Python ensemble.IsolationForest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 IsolationForest [as 别名]
def __init__(self, hybrid=False, n_estimators=100, max_samples='auto', contamination=0.1, n_jobs=-1, seed=None,
                 **kwargs):
        """Init Isolation Forest instance."""
        self.n_estimators = n_estimators
        self.max_samples = max_samples
        self.contamination = contamination
        self.n_jobs = n_jobs
        self.seed = seed

        self.model = IsolationForest(n_estimators=n_estimators, max_samples=max_samples, contamination=contamination,
                                     n_jobs=n_jobs, random_state=seed, **kwargs)

        self.hybrid = hybrid
        self.ae_net = None  # autoencoder network for the case of a hybrid model

        self.results = {
            'train_time': None,
            'test_time': None,
            'test_auc': None,
            'test_scores': None
        } 

# 需要导入模块: from sklearn import ensemble [as 别名]
# 或者: from sklearn.ensemble import IsolationForest [as 别名]
def test_iforest_sparse():
    """Check IForest for various parameter settings on sparse input."""
    rng = check_random_state(0)
    X_train, X_test, y_train, y_test = train_test_split(boston.data[:50],
                                                        boston.target[:50],
                                                        random_state=rng)
    grid = ParameterGrid({"max_samples": [0.5, 1.0],
                          "bootstrap": [True, False]})

    for sparse_format in [csc_matrix, csr_matrix]:
        X_train_sparse = sparse_format(X_train)
        X_test_sparse = sparse_format(X_test)

        for params in grid:
            # Trained on sparse format
            sparse_classifier = IsolationForest(
                n_estimators=10, random_state=1, **params).fit(X_train_sparse)
            sparse_results = sparse_classifier.predict(X_test_sparse)

            # Trained on dense format
            dense_classifier = IsolationForest(
                n_estimators=10, random_state=1, **params).fit(X_train)
            dense_results = dense_classifier.predict(X_test)

            assert_array_equal(sparse_results, dense_results) 

# 需要导入模块: from sklearn import ensemble [as 别名]
# 或者: from sklearn.ensemble import IsolationForest [as 别名]
def test_iforest_performance():
    """Test Isolation Forest performs well"""

    # Generate train/test data
    rng = check_random_state(2)
    X = 0.3 * rng.randn(120, 2)
    X_train = np.r_[X + 2, X - 2]
    X_train = X[:100]

    # Generate some abnormal novel observations
    X_outliers = rng.uniform(low=-4, high=4, size=(20, 2))
    X_test = np.r_[X[100:], X_outliers]
    y_test = np.array([0] * 20 + [1] * 20)

    # fit the model
    clf = IsolationForest(max_samples=100, random_state=rng).fit(X_train)

    # predict scores (the lower, the more normal)
    y_pred = - clf.decision_function(X_test)

    # check that there is at most 6 errors (false positive or false negative)
    assert_greater(roc_auc_score(y_test, y_pred), 0.98) 

# 需要导入模块: from sklearn import ensemble [as 别名]
# 或者: from sklearn.ensemble import IsolationForest [as 别名]
def test_deprecation():
    X = [[0.0], [1.0]]
    clf = IsolationForest()

    assert_warns_message(FutureWarning,
                         'default contamination parameter 0.1 will change '
                         'in version 0.22 to "auto"',
                         clf.fit, X)

    assert_warns_message(FutureWarning,
                         'behaviour="old" is deprecated and will be removed '
                         'in version 0.22',
                         clf.fit, X)

    clf = IsolationForest().fit(X)
    assert_warns_message(DeprecationWarning,
                         "threshold_ attribute is deprecated in 0.20 and will"
                         " be removed in 0.22.",
                         getattr, clf, "threshold_") 

# 需要导入模块: from sklearn import ensemble [as 别名]
# 或者: from sklearn.ensemble import IsolationForest [as 别名]
def sample_hyps_iso_forest(nest, contam, boot):
    """

    :param nest:
    :param contam:
    :param boot:
    :return: An IsolationForest object with specified hyperparameters, used to detect anomaly.
    """

    n_estimators = nest # random.choice(range(20, 300))  # default is 100
    max_samples = 'auto'
    contamination = contam #randrange_float(0.0, 0.5, 0.05)
    max_features = 1.0 # default is 1.0 (use all features)
    bootstrap = boot # random.choice(['True', 'False'])
    n_jobs = -1  # Uses all cores
    verbose = 0

    model = IsolationForest(n_estimators=n_estimators, max_samples=max_samples,
                            contamination=contamination, max_features=max_features,
                            bootstrap=bootstrap, n_jobs=n_jobs, verbose=verbose)
    return model 

# 需要导入模块: from sklearn import ensemble [as 别名]
# 或者: from sklearn.ensemble import IsolationForest [as 别名]
def run_isolation_forest(features, id_list, fraction_of_outliers=.3):
    """Performs anomaly detection based on Isolation Forest."""

    rng = np.random.RandomState(1984)

    num_samples = features.shape[0]
    iso_f = IsolationForest(max_samples=num_samples,
                            contamination=fraction_of_outliers,
                            random_state=rng)
    iso_f.fit(features)
    pred_scores = iso_f.decision_function(features)

    threshold = stats.scoreatpercentile(pred_scores, 100 * fraction_of_outliers)
    outlying_ids = id_list[pred_scores < threshold]

    return outlying_ids 

# 需要导入模块: from sklearn import ensemble [as 别名]
# 或者: from sklearn.ensemble import IsolationForest [as 别名]
def test_iforest_error():
    """Test that it gives proper exception on deficient input."""
    X = iris.data

