# 混淆矩阵
print("Confusion Matrix...")
cm = metrics.confusion_matrix(y_test_cls, y_pred_cls)
print(cm)
time_dif = get_time_dif(start_time)
print("Time usage:", time_dif)
if __name__ == '__main__':
# 输入参数 train 和 test 表示训练与测试
# 需要在命令行运行 python run_cnn.py <train>|<test>
if len(sys.argv) != 2 or sys.argv[1] not in ['train', 'test']:
raise ValueError("""usage: python run_cnn.py [train / test]""")
print('Configuring CNN model...')
config = TCNNConfig() # 获得TCNNConfig设置，TCNNConfig表示CNN配置参数
if not os.path.exists(
vocab_dir): # 如果不存在词汇表，重建 单词表长度5000，是train里面出现最频繁的5000个单词
build_vocab(train_dir, vocab_dir, config.vocab_size)
categories, cat_to_id = read_category(
) # read_category()获取目录，cat_to_id 标签:序号的字典
words, word_to_id = read_vocab(vocab_dir) # 将词汇表的各个单词编号
config.vocab_size = len(words) # 更新词汇表长度
model = TextCNN(config) # 构建CNN模型，很重要
if sys.argv[1] == 'train':
train()
else:
test()
}
y_pred_cls[start_id:end_id] = session.run(model.y_pred_cls, feed_dict=feed_dict)
# 评估
print("Precision, Recall and F1-Score...")
print(metrics.classification_report(y_test_cls, y_pred_cls, target_names=categories))
# 混淆矩阵
print("Confusion Matrix...")
cm = metrics.confusion_matrix(y_test_cls, y_pred_cls)
print(cm)
time_dif = get_time_dif(start_time)
print("Time usage:", time_dif)
if __name__ == '__main__':
print('Configuring CNN model...')
config = TCNNConfig()
if not os.path.exists(vocab_dir):
build_vocab(train_dir, vocab_dir, config.vocab_size)
categories, cat_to_id = read_category()
words, word_to_id = read_vocab(vocab_dir)
config.vocab_size = len(words)
model = TextCNN(config)
if sys.argv[1] == 'train':
train()
else:
test()
for i in range(0, cnn.config.vocab_size):
if(cnn.words[i] in word_vector_map): # word_vector_map.has_key(cnn.words[i])
count = count
sub_embeddings[i]= word_vector_map.get(cnn.words[i])
else:
count = count + 1
missing_words_file.write(cnn.words[i]+'\n')
print('no embedding: ' + str(1.0 * count/len(cnn.words)))
print(str(len(sub_embeddings)) + '\t' + str(len(sub_embeddings[0])))
missing_words_file.close()
print(sub_embeddings[0])
cnn.embedding_matrix = sub_embeddings
#print(cnn.embedding_matrix.shape)
cnn.model = TextCNN(cnn.config)
cnn.train()
predict_y = cnn.test() #predicting results
print(predict_y)
print(len(predict_y))
print(len(test_data_Y))
tf.reset_default_graph()
correct_count = 0
for i in range(len(test_data_Y)):
if cnn.id_to_cat[predict_y[i]] == test_data_Y[i]:
correct_count += 1
doc_node = doc.createElement("doc")
doc_node.setAttribute("id", test_docs[i].split(',')[0])
