Upload 8 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+data2_pro.xlsx filter=lfs diff=lfs merge=lfs -text

data2_pro.xlsx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a445e6894cb129b40c63aa4cdb2a1a177e532fa6214fd21292a9b5c1cf0cbcc6
+size 79735899

flip.py

@@ -0,0 +1,92 @@
+import numpy as np
+import gradio as gr
+import random
+import time
+from updated_predict import working_func
+
+theme = gr.themes.Soft(
+    primary_hue="emerald",
+    secondary_hue="teal",
+    neutral_hue="indigo",
+#    text_size="text_lg",
+#    radius_size="radius_lg",
+).set(
+    #body_background_fill='*checkbox_label_background_fill',
+    #body_background_fill='*block_title_background_fill',
+    body_background_fill='*background_fill_secondary',
+    background_fill_primary='*neutral_200',
+    block_background_fill='*table_even_background_fill',
+    button_border_width='*block_title_border_width',
+    button_shadow='*button_shadow_hover'
+)
+
+
+def flip_text(x):
+    return x[::-1]
+
+
+def flip_image(x):
+    return np.fliplr(x)
+
+def diagnosed_huxi():
+    return "呼吸科"
+
+def diagnosed_shennei():
+    return "神经内科"
+
+def diagnosed_xiaohua():
+    return "内科 消化科/胃肠科"
+
+def diagnosed_xinnei():
+    return "内科 心脏内科"
+text_output = gr.Textbox(label="科室")
+
+with gr.Blocks(theme=theme) as demo:
+    gr.Markdown("医疗分诊助手")
+    gr.Image("bar.png")
+    with gr.Tab("常见疑问"):
+        with gr.Row():
+              btn1 = gr.Button(value="癫痫")
+              btn1.click(diagnosed_shennei, inputs=[], outputs=[text_output])
+
+              btn2 = gr.Button(value="咳嗽")
+              btn2.click(diagnosed_huxi, inputs=[], outputs=[text_output])
+
+              btn3 = gr.Button(value="感冒")
+              btn3.click(diagnosed_huxi, inputs=[], outputs=[text_output])
+
+
+        with gr.Row():
+              btn4 = gr.Button(value="高血压")
+              btn4.click(diagnosed_xinnei, inputs=[], outputs=[text_output])
+
+              btn5 = gr.Button(value="发烧")
+              btn5.click(diagnosed_huxi, inputs=[], outputs=[text_output])
+
+              btn6 = gr.Button(value="胃炎")
+              btn6.click(diagnosed_xiaohua, inputs=[], outputs=[text_output])
+
+        with gr.Row():
+            text_output.render()
+
+    with gr.Tab("手动键入"):
+        chatbot = gr.Chatbot()
+        msg = gr.Textbox()
+        clear = gr.ClearButton([msg, chatbot])
+        def respond(message, chat_history):
+            result = working_func(message)
+            bot_message = "科室：" + result[0] + ',' + result[1] + '\n' + "回答：" + result[2]
+            chat_history.append((message, bot_message))
+            time.sleep(2)
+            return "", chat_history
+
+
+        msg.submit(respond, [msg, chatbot], [msg, chatbot])
+
+    with gr.Accordion("Open for More!"):
+        gr.Markdown("Look at me...")
+
+    #text_button.click(flip_text, inputs=text_input, outputs=text_output)
+    #image_button.click(flip_image, inputs=image_input, outputs=image_output)
+
+demo.launch()

naive_bayes_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33e0de74a3ee49f0bbae068452f0e357d0fbcc4e39ad7f3c7353324ece2adf96
+size 480800

stop_words.txt

@@ -0,0 +1,746 @@
+$
+0
+1
+2
+3
+4
+5
+6
+7
+8
+9
+?
