Python under_sampling.ClusterCentroids類代碼示例

def test_sample_wrong_X():
    """Test either if an error is raised when X is different at fitting
    and sampling"""

    # Create the object
    cc = ClusterCentroids(random_state=RND_SEED)
    cc.fit(X, Y)
    assert_raises(RuntimeError, cc.sample, np.random.random((100, 40)),
                  np.array([0] * 50 + [1] * 50))

def test_multiclass_fit_sample():
    y = Y.copy()
    y[5] = 2
    y[6] = 2
    cc = ClusterCentroids(random_state=RND_SEED)
    X_resampled, y_resampled = cc.fit_sample(X, y)
    count_y_res = Counter(y_resampled)
    assert count_y_res[0] == 2
    assert count_y_res[1] == 2
    assert count_y_res[2] == 2

def test_fit_resample_auto():
    sampling_strategy = 'auto'
    cc = ClusterCentroids(
        sampling_strategy=sampling_strategy, random_state=RND_SEED)
    X_resampled, y_resampled = cc.fit_resample(X, Y)
    X_gt = np.array([[0.92923648, 0.76103773], [0.47104475, 0.44386323],
                     [0.13347175, 0.12167502], [0.06738818, -0.529627],
                     [0.17901516, 0.69860992], [0.094035, -2.55298982]])
    y_gt = np.array([0, 0, 0, 1, 1, 1])
    assert_allclose(X_resampled, X_gt, rtol=R_TOL)
    assert_array_equal(y_resampled, y_gt)

def test_fit_resample_half():
    sampling_strategy = {0: 3, 1: 6}
    cc = ClusterCentroids(
        sampling_strategy=sampling_strategy, random_state=RND_SEED)
    X_resampled, y_resampled = cc.fit_resample(X, Y)
    X_gt = np.array([[0.92923648, 0.76103773], [0.13347175, 0.12167502], [
        0.47104475, 0.44386323
    ], [0.09125309, -0.85409574], [0.19220316, 0.32337101],
                     [0.094035, -2.55298982], [0.20792588, 1.49407907],
                     [0.04352327, -0.20515826], [0.12372842, 0.6536186]])
    y_gt = np.array([0, 0, 0, 1, 1, 1, 1, 1, 1])
    print(X_resampled)
    assert_allclose(X_resampled, X_gt, rtol=R_TOL)
    assert_array_equal(y_resampled, y_gt)

def test_fit_sample_object():
    ratio = 'auto'
    cluster = KMeans(random_state=RND_SEED)
    cc = ClusterCentroids(
        ratio=ratio, random_state=RND_SEED, estimator=cluster)

    X_resampled, y_resampled = cc.fit_sample(X, Y)
    X_gt = np.array([[0.92923648, 0.76103773],
                     [0.47104475, 0.44386323],
                     [0.13347175, 0.12167502],
                     [0.06738818, -0.529627],
                     [0.17901516, 0.69860992],
                     [0.094035, -2.55298982]])
    y_gt = np.array([0, 0, 0, 1, 1, 1])
    assert_allclose(X_resampled, X_gt, rtol=R_TOL)
    assert_array_equal(y_resampled, y_gt)

def test_cc_fit():
    """Test the fitting method"""

    # Define the parameter for the under-sampling
    ratio = 'auto'

    # Create the object
    cc = ClusterCentroids(ratio=ratio, random_state=RND_SEED)
    # Fit the data
    cc.fit(X, Y)

    # Check if the data information have been computed
    assert_equal(cc.min_c_, 0)
    assert_equal(cc.maj_c_, 1)
    assert_equal(cc.stats_c_[0], 500)
    assert_equal(cc.stats_c_[1], 4500)

def test_multiclass_fit_sample():
    """Test fit sample method with multiclass target"""

    # Make y to be multiclass
    y = Y.copy()
    y[0:1000] = 2

    # Resample the data
    cc = ClusterCentroids(random_state=RND_SEED)
    X_resampled, y_resampled = cc.fit_sample(X, y)

    # Check the size of y
    count_y_res = Counter(y_resampled)
    assert_equal(count_y_res[0], 400)
    assert_equal(count_y_res[1], 400)
    assert_equal(count_y_res[2], 400)

def test_fit_sample_half():
    """Test fit and sample routines with ratio of .5"""

    # Define the parameter for the under-sampling
    ratio = .5

    # Create the object
    cc = ClusterCentroids(ratio=ratio, random_state=RND_SEED)

    # Fit and sample
    X_resampled, y_resampled = cc.fit_sample(X, Y)

    currdir = os.path.dirname(os.path.abspath(__file__))
    X_gt = np.load(os.path.join(currdir, 'data', 'cc_x_05.npy'))
    y_gt = np.load(os.path.join(currdir, 'data', 'cc_y_05.npy'))
    assert_array_equal(X_resampled, X_gt)
    assert_array_equal(y_resampled, y_gt)

def test_fit_sample_auto():
    """Test fit and sample routines with auto ratio"""

