def load_data(self):
features = []
targets = []
f_train = open(raw_trainingset, 'r')
for line in f_train:
corpus = gen_training_corpus(line)
feat = feature(corpus.title, corpus.person1, corpus.person2)
features.append(np.array(feat))
targets.append(corpus.label)
self.features = np.array(features)
self.targets = np.array(targets)
f_train.close()
def predict_main():
fi_test = open(test_file, 'r')
for line in fi_test:
corpus = gen_training_corpus(line)
test_corpora = gen_test_corpora(corpus.title)
if test_corpora == None: continue
print '--------------'
max_proba = 0.0
pred_label = -1
for corpus in test_corpora:
feats = feature(corpus.title, corpus.person1, corpus.person2)
cls = classfier.predict_proba(feats)
for i in range(len(relations)):
if cls[0][i] > max_proba:
max_proba = cls[0][i]
pred_label = i
print pred_label, max_proba
print '--------------'
fi_test.close()
trainset_prefix = "project2_TrainingSet7000_"
# 将每一种关系实例归类
if __name__ == '__main__':
fi_train = open(raw_trainingset, 'r')
# 为每一种关系建立一个预处理文件
file_out_list = []
fo_relation_list = []
for i in range(len(relations)):
filename = trainset_prefix + str(i)
filename = os.path.join(data_dir, filename)
file_out_list.append(filename)
fo_relation_list.append(open(filename.decode('utf-8'), 'w'))
# 读取训练集
for line in fi_train:
corpus = gen_training_corpus(line)
sp_list = divide_line(corpus.title, corpus.person1, corpus.person2)# 将新闻标题以人名为分隔符划分成3部分
string = ""
idx = 0
for sp in sp_list:
if sp != '':
for t in Seg(sp): # 调用中科院的分词
s = '%s:%s;' % (t[0],t[1])
string += s
idx += 1
if idx < len(sp_list):
string += '||'
string += '\n'
fo_relation_list[corpus.label].write(string)
fi_train.close()
for fo in fo_relation_list:
