def test_mutual_info_classif_mixed():
# Here the target is discrete and there are two continuous and one
# discrete feature. The idea of this test is clear from the code.
rng = check_random_state(0)
X = rng.rand(1000, 3)
X[:, 1] += X[:, 0]
y = ((0.5 * X[:, 0] + X[:, 2]) > 0.5).astype(int)
X[:, 2] = X[:, 2] > 0.5
mi = mutual_info_classif(X,
y,
discrete_features=[2],
n_neighbors=3,
random_state=0)
assert_array_equal(np.argsort(-mi), [2, 0, 1])
for n_neighbors in [5, 7, 9]:
mi_nn = mutual_info_classif(X,
y,
discrete_features=[2],
n_neighbors=n_neighbors,
random_state=0)
# Check that the continuous values have an higher MI with greater
# n_neighbors
assert mi_nn[0] > mi[0]
assert mi_nn[1] > mi[1]
# The n_neighbors should not have any effect on the discrete value
# The MI should be the same
assert mi_nn[2] == mi[2]
def test_mutual_info_classif_discrete():
X = np.array([[0, 0, 0], [1, 1, 0], [2, 0, 1], [2, 0, 1], [2, 0, 1]])
y = np.array([0, 1, 2, 2, 1])
# Here X[:, 0] is the most informative feature, and X[:, 1] is weakly
# informative.
mi = mutual_info_classif(X, y, discrete_features=True)
assert_array_equal(np.argsort(-mi), np.array([0, 2, 1]))
def test_mutual_info_classif_mixed():
# Here the target is discrete and there are two continuous and one
# discrete feature. The idea of this test is clear from the code.
np.random.seed(0)
X = np.random.rand(1000, 3)
X[:, 1] += X[:, 0]
y = ((0.5 * X[:, 0] + X[:, 2]) > 0.5).astype(int)
X[:, 2] = X[:, 2] > 0.5
mi = mutual_info_classif(X, y, discrete_features=[2], random_state=0)
assert_array_equal(np.argsort(-mi), [2, 0, 1])
def test_mutual_info_classif_mixed():
# Here the target is discrete and there are two continuous and one
# discrete feature. The idea of this test is clear from the code.
np.random.seed(0)
X = np.random.rand(1000, 3)
X[:, 1] += X[:, 0]
y = ((0.5 * X[:, 0] + X[:, 2]) > 0.5).astype(int)
X[:, 2] = X[:, 2] > 0.5
mi = mutual_info_classif(X, y, discrete_features=[2], random_state=0)
assert_array_equal(np.argsort(-mi), [2, 0, 1])
def test_mutual_info_classif_discrete():
X = np.array([[0, 0, 0],
[1, 1, 0],
[2, 0, 1],
[2, 0, 1],
[2, 0, 1]])
y = np.array([0, 1, 2, 2, 1])
# Here X[:, 0] is the most informative feature, and X[:, 1] is weakly
# informative.
mi = mutual_info_classif(X, y, discrete_features=True)
assert_array_equal(np.argsort(-mi), np.array([0, 2, 1]))
def test_mutual_info_classif_mixed():
# Here the target is discrete and there are two continuous and one
# discrete feature. The idea of this test is clear from the code.
rng = check_random_state(0)
X = rng.rand(1000, 3)
X[:, 1] += X[:, 0]
y = ((0.5 * X[:, 0] + X[:, 2]) > 0.5).astype(int)
X[:, 2] = X[:, 2] > 0.5
mi = mutual_info_classif(X, y, discrete_features=[2], n_neighbors=3,
random_state=0)
assert_array_equal(np.argsort(-mi), [2, 0, 1])
for n_neighbors in [5, 7, 9]:
mi_nn = mutual_info_classif(X, y, discrete_features=[2],
n_neighbors=n_neighbors, random_state=0)
# Check that the continuous values have an higher MI with greater
# n_neighbors
assert_greater(mi_nn[0], mi[0])
assert_greater(mi_nn[1], mi[1])
# The n_neighbors should not have any effect on the discrete value
# The MI should be the same
assert_equal(mi_nn[2], mi[2])
def get_mutual_information(inputs, targets, token2idx, stop_words = None, mask_token = None):
# convert X to CSC format
data, row, col = convert_X_to_ijv_format(inputs)
counts = csc_matrix((data, (row, col)), shape = (inputs.shape[0], len(token2idx)))
# tf_idf_transformer = TfidfTransformer(norm = 'l2', use_idf = True, smooth_idf = True, sublinear_tf = True)
# tf_idf_transformer.fit(counts)
# counts = tf_idf_transformer.transform(counts)
mi = mutual_info_classif(counts, targets)
mi[token2idx[mask_token]] = 0.0
for stop_word in stop_words:
if stop_word in token2idx:
mi[token2idx[stop_word]] = 0.0
print('Maximum mutual information:', np.max(mi))
print('Minimum mutual information:', np.min(mi))
mi += 1e-9
return mi
