Python sklearn.ensemble.BaggingClassifier() Examples

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(tol=1e-3),
                           DecisionTreeClassifier(),
                           KNeighborsClassifier(),
                           SVC(gamma="scale")]:
        for params in grid:
            BaggingClassifier(base_estimator=base_estimator,
                              random_state=rng,
                              **params).fit(X_train, y_train).predict(X_test) 

def test_warm_start(random_state=42):
    # Test if fitting incrementally with warm start gives a forest of the
    # right size and the same results as a normal fit.
    X, y = make_hastie_10_2(n_samples=20, random_state=1)

    clf_ws = None
    for n_estimators in [5, 10]:
        if clf_ws is None:
            clf_ws = BaggingClassifier(n_estimators=n_estimators,
                                       random_state=random_state,
                                       warm_start=True)
        else:
            clf_ws.set_params(n_estimators=n_estimators)
        clf_ws.fit(X, y)
        assert_equal(len(clf_ws), n_estimators)

    clf_no_ws = BaggingClassifier(n_estimators=10, random_state=random_state,
                                  warm_start=False)
    clf_no_ws.fit(X, y)

    assert_equal(set([tree.random_state for tree in clf_ws]),
                 set([tree.random_state for tree in clf_no_ws])) 

def test_warm_start_equal_n_estimators():
    # Test that nothing happens when fitting without increasing n_estimators
    X, y = make_hastie_10_2(n_samples=20, random_state=1)
    X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=43)

    clf = BaggingClassifier(n_estimators=5, warm_start=True, random_state=83)
    clf.fit(X_train, y_train)

    y_pred = clf.predict(X_test)
    # modify X to nonsense values, this should not change anything
    X_train += 1.

    assert_warns_message(UserWarning,
                         "Warm-start fitting without increasing n_estimators does not",
                         clf.fit, X_train, y_train)
    assert_array_equal(y_pred, clf.predict(X_test)) 

def test_warm_start_equivalence():
    # warm started classifier with 5+5 estimators should be equivalent to
    # one classifier with 10 estimators
    X, y = make_hastie_10_2(n_samples=20, random_state=1)
    X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=43)

    clf_ws = BaggingClassifier(n_estimators=5, warm_start=True,
                               random_state=3141)
    clf_ws.fit(X_train, y_train)
    clf_ws.set_params(n_estimators=10)
    clf_ws.fit(X_train, y_train)
    y1 = clf_ws.predict(X_test)

    clf = BaggingClassifier(n_estimators=10, warm_start=False,
                            random_state=3141)
    clf.fit(X_train, y_train)
    y2 = clf.predict(X_test)

    assert_array_almost_equal(y1, y2) 

def main():
    indata = np.load(inputs)
    training_data = indata['data_training']
    training_labels = indata['label_training']
    validation_data = indata['data_val']
    validation_labels = indata['label_val']
    ts = range(1,11)
    sampling_rates = [round(0.1*t, 1) for t in ts]
    forest_sizes = [10, 20, 50, 100]


    for sampling_rate in sampling_rates:
        legend_label = 'sampling rate='+str(sampling_rate)
        accuracy_results = []
        for forest_size in forest_sizes:
            rf_clf = ensemble.BaggingClassifier(n_estimators=forest_size, max_samples=sampling_rate)
            rf_clf.fit(training_data, training_labels)
            predictions = rf_clf.predict(validation_data)
            accuracy = metrics.accuracy_score(validation_labels, predictions)
            accuracy_results.append(accuracy)
        plt.plot(range(len(forest_sizes)), accuracy_results, label=legend_label)

    plt.xticks(range(len(forest_sizes)), forest_sizes, size='small')
    plt.legend()
    plt.show() 

def main():
	# prepare data
	trainingSet=[]
	testSet=[]
	accuracy = 0.0
	split = 0.25
	loadDataset('../Dataset/LDAdata.csv', split, trainingSet, testSet)
	print('Train set: ' + repr(len(trainingSet)))
	print('Test set: ' + repr(len(testSet)))
	trainData = np.array(trainingSet)[:,0:np.array(trainingSet).shape[1] - 1]
	columns = trainData.shape[1] 
	X = np.array(trainData)
	y = np.array(trainingSet)[:,columns]
	clf = BaggingClassifier(LDA())
	clf.fit(X, y)
	testData = np.array(testSet)[:,0:np.array(trainingSet).shape[1] - 1]
	X_test = np.array(testData)
	y_test = np.array(testSet)[:,columns]
	accuracy = clf.score(X_test,y_test)
	accuracy *= 100
	print("Accuracy %:",accuracy) 

