test_mondrian.py 文件源码

def check_proba_classif_convergence(X_train, y_train, mc):
    lb = LabelBinarizer()
    y_bin = lb.fit_transform(y_train)

    le = LabelEncoder()
    y_enc = le.fit_transform(y_train)

    proba = mc.predict_proba(X_train)
    labels = mc.predict(X_train)
    assert_array_equal(proba, y_bin)
    assert_array_equal(labels, lb.inverse_transform(y_bin))

    # For points completely far away from the training data, this
    # should converge to the empirical distribution of labels.
    # X is scaled between to -1.0 and 1.0
    X_inf = np.vstack((30.0 * np.ones(X_train.shape[1]),
                       -30.0 * np.ones(X_train.shape[1])))
    inf_proba = mc.predict_proba(X_inf)
    emp_proba = np.bincount(y_enc) / float(len(y_enc))
    assert_array_almost_equal(inf_proba, [emp_proba, emp_proba])