app.py

import argparse
import os
from importlib import import_module

import gradio as gr
from tqdm import tqdm
import models.TextCNN
import torch
import pickle as pkl
from utils import build_dataset

classes = ['金融类', '房地产类', '股票类', '教育类', '科技类', '社会类', '政治类', '体育类', '游戏类',
           '娱乐类']

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 greet(text):
    parser = argparse.ArgumentParser(description='Chinese Text Classification')
    parser.add_argument('--word', default=False, type=bool, help='True for word, False for char')
    args = parser.parse_args()
    model_name = 'TextCNN'
    dataset = 'THUCNews'  # 数据集
    embedding = 'embedding_SougouNews.npz'
    x = import_module('models.' + model_name)

    config = x.Config(dataset, embedding)
    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

    model = models.TextCNN.Model(config)

    # vocab, train_data, dev_data, test_data = build_dataset(config, args.word)
    model.load_state_dict(torch.load('THUCNews/saved_dict/TextCNN.ckpt', map_location=torch.device('cpu')))
    model.to(device)
    model.eval()

    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'))
    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)}")

    # content='时评：“国学小天才”录取缘何少佳话'
    content = text

    words_line = []
    token = tokenizer(content)
    seq_len = len(token)
    pad_size = 32
    contents = []

    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, seq_len))
    # print(words_line)
    # input = torch.LongTensor(words_line).unsqueeze(1).to(device)  # convert words_line to LongTensor and add batch dimension
    x = torch.LongTensor([_[0] for _ in contents]).to(device)

    # pad前的长度(超过pad_size的设为pad_size)
    seq_len = torch.LongTensor([_[1] for _ in contents]).to(device)
    input = (x, seq_len)
    # print(input)
    with torch.no_grad():
        output = model(input)
        predic = torch.max(output.data, 1)[1].cpu().numpy()
    # print(predic)
    # print('类别为：{}'.format(classes[predic[0]]))
    return classes[predic[0]]




inputs = gr.inputs.Textbox(label="输入文本")
outputs = gr.outputs.Textbox(label="输出结果")

css = """
.gradio-input-wrapper {
    margin-bottom: 20px;
}

.gradio-output-wrapper {
    margin-top: 20px;
}

.gradio-interface {
    max-width: 600px;
    margin: 0 auto;
    background-color: #f8f8f8;
    padding: 20px;
    border-radius: 10px;
    box-shadow: 2px 2px 10px rgba(0, 0, 0, 0.2);
}

.gradio-interface h1 {
    font-size: 32px;
    font-weight: bold;
    text-align: center;
    margin-bottom: 20px;
}

.gradio-input label, .gradio-output label {
    display: block;
    margin-bottom: 10px;
    font-size: 18px;
    font-weight: bold;
}

.gradio-input textarea, .gradio-output textarea {
    width: 100%;
    height: 120px;
    padding: 10px;
    border: none;
    border-radius: 5px;
    box-shadow: inset 1px 1px 5px rgba(0, 0, 0, 0.1);
    font-size: 16px;
    line-height: 24px;
}

.gradio-output textarea {
    background-color: #f8f8f8;
    color: #333;
}

.gradio-btn {
    display: inline-block;
    padding: 12px 20px;
    margin-top: 20px;
    font-size: 18px;
    font-weight: bold;
    text-align: center;
    color: #ffffff;
    background-color: #1abc9c;
    border: none;
    border-radius: 5px;
    cursor: pointer;
    transition: background-color 0.2s;
}

.gradio-btn:hover {
    background-color: #16a085;
}
"""

interface = gr.Interface(fn=classify_text, inputs=inputs, outputs=outputs, title="中文文本分类器", css=css)

interface.launch()


# demo = gr.Interface(fn=greet, inputs="text", outputs="text", title="text-classification app", 
#                      layout="vertical", description="This is a demo for text classification.")
# demo.launch()