def main():
	# prepare data
	trainingSet=[]
	testSet=[]
	accuracy = 0.0
	split = 0.25
	loadDataset('../Dataset/combined.csv', split, trainingSet, testSet)
	print 'Train set: ' + repr(len(trainingSet))
	print 'Test set: ' + repr(len(testSet))
	# generate predictions
	predictions=[]
	trainData = np.array(trainingSet)[:,0:np.array(trainingSet).shape[1] - 1]
  	columns = trainData.shape[1] 
	X = np.array(trainData)
	y = np.array(trainingSet)[:,columns]
	clf = BaggingClassifier(QDA())
	clf.fit(X, y)
	testData = np.array(testSet)[:,0:np.array(trainingSet).shape[1] - 1]
	X_test = np.array(testData)
	y_test = np.array(testSet)[:,columns]
	accuracy = clf.score(X_test,y_test)
	accuracy *= 100
	print("Accuracy %:",accuracy) 

def main():
	# prepare data
	trainingSet=[]
	testSet=[]
	accuracy = 0.0
	split = 0.25
	loadDataset('../Dataset/combined.csv', split, trainingSet, testSet)
	print 'Train set: ' + repr(len(trainingSet))
	print 'Test set: ' + repr(len(testSet))
	# generate predictions
	predictions=[]
	trainData = np.array(trainingSet)[:,0:np.array(trainingSet).shape[1] - 1]
  	columns = trainData.shape[1] 
	X = np.array(trainData)
	y = np.array(trainingSet)[:,columns]
	clf = BaggingClassifier(KNN(n_neighbors=10, weights='uniform', algorithm='auto', leaf_size=10, p=1, metric='minkowski', metric_params=None, n_jobs=1))
	clf.fit(X, y)
	testData = np.array(testSet)[:,0:np.array(trainingSet).shape[1] - 1]
	X_test = np.array(testData)
	y_test = np.array(testSet)[:,columns]
	accuracy = clf.score(X_test,y_test)
	accuracy *= 100
	print("Accuracy %:",accuracy) 

def main():
	# prepare data
	trainingSet=[]
	testSet=[]
	accuracy = 0.0
	split = 0.25
	loadDataset('../Dataset/combined.csv', split, trainingSet, testSet)
	print 'Train set: ' + repr(len(trainingSet))
	print 'Test set: ' + repr(len(testSet))
	# generate predictions
	predictions=[]
	trainData = np.array(trainingSet)[:,0:np.array(trainingSet).shape[1] - 1]
  	columns = trainData.shape[1] 
	X = np.array(trainData)
	y = np.array(trainingSet)[:,columns]
	clf = BaggingClassifier(SVC(C=1.0, kernel='linear', degree=5, gamma='auto', coef0=0.0, shrinking=True, probability=False,tol=0.001, cache_size=200, class_weight=None, verbose=False, max_iter=-1, random_state=None))
	clf.fit(X, y)
	testData = np.array(testSet)[:,0:np.array(trainingSet).shape[1] - 1]
	X_test = np.array(testData)
	y_test = np.array(testSet)[:,columns]
	accuracy = clf.score(X_test,y_test)
	accuracy *= 100
	print("Accuracy %:",accuracy) 

def __init__(self,
                 base_classifier=None,
                 n_classifiers=100,
                 combination_rule='majority_vote'):

        self.base_classifier = base_classifier
        self.n_classifiers = n_classifiers

        # using the sklearn implementation of bagging for now
        self.sk_bagging = BaggingClassifier(base_estimator=base_classifier,
                                            n_estimators=n_classifiers,
                                            max_samples=1.0,
                                            max_features=1.0)

        self.ensemble = Ensemble()
        self.combiner = Combiner(rule=combination_rule) 

def __init__(self,
                 base_classifier=None,
                 n_classifiers=100,
                 combination_rule='majority_vote'):

        self.base_classifier = base_classifier
        self.n_classifiers = n_classifiers

        # using the sklearn implementation of bagging for now
        self.sk_bagging = BaggingClassifier(base_estimator=base_classifier,
                                            n_estimators=n_classifiers,
                                            max_samples=1.0,
                                            max_features=1.0)

        self.ensemble = Ensemble()
        self.combiner = Combiner(rule=combination_rule) 

