def load_data(self, ):
temp_cfy = Classify()
temp_cfy.add_jieba_dict(self.words)
p_wls = [temp_cfy.doc2words(c) for c in load_positive_contents()]
n_wls = [temp_cfy.doc2words(c) for c in load_negative_contents()]
n = len(p_wls) * 80 / 100
self.train_data = p_wls[:]
self.test_data = n_wls
self.test_y = [-1] * len(n_wls)
for wl in p_wls[n:]:
self.test_data.append(wl)
self.test_y.append(1)
def test(self, params):
fnum, na, nu, gs = params
cfy = Classify(fnum, na, nu, gs)
cfy.add_jieba_dict(self.words)
cfy.use_dict(self.words)
cfy.train_by_wls(self.train_data)
y_pred = cfy.predict_by_wls(self.test_data)
r = zip(map(int, y_pred), self.test_y)
tp = r.count((1, 1))
fp = r.count((1, -1))
fn = r.count((-1, 1))
if (tp == 0):
precision = 0
recall = 0
f1 = 0
else:
precision = tp * 1.0 / (tp + fp)
recall = tp * 1.0 / (tp + fn)
f1 = 5 * precision * recall / (4 * precision + recall)
print(fnum, na, nu, gs, precision, recall, f1)
return (precision, recall, f1)