python 构建RNN分类器对“名字-国家”文本分类、并使用Visdom绘制loss值和acc值

---

前言

为什么使用RNN对文本的分类？
RNN考虑当前输入以及先前接收的输入，前文出现内容将影响接下来要出现的内容。因此RNN是文本和语音分析的理想选择。

Visdom的安装与使用：

https://blog.csdn.net/qq_42962681/article/details/116271548?spm=1001.2014.3001.5501

刘二大人b站讲解视频：

https://www.bilibili.com/video/BV1Y7411d7Ys？p=13&share_source=copy_web

---

提示：以下是本篇文章正文内容，下面案例可供参考

一、名字对应的国家分类

如图所示：通过训练，快速的预测各个姓名对应的国家。

---

二、整体程序

1.代码

代码中使用的数据集连接如下

链接：https://pan.baidu.com/s/1jCmi8Qj6lzzb4R4rUgMEew
提取码：trac

---

代码如下（示例）：

import torch
import time
from torch.utils.data import DataLoader
from torch.utils.data import Dataset
import gzip
import csv
import matplotlib.pyplot as plt
import numpy as np
import math
from torch.nn.utils.rnn import pack_padded_sequence
# 引入可视化工具visdom
import visdom

#国家-人名进行分类
HIDDEN_SIZE = 100
BATCH_SIZE =256
N_LAYER =2
N_EPOCHS = 100
N_CHARS = 128
USE_GPU = True

# 为训练添加环境变量，之后程序产生的所有数据都会出现在这个环境变量中，visdom就可以监听数据实现可视化
# 而且在visdom中还可以按照环境变量名选择性监听，便于分类管理
viz = visdom.Visdom(env='countries_names')

# 创建线图初始点。loss是差值图，acc是精度图
viz.line([0], [0], win='train_loss', opts=dict(title='train loss'))
viz.line([0], [0], win='acc', opts=dict(title='test acc'))

#读取数据集
class NameDataset(Dataset):
    def __init__(self, is_train_set = True):
        # 判断是否要训练集还是测试集
        filename = 'names_train.csv.gz' if is_train_set else 'names_test.csv.gz'
        with gzip.open(filename, 'rt') as f:
            reader = csv.reader(f)
            rows = list(reader)
        # 提取数据集中的名字
        self.names = [row[0] for row in rows]
        self.len = len(self.names)
        self.countries = [row[1] for row in rows]
        # set变成集合去除重复国家 sort排序 list 生成列表
        self.country_list = list(sorted(set(self.countries)))
        # 将列表变成词典
        self.country_dict = self.getCountryDict()
        self.country_num = len(self.country_list)

    # 返回名字（字符串）和对应的国家（索引）
    def __getitem__(self, index):
        return self.names[index], self.country_dict[self.countries[index]]

    def __len__(self):
        return self.len

    def getCountryDict(self):
        country_dict = dict()
        for idx, country_name in enumerate(self.country_list, 0):
            country_dict[country_name] = idx
        return  country_dict

    def idx2country(self, index):
        return self.country_list[index]

    def getCountriesNum(self):
        return self.country_num

trainset = NameDataset(is_train_set=True)
# print(len(trainset))
trainloader = DataLoader(trainset, batch_size = BATCH_SIZE, shuffle=True)
testset = NameDataset(is_train_set=False)
testloader = DataLoader(testset, batch_size = BATCH_SIZE, shuffle=False)

N_COUNTRY = trainset.getCountriesNum()

#构建模型
class RNNClassifier(torch.nn.Module):
    def __init__(self, input_size, hidden_size, output_size, n_layers=1, bidirectional=True):  # 构造函数
        super(RNNClassifier, self).__init__()
        self.hidden_size = hidden_size
        self.n_layers = n_layers
        self.n_directions = 2 if bidirectional else 1

        # bidirectional 双向循环网络
        self.embedding = torch.nn.Embedding(input_size, hidden_size)
        self.gru = torch.nn.GRU(hidden_size, hidden_size, n_layers,
                                bidirectional=bidirectional)
        self.fc = torch.nn.Linear(hidden_size*self.n_directions, output_size)

    def _init_hidden(self, batch_size):
        hidden = torch.zeros((self.n_layers * self.n_directions,
                              batch_size, self.hidden_size))
        return create_tensor(hidden)

    def forward(self, input, seq_lengths):
        #input shape: BXS -> SXB
        #结合下方make_tensors和trainModel
        input = input.t()
        batch_size = input.size(1)

        hidden = self._init_hidden(batch_size)
        embedding = self.embedding(input)

        #pack them up
        # 将填充的0计算时去除，提升运算效率，并按单词序列长度从大到小进行排序
        gru_input = pack_padded_sequence(embedding, seq_lengths)

        output, hidden = self.gru(gru_input, hidden)
        # 判断是否为双向gru,是的话进行拼接
        if self.n_directions == 2:
            hidden_cat = torch.cat([hidden[-1], hidden[-2]],dim=1)
        else:
            hidden_cat = hidden[-1]
        fc_output = self.fc(hidden_cat)
        return fc_output

