def fit(self, X, y):
if self.method is 'mi':
self._weights = mutual_information(X, y)
elif self.method is 'pmi':
self._weights = pointwise_mutual_information(X, y, normalize=False)
elif self.method is 'npmi':
self._weights = pointwise_mutual_information(X, y, normalize=True)
elif self.method is 'ppmi_exp':
self._weights = pointwise_mutual_information(X,
y,
normalize=True,
positive='exp')
elif self.method is 'pmi_k':
self._weights = pointwise_mutual_information(X,
y,
normalize=True,
k_weight=self.pmi_k)
elif self.method is 'ppmi':
self._weights = pointwise_mutual_information(X,
y,
normalize=False,
positive='cutoff')
elif self.method is 'cp_raw':
self._weights = conditional_probabilities(X, y, ratio=False)
elif self.method is 'cp_ratio':
self._weights = conditional_probabilities(X, y, ratio=True)
else:
raise ValueError
return self
def test_pointwise_mutual_information(self):
X = array([[0, 1], [1, 0], [1, 1]])
y = array([[0, 1], [1, 0], [1, 0]])
assert_array_approx_equal(pointwise_mutual_information(X, y),
[0.1178, 0.1178],
decimal=3)
assert_array_approx_equal(pointwise_mutual_information(
csr_matrix(X), csr_matrix(y)), [0.1178, 0.1178],
decimal=3)
def test_pointwise_mutual_information(self):
X = array([[0, 1],
[1, 0],
[1, 1]])
y = array([[0, 1],
[1, 0],
[1, 0]])
assert_array_approx_equal(pointwise_mutual_information(X, y), [0.1178, 0.1178], decimal=3)
assert_array_approx_equal(pointwise_mutual_information(csr_matrix(X), csr_matrix(y)),
[0.1178, 0.1178], decimal=3)
def fit(self, X, y):
if self.method is 'mi':
self._weights = mutual_information(X, y)
elif self.method is 'pmi':
self._weights = pointwise_mutual_information(X, y, normalize=False)
elif self.method is 'npmi':
self._weights = pointwise_mutual_information(X, y, normalize=True)
elif self.method is 'ppmi_exp':
self._weights = pointwise_mutual_information(X, y, normalize=True, positive='exp')
elif self.method is 'pmi_k':
self._weights = pointwise_mutual_information(X, y, normalize=True, k_weight=self.pmi_k)
elif self.method is 'ppmi':
self._weights = pointwise_mutual_information(X, y, normalize=False, positive='cutoff')
elif self.method is 'cp_raw':
self._weights = conditional_probabilities(X, y, ratio=False)
elif self.method is 'cp_ratio':
self._weights = conditional_probabilities(X, y, ratio=True)
else:
raise ValueError
return self