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(tol=1e-3),
                           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_warm_start(random_state=42):
    # Test if fitting incrementally with warm start gives a forest of the
    # right size and the same results as a normal fit.
    X, y = make_hastie_10_2(n_samples=20, random_state=1)

    clf_ws = None
    for n_estimators in [5, 10]:
        if clf_ws is None:
            clf_ws = BaggingClassifier(n_estimators=n_estimators,
                                       random_state=random_state,
                                       warm_start=True)
        else:
            clf_ws.set_params(n_estimators=n_estimators)
        clf_ws.fit(X, y)
        assert_equal(len(clf_ws), n_estimators)

    clf_no_ws = BaggingClassifier(n_estimators=10, random_state=random_state,
                                  warm_start=False)
    clf_no_ws.fit(X, y)

    assert_equal(set([tree.random_state for tree in clf_ws]),
                 set([tree.random_state for tree in clf_no_ws])) 

def test_warm_start_equal_n_estimators():
    # Test that nothing happens when fitting without increasing n_estimators
    X, y = make_hastie_10_2(n_samples=20, random_state=1)
    X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=43)

    clf = BaggingClassifier(n_estimators=5, warm_start=True, random_state=83)
    clf.fit(X_train, y_train)

    y_pred = clf.predict(X_test)
    # modify X to nonsense values, this should not change anything
    X_train += 1.

    assert_warns_message(UserWarning,
                         "Warm-start fitting without increasing n_estimators does not",
                         clf.fit, X_train, y_train)
    assert_array_equal(y_pred, clf.predict(X_test)) 

def test_warm_start_equivalence():
    # warm started classifier with 5+5 estimators should be equivalent to
    # one classifier with 10 estimators
    X, y = make_hastie_10_2(n_samples=20, random_state=1)
    X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=43)

    clf_ws = BaggingClassifier(n_estimators=5, warm_start=True,
                               random_state=3141)
    clf_ws.fit(X_train, y_train)
    clf_ws.set_params(n_estimators=10)
    clf_ws.fit(X_train, y_train)
    y1 = clf_ws.predict(X_test)

    clf = BaggingClassifier(n_estimators=10, warm_start=False,
                            random_state=3141)
    clf.fit(X_train, y_train)
    y2 = clf.predict(X_test)

    assert_array_almost_equal(y1, y2) 

def test_base():
    # Check BaseEnsemble methods.
    ensemble = BaggingClassifier(
        base_estimator=Perceptron(tol=1e-3, random_state=None), n_estimators=3)

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

    ensemble._make_estimator()
    random_state = np.random.RandomState(3)
    ensemble._make_estimator(random_state=random_state)
    ensemble._make_estimator(random_state=random_state)
    ensemble._make_estimator(append=False)

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

    assert isinstance(ensemble[0], Perceptron)
    assert_equal(ensemble[0].random_state, None)
    assert isinstance(ensemble[1].random_state, int)
    assert isinstance(ensemble[2].random_state, int)
    assert_not_equal(ensemble[1].random_state, ensemble[2].random_state)

    np_int_ensemble = BaggingClassifier(base_estimator=Perceptron(tol=1e-3),
                                        n_estimators=np.int32(3))
    np_int_ensemble.fit(iris.data, iris.target) 

def test_base_zero_n_estimators():
    # Check that instantiating a BaseEnsemble with n_estimators<=0 raises
    # a ValueError.
    ensemble = BaggingClassifier(base_estimator=Perceptron(tol=1e-3),
                                 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_base_not_int_n_estimators():
    # Check that instantiating a BaseEnsemble with a string as n_estimators
    # raises a ValueError demanding n_estimators to be supplied as an integer.
    string_ensemble = BaggingClassifier(base_estimator=Perceptron(tol=1e-3),
                                        n_estimators='3')
    iris = load_iris()
    assert_raise_message(ValueError,
                         "n_estimators must be an integer",
                         string_ensemble.fit, iris.data, iris.target)
    float_ensemble = BaggingClassifier(base_estimator=Perceptron(tol=1e-3),
                                       n_estimators=3.0)
    assert_raise_message(ValueError,
                         "n_estimators must be an integer",
                         float_ensemble.fit, iris.data, iris.target) 

def test_oob_score_classification():
    # Check that oob prediction is a good estimation of the generalization
    # error.
    rng = check_random_state(0)
    X_train, X_test, y_train, y_test = train_test_split(iris.data,
                                                        iris.target,
                                                        random_state=rng)

    for base_estimator in [DecisionTreeClassifier(), SVC(gamma="scale")]:
        clf = BaggingClassifier(base_estimator=base_estimator,
                                n_estimators=100,
                                bootstrap=True,
                                oob_score=True,
                                random_state=rng).fit(X_train, y_train)

        test_score = clf.score(X_test, y_test)

        assert_less(abs(test_score - clf.oob_score_), 0.1)

