RNN Classifier – Name Classification

RNN Classifier – Name Classification

实验使用的数据集链接：

链接: https://pan.baidu.com/s/1EXEX3349JrWSuI-Bwp4Ywg 提取码: vzk5

实验目标：预测给出的姓名是属于哪种语言（共有18中语言）。下图示例：

实验模型：

1.将姓名转换成对应的字母序列，方便使用循环神经网络进行处理。
2.使用嵌入层将字母序列进行维度的转变。
3.将转变后的数据放入GRU中进行处理（选择双向循环神经网络）。
4.使用线性层输出18维，用于判断从属类型。
模型流程图：

网络模型：

class RNNClassifier(torch.nn.Module):
    def __init__(self, input_size, hidden_size, output_size, n_layers=1, bidirectional=True):
        super(RNNClassifier, self).__init__()
        self.hidden_size = hidden_size
        self.n_layers = n_layers
        self.n_directions = 2 if bidirectional else 1
        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, inputs, seq_lengths):
        # input shape : B x S -> S x B
        # print(type(inputs))
        # print(inputs)
        inputs = inputs.t()
        # Save batch-size for make initial hidden.
        batch_size = inputs.size(1)
        # 构建 h0-> (nlayer*nDirections,batchSize,hiddenSize)
        hidden = self._init_hidden(batch_size)
        # embedding 的形状 (seqlen,batchsize,hiddensize)
        embedding = self.embedding(inputs)
        # pack them up   目的：快速进行整合  整体快速运算  It returns a PackedSquence object.
        gru_input = pack_padded_sequence(embedding, seq_lengths)
        # print(len(gru_input))
        # 返回hidden   （nlayer*nDirection,batchsize,hiddensize） 
        output, hidden = self.gru(gru_input, hidden)
        # f we use bidirectional GRU, the forward hidden and backward hidden should be concatenate.
        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

Convert name to tensor:

# Convert name to tensor
def make_tensors(names, countries):
    """

    :param names: 人名
    :param countries: 人名->国家
    :return:
    """
    # 构建姓名字母列表
    sequences_and_lengths = [name2list(name) for name in names]
    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()
    # 做填充padding
    # make tensor of name, BatchSize x SeqLen
    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
    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)

Datesets 处理：

class NameDataset(Dataset):
    def __init__(self, is_train_set=True):
        super(NameDataset, self).__init__()
        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)
        self.names = [row[0] for row in rows]
        self.len = len(self.names)
        self.countries = [row[1] for row in rows]
        self.country_list = list(sorted(set(self.countries)))  # set 去重
        self.country_dict = self.getCountryDict()
        self.country_num = len(self.country_list)

    def __getitem__(self, index):
        return self.names[index], self.country_dict[self.countries[index]]

    def __len__(self):
        return self.len

    def getCountryDict(self):
    	# 将list 转换成 dictionary
        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)
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()

完整实验代码：

import csv
import gzip
import math
import time

import matplotlib.pyplot as plt
import numpy as np
import torch
from torch.nn.utils.rnn import pack_padded_sequence
from torch.utils.data import DataLoader, Dataset

#  数据准备


# Parameters
HIDDEN_SIZE = 100
BATCH_SIZE = 256
N_LAYER = 2
N_EPOCHS = 100
N_CHARS = 128
USE_GPU = False


class NameDataset(Dataset):
    def __init__(self, is_train_set=True):
        super(NameDataset, self).__init__()
        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)
        self.names = [row[0] for row in rows]
        self.len = len(self.names)
        self.countries = [row[1] for row in rows]
        self.country_list = list(sorted(set(self.countries)))  # set 去重
        self.country_dict = self.getCountryDict()
        self.country_num = len(self.country_list)

    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)
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()


# 将Tensor 转到gpu上
def create_tensor(tensor):
    device = ('cuda' if torch.cuda.is_available() else 'cpu')
    tensor = tensor.to(device)
    return tensor


# 将姓名字母转换成对应的ASCll值
def name2list(name):
    arr = [ord(c) for c in name]
    return arr, len(arr)


# Convert name to tensor
def make_tensors(names, countries):
    """

    :param names: 人名
    :param countries: 人名->国家
    :return:
    """
    sequences_and_lengths = [name2list(name) for name in names]
    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()
    # 做填充padding
    # make tensor of name, BatchSize x SeqLen
    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
    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)


class RNNClassifier(torch.nn.Module):
    def __init__(self, input_size, hidden_size, output_size, n_layers=1, bidirectional=True):
        super(RNNClassifier, self).__init__()
        self.hidden_size = hidden_size
        self.n_layers = n_layers
        self.n_directions = 2 if bidirectional else 1
        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, inputs, seq_lengths):
        # input shape : B x S -> S x B
        # print(type(inputs))
        # print(inputs)
        inputs = inputs.t()
        batch_size = inputs.size(1)
        hidden = self._init_hidden(batch_size)
        embedding = self.embedding(inputs)
        # pack them up   快速进行整合  整体快速运算
        gru_input = pack_padded_sequence(embedding, seq_lengths)
        # print(len(gru_input))
        output, hidden = self.gru(gru_input, hidden)
        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


# 模型训练
def trainModel():
    """

    :return: 返回损失
    """
    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)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        total_loss += loss.item()
        if i % 10 == 0:
            print(f'[{time_since(start)}] Epoch {epoch} ', end='')
            print(f'[{i * len(inputs)}/{len(trainset)}] ', end='')
            print(f'loss={total_loss / (i * len(inputs))}')
    return total_loss


# 测试
def testModel():
    """

    :return:  返回准确率
    """
    correct = 0
    total = len(testset)
    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()
        percent = '%.2f' % (100 * correct / total)
        print(f'Test set: Accuracy {correct}/{total} {percent}%')
    return correct / total


def time_since(since):
    """

    :param since:
    :return:  计算每一次运行花费多长时间
    """
    s = time.time() - since
    m = math.floor(s / 60)
    s -= m * 60
    return '%dm %ds' % (m, s)


if __name__ == '__main__':
    classifier = RNNClassifier(N_CHARS, HIDDEN_SIZE, N_COUNTRY, N_LAYER)
    if USE_GPU:
        device = torch.device("cuda:0")
        classifier.to(device)
    criterion = torch.nn.CrossEntropyLoss()
    optimizer = torch.optim.Adam(classifier.parameters(), lr=0.001)
    start = time.time()
    print("Training for %d epochs..." % N_EPOCHS)
    acc_list = []
    for epoch in range(1, N_EPOCHS + 1):
        # Train cycle
        trainModel()
        acc = testModel()
        acc_list.append(acc)

    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()

实验结果：

实验在20个epoch内准确率达到了最大，准确率接近85%。