+_
+“
+”
+、
+。
+《
+》
+一
+一些
+一何
+一切
+一则
+一方面
+一旦
+一来
+一样
+一般
+一转眼
+万一
+上
+上下
+下
+不
+不仅
+不但
+不光
+不单
+不只
+不外乎
+不如
+不妨
+不尽
+不尽然
+不得
+不怕
+不惟
+不成
+不拘
+不料
+不是
+不比
+不然
+不特
+不独
+不管
+不至于
+不若
+不论
+不过
+不问
+与
+与其
+与其说
+与否
+与此同时
+且
+且不说
+且说
+两者
+个
+个别
+临
+为
+为了
+为什么
+为何
+为止
+为此
+为着
+乃
+乃至
+乃至于
+么
+之
+之一
+之所以
+之类
+乌乎
+乎
+乘
+也
+也好
+也罢
+了
+二来
+于
+于是
+于是乎
+云云
+云尔
+些
+亦
+人
+人们
+人家
+什么
+什么样
+今
+介于
+仍
+仍旧
+从
+从此
+从而
+他
+他人
+他们
+以
+以上
+以为
+以便
+以免
+以及
+以故
+以期
+以来
+以至
+以至于
+以致
+们
+任
+任何
+任凭
+似的
+但
+但凡
+但是
+何
+何以
+何况
+何处
+何时
+余外
+作为
+你
+你们
+使
+使得
+例如
+依
+依据
+依照
+便于
+俺
+俺们
+倘
+倘使
+倘或
+倘然
+倘若
+借
+假使
+假如
+假若
+傥然
+像
+儿
+先不先
+光是
+全体
+全部
+兮
+关于
+其
+其一
+其中
+其二
+其他
+其余
+其它
+其次
+具体地说
+具体说来
+兼之
+内
+再
+再其次
+再则
+再有
+再者
+再者说
+再说
+冒
+冲
+况且
+几
+几时
+凡
+凡是
+凭
+凭借
+出于
+出来
+分别
+则
+则甚
+别
+别人
+别处
+别是
+别的
+别管
+别说
+到
+前后
+前此
+前者
+加之
+加以
+即
+即令
+即使
+即便
+即如
+即或
+即若
+却
+去
+又
+又及
+及
+及其
+及至
+反之
+反而
+反过来
+反过来说
+受到
+另
+另一方面
+另外
+另悉
+只
+只当
+只怕
+只是
+只有
+只消
+只要
+只限
+叫
+叮咚
+可
+可以
+可是
+可见
+各
+各个
+各位
+各种
+各自
+同
+同时
+后
+后者
+向
+向使
+向着
+吓
+吗
+否则
+吧
+吧哒
+吱
+呀
+呃
+呕
+呗
+呜
+呜呼
+呢
+呵
+呵呵
+呸
+呼哧
+咋
+和
+咚
+咦
+咧
+咱
+咱们
+咳
+哇
+哈
+哈哈
+哉
+哎
+哎呀
+哎哟
+哗
+哟
+哦
+哩
+哪
+哪个
+哪些
+哪儿
+哪天
+哪年
+哪怕
+哪样
+哪边
+哪里
+哼
+哼唷
+唉
+唯有
+啊
+啐
+啥
+啦
+啪达
+啷当
+喂
+喏
+喔唷
+喽
+嗡
+嗡嗡
+嗬
+嗯
+嗳
+嘎
+嘎登
+嘘
+嘛
+嘻
+嘿
+嘿嘿
+因
+因为
+因了
+因此
+因着
+因而
+固然
+在
+在下
+在于
+地
+基于
+处在
+多
+多么
+多少
+大
+大家
+她
+她们
+好
+如
+如上
+如上所述
+如下
+如何
+如其
+如同
+如是
+如果
+如此
+如若
+始而
+孰料
+孰知
+宁
+宁可
+宁愿
+宁肯
+它
+它们
+对
+对于
+对待
+对方
+对比
+将
+小
+尔
+尔后
+尔尔
+尚且
+就
+就是
+就是了
+就是说
+就算
+就要
+尽
+尽管
+尽管如此
+岂但
+己
+已
+已矣
+巴
+巴巴
+并
+并且
+并非
+庶乎
+庶几
+开外
+开始
+归
+归齐
+当
+当地
+当然
+当着
+彼
+彼时
+彼此
+往
+待
+很
+得
+得了
+怎
+怎么
+怎么办
+怎么样
+怎奈
+怎样
+总之
+总的来看
+总的来说
+总的说来
+总而言之
+恰恰相反
+您
+惟其
+慢说
+我
+我们
+或
+或则
+或是
+或曰
+或者
+截至
+所
+所以
+所在
+所幸
+所有
+才
+才能
+打
+打从
+把
+抑或
+拿
+按
+按照
+换句话说
+换言之
+据
+据此
+接着
+故
+故此
+故而
+旁人
+无
+无宁
+无论
+既
+既往
+既是
+既然
+时候
+是
+是以
+是的
+曾
+替
+替代
+最
+有
+有些
+有关
+有及
+有时
+有的
+望
+朝
+朝着
+本
+本人
+本地
+本着
+本身
+来
+来着
+来自
+来说
+极了
+果然
+果真
+某
+某个
+某些
+某某
+根据
+欤
+正值
+正如
+正巧
+正是
+此
+此地
+此处
+此外
+此时
+此次
+此间
+毋宁
+每
+每当
+比
+比及
+比如
+比方
+没奈何
+沿
+沿着
+漫说
+焉
+然则
+然后
+然而
+照
+照着
+犹且
+犹自
+甚且
+甚么
+甚或
+甚而
+甚至
+甚至于
+用
+用来
+由
+由于
+由是
+由此
+由此可见
+的
+的确
+的话
+直到
+相对而言
+省得
+看
+眨眼
+着
+着呢
+矣
+矣乎
+矣哉
+离
+竟而
+第
+等
+等到
+等等
+简言之
+管
+类如
+紧接着
+纵
+纵令
+纵使
+纵然
+经
+经过
+结果
+给
+继之
+继后
+继而
+综上所述
+罢了
