Python ensemble.GradientBoostingClassifier方法代码示例

# 需要导入模块: from sklearn import ensemble [as 别名]
# 或者: from sklearn.ensemble import GradientBoostingClassifier [as 别名]
def search_cv(x_train, y_train, x_test, y_test, model=GradientBoostingClassifier(n_estimators=30)):
    # grid search找到最好的参数
    parameters = {'kernel': ('linear', 'rbf'), 'C': [1, 2, 4], 'gamma': [0.125, 0.25, 0.5, 1, 2, 4]}
    clf = GridSearchCV(model, param_grid=parameters)
    grid_search = clf.fit(x_train, y_train)
    # 对结果打分
    print("Best score: %0.3f" % grid_search.best_score_)
    print(grid_search.best_estimator_)

    # best prarams
    print('best prarams:', clf.best_params_)

    print('-----grid search end------------')
    print('on all train set')
    scores = cross_val_score(grid_search.best_estimator_, x_train, y_train, cv=3, scoring='accuracy')
    print(scores.mean(), scores)
    print('on test set')
    scores = cross_val_score(grid_search.best_estimator_, x_test, y_test, cv=3, scoring='accuracy')
    print(scores.mean(), scores) 

# 需要导入模块: from sklearn import ensemble [as 别名]
# 或者: from sklearn.ensemble import GradientBoostingClassifier [as 别名]
def Train(data, modelcount, censhu, yanzhgdata):
    model = GradientBoostingClassifier(loss='deviance', n_estimators=modelcount, max_depth=censhu, learning_rate=0.1, max_features='sqrt')

    model.fit(data[:, :-1], data[:, -1])
    # 给出训练数据的预测值
    train_out = model.predict(data[:, :-1])
    # 计算MSE
    train_mse = fmse(data[:, -1], train_out)[0]

    # 给出验证数据的预测值
    add_yan = model.predict(yanzhgdata[:, :-1])
    # 计算f1度量
    add_mse = fmse(yanzhgdata[:, -1], add_yan)[0]
    print(train_mse, add_mse)
    return train_mse, add_mse

# 最终确定组合的函数 

# 需要导入模块: from sklearn import ensemble [as 别名]
# 或者: from sklearn.ensemble import GradientBoostingClassifier [as 别名]
def recspre(estrs, predata, datadict, zhe):

    mo, ze = estrs.split('-')
    model = GradientBoostingClassifier(loss='deviance', n_estimators=int(mo), max_depth=int(ze), learning_rate=0.1)

    model.fit(datadict[zhe]['train'][:, :-1], datadict[zhe]['train'][:, -1])

    # 预测
    yucede = model.predict(predata[:, :-1])
    # 计算混淆矩阵

    print(ConfuseMatrix(predata[:, -1], yucede))

    return fmse(predata[:, -1], yucede)

# 主函数 

# 需要导入模块: from sklearn import ensemble [as 别名]
# 或者: from sklearn.ensemble import GradientBoostingClassifier [as 别名]
def check_classification_synthetic(presort, loss):
    # Test GradientBoostingClassifier on synthetic dataset used by
    # Hastie et al. in ESLII Example 12.7.
    X, y = datasets.make_hastie_10_2(n_samples=12000, random_state=1)

    X_train, X_test = X[:2000], X[2000:]
    y_train, y_test = y[:2000], y[2000:]

    gbrt = GradientBoostingClassifier(n_estimators=100, min_samples_split=2,
                                      max_depth=1, loss=loss,
                                      learning_rate=1.0, random_state=0)
    gbrt.fit(X_train, y_train)
    error_rate = (1.0 - gbrt.score(X_test, y_test))
    assert_less(error_rate, 0.09)

    gbrt = GradientBoostingClassifier(n_estimators=200, min_samples_split=2,
                                      max_depth=1, loss=loss,
                                      learning_rate=1.0, subsample=0.5,
                                      random_state=0,
                                      presort=presort)
    gbrt.fit(X_train, y_train)
    error_rate = (1.0 - gbrt.score(X_test, y_test))
    assert_less(error_rate, 0.08) 

# 需要导入模块: from sklearn import ensemble [as 别名]
# 或者: from sklearn.ensemble import GradientBoostingClassifier [as 别名]
def test_probability_log():
    # Predict probabilities.
    clf = GradientBoostingClassifier(n_estimators=100, random_state=1)

    assert_raises(ValueError, clf.predict_proba, T)

    clf.fit(X, y)
    assert_array_equal(clf.predict(T), true_result)