    # Test max_samples
    assert_raises(ValueError,
                  IsolationForest(max_samples=-1).fit, X)
    assert_raises(ValueError,
                  IsolationForest(max_samples=0.0).fit, X)
    assert_raises(ValueError,
                  IsolationForest(max_samples=2.0).fit, X)
    # The dataset has less than 256 samples, explicitly setting
    # max_samples > n_samples should result in a warning. If not set
    # explicitly there should be no warning
    assert_warns_message(UserWarning,
                         "max_samples will be set to n_samples for estimation",
                         IsolationForest(max_samples=1000).fit, X)
    assert_no_warnings(IsolationForest(max_samples='auto').fit, X)
    assert_no_warnings(IsolationForest(max_samples=np.int64(2)).fit, X)
    assert_raises(ValueError, IsolationForest(max_samples='foobar').fit, X)
    assert_raises(ValueError, IsolationForest(max_samples=1.5).fit, X) 

# 需要导入模块: from sklearn import ensemble [as 别名]
# 或者: from sklearn.ensemble import IsolationForest [as 别名]
def __init__(self, _id, _config):
        super(IsolationForest, self).__init__(_id, _config)
        self._nb_samples = int(_config['nb_samples']) 

# 需要导入模块: from sklearn import ensemble [as 别名]
# 或者: from sklearn.ensemble import IsolationForest [as 别名]
def get_default_config():
        return {
            'module': IsolationForest.__name__,
            'nb_samples': N_SAMPLES
        } 

# 需要导入模块: from sklearn import ensemble [as 别名]
# 或者: from sklearn.ensemble import IsolationForest [as 别名]
def _get_best_detector(self, train):
        detector = ensemble.IsolationForest()
        detector.fit(train)
        return detector 

# 需要导入模块: from sklearn import ensemble [as 别名]
# 或者: from sklearn.ensemble import IsolationForest [as 别名]
def setUp(self):
        super(TestIsolationForest, self).setUp()
        self.if_sml = isolation_forest.IsolationForest(
            "fakeid", {"module": "fake", "nb_samples": 1000}) 

# 需要导入模块: from sklearn import ensemble [as 别名]
# 或者: from sklearn.ensemble import IsolationForest [as 别名]
def test_learn_structure(self):
        data = self.get_testing_data()
        clf = self.if_sml.learn_structure(data)
        self.assertIsInstance(clf, ensemble.IsolationForest) 

# 需要导入模块: from sklearn import ensemble [as 别名]
# 或者: from sklearn.ensemble import IsolationForest [as 别名]
def test_iforest():
    """Check Isolation Forest for various parameter settings."""
    X_train = np.array([[0, 1], [1, 2]])
    X_test = np.array([[2, 1], [1, 1]])

    grid = ParameterGrid({"n_estimators": [3],
                          "max_samples": [0.5, 1.0, 3],
                          "bootstrap": [True, False]})

    with ignore_warnings():
        for params in grid:
            IsolationForest(random_state=rng,
                            **params).fit(X_train).predict(X_test) 

# 需要导入模块: from sklearn import ensemble [as 别名]
# 或者: from sklearn.ensemble import IsolationForest [as 别名]
def test_iforest_error():
    """Test that it gives proper exception on deficient input."""
    X = iris.data

    # Test max_samples
    assert_raises(ValueError,
                  IsolationForest(max_samples=-1).fit, X)
    assert_raises(ValueError,
                  IsolationForest(max_samples=0.0).fit, X)
    assert_raises(ValueError,
                  IsolationForest(max_samples=2.0).fit, X)
    # The dataset has less than 256 samples, explicitly setting
    # max_samples > n_samples should result in a warning. If not set
    # explicitly there should be no warning
    assert_warns_message(UserWarning,
                         "max_samples will be set to n_samples for estimation",
                         IsolationForest(max_samples=1000).fit, X)
    # note that assert_no_warnings does not apply since it enables a
    # PendingDeprecationWarning triggered by scipy.sparse's use of
    # np.matrix. See issue #11251.
    with pytest.warns(None) as record:
        IsolationForest(max_samples='auto').fit(X)
    user_warnings = [each for each in record
                     if issubclass(each.category, UserWarning)]
    assert len(user_warnings) == 0
    with pytest.warns(None) as record:
        IsolationForest(max_samples=np.int64(2)).fit(X)
    user_warnings = [each for each in record
                     if issubclass(each.category, UserWarning)]
    assert len(user_warnings) == 0

    assert_raises(ValueError, IsolationForest(max_samples='foobar').fit, X)
    assert_raises(ValueError, IsolationForest(max_samples=1.5).fit, X)

    # test X_test n_features match X_train one:
    assert_raises(ValueError, IsolationForest().fit(X).predict, X[:, 1:])

    # test threshold_ attribute error when behaviour is not old:
    msg = "threshold_ attribute does not exist when behaviour != 'old'"
    assert_raises_regex(AttributeError, msg, getattr,
                        IsolationForest(behaviour='new'), 'threshold_') 

# 需要导入模块: from sklearn import ensemble [as 别名]
# 或者: from sklearn.ensemble import IsolationForest [as 别名]
def test_recalculate_max_depth():
    """Check max_depth recalculation when max_samples is reset to n_samples"""
    X = iris.data
    clf = IsolationForest().fit(X)
    for est in clf.estimators_:
        assert_equal(est.max_depth, int(np.ceil(np.log2(X.shape[0]))))