Pytorch：预测姓名的所属国家

Posted 2021-05-02 CollectTime

目的：通过建立RNN模型，给定一个姓名，预测该姓名属于哪一个国家。

方法：首先将字母进行独热编码，然后输入给RNN，output与target比较并且训练网络。

数据：https://download.pytorch.org/tutorial/data.zip

里面有各种国家的姓名，都是使用英文表示的。

用python读取数据，同时将每一个国家的数据全部读取到一个列表中，全部使用字典进行表示。

{language: [names ...]}

代码：

# -*- coding: utf-8 -*-
from __future__ import unicode_literals, print_function, division
from io import open
import glob

def findFiles(path): return glob.glob(path)

print(findFiles(r'./data/data/names/*.txt'))#获得data/name下所有txt文件

import unicodedata
import string        

all_letters = string.ascii_letters + " .,;'"
n_letters = len(all_letters)#用于one hot 编码

# Turn a Unicode string to plain ASCII, thanks to http://stackoverflow.com/a/518232/2809427
def unicodeToAscii(s):
    return ''.join(
        c for c in unicodedata.normalize('NFD', s)
        if unicodedata.category(c) != 'Mn'
        and c in all_letters
    )

print(unicodeToAscii('Ślusàrski'))

out:

['data/names/Russian.txt', 'data/names/Scottish.txt', 
'data/names/Spanish.txt', 'data/names/Vietnamese.txt', 
'data/names/Arabic.txt', 'data/names/Chinese.txt', 
'data/names/Czech.txt', 'data/names/Dutch.txt', 
'data/names/English.txt', 'data/names/French.txt', 
'data/names/German.txt', 'data/names/Greek.txt', 
'data/names/Irish.txt', 'data/names/Italian.txt', 
'data/names/Japanese.txt', 'data/names/Korean.txt', 
'data/names/Polish.txt', 'data/names/Portuguese.txt']
Slusarski

2:对数据更新字母层面上的独热编码：

# Build the category_lines dictionary, a list of names per language
category_lines = {}
all_categories = []

#{language: [names ...]}
# Read a file and split into lines
def readLines(filename):
    lines = open(filename, encoding='utf-8').read().strip().split('\n')
    return [unicodeToAscii(line) for line in lines]

for filename in findFiles(r'./data/data/names/*.txt'):
    category = filename.split('/')[-1].split('.')[0]
    all_categories.append(category)
    lines = readLines(filename)
    category_lines[category] = lines

n_categories = len(all_categories)
print(n_categories)

import torch

# Find letter index from all_letters, e.g. "a" = 0
def letterToIndex(letter):
    return all_letters.find(letter)

# Just for demonstration, turn a letter into a <1 x n_letters> Tensor
def letterToTensor(letter):
    tensor = torch.zeros(1, n_letters) #n_letters = len(all_letters)
    tensor[0][letterToIndex(letter)] = 1
    return tensor

# Turn a line into a <line_length x 1 x n_letters>,
# or an array of one-hot letter vectors
def lineToTensor(line):
    tensor = torch.zeros(len(line), 1, n_letters)
    for li, letter in enumerate(line):
        tensor[li][0][letterToIndex(letter)] = 1
    return tensor#转化为矩阵

print(letterToTensor('J'))

print(lineToTensor('Jones').size())

Columns 0 to 12
    0     0     0     0     0     0     0     0     0     0     0     0     0Columns 13 to 25
    0     0     0     0     0     0     0     0     0     0     0     0     0Columns 26 to 38
    0     0     0     0     0     0     0     0     0     1     0     0     0Columns 39 to 51
    0     0     0     0     0     0     0     0     0     0     0     0     0Columns 52 to 56
    0     0     0     0     0
[torch.FloatTensor of size 1x57]

torch.Size([5, 1, 57])

3：构建RNN网络，框架和之前的CNN网络类似，只不过需要具体到RNN内部结构的一些设计。

RNN结构：

import torch.nn as nn
from torch.autograd import Variable

class RNN(nn.Module):
    def __init__(self, input_size, hidden_size, output_size):
        super(RNN, self).__init__()

        self.hidden_size = hidden_size

        self.i2h = nn.Linear(input_size + hidden_size, hidden_size)
        self.i2o = nn.Linear(input_size + hidden_size, output_size)
        self.softmax = nn.LogSoftmax(dim=1)

    def forward(self, input, hidden):
        combined = torch.cat((input, hidden), 1)
        hidden = self.i2h(combined)
        output = self.i2o(combined)
        output = self.softmax(output)
        return output, hidden

    def initHidden(self):
        return Variable(torch.zeros(1, self.hidden_size))

n_hidden = 128
rnn = RNN(n_letters, n_hidden, n_categories)

input = Variable(lineToTensor('Albert'))
hidden = Variable(torch.zeros(1, n_hidden))

output, next_hidden = rnn(input[0], hidden)
print(output)
#print(next_hidden)

out:

Variable containing:
Columns 0 to 9-2.9346 -2.9036 -2.9996 -2.8229 -2.9089 
-2.7909 -2.8781 -2.8332 -2.8440 -2.8522
Columns 10 to 17-3.0306 -2.8079 -2.9677 -2.9351 -2.8750 -2.9376
 -2.7807 -2.9693
[torch.FloatTensor of size 1x18]

4:训练网络

def categoryFromOutput(output):
    top_n, top_i = output.data.topk(1) # Tensor out of Variable with .data#topk类似与找最大值，并返回最大值的数值和索引
    category_i = top_i[0][0]
    return all_categories[category_i], category_i

print(categoryFromOutput(output))

上面的函数功能是计算出output中哪一个概率最大然后找出对应的category的索引值。

训练网络的步骤：

》生成输入和目标数据的tensor

》建立并且初始化隐藏层

》读取每个数据并且进行RNN结构之间的传递

》比较output和target

》反向传播更新梯度

》返回output和loss.

代码：

criterion = nn.NLLLoss()
learning_rate = 0.005 # If you set this too high, it might explode. If too low, it might not learn

def train(category_tensor, line_tensor):
    hidden = rnn.initHidden()

    rnn.zero_grad()

    for i in range(line_tensor.size()[0]):
        output, hidden = rnn(line_tensor[i], hidden)

    loss = criterion(output, category_tensor)
    loss.backward()

    # Add parameters' gradients to their values, multiplied by learning rate
    for p in rnn.parameters():
        p.data.add_(-learning_rate, p.grad.data)

    return output, loss.data[0]

    
import time
import math

n_iters = 100000
print_every = 5000
plot_every = 1000



# Keep track of losses for plotting
current_loss = 0
all_losses = []

def timeSince(since):
    now = time.time()
    s = now - since
    m = math.floor(s / 60)
    s -= m * 60
    return '%dm %ds' % (m, s)

start = time.time()

for iter in range(1, n_iters + 1):
    category, line, category_tensor, line_tensor = randomTrainingExample()
    output, loss = train(category_tensor, line_tensor)
    current_loss += loss

    # Print iter number, loss, name and guess
    if iter % print_every == 0:
        guess, guess_i = categoryFromOutput(output)
        correct = 'yes' if guess == category else 'no (%s)' % category
        print('%d %d%% (%s) %.4f %s / %s %s' % (iter, iter / n_iters * 100, timeSince(start), loss, line, guess, correct))

    # Add current loss avg to list of losses
    if iter % plot_every == 0:
        all_losses.append(current_loss / plot_every)
        current_loss = 0

后面还有测试方面的代码：待续