+者
+而
+而且
+而况
+而后
+而外
+而已
+而是
+而言
+能
+能否
+腾
+自
+自个儿
+自从
+自各儿
+自后
+自家
+自己
+自打
+自身
+至
+至于
+至今
+至若
+致
+般的
+若
+若夫
+若是
+若果 
+若非
+莫不然
+莫如
+莫若
+虽
+虽则
+虽然
+虽说
+被
+要
+要不
+要不是
+要不然
+要么
+要是
+譬喻
+譬如
+让
+许多
+论
+设使
+设或
+设若
+诚如
+诚然
+该
+说来
+诸
+诸位
+诸如
+谁
+谁人
+谁料
+谁知
+贼死
+赖以
+赶
+起
+起见
+趁
+趁着
+越是
+距
+跟
+较
+较之
+边
+过
+还
+还是
+还有
+还要
+这
+这一来
+这个
+这么
+这么些
+这么样
+这么点儿
+这些
+这会儿
+这儿
+这就是说
+这时
+这样
+这次
+这般
+这边
+这里
+进而
+���
+连同
+逐步
+通过
+遵循
+遵照
+那
+那个
+那么
+那么些
+那么样
+那些
+那会儿
+那儿
+那时
+那样
+那般
+那边
+那里
+都
+鄙人
+鉴于
+针对
+阿
+除
+除了
+除外
+除开
+除此之外
+除非
+随
+随后
+随时
+随着
+难道说
+非但
+非徒
+非特
+非独
+靠
+顺
+顺着
+首先
+！
+，
+：
+；
+？

train_eval.py

@@ -0,0 +1,119 @@
+# coding: UTF-8
+import numpy as np
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from sklearn import metrics
+import time
+from utils import get_time_dif
+from tensorboardX import SummaryWriter
+
+
+# 权重初始化，默认xavier
+def init_network(model, method='xavier', exclude='embedding', seed=123):
+    for name, w in model.named_parameters():
+        if exclude not in name:
+            if 'weight' in name:
+                if method == 'xavier':
+                    nn.init.xavier_normal_(w)
+                elif method == 'kaiming':
+                    nn.init.kaiming_normal_(w)
+                else:
+                    nn.init.normal_(w)
+            elif 'bias' in name:
+                nn.init.constant_(w, 0)
+            else:
+                pass
+
+
+def train(config, model, train_iter, dev_iter, test_iter):
+    start_time = time.time()
+    model.train()
+    optimizer = torch.optim.Adam(model.parameters(), lr=config.learning_rate)
+
+    # 学习率指数衰减，每次epoch：学习率 = gamma * 学习率
+    # scheduler = torch.optim.lr_scheduler.ExponentialLR(optimizer, gamma=0.9)
+    total_batch = 0  # 记录进行到多少batch
+    dev_best_loss = float('inf')
+    last_improve = 0  # 记录上次验证集loss下降的batch数
+    flag = False  # 记录是否很久没有效果提升
+    writer = SummaryWriter(log_dir=config.log_path + '/' + time.strftime('%m-%d_%H.%M', time.localtime()))
+    for epoch in range(config.num_epochs):
+        print('Epoch [{}/{}]'.format(epoch + 1, config.num_epochs))
+        # scheduler.step() # 学习率衰减
+        for i, (trains, labels) in enumerate(train_iter):
+            outputs = model(trains)