#将名字转换成ASSIC并进行填充，输入序列为矩阵，因为名字长短不一，
# 需要将名字填充到最长的名字的长度名字转换为tensor
def name2list(name):
    arr = [ord(c) for c in name]
    return arr, len(arr)

def make_tensors(names, countries):
    sequences_and_lengths = [name2list(name) for name in names]
    # 名字长度
    name_sequences = [sl[0] for sl in sequences_and_lengths]
    seq_lengths = torch.LongTensor([sl[1] for sl in sequences_and_lengths])
    countries = countries.long()

    #make tensor of name, BatchSize x SeqLen
    # 先生成全0的tensor，再将名字序列赋值进去
    seq_tensor = torch.zeros(len(name_sequences), seq_lengths.max()).long()
    for idx, (seq, seq_len) in enumerate(zip(name_sequences, seq_lengths), 0):
        seq_tensor[idx, :seq_len] = torch.LongTensor(seq)

    #sort by length to use pack_padded_sequence
    # 按照序列长度进行排序sort返回排序后的序列和排序后的索引
    seq_lengths, perm_idx = seq_lengths.sort(dim=0, descending=True)
    seq_tensor = seq_tensor[perm_idx]
    countries = countries[perm_idx]

    return create_tensor(seq_tensor),create_tensor(seq_lengths), create_tensor(countries)

global_step = 0.0
global_step2 = 0.0
#训练
#python中计时以秒做单位，除以60转换为分钟，做后做一个分钟和秒的显示
def trainModel():
    def time_since(since):
        s = time.time() - since
        m = math.floor(s / 60)
        s -= m * 60
        return '%dm %ds' % (m, s)

    global global_step
    total_loss = 0
    for i, (names, countries) in enumerate(trainloader, 1):
        inputs, seq_lengths, target = make_tensors(names, countries)
        output = classifier(inputs, seq_lengths)
        loss = criterion(output, target)
        # print( loss)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        # 更新全局步数
        global_step = global_step + 1
        # print(global_step,loss)
        # 数据变化，点与点用线line连接
        viz.line([loss.item()], [global_step], win='train_loss', update='append')
        total_loss += loss.item()
        
        #10个batch_size进行一轮输出
        if i % 10 == 0:
            print(f'[{time_since(start)}] Epoch {epoch}',end='')
            print(f'[{i * len(inputs)} / {len(trainset)}]', end='')
            # ?len(inputs)应该删除？
            print(f'loss={total_loss / (i )}')
            # print(f'loss={total_loss / (i * len(inputs))}')
    return total_loss

#测试
def testModel():
    correct = 0
    # total = len(testset)
    total = 0
    global global_step2
    print('evaluating trained model ...')
    with torch.no_grad():
        for i, (names,countries) in enumerate(testloader, 1):
            inputs, seq_lengths, target = make_tensors(names, countries)
            output = classifier(inputs, seq_lengths)
            pred = output.max(dim=1, keepdim=True)[1]
            correct += pred.eq(target.view_as(pred)).sum().item()

            total += target.size(0)
            # 更新全局步数
            global_step2 = global_step2 + 1
            # 精度可视化显示
        viz.line([correct / total], [global_step2], win='acc', update='append')

        percent = '%.2f' % (100 * correct / total)
        print(f'Test set: Accuracy {correct}/{total} {percent}%')

    return correct / total

#调用GPU
def create_tensor(tensor):
    if USE_GPU:
        device = torch.device("cuda:0")
        tensor = tensor.to(device)
    return tensor

#训练
#N_CHARS：英文字母
classifier = RNNClassifier(N_CHARS, HIDDEN_SIZE, N_COUNTRY, N_LAYER)
classifier = create_tensor(classifier)

#损失函数和优化器
criterion = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(classifier.parameters(), lr=0.01)

start = time.time()
print('Training for %d epochs...'% N_EPOCHS)
# acc_list = []
if __name__=='__main__':
    for epoch in  range(1, N_EPOCHS + 1):
        # TRAIN CYCLE
        trainModel()
        acc = testModel()
        #
        # #每个epoch 记录准确率
        # acc_list.append(acc)

#也可使用matplolib进行可视化绘图
#可视化
# epoch = np.arange(1, len(acc_list) + 1, 1)
# acc_list = np.array(acc_list)
# plt.plot(epoch, acc_list)
# plt.xlabel('Epoch')
# plt.ylabel('Accuracy')
# plt.grid()
# plt.show()

---

2.Visdom输出的结果

loss值如下：

acc值如下：

---

总结

以上就是对学习的一个小总结，也是对RNN网络的一个简单了解、本文仅仅是简单的举了一个学习的小例子，以后的学习还需要倍加努力。前方要学习的还很多，你我共勉！加油！