        # Test with few estimators
        assert_warns(UserWarning,
                     BaggingClassifier(base_estimator=base_estimator,
                                       n_estimators=1,
                                       bootstrap=True,
                                       oob_score=True,
                                       random_state=rng).fit,
                     X_train,
                     y_train) 

def test_error():
    # Test that it gives proper exception on deficient input.
    X, y = iris.data, iris.target
    base = DecisionTreeClassifier()

    # Test max_samples
    assert_raises(ValueError,
                  BaggingClassifier(base, max_samples=-1).fit, X, y)
    assert_raises(ValueError,
                  BaggingClassifier(base, max_samples=0.0).fit, X, y)
    assert_raises(ValueError,
                  BaggingClassifier(base, max_samples=2.0).fit, X, y)
    assert_raises(ValueError,
                  BaggingClassifier(base, max_samples=1000).fit, X, y)
    assert_raises(ValueError,
                  BaggingClassifier(base, max_samples="foobar").fit, X, y)

    # Test max_features
    assert_raises(ValueError,
                  BaggingClassifier(base, max_features=-1).fit, X, y)
    assert_raises(ValueError,
                  BaggingClassifier(base, max_features=0.0).fit, X, y)
    assert_raises(ValueError,
                  BaggingClassifier(base, max_features=2.0).fit, X, y)
    assert_raises(ValueError,
                  BaggingClassifier(base, max_features=5).fit, X, y)
    assert_raises(ValueError,
                  BaggingClassifier(base, max_features="foobar").fit, X, y)

    # Test support of decision_function
    assert not hasattr(BaggingClassifier(base).fit(X, y), 'decision_function') 

def test_gridsearch():
    # Check that bagging ensembles can be grid-searched.
    # Transform iris into a binary classification task
    X, y = iris.data, iris.target
    y[y == 2] = 1

    # Grid search with scoring based on decision_function
    parameters = {'n_estimators': (1, 2),
                  'base_estimator__C': (1, 2)}

    GridSearchCV(BaggingClassifier(SVC(gamma="scale")),
                 parameters,
                 scoring="roc_auc").fit(X, y) 

def test_bagging_sample_weight_unsupported_but_passed():
    estimator = BaggingClassifier(DummyZeroEstimator())
    rng = check_random_state(0)

    estimator.fit(iris.data, iris.target).predict(iris.data)
    assert_raises(ValueError, estimator.fit, iris.data, iris.target,
                  sample_weight=rng.randint(10, size=(iris.data.shape[0]))) 

def test_warm_start_smaller_n_estimators():
    # Test if warm start'ed second fit with smaller n_estimators raises error.
    X, y = make_hastie_10_2(n_samples=20, random_state=1)
    clf = BaggingClassifier(n_estimators=5, warm_start=True)
    clf.fit(X, y)
    clf.set_params(n_estimators=4)
    assert_raises(ValueError, clf.fit, X, y) 

def test_oob_score_removed_on_warm_start():
    X, y = make_hastie_10_2(n_samples=2000, random_state=1)

    clf = BaggingClassifier(n_estimators=50, oob_score=True)
    clf.fit(X, y)

    clf.set_params(warm_start=True, oob_score=False, n_estimators=100)
    clf.fit(X, y)

    assert_raises(AttributeError, getattr, clf, "oob_score_") 

def test_oob_score_consistency():
    # Make sure OOB scores are identical when random_state, estimator, and
    # training data are fixed and fitting is done twice
    X, y = make_hastie_10_2(n_samples=200, random_state=1)
    bagging = BaggingClassifier(KNeighborsClassifier(), max_samples=0.5,
                                max_features=0.5, oob_score=True,
                                random_state=1)
    assert_equal(bagging.fit(X, y).oob_score_, bagging.fit(X, y).oob_score_) 

def test_estimators_samples():
    # Check that format of estimators_samples_ is correct and that results
    # generated at fit time can be identically reproduced at a later time
    # using data saved in object attributes.
    X, y = make_hastie_10_2(n_samples=200, random_state=1)
    bagging = BaggingClassifier(LogisticRegression(), max_samples=0.5,
                                max_features=0.5, random_state=1,
                                bootstrap=False)
    bagging.fit(X, y)