+            model.zero_grad()
+            loss = F.cross_entropy(outputs, labels)
+            loss.backward()
+            optimizer.step()
+            if total_batch % 100 == 0:
+                # 每多少轮输出在训练集和验证集上的效果
+                true = labels.data.cpu()
+                predic = torch.max(outputs.data, 1)[1].cpu()
+                train_acc = metrics.accuracy_score(true, predic)
+                dev_acc, dev_loss = evaluate(config, model, dev_iter)
+                if dev_loss < dev_best_loss:
+                    dev_best_loss = dev_loss
+                    torch.save(model.state_dict(), config.save_path)
+                    improve = '*'
+                    last_improve = total_batch
+                else:
+                    improve = ''
+                time_dif = get_time_dif(start_time)
+                msg = 'Iter: {0:>6},  Train Loss: {1:>5.2},  Train Acc: {2:>6.2%},  Val Loss: {3:>5.2},  Val Acc: {4:>6.2%},  Time: {5} {6}'
+                print(msg.format(total_batch, loss.item(), train_acc, dev_loss, dev_acc, time_dif, improve))
+                writer.add_scalar("loss/train", loss.item(), total_batch)
+                writer.add_scalar("loss/dev", dev_loss, total_batch)
+                writer.add_scalar("acc/train", train_acc, total_batch)
+                writer.add_scalar("acc/dev", dev_acc, total_batch)
+                model.train()
+            total_batch += 1
+            if total_batch - last_improve > config.require_improvement:
+                # 验证集loss超过1000batch没下降，结束训练
+                print("No optimization for a long time, auto-stopping...")
+                flag = True
+                break
+        if flag:
+            break
+    writer.close()
+    test(config, model, test_iter)
+
+
+def test(config, model, test_iter):
+    # test
+    model.load_state_dict(torch.load(config.save_path))
+    model.eval()
+    start_time = time.time()
+    test_acc, test_loss, test_report, test_confusion = evaluate(config, model, test_iter, test=True)
+    msg = 'Test Loss: {0:>5.2},  Test Acc: {1:>6.2%}'
+    print(msg.format(test_loss, test_acc))
+    print("Precision, Recall and F1-Score...")
+    print(test_report)
+    print("Confusion Matrix...")