    # check if probabilities are in [0, 1].
    y_proba = clf.predict_proba(T)
    assert np.all(y_proba >= 0.0)
    assert np.all(y_proba <= 1.0)

    # derive predictions from probabilities
    y_pred = clf.classes_.take(y_proba.argmax(axis=1), axis=0)
    assert_array_equal(y_pred, true_result) 

# 需要导入模块: from sklearn import ensemble [as 别名]
# 或者: from sklearn.ensemble import GradientBoostingClassifier [as 别名]
def test_check_inputs_predict_stages():
    # check that predict_stages through an error if the type of X is not
    # supported
    x, y = datasets.make_hastie_10_2(n_samples=100, random_state=1)
    x_sparse_csc = csc_matrix(x)
    clf = GradientBoostingClassifier(n_estimators=100, random_state=1)
    clf.fit(x, y)
    score = np.zeros((y.shape)).reshape(-1, 1)
    assert_raise_message(ValueError,
                         "When X is a sparse matrix, a CSR format is expected",
                         predict_stages, clf.estimators_, x_sparse_csc,
                         clf.learning_rate, score)
    x_fortran = np.asfortranarray(x)
    assert_raise_message(ValueError,
                         "X should be C-ordered np.ndarray",
                         predict_stages, clf.estimators_, x_fortran,
                         clf.learning_rate, score) 

# 需要导入模块: from sklearn import ensemble [as 别名]
# 或者: from sklearn.ensemble import GradientBoostingClassifier [as 别名]
def test_serialization():
    # Check model serialization.
    clf = GradientBoostingClassifier(n_estimators=100, random_state=1)

    clf.fit(X, y)
    assert_array_equal(clf.predict(T), true_result)
    assert_equal(100, len(clf.estimators_))

    try:
        import cPickle as pickle
    except ImportError:
        import pickle

    serialized_clf = pickle.dumps(clf, protocol=pickle.HIGHEST_PROTOCOL)
    clf = None
    clf = pickle.loads(serialized_clf)
    assert_array_equal(clf.predict(T), true_result)
    assert_equal(100, len(clf.estimators_)) 

# 需要导入模块: from sklearn import ensemble [as 别名]
# 或者: from sklearn.ensemble import GradientBoostingClassifier [as 别名]
def test_verbose_output():
    # Check verbose=1 does not cause error.
    from io import StringIO

    import sys
    old_stdout = sys.stdout
    sys.stdout = StringIO()
    clf = GradientBoostingClassifier(n_estimators=100, random_state=1,
                                     verbose=1, subsample=0.8)
    clf.fit(X, y)
    verbose_output = sys.stdout
    sys.stdout = old_stdout

    # check output
    verbose_output.seek(0)
    header = verbose_output.readline().rstrip()
    # with OOB
    true_header = ' '.join(['%10s'] + ['%16s'] * 3) % (
        'Iter', 'Train Loss', 'OOB Improve', 'Remaining Time')
    assert_equal(true_header, header)

    n_lines = sum(1 for l in verbose_output.readlines())
    # one for 1-10 and then 9 for 20-100
    assert_equal(10 + 9, n_lines) 

# 需要导入模块: from sklearn import ensemble [as 别名]
# 或者: from sklearn.ensemble import GradientBoostingClassifier [as 别名]
def test_more_verbose_output():
    # Check verbose=2 does not cause error.
    from io import StringIO
    import sys
    old_stdout = sys.stdout
    sys.stdout = StringIO()
    clf = GradientBoostingClassifier(n_estimators=100, random_state=1,
                                     verbose=2)
    clf.fit(X, y)
    verbose_output = sys.stdout
    sys.stdout = old_stdout

    # check output
    verbose_output.seek(0)
    header = verbose_output.readline().rstrip()
    # no OOB
    true_header = ' '.join(['%10s'] + ['%16s'] * 2) % (
        'Iter', 'Train Loss', 'Remaining Time')
    assert_equal(true_header, header)

    n_lines = sum(1 for l in verbose_output.readlines())
    # 100 lines for n_estimators==100
    assert_equal(100, n_lines) 

# 需要导入模块: from sklearn import ensemble [as 别名]
# 或者: from sklearn.ensemble import GradientBoostingClassifier [as 别名]
def test_zero_estimator_clf():
    # Test if init='zero' works for classification.
    X = iris.data
    y = np.array(iris.target)

    est = GradientBoostingClassifier(n_estimators=20, max_depth=1,
                                     random_state=1, init='zero')
    est.fit(X, y)

    assert_greater(est.score(X, y), 0.96)