    # Get relevant attributes
    estimators_samples = bagging.estimators_samples_
    estimators_features = bagging.estimators_features_
    estimators = bagging.estimators_

    # Test for correct formatting
    assert_equal(len(estimators_samples), len(estimators))
    assert_equal(len(estimators_samples[0]), len(X) // 2)
    assert_equal(estimators_samples[0].dtype.kind, 'i')

    # Re-fit single estimator to test for consistent sampling
    estimator_index = 0
    estimator_samples = estimators_samples[estimator_index]
    estimator_features = estimators_features[estimator_index]
    estimator = estimators[estimator_index]

    X_train = (X[estimator_samples])[:, estimator_features]
    y_train = y[estimator_samples]

    orig_coefs = estimator.coef_
    estimator.fit(X_train, y_train)
    new_coefs = estimator.coef_

    assert_array_almost_equal(orig_coefs, new_coefs) 

def test_estimators_samples_deterministic():
    # This test is a regression test to check that with a random step
    # (e.g. SparseRandomProjection) and a given random state, the results
    # generated at fit time can be identically reproduced at a later time using
    # data saved in object attributes. Check issue #9524 for full discussion.

    iris = load_iris()
    X, y = iris.data, iris.target

    base_pipeline = make_pipeline(SparseRandomProjection(n_components=2),
                                  LogisticRegression())
    clf = BaggingClassifier(base_estimator=base_pipeline,
                            max_samples=0.5,
                            random_state=0)
    clf.fit(X, y)
    pipeline_estimator_coef = clf.estimators_[0].steps[-1][1].coef_.copy()

    estimator = clf.estimators_[0]
    estimator_sample = clf.estimators_samples_[0]
    estimator_feature = clf.estimators_features_[0]

    X_train = (X[estimator_sample])[:, estimator_feature]
    y_train = y[estimator_sample]

    estimator.fit(X_train, y_train)
    assert_array_equal(estimator.steps[-1][1].coef_, pipeline_estimator_coef) 

def test_max_samples_consistency():
    # Make sure validated max_samples and original max_samples are identical
    # when valid integer max_samples supplied by user
    max_samples = 100
    X, y = make_hastie_10_2(n_samples=2*max_samples, random_state=1)
    bagging = BaggingClassifier(KNeighborsClassifier(),
                                max_samples=max_samples,
                                max_features=0.5, random_state=1)
    bagging.fit(X, y)
    assert_equal(bagging._max_samples, max_samples) 

def test_bagging_classifier_with_missing_inputs():
    # Check that BaggingClassifier can accept X with missing/infinite data
    X = np.array([
        [1, 3, 5],
        [2, None, 6],
        [2, np.nan, 6],
        [2, np.inf, 6],
        [2, np.NINF, 6],
    ])
    y = np.array([3, 6, 6, 6, 6])
    classifier = DecisionTreeClassifier()
    pipeline = make_pipeline(
        FunctionTransformer(replace, validate=False),
        classifier
    )
    pipeline.fit(X, y).predict(X)
    bagging_classifier = BaggingClassifier(pipeline)
    bagging_classifier.fit(X, y)
    y_hat = bagging_classifier.predict(X)
    assert_equal(y.shape, y_hat.shape)
    bagging_classifier.predict_log_proba(X)
    bagging_classifier.predict_proba(X)

    # Verify that exceptions can be raised by wrapper classifier
    classifier = DecisionTreeClassifier()
    pipeline = make_pipeline(classifier)
    assert_raises(ValueError, pipeline.fit, X, y)
    bagging_classifier = BaggingClassifier(pipeline)
    assert_raises(ValueError, bagging_classifier.fit, X, y) 

def test_bagging_small_max_features():
    # Check that Bagging estimator can accept low fractional max_features

    X = np.array([[1, 2], [3, 4]])
    y = np.array([1, 0])

    bagging = BaggingClassifier(LogisticRegression(),
                                max_features=0.3, random_state=1)
    bagging.fit(X, y)