+    print(test_confusion)
+    time_dif = get_time_dif(start_time)
+    print("Time usage:", time_dif)
+
+
+def evaluate(config, model, data_iter, test=False):
+    model.eval()
+    loss_total = 0
+    predict_all = np.array([], dtype=int)
+    labels_all = np.array([], dtype=int)
+    with torch.no_grad():
+        for texts, labels in data_iter:
+            outputs = model(texts)
+            loss = F.cross_entropy(outputs, labels)
+            loss_total += loss
+            labels = labels.data.cpu().numpy()
+            predic = torch.max(outputs.data, 1)[1].cpu().numpy()
+            labels_all = np.append(labels_all, labels)
+            predict_all = np.append(predict_all, predic)
+
+    acc = metrics.accuracy_score(labels_all, predict_all)
+    if test:
+        report = metrics.classification_report(labels_all, predict_all, target_names=config.class_list, digits=4)
+        confusion = metrics.confusion_matrix(labels_all, predict_all)
+        return acc, loss_total / len(data_iter), report, confusion
+    return acc, loss_total / len(data_iter)

updated_predict.py

@@ -0,0 +1,223 @@
+from importlib import import_module
+import torch
+import pandas as pd
+import pickle as pkl
+from tqdm import tqdm
+from numpy.linalg import norm
+from utils import build_vocab, build_iterator
+import numpy as np
+import os
+from sklearn.feature_extraction.text import CountVectorizer
+import jieba
+import joblib
+from sklearn.model_selection import train_test_split
+import fasttext
+import gradio as gr
+
+
+MAX_VOCAB_SIZE = 10000
+UNK, PAD = '<UNK>', '<PAD>'
+module = import_module("models.TextCNN")
+dataset = 'THUCNews'
+embedding = 'embedding_SougouNews.npz'  # 预训练的词向量表
+config = module.Config(dataset, embedding)
+model = module.Model(config).to(config.device)
+model.load_state_dict(torch.load(config.save_path))
+model.eval()
+
+
+def build_dataset(content, config, ues_word):
+    if ues_word:
+        tokenizer = lambda x: x.split(' ')  # 以空格隔开，word-level
+    else:
+        tokenizer = lambda x: [y for y in x]  # char-level
+    if os.path.exists(config.vocab_path):
+        vocab = pkl.load(open(config.vocab_path, 'rb'))  #打开词表文件
+    else:
+        vocab = build_vocab(config.train_path, tokenizer=tokenizer, max_size=MAX_VOCAB_SIZE, min_freq=1)
+        pkl.dump(vocab, open(config.vocab_path, 'wb'))
+    def load_dataset(pad_size=32):
+        contents = []
+        words_line = []
+        token = tokenizer(content)
+        seq_len = len(token)
+        if pad_size:
+            if len(token) < pad_size:
+                token.extend([PAD] * (pad_size - len(token)))
+            else:
+                token = token[:pad_size]
+                seq_len = pad_size
+        for word in token:
+            words_line.append(vocab.get(word, vocab.get(UNK)))
+        contents.append((words_line, -1, seq_len))
+        return contents  # [([...], 0), ([...], 1), ...]
+    train = load_dataset(config.pad_size)
+    return vocab, train
+
+def wordvector(config,df,pad_size=32):
+    wordvectorlist = []
+    answerlist = []
+    sentences = []
+    department = []
+    tokenizer = lambda x: [y for y in x]  # char-level
+    if os.path.exists(config.vocab_path):
+        vocab = pkl.load(open(config.vocab_path, 'rb'))  # 打开词表文件
+    else:
+        vocab = build_vocab(config.train_path, tokenizer=tokenizer, max_size=MAX_VOCAB_SIZE, min_freq=1)
+        pkl.dump(vocab, open(config.vocab_path, 'wb'))
+    for row in df.index:
+        content = df.loc[row]['ask']
+        answer = df.loc[row]['answer']
+        department.append(df.loc[row]['department'])
+        answerlist.append(answer)
+        sentences.append(content)
+        words_line = []
+        token = tokenizer(content)
+        if pad_size:
+            if len(token) < pad_size:
+                token.extend([PAD] * (pad_size - len(token)))
+            else:
+                token = token[:pad_size]
+                seq_len = pad_size
+        for word in token:
+            words_line.append(vocab.get(word, vocab.get(UNK)))
+        vector = words_line
+        wordvectorlist.append(vector)
+    return wordvectorlist, answerlist
+def cos_similarity_test(vector,word_vector_list):
+    best_cosine = -10
+    for i in range(len(word_vector_list)):
+        best_index = 0
+        B = word_vector_list[i]
+        cosine = np.dot(vector, B) / (norm(vector) * norm(B))
+        if cosine > best_cosine:
