def predict_test(sess, model):
"""Test on the valid data."""
time0 = time.time()
predict_labels_list = list() # 所有的预测结果
predict_score20_list = list() # 预测排名前20的分数
predict_labels_list2 = list() #前五名的结果
marked_labels_list = list()
topic_num = list()
predict_scores = list()
for i in tqdm(xrange(n_te_batches)):
[X1_batch, X2_batch, y_batch] = get_batch_t(i)
marked_labels_list.extend(y_batch)#真实标签结果 没-1
y_batch = to_categorical(y_batch)
_batch_size = len(X1_batch)
fetches = [model.y_pred]#每个类别的分数
feed_dict = {model.X1_inputs: X1_batch, model.X2_inputs: X2_batch,
model.batch_size: _batch_size, model.tst: True, model.keep_prob: 1.0}
predict_labels = sess.run(fetches, feed_dict)[0]
predict_labels = softmax(predict_labels)#128
predict_scores.append(predict_labels)#每个类别的分数
predict_top5score = map(lambda label: np.sort(label,axis=-1)[-1:-6:-1], predict_labels) # 取最大的5个分数 128
index = map(findindex,predict_top5score)#list 128
#print (index,'index.type:',type(index),'len.index',len(index))
predict_toplabels = list()
for i in range(len(index)):
if index[i] == None:
toplabel = predict_labels[i].argsort()[-1:-6:-1]
elif index[i] == 0:
toplabel = predict_labels[i].argsort()[-1:-2:-1]
else:
toplabel = predict_labels[i].argsort()[-1:-1*index[i]-1:-1]
predict_toplabels.append(toplabel)
predict_labels_list.extend(predict_toplabels)
#print('predict_toplabels:',predict_toplabels,type(predict_toplabels),len(predict_toplabels))
predict_label_and_marked_label_list = zip(predict_labels_list, marked_labels_list)#都-1了 不知道为啥
print (predict_label_and_marked_label_list[0:2])
#(array([ 15, 327, 307, 478, 10]), [8, 15, 307, 0])，真实是[9, 16, 308, 1]
precision, recall, f1 = score_eval(predict_label_and_marked_label_list)#计算分数
print('Local test p=%g, r=%g, f1=%g' % (precision, recall, f1))
predict_scores = np.vstack(np.asarray(predict_scores))
print('predict_scores:',predict_scores.shape)
local_scores_name = local_scores_path + model_name + '_test.npy'
np.save(local_scores_name, predict_scores)#保存每个类别的分数
print('local_scores.shape=', predict_scores.shape)
print('Writed the test scores into %s, time %g s' % (local_scores_name, time.time() - time0))
def predict_dev(sess, model):
"""Test on the valid data."""
time0 = time.time()
predict_labels_list = list() # 所有的预测结果
predict_score20_list = list() # 预测排名前20的分数
predict_labels_list2 = list() #前五名的结果
marked_labels_list = list()
topic_num = list()
predict_scores = list()
for i in tqdm(xrange(n_va_batches)):#验证集
[X1_batch, X2_batch, y_batch] = get_batch(i)
X1_length, X2_length = get_sequence_length(X1_batch, X2_batch)
marked_labels_list.extend(y_batch)#真实标签结果 没-1
y_batch = to_categorical(y_batch)
_batch_size = len(X1_batch)
fetches = [model.y_pred]#每个类别的分数
feed_dict = {model.X1_inputs: X1_batch, model.X2_inputs: X2_batch,
model.batch_size: _batch_size, model.X1_length: X1_length, model.X2_length: X2_length,
model.tst: True, model.keep_prob: 1.0}
predict_labels = sess.run(fetches, feed_dict)[0]
predict_labels = softmax(predict_labels)#128
predict_scores.append(predict_labels)#每个类别的分数
predict_top5score = map(lambda label: np.sort(label,axis=-1)[-1:-6:-1], predict_labels) # 取最大的5个分数 128
#predict_top20score = map(lambda label: np.sort(label,axis=-1)[-1:-21:-1], predict_labels) # 取最大的20个分数 128
#print (type(predict_score20_list))
#print (type(predict_top20score))
#predict_score20_list.extend(predict_top20score) #所有
#list,predict_score_list1[0]=[ 0.63514245 0.09193601 0.0417341 0.02742104 0.02721145]
index = map(findindex,predict_top5score)#list 128
#print (index,'index.type:',type(index),'len.index',len(index))
predict_toplabels = list()
for i in range(len(index)):
if index[i] == None:
toplabel = predict_labels[i].argsort()[-1:-6:-1]
elif index[i] == 0:
toplabel = predict_labels[i].argsort()[-1:-2:-1]
else:
toplabel = predict_labels[i].argsort()[-1:-1*index[i]-1:-1]
predict_toplabels.append(toplabel)
predict_labels_list.extend(predict_toplabels)
#print('predict_toplabels:',predict_toplabels,type(predict_toplabels),len(predict_toplabels))
#predict_top5labels = map(lambda label: label.argsort()[-1:-6:-1], predict_labels) # 取最大的5个下标
#predict_labels_list2.extend(predict_top5labels)
#predict_labels_list2.to_csv('predict_labels_list2.csv')
#predict_score20_list = DataFrame(predict_score20_list)
#predict_labels_list2 = DataFrame(predict_labels_list2)
#predict_score20_list.to_csv('score20list.csv')
#predict_labels_list2.to_csv('predict_labels_list2.csv')
#topic_num = map(tolen,marked_labels_list)
#topic_num = DataFrame(topic_num)
#topic_num.to_csv('topic_num.csv')
predict_label_and_marked_label_list = zip(predict_labels_list, marked_labels_list)#都-1了 不知道为啥
print (predict_label_and_marked_label_list[0:2])
#(array([ 15, 327, 307, 478, 10]), [8, 15, 307, 0])，真实是[9, 16, 308, 1]
precision, recall, f1 = score_eval(predict_label_and_marked_label_list)#计算分数
print('Local valid p=%g, r=%g, f1=%g' % (precision, recall, f1))
predict_scores = np.vstack(np.asarray(predict_scores))
print('predict_scores:',predict_scores.shape)
local_scores_name = local_scores_path + model_name + '_dev.npy'
np.save(local_scores_name, predict_scores)#保存每个类别的分数
print('local_scores.shape=', predict_scores.shape)
print('Writed the dev scores into %s, time %g s' % (local_scores_name, time.time() - time0))