    # Define the parameter for the under-sampling
    ratio = 'auto'

    # Create the object
    cc = ClusterCentroids(ratio=ratio, random_state=RND_SEED)

    # Fit and sample
    X_resampled, y_resampled = cc.fit_sample(X, Y)

    X_gt = np.array([[0.92923648, 0.76103773], [0.47104475, 0.44386323],
                     [0.13347175, 0.12167502], [0.06738818, -0.529627],
                     [0.17901516, 0.69860992], [0.094035, -2.55298982]])
    y_gt = np.array([0, 0, 0, 1, 1, 1])
    assert_array_almost_equal(X_resampled, X_gt)
    assert_array_equal(y_resampled, y_gt)

def test_fit_hard_voting():
    sampling_strategy = 'auto'
    voting = 'hard'
    cluster = KMeans(random_state=RND_SEED)
    cc = ClusterCentroids(
        sampling_strategy=sampling_strategy,
        random_state=RND_SEED,
        estimator=cluster,
        voting=voting)

    X_resampled, y_resampled = cc.fit_resample(X, Y)
    X_gt = np.array([[0.92923648, 0.76103773], [0.47104475, 0.44386323],
                     [0.13347175, 0.12167502], [0.09125309, -0.85409574],
                     [0.12372842, 0.6536186], [0.094035, -2.55298982]])
    y_gt = np.array([0, 0, 0, 1, 1, 1])
    assert_allclose(X_resampled, X_gt, rtol=R_TOL)
    assert_array_equal(y_resampled, y_gt)
    for x in X_resampled:
        assert np.any(np.all(x == X, axis=1))

def test_fit_sample_half():
    """Test fit and sample routines with ratio of .5"""

    # Define the parameter for the under-sampling
    ratio = .5

    # Create the object
    cc = ClusterCentroids(ratio=ratio, random_state=RND_SEED)

    # Fit and sample
    X_resampled, y_resampled = cc.fit_sample(X, Y)

    X_gt = np.array([[0.92923648, 0.76103773], [0.47104475, 0.44386323],
                     [0.13347175, 0.12167502], [0.09125309, -0.85409574],
                     [0.19220316, 0.32337101], [0.094035, -2.55298982],
                     [0.20792588, 1.49407907], [0.04352327, -0.20515826],
                     [0.12372842, 0.6536186]])
    y_gt = np.array([0, 0, 0, 1, 1, 1, 1, 1, 1])
    assert_array_almost_equal(X_resampled, X_gt)
    assert_array_equal(y_resampled, y_gt)

def test_fit_sample_check_voting():
    cc = ClusterCentroids(random_state=RND_SEED)
    cc.fit_sample(X, Y)
    assert cc.voting_ == 'soft'
    cc = ClusterCentroids(random_state=RND_SEED)
    cc.fit_sample(sparse.csr_matrix(X), Y)
    assert cc.voting_ == 'hard'

def test_fit_sample_error():
    ratio = 'auto'
    cluster = 'rnd'
    cc = ClusterCentroids(
        ratio=ratio, random_state=RND_SEED, estimator=cluster)
    with raises(ValueError, match="has to be a KMeans clustering"):
        cc.fit_sample(X, Y)

    voting = 'unknown'
    cc = ClusterCentroids(ratio=ratio, voting=voting, random_state=RND_SEED)
    with raises(ValueError, match="needs to be one of"):
        cc.fit_sample(X, Y)

from imblearn.under_sampling import ClusterCentroids

# 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=5000, 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 Cluster Centroids
cc = ClusterCentroids()
X_resampled, y_resampled = cc.fit_sample(X, y)
X_res_vis = pca.transform(X_resampled)

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

ax1.scatter(X_vis[y == 0, 0], X_vis[y == 0, 1], label="Class #0", alpha=0.5,
            edgecolor=almost_black, facecolor=palette[0], linewidth=0.15)
ax1.scatter(X_vis[y == 1, 0], X_vis[y == 1, 1], label="Class #1", alpha=0.5,
            edgecolor=almost_black, facecolor=palette[2], linewidth=0.15)
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=.5, edgecolor=almost_black,
            facecolor=palette[0], linewidth=0.15)

    for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):
        plt.text(j, i, cm[i, j],
                 horizontalalignment="center",
                 color="white" if cm[i, j] > thresh else "black")

    plt.tight_layout()
    plt.ylabel('True label')
    plt.xlabel('Predicted label')


#define X y
X, y = data.loc[:,data.columns != 'state'].values, data.loc[:,data.columns == 'state'].values
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)

#ClusterCentroids
cc = ClusterCentroids(random_state=0)
os_X,os_y = cc.fit_sample(X_train,y_train)

#XGboost
clf_XG = XGBClassifier(learning_rate= 0.3, min_child_weight=1,
                       max_depth=6,gamma=0,subsample=1, max_delta_step=0, colsample_bytree=1,
                       reg_lambda=1, n_estimators=100, seed=1000, scale_pos_weight=1000)  
clf_XG.fit(os_X, os_y,eval_set=[(os_X, os_y), (X_test, y_test)],eval_metric='auc',verbose=False)  
evals_result = clf_XG.evals_result()  
y_true, y_pred = y_test, clf_XG.predict(X_test)  

#F1_score, precision, recall, specifity, G score
print "F1_score : %.4g" % metrics.f1_score(y_true, y_pred)  
print "Recall : %.4g" % metrics.recall_score(y_true, y_pred)
recall = metrics.recall_score(y_true, y_pred)  
print "Precision : %.4g" % metrics.precision_score(y_true, y_pred)