+            best_cosine = cosine
+            best_index = i
+    return best_index
+
+def predict_single_text(text,flag):
+    # 预测单条文本的分类
+    ft_model = None
+    if flag == 4:
+        ft_model = fasttext.load_model("./fasttext_model_erke.bin")
+    if flag == 5:
+        ft_model = fasttext.load_model("./fasttext_model_waike.bin")
+    prediction = ft_model.predict([text], k=1)  # k=1表示只返回概率最高的标签
+    if prediction:
+        label = prediction[0][0][len('__label__'):]  # 获取标签
+        str = prediction[0][0][0]
+        label = str[9:-1]
+        # print(str)
+        confidence = prediction[1][0]  # 获取置信度
+        return label, confidence
+    else:
+        return None, None
+def proceed(content,NumOfChamber,content_vector):
+    with open('./stop_words.txt', 'r', encoding="utf-8") as f:
+        stop_words = list(l.strip() for l in f.readlines())
+    stop_words.extend(['\n', '（', '）', ' '])  # 由于停用词中没有'\n'和中文的左右括号和空格，所以单独再加上去
+    if NumOfChamber == 0:
+        print("大类为：男科")
+        file = pd.read_csv("./THUCNews/data/Data/nanke/nanke1.csv", encoding='utf-8')
+        df = file[["department", "ask", "answer"]]
+        word_vector_list, answer_list = wordvector(config, df)
+        most_similar_index = cos_similarity_test(content_vector,word_vector_list)
+        most_similar_answer = answer_list[most_similar_index]
+        return None, most_similar_answer
+    if NumOfChamber == 2:
+        print("大类为：妇产科")
+        file = pd.read_csv("./THUCNews/data/Data/fuchanke/fuchanke1.csv", encoding='utf-8')
+        df = file[["department", "ask", "answer"]]
+        word_vector_list, answer_list = wordvector(config, df)
+        most_similar_index = cos_similarity_test(content_vector,word_vector_list)
+        most_similar_answer = answer_list[most_similar_index]
+        return None, most_similar_answer
+    if NumOfChamber == 3:
+        print("大类为：肿瘤科")
+        file = pd.read_csv("./THUCNews/data/Data/zhongliuke/zhongliuke1.csv", encoding='utf-8')
+        df = file[["department", "ask", "answer"]]
+        word_vector_list, answer_list = wordvector(config, df)
+        most_similar_index = cos_similarity_test(content_vector,word_vector_list)
+        most_similar_answer = answer_list[most_similar_index]
+        return None, most_similar_answer
+    if NumOfChamber == 1:
+        print("大类为：内科")
+        data2 = pd.read_excel(io="data2_pro.xlsx", engine="openpyxl")
+        department_counts = data2['department'].value_counts()
+        underrepresented_categories = department_counts[department_counts < 20000].index
+        data2 = data2[~data2['department'].isin(underrepresented_categories)]
+        data2['Pre_Text'].fillna('', inplace=True)
+        X = data2['Pre_Text']  # 文本数据
+        y = data2['department']  # 标签
+        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+        count_vectorizer = CountVectorizer(stop_words=stop_words, max_features=5000)
+        X_train_count = count_vectorizer.fit_transform(X_train)
+        X_test_count = count_vectorizer.transform(X_test)
+        input_text = content
+        nb_classifier = joblib.load('naive_bayes_model.pkl')
+        input_text_processed = " ".join([w for w in list(jieba.cut(str(input_text))) if w not in stop_words])
+        input_text_processed = count_vectorizer.transform([input_text_processed])
+        predicted_department = nb_classifier.predict(input_text_processed)
+
+        file = pd.read_csv("./THUCNews/data/Data/neike/neike1.csv", encoding='utf-8')
+        df = file[file["department"] == predicted_department[0]]
+        df = df[["department", "ask", "answer"]]
+        word_vector_list, answer_list = wordvector(config, df)
+        most_similar_index = cos_similarity_test(content_vector,word_vector_list)
+        most_similar_answer = answer_list[most_similar_index]
+        return predicted_department[0], most_similar_answer
+    if NumOfChamber == 4:
+        print("大类为：儿科")
+        input_text = ' '.join([word for word in jieba.lcut(content) if word not in stop_words])
+        predicted_department, confidence_score = predict_single_text(input_text,4)
+        file = pd.read_csv("./THUCNews/data/Data/erke/erke1.csv", encoding='utf-8')
+        df = file[file["department"] == predicted_department]
+        df = df[["department", "ask", "answer"]]
+        word_vector_list, answer_list = wordvector(config, df)
+        most_similar_index = cos_similarity_test(content_vector,word_vector_list)
