Python SMOTEENN.fit_resample方法代码示例

# 需要导入模块: from imblearn.combine import SMOTEENN [as 别名]
# 或者: from imblearn.combine.SMOTEENN import fit_resample [as 别名]
def test_error_wrong_object():
    smote = 'rnd'
    enn = 'rnd'
    smt = SMOTEENN(smote=smote, random_state=RND_SEED)
    with raises(ValueError, match="smote needs to be a SMOTE"):
        smt.fit_resample(X, Y)
    smt = SMOTEENN(enn=enn, random_state=RND_SEED)
    with raises(ValueError, match="enn needs to be an "):
        smt.fit_resample(X, Y)

# 需要导入模块: from imblearn.combine import SMOTEENN [as 别名]
# 或者: from imblearn.combine.SMOTEENN import fit_resample [as 别名]
def test_validate_estimator_default():
    smt = SMOTEENN(random_state=RND_SEED)
    X_resampled, y_resampled = smt.fit_resample(X, Y)
    X_gt = np.array([[1.52091956, -0.49283504], [0.84976473, -0.15570176], [
        0.61319159, -0.11571667
    ], [0.66052536, -0.28246518], [-0.28162401, -2.10400981],
                     [0.83680821, 1.72827342], [0.08711622, 0.93259929]])
    y_gt = np.array([0, 0, 0, 0, 1, 1, 1])
    assert_allclose(X_resampled, X_gt, rtol=R_TOL)
    assert_array_equal(y_resampled, y_gt)

# 需要导入模块: from imblearn.combine import SMOTEENN [as 别名]
# 或者: from imblearn.combine.SMOTEENN import fit_resample [as 别名]
def test_sample_regular_half():
    sampling_strategy = {0: 10, 1: 12}
    smote = SMOTEENN(
        sampling_strategy=sampling_strategy, random_state=RND_SEED)
    X_resampled, y_resampled = smote.fit_resample(X, Y)

    X_gt = np.array([[1.52091956, -0.49283504], [-0.28162401, -2.10400981],
                     [0.83680821, 1.72827342], [0.08711622, 0.93259929]])
    y_gt = np.array([0, 1, 1, 1])
    assert_allclose(X_resampled, X_gt)
    assert_array_equal(y_resampled, y_gt)

# 需要导入模块: from imblearn.combine import SMOTEENN [as 别名]
# 或者: from imblearn.combine.SMOTEENN import fit_resample [as 别名]
def test_validate_estimator_init():
    smote = SMOTE(random_state=RND_SEED)
    enn = EditedNearestNeighbours(sampling_strategy='all')
    smt = SMOTEENN(smote=smote, enn=enn, random_state=RND_SEED)
    X_resampled, y_resampled = smt.fit_resample(X, Y)
    X_gt = np.array([[1.52091956, -0.49283504], [0.84976473, -0.15570176], [
        0.61319159, -0.11571667
    ], [0.66052536, -0.28246518], [-0.28162401, -2.10400981],
                     [0.83680821, 1.72827342], [0.08711622, 0.93259929]])
    y_gt = np.array([0, 0, 0, 0, 1, 1, 1])
    assert_allclose(X_resampled, X_gt, rtol=R_TOL)
    assert_array_equal(y_resampled, y_gt)

# 需要导入模块: from imblearn.combine import SMOTEENN [as 别名]
# 或者: from imblearn.combine.SMOTEENN import fit_resample [as 别名]
def train_decisiontree_with(configurationname, train_data, k, score_function, undersam=False, oversam=False,
                            export=False):
    assert k > 0
    print("Training with configuration " + configurationname)
    X_train, y_train, id_to_a_train = train_data
    dtc = DecisionTreeClassifier(random_state=0)

    print("Feature Selection")
    # selector = SelectFpr(score_function)
    selector = SelectKBest(score_function, k=k)
    result = selector.fit(X_train, y_train)
    X_train = selector.transform(X_train)

    fitted_ids = [i for i in result.get_support(indices=True)]

    print("Apply Resampling")
    print(Counter(y_train))
    if undersam and not oversam:
        renn = RepeatedEditedNearestNeighbours()
        X_train, y_train = renn.fit_resample(X_train, y_train)
    if oversam and not undersam:
        # feature_indices_array = list(range(len(f_to_id)))
        # smote_nc = SMOTENC(categorical_features=feature_indices_array, random_state=0)
        # X_train, y_train = smote_nc.fit_resample(X_train, y_train)
        sm = SMOTE(random_state=42)
        X_train, y_train = sm.fit_resample(X_train, y_train)
    if oversam and undersam:
        smote_enn = SMOTEENN(random_state=0)
        X_train, y_train = smote_enn.fit_resample(X_train, y_train)
    print(Counter(y_train))

    print("Train Classifier")
    dtc = dtc.fit(X_train, y_train, check_input=True)

    if export:
        export_graphviz(dtc, out_file=DATAP + "/temp/trees/sltree_" + configurationname + ".dot", filled=True)
        transform(fitted_ids, configurationname)

    print("Self Accuracy: " + str(dtc.score(X_train, y_train)))

    return selector, dtc

# 需要导入模块: from imblearn.combine import SMOTEENN [as 别名]
# 或者: from imblearn.combine.SMOTEENN import fit_resample [as 别名]
print(__doc__)

# Generate the dataset
X, y = make_classification(n_classes=2, class_sep=2, weights=[0.1, 0.9],
                           n_informative=3, n_redundant=1, flip_y=0,
                           n_features=20, n_clusters_per_class=1,
                           n_samples=100, random_state=10)

# Instanciate a PCA object for the sake of easy visualisation
pca = PCA(n_components=2)
# Fit and transform x to visualise inside a 2D feature space
X_vis = pca.fit_transform(X)

# Apply SMOTE + ENN
sm = SMOTEENN()
X_resampled, y_resampled = sm.fit_resample(X, y)
X_res_vis = pca.transform(X_resampled)

# Two subplots, unpack the axes array immediately
f, (ax1, ax2) = plt.subplots(1, 2)

c0 = ax1.scatter(X_vis[y == 0, 0], X_vis[y == 0, 1], label="Class #0",
                 alpha=0.5)
c1 = ax1.scatter(X_vis[y == 1, 0], X_vis[y == 1, 1], label="Class #1",
                 alpha=0.5)
ax1.set_title('Original set')

ax2.scatter(X_res_vis[y_resampled == 0, 0], X_res_vis[y_resampled == 0, 1],
            label="Class #0", alpha=0.5)
ax2.scatter(X_res_vis[y_resampled == 1, 0], X_res_vis[y_resampled == 1, 1],
            label="Class #1", alpha=0.5)

# 需要导入模块: from imblearn.combine import SMOTEENN [as 别名]
# 或者: from imblearn.combine.SMOTEENN import fit_resample [as 别名]
def test_error_wrong_object(smote_params, err_msg):
    smt = SMOTEENN(**smote_params)
    with pytest.raises(ValueError, match=err_msg):
        smt.fit_resample(X, Y)