    # binary clf
    mask = y != 0
    y[mask] = 1
    y[~mask] = 0
    est = GradientBoostingClassifier(n_estimators=20, max_depth=1,
                                     random_state=1, init='zero')
    est.fit(X, y)
    assert_greater(est.score(X, y), 0.96)

    est = GradientBoostingClassifier(n_estimators=20, max_depth=1,
                                     random_state=1, init='foobar')
    assert_raises(ValueError, est.fit, X, y) 

# 需要导入模块: from sklearn import ensemble [as 别名]
# 或者: from sklearn.ensemble import GradientBoostingClassifier [as 别名]
def test_probability_exponential():
    # Predict probabilities.
    clf = GradientBoostingClassifier(loss='exponential',
                                     n_estimators=100, random_state=1)

    assert_raises(ValueError, clf.predict_proba, T)

    clf.fit(X, y)
    assert_array_equal(clf.predict(T), true_result)

    # check if probabilities are in [0, 1].
    y_proba = clf.predict_proba(T)
    assert np.all(y_proba >= 0.0)
    assert np.all(y_proba <= 1.0)
    score = clf.decision_function(T).ravel()
    assert_array_almost_equal(y_proba[:, 1], expit(2 * score))

    # derive predictions from probabilities
    y_pred = clf.classes_.take(y_proba.argmax(axis=1), axis=0)
    assert_array_equal(y_pred, true_result) 

# 需要导入模块: from sklearn import ensemble [as 别名]
# 或者: from sklearn.ensemble import GradientBoostingClassifier [as 别名]
def test_early_stopping_n_classes():
    # when doing early stopping (_, , y_train, _ = train_test_split(X, y))
    # there might be classes in y that are missing in y_train. As the init
    # estimator will be trained on y_train, we need to raise an error if this
    # happens.

    X = [[1]] * 10
    y = [0, 0] + [1] * 8  # only 2 negative class over 10 samples
    gb = GradientBoostingClassifier(n_iter_no_change=5, random_state=0,
                                    validation_fraction=8)
    with pytest.raises(
                ValueError,
                match='The training data after the early stopping split'):
        gb.fit(X, y)

    # No error if we let training data be big enough
    gb = GradientBoostingClassifier(n_iter_no_change=5, random_state=0,
                                    validation_fraction=4) 

# 需要导入模块: from sklearn import ensemble [as 别名]
# 或者: from sklearn.ensemble import GradientBoostingClassifier [as 别名]
def test_recursion_decision_function(target_feature):
    # Make sure the recursion method (implicitly uses decision_function) has
    # the same result as using brute method with
    # response_method=decision_function

    X, y = make_classification(n_classes=2, n_clusters_per_class=1,
                               random_state=1)
    assert np.mean(y) == .5  # make sure the init estimator predicts 0 anyway

    est = GradientBoostingClassifier(random_state=0, loss='deviance')
    est.fit(X, y)

    preds_1, _ = partial_dependence(est, X, [target_feature],
                                    response_method='decision_function',
                                    method='recursion')
    preds_2, _ = partial_dependence(est, X, [target_feature],
                                    response_method='decision_function',
                                    method='brute')

    assert_allclose(preds_1, preds_2, atol=1e-7) 

# 需要导入模块: from sklearn import ensemble [as 别名]
# 或者: from sklearn.ensemble import GradientBoostingClassifier [as 别名]
def test_warning_recursion_non_constant_init():
    # make sure that passing a non-constant init parameter to a GBDT and using
    # recursion method yields a warning.

    gbc = GradientBoostingClassifier(init=DummyClassifier(), random_state=0)
    gbc.fit(X, y)

    with pytest.warns(
            UserWarning,
            match='Using recursion method with a non-constant init predictor'):
        partial_dependence(gbc, X, [0], method='recursion')

    with pytest.warns(
            UserWarning,
            match='Using recursion method with a non-constant init predictor'):
        partial_dependence(gbc, X, [0], method='recursion') 

# 需要导入模块: from sklearn import ensemble [as 别名]
# 或者: from sklearn.ensemble import GradientBoostingClassifier [as 别名]
def setUpClass(self):
        """
        Set up the unit test by loading the dataset and training a model.
        """
        from sklearn.datasets import load_boston
        import numpy as np

        scikit_data = load_boston()
        scikit_model = GradientBoostingClassifier(random_state=1)
        t = scikit_data.target
        target = np.digitize(t, np.histogram(t)[1]) - 1
        scikit_model.fit(scikit_data.data, target)
        self.target = target

        # Save the data and the model
        self.scikit_data = scikit_data
        self.scikit_model = scikit_model