pytorch-task4

import os
import csv
import jieba
import warnings
import numpy as np
import pandas as pd
from tqdm import tqdm
from gensim.models import Word2Vec
import torch
import torch.nn as nn
from torch.optim import Adam
import torch.autograd as autograd
from sklearn.model_selection import train_test_split

warnings.filterwarnings("ignore")

class_num = 10
batch_size = 256
maxlen = 500
word2vec_size = 100

train_dir = './data/cnews/cnews.train.txt'
valid_dir = './data/cnews/cnews.val.txt'
test_dir = './data/cnews/cnews.test.txt'
word2vec_dir = './word2vec/word2vec.hdf5'
userdict_dir = './dict/userdict.txt'
stopword_dir = './dict/stopword.txt'

def cut_word(x, stop_word):
    words = []
    for word in list(jieba.cut(x)):
        if word not in stop_word and len(word) != 1:
            words.append(word)
    return words


def get_word_vocab(content):
    word_vocb = []
    for sentence in content:
        word_vocb.extend(list(set(sentence)))
    return list(set(word_vocb))


def get_x(content, word_index):
    X = np.array((len(content), maxlen))
    for i in range(len(content)):
        if len(content[i]) < maxlen:
            for j in range(0, len(content[i])):
                X[i][j] = word_index[content[i][j]]
        else:
            for j in range(0, maxlen):
                X[i][j] = word_index[content[i][j]]
    return X


def get_label_vector(label):
    label_code = pd.get_dummies(list(set(label)))
    label_vector = dict()
    for col in label_code.columns:
        label_vector[col] = label_code[col].tolist()
    return label_vector


print('read data')
data = pd.read_csv(test_dir, delimiter='\t', index_col=None, names=['label', 'content'])
test = pd.read_csv(valid_dir, delimiter='\t', index_col=None, names=['label', 'content'])

print(data.shape)
print(test.shape)

print('cut word')
jieba.load_userdict(userdict_dir)
stop_word = pd.read_csv(stopword_dir, quoting=csv.QUOTE_NONE, index_col=None, names=['word'])['word'].tolist()
data['content'] = data['content'].apply(lambda x: cut_word(x, stop_word))
test['content'] = test['content'].apply(lambda x: cut_word(x, stop_word))
content = pd.concat([data['content'], test['content']], axis=0, ignore_index=True)

print('word vocab')
word_vocab = get_word_vocab(content)
word_index = dict(zip(word_vocab, range(1, len(word_vocab) + 1)))
index_word = dict(zip(list(word_index.values()), list(word_index.keys())))

print('word2vec')
if not os.path.exists(word2vec_dir):
    model = Word2Vec(content, size=word2vec_size, seed=2019, min_count=6, window=10, iter=8, workers=8)
    model.save(word2vec_dir)
else:
    model = Word2Vec.load(word2vec_dir)

embedding_matrix = np.zeros((len(word_index) + 1, word2vec_size))
for word, i in word_index.items():
    if word in model:
        embedding_matrix[i] = model[word]
print(embedding_matrix.shape)

print('label_vector')
label_vector = get_label_vector(data['label'])

class DataLoader(object):
    def __init__(self, data, config):
        self.data = data
        self.batch_size = config['batch_size']
        self.maxlen = config['maxlen']
        self.word_index = config['word_index']
        self.label_vector = config['label_vector']

    def pad_sequences(self, content):
        sequences = np.zeros((len(content), self.maxlen))
        for i in range(len(content)):
            if len(content[i]) < maxlen:
                for j in range(0, len(content[i])):
                    sequences[i][j] = self.word_index[content[i][j]]
            else:
                for j in range(0, maxlen):
                    sequences[i][j] = self.word_index[content[i][j]]
        return sequences

    def train_batch_data(self, is_shuffle=True):
        if is_shuffle:
            self.data = self.data.sample(frac=1).reset_index(drop=True)

        length = len(self.data) // self.batch_size

        if self.batch_size * length < len(self.data):
            length += 1

        for i in tqdm(range(length)):
            if self.batch_size * (i + 1) > len(self.data):
                batch_data = self.data['content'].iloc[self.batch_size * i:]
            else:
                batch_data = self.data['content'].iloc[self.batch_size * i:self.batch_size * (i + 1)]
            sequences = self.pad_sequences(batch_data)
            label = self.data['label'].map(self.label_vector)
            yield torch.LongTensor(sequences), torch.LongTensor(label)