+        most_similar_answer = answer_list[most_similar_index]
+        return predicted_department, most_similar_answer
+    if NumOfChamber == 5:
+        print("大类为：外科")
+        input_text = ' '.join([word for word in jieba.lcut(content) if word not in stop_words])
+        predicted_department, confidence_score = predict_single_text(input_text,5)
+        file = pd.read_csv("./THUCNews/data/Data/waike/waike1.csv", encoding='utf-8')
+        print(type(predicted_department))
+        print(predicted_department)
+        df = file[file["department"] == predicted_department]
+        df = df[["department", "ask", "answer"]]
+        word_vector_list, answer_list = wordvector(config, df)
+        most_similar_index = cos_similarity_test(content_vector,word_vector_list)
+        most_similar_answer = answer_list[most_similar_index]
+        return predicted_department, most_similar_answer
+
+
+
+def working_func(content):
+    # content = input("请输入您的病情描述：")
+    vocab, train_data = build_dataset(content,config, False)
+    content_vector = train_data[0][0]
+    config.n_vocab = len(vocab)
+    train_iter = build_iterator(train_data, config)
+    predict_all = np.array([], dtype=int)
+    labels_all = np.array([], dtype=int)
+    result_list = ["男科","内科","妇产科","肿瘤科","儿科","外科"]
+    text = []
+    for texts, labels in train_iter:
+        outputs = model(texts)
+        labels = labels.data.cpu().numpy()
+        predic = torch.max(outputs.data, 1)[1].cpu().numpy()
+        labels_all = np.append(labels_all, labels)
+        predict_all = np.append(predict_all, predic)
+        result = predict_all[0] # 大科室对应的 数字顺序
+        DaKeShi = result_list[result]
+        text.append(DaKeShi)
+        XiaoKeShi, most_similar_answer = proceed(content, result, content_vector)
+        text.append(XiaoKeShi)
+        text.append(most_similar_answer)
+        print(XiaoKeShi)
+        print(most_similar_answer)
+    return text
+
+
+

utils.py

@@ -0,0 +1,156 @@
+# coding: UTF-8
+import os
+import torch
+import numpy as np
+import pickle as pkl
+from tqdm import tqdm
+import time
+from datetime import timedelta
+
+
+MAX_VOCAB_SIZE = 10000  # 词表长度限制
+UNK, PAD = '<UNK>', '<PAD>'  # 未知字，padding符号
+
+
+def build_vocab(file_path, tokenizer, max_size, min_freq):
+    vocab_dic = {}
+    with open(file_path, 'r', encoding='UTF-8') as f:
+        for line in tqdm(f):
+            lin = line.strip()
+            if not lin:
+                continue
+            content = lin.split('\t')[0]
+            for word in tokenizer(content):
+                vocab_dic[word] = vocab_dic.get(word, 0) + 1
+        vocab_list = sorted([_ for _ in vocab_dic.items() if _[1] >= min_freq], key=lambda x: x[1], reverse=True)[:max_size]
+        vocab_dic = {word_count[0]: idx for idx, word_count in enumerate(vocab_list)}
+        vocab_dic.update({UNK: len(vocab_dic), PAD: len(vocab_dic) + 1})
+    return vocab_dic
+
+
+def build_dataset(config, ues_word):
+    if ues_word:
+        tokenizer = lambda x: x.split(' ')  # 以空格隔开，word-level
+    else:
+        tokenizer = lambda x: [y for y in x]  # char-level
+    if os.path.exists(config.vocab_path):
+        vocab = pkl.load(open(config.vocab_path, 'rb'))  #打开词表文件
+    else:
+        vocab = build_vocab(config.train_path, tokenizer=tokenizer, max_size=MAX_VOCAB_SIZE, min_freq=1)
+        pkl.dump(vocab, open(config.vocab_path, 'wb'))
+    print(f"Vocab size: {len(vocab)}")
+
+    def load_dataset(path, pad_size=32):
+        contents = []
+        with open(path, 'r', encoding='UTF-8') as f:
+            for line in tqdm(f):
+                lin = line.strip()
+                if not lin:
+                    continue
+                content, label = lin.split('\t')
+                words_line = []
+                token = tokenizer(content)
+                seq_len = len(token)
+                if pad_size:
+                    if len(token) < pad_size:
+                        token.extend([PAD] * (pad_size - len(token)))
+                    else:
+                        token = token[:pad_size]
+                        seq_len = pad_size
+                # word to id
+                for word in token:
+                    words_line.append(vocab.get(word, vocab.get(UNK)))
+                contents.append((words_line, int(label), seq_len))
+        return contents  # [([...], 0), ([...], 1), ...]
