the same state
        forest_.fit(X, y[:, i])
        assert_equal(list(forest_.predict(X)), list(predictions[:, i]))
        assert_array_equal(list(forest_.predict_proba(X)),
                           list(predict_proba[i]))

# 需要导入模块: from sklearn.multioutput import MultiOutputClassifier [as 别名]
# 或者: from sklearn.multioutput.MultiOutputClassifier import predict [as 别名]
def test_multi_output_classification_partial_fit_sample_weights():
    # weighted classifier
    Xw = [[1, 2, 3], [4, 5, 6], [1.5, 2.5, 3.5]]
    yw = [[3, 2], [2, 3], [3, 2]]
    w = np.asarray([2., 1., 1.])
    sgd_linear_clf = SGDClassifier(random_state=1)
    clf_w = MultiOutputClassifier(sgd_linear_clf)
    clf_w.fit(Xw, yw, w)

    # unweighted, but with repeated samples
    X = [[1, 2, 3], [1, 2, 3], [4, 5, 6], [1.5, 2.5, 3.5]]
    y = [[3, 2], [3, 2], [2, 3], [3, 2]]
    sgd_linear_clf = SGDClassifier(random_state=1)
    clf = MultiOutputClassifier(sgd_linear_clf)
    clf.fit(X, y)
    X_test = [[1.5, 2.5, 3.5]]
    assert_array_almost_equal(clf.predict(X_test), clf_w.predict(X_test))

# 需要导入模块: from sklearn.multioutput import MultiOutputClassifier [as 别名]
# 或者: from sklearn.multioutput.MultiOutputClassifier import predict [as 别名]
def test_multi_output_classification_sample_weights():
    # weighted classifier
    Xw = [[1, 2, 3], [4, 5, 6]]
    yw = [[3, 2], [2, 3]]
    w = np.asarray([2., 1.])
    forest = RandomForestClassifier(n_estimators=10, random_state=1)
    clf_w = MultiOutputClassifier(forest)
    clf_w.fit(Xw, yw, w)

    # unweighted, but with repeated samples
    X = [[1, 2, 3], [1, 2, 3], [4, 5, 6]]
    y = [[3, 2], [3, 2], [2, 3]]
    forest = RandomForestClassifier(n_estimators=10, random_state=1)
    clf = MultiOutputClassifier(forest)
    clf.fit(X, y)

    X_test = [[1.5, 2.5, 3.5], [3.5, 4.5, 5.5]]
    assert_almost_equal(clf.predict(X_test), clf_w.predict(X_test))

# 需要导入模块: from sklearn.multioutput import MultiOutputClassifier [as 别名]
# 或者: from sklearn.multioutput.MultiOutputClassifier import predict [as 别名]
def test_multiclass_multioutput_estimator():
    # test to check meta of meta estimators
    svc = LinearSVC(random_state=0)
    multi_class_svc = OneVsRestClassifier(svc)
    multi_target_svc = MultiOutputClassifier(multi_class_svc)

    multi_target_svc.fit(X, y)

    predictions = multi_target_svc.predict(X)
    assert_equal((n_samples, n_outputs), predictions.shape)

    # train the forest with each column and assert that predictions are equal
    for i in range(3):
        multi_class_svc_ = clone(multi_class_svc)  # create a clone
        multi_class_svc_.fit(X, y[:, i])
        assert_equal(list(multi_class_svc_.predict(X)), list(predictions[:, i]))

# 需要导入模块: from sklearn.multioutput import MultiOutputClassifier [as 别名]
# 或者: from sklearn.multioutput.MultiOutputClassifier import predict [as 别名]
audios = np.unique(mfcc_audio["Audio"])
train_audio, test_audio = train_test_split(
    audios, train_size=0.7, test_size=0.3, random_state=0)

X_train = mfcc_audio[mfcc_audio["Audio"].isin(train_audio)]
X_test = mfcc_audio[mfcc_audio["Audio"].isin(test_audio)]
y_train = X_train[columns]
y_test = X_test[columns]

X_train.drop(columns + ["Audio"], inplace=True, axis=1)
X_test.drop(columns + ["Audio"], inplace=True, axis=1)

mor = MultiOutputClassifier(
    RandomForestClassifier(random_state=0, n_estimators=1000), n_jobs=-1)
mor.fit(X_train, y_train)
mor_pred = mor.predict(X_test)

dummy = DummyClassifier()
dummy.fit(X_train, y_train)
dummy_pred = dummy.predict(X_test)

estimators = mor.estimators_

for i, col in enumerate(columns):

    true = y_test[col]
    pred = mor_pred[:, i]
    d_p = dummy_pred[:, i]

    print(col)
    print("accuracy score")