    def test_batch_data(self):
        length = len(self.data) // self.batch_size

        if self.batch_size * length < len(self.data):
            length += 1

        for i in tqdm(range(length)):
            if self.batch_size * (i + 1) > len(self.data):
                batch_data = self.data['content'].iloc[self.batch_size * i:]
            else:
                batch_data = self.data['content'].iloc[self.batch_size * i:self.batch_size * (i + 1)]
            sequences = self.pad_sequences(batch_data)
            yield torch.LongTensor(sequences)

class TextCNN(nn.Module):
    def __init__(self, config):
        super(TextCNN, self).__init__()
        self.class_num = config['class_num']
        self.embedding_matrix = config['embedding_matrix']

        self.embeding = nn.Embedding(self.embedding_matrix.shape[0], self.embedding_matrix.shape[1], _weight=self.embedding_matrix)
        self.conv1 = nn.Sequential(
            nn.Conv2d(in_channels=1, out_channels=16, kernel_size=5, stride=1, padding=2),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2))
        self.conv2 = nn.Sequential(
            nn.Conv2d(in_channels=16, out_channels=32, kernel_size=5, stride=1, padding=2),
            nn.ReLU(),
            nn.MaxPool2d(2))
        self.conv3 = nn.Sequential(
            nn.Conv2d(in_channels=32, out_channels=64, kernel_size=5, stride=1, padding=2),
            nn.ReLU(),
            nn.MaxPool2d(2))
        self.conv4 = nn.Sequential(
            nn.Conv2d(in_channels=64, out_channels=128, kernel_size=5, stride=1, padding=2),
            nn.ReLU(),
            nn.MaxPool2d(2))
        self.out = nn.Linear(256, self.class_num)

    def forward(self, x):
        x = self.embeding(x)
        x = x.view(x.size(0), 1, maxlen, word2vec_size)
        x = self.conv1(x)
        x = self.conv2(x)
        x = self.conv3(x)
        x = self.conv4(x)
        x = x.view(x.size(0), -1)  # 将（batch，outchanel,w,h）展平为（batch，outchanel*w*h）
        print(x.size(0))
        print(x.size())
        output = self.out(x)
        return output

class Model(object):
    def __init__(self, train_loader, valid_loader, test_loader, config):
        self.train_loader = train_loader
        self.valid_loader = valid_loader
        self.test_loader = test_loader
        self.model = TextCNN(config=config)
        self.criterion = nn.CrossEntropyLoss()
        self.optimizer = Adam(self.model.parameters(), lr=config['learning_rate'])

    def verification(self):
        res = []
        for query, title, fea, label in self.valid_loader.train_batch_data(is_shuffle=True):
            out = self.model(query, title, fea)
            res.extend([item.detach().numpy()[1] for item in list(out)])
    
        res = pd.DataFrame(res, columns=['pred'])
        valid_ans = pd.concat([self.valid_loader.data.loc[:, ['query_id', 'label']], res], axis=1)
    
        qauc = calculate_qauc(valid_ans)
        print('qauc is:')
        print(qauc)
        if qauc > self.mx_qauc:
            self.mx_qauc = qauc
            torch.save(self.model, './wnd/model/model.pkl')

    def fit(self, epoch):
        for i in range(epoch):
            for sequences, label in self.train_loader.train_batch_data():
                print(sequences)
                out = self.model(sequences)  # 前向传播求出的预测值
                self.optimizer.zero_grad()  # 将梯度初始化为零
                loss = self.criterion(out, autograd.Variable(label.long()))  # 损失函数
                loss.backward()  # 反向传播求梯度
                self.optimizer.step()  # 更新所有参数

            # self.verification()

    def restore(self):
        self.model = torch.load('./wnd/model/model.pkl')

    def predict(self):
        res = []
        for sequences in self.test_loader.test_batch_data():
            out = self.model(sequences)
            res.extend([item.detach().numpy()[1] for item in list(out)])

        res = pd.DataFrame(res, columns=['pred'])
        res.to_csv('./nn_res.csv', header=None, index=None, sep=',')

config = dict()
config['batch_size'] = batch_size
config['maxlen'] = maxlen
config['word_index'] = word_index
config['label_vector'] = label_vector
config['class_num'] = class_num
config['learning_rate'] = 1e-3
config['embedding_matrix'] = torch.Tensor(embedding_matrix)

data = data.sample(frac=1).reset_index(drop=True)
train = data.head(8000)
valid = data.tail(2000)

print('data', data.shape)
print('train', train.shape)
print('valid', valid.shape)
print('test', test.shape)

train_loader = DataLoader(train, config)
valid_loader = DataLoader(valid, config)
test_loader = DataLoader(test, config)
model = Model(train_loader, valid_loader, test_loader, config)
model.fit(2)
# model = Model(train_loader, valid_loader, test_loader, config)
# model.restore()
model.predict()