+    train = load_dataset(config.train_path, config.pad_size)
+    dev = load_dataset(config.dev_path, config.pad_size)
+    test = load_dataset(config.test_path, config.pad_size)
+    return vocab, train, dev, test
+
+
+class DatasetIterater(object):
+    def __init__(self, batches, batch_size, device):
+        self.batch_size = batch_size
+        self.batches = batches
+        self.n_batches = len(batches) // batch_size
+        self.residue = False  # 记录batch数量是否为整数
+        # if len(batches) % self.n_batches != 0:
+        #     self.residue = True
+        self.residue = True #手动加一句
+        self.index = 0
+        self.device = device
+
+    def _to_tensor(self, datas):
+        x = torch.LongTensor([_[0] for _ in datas]).to(self.device)
+        y = torch.LongTensor([_[1] for _ in datas]).to(self.device)
+
+        # pad前的长度(超过pad_size的设为pad_size)
+        seq_len = torch.LongTensor([_[2] for _ in datas]).to(self.device)
+        return (x, seq_len), y
+
+    def __next__(self):
+        if self.residue and self.index == self.n_batches:
+            batches = self.batches[self.index * self.batch_size: len(self.batches)]
+            self.index += 1
+            batches = self._to_tensor(batches)
+            return batches
+
+        elif self.index >= self.n_batches:
+            self.index = 0
+            raise StopIteration
+        else:
+            batches = self.batches[self.index * self.batch_size: (self.index + 1) * self.batch_size]
+            self.index += 1
+            batches = self._to_tensor(batches)
+            return batches
+
+    def __iter__(self):
+        return self
+
+    def __len__(self):
+        if self.residue:
+            return self.n_batches + 1
+        else:
+            return self.n_batches
+
+
+def build_iterator(dataset, config):
+    iter = DatasetIterater(dataset, config.batch_size, config.device)
+    return iter
+
+
+def get_time_dif(start_time):
+    """获取已使用时间"""
+    end_time = time.time()
+    time_dif = end_time - start_time
+    return timedelta(seconds=int(round(time_dif)))
+
+
+if __name__ == "__main__":
+    '''提取预训练词向量'''
+    # 下面的目录、文件名按需更改。
+    train_dir = "./THUCNews/data/train.txt"
+    vocab_dir = "./THUCNews/data/vocab.pkl"
+    pretrain_dir = "./THUCNews/data/sgns.sogou.char"
+    emb_dim = 300
+    filename_trimmed_dir = "./THUCNews/data/embedding_SougouNews"
+    if os.path.exists(vocab_dir):
+        word_to_id = pkl.load(open(vocab_dir, 'rb'))
+    else:
+        # tokenizer = lambda x: x.split(' ')  # 以词为单���构建词表(数据集中词之间以空格隔开)
+        tokenizer = lambda x: [y for y in x]  # 以字为单位构建词表
+        word_to_id = build_vocab(train_dir, tokenizer=tokenizer, max_size=MAX_VOCAB_SIZE, min_freq=1)
+        pkl.dump(word_to_id, open(vocab_dir, 'wb'))
+
+    embeddings = np.random.rand(len(word_to_id), emb_dim)
+    f = open(pretrain_dir, "r", encoding='UTF-8')
+    for i, line in enumerate(f.readlines()):
+        # if i == 0:  # 若第一行是标题，则跳过
+        #     continue
+        lin = line.strip().split(" ")
+        if lin[0] in word_to_id:
+            idx = word_to_id[lin[0]]
+            emb = [float(x) for x in lin[1:301]]
+            embeddings[idx] = np.asarray(emb, dtype='float32')
+    f.close()
+    np.savez_compressed(filename_trimmed_dir, embeddings=embeddings)