torchtext处理IMDB数据

感谢这个博客，之前一直在想，torchtext能不能对这个数据进行操作，尝试了一下不行，昨天搜索之后发现了这个教程，真的很有用。
我们先看一下之前做的时候预处理的流程。

image.png

在前面已经训练好了word2vec，这里不再处理。

import pandas as pd
import numpy as np
import spacy

# Read data from files 
train_data = pd.read_csv( "./drive/My Drive/NLPdata/train.tsv", header=0, delimiter="\t", quoting=3,encoding='latin-1' )
test_data = pd.read_csv( "./drive/My Drive/NLPdata/test.tsv", header=0, delimiter="\t", quoting=3,encoding='latin-1')
# unlabeled_train = pd.read_csv( "./train01.tsv", header=0, delimiter="\t", quoting=3,encoding='latin-1' )

# Verify the number of reviews that were read (100,000 in total)
print("Read %d labeled train reviews, %d labeled test reviews, "% (train_data["Phrase"].size, test_data["Phrase"].size ))

导入之前生成的word2vec

import logging
import gensim
from gensim.models import word2vec
model=gensim.models.KeyedVectors.load_word2vec_format("./drive/My Drive/NLPdata/word2Vec03.bin",binary=True)

index2word=model.index2word
print(len(index2word))
index2word_set=set(model.index2word)
print(len(index2word_set))
print(model)

对语料库数据进行处理

包括分句、分词、单词小写等

# text是输入的已经分好词的语料库文本
# model是之前生成的word2vec模型
# num_features是word2vec模型中每个词维度大小，这里是200
def word2vec(text,model,num_features):
    featureVec = np.zeros((200,),dtype="float32")
    nwords=0
    for word in text:
        if word in index2word_set:
            nwords+=1
            featureVec=np.add(featureVec,model[word])
    featureVec = np.divide(featureVec,nwords)
    return featureVec
# print(word2vec(token))
def getAvgFeatureVecs(phrases,model,num_features):
    counter=0
    phraseFeatureVecs = np.zeros((len(phrases),num_features),dtype="float32")
    for phrase in phrases:
        if counter % 2000==0:
            print("Phrase %d of %d" % (counter, len(phrases)))
        phraseFeatureVecs[counter]=word2vec(phrase, model, num_features)
        counter = counter+1
    return phraseFeatureVecs

from nltk.corpus import stopwords
import re
def phrase_to_wordlist(phrase, remove_stopwords=False):
    phrase_text = re.sub("[^a-zA-Z]"," ", phrase)
    words = phrase_text.lower().split()
#     if remove_stopwords:
#         stops = set(stopwords.words("english"))
#         words = [w for w in words if not w in stops]
    return(words)

处理训练集和测试集数据

clean_train_phrases = []
for phrase in train_data["Phrase"]:
    clean_train_phrases.append( phrase_to_wordlist( phrase, remove_stopwords=True ))
    
num_features=200
trainDataVecs = getAvgFeatureVecs( clean_train_phrases, model, num_features )

clean_test_phrases = []
for phrase in test_data["Phrase"]:
    clean_test_phrases.append( phrase_to_wordlist( phrase, remove_stopwords=True ))
    
num_features=200
testDataVecs = getAvgFeatureVecs( clean_test_phrases, model, num_features )

# np.isnan(trainDataVecs).any()
nullFeatureVec = np.zeros((200,),dtype="float32")
# print(trainDataVecs[4])
trainDataVecs[np.isnan(trainDataVecs)] = 0
print(trainDataVecs[3])

对向量化的数据中空值进行赋值

# np.isnan(trainDataVecs).any()
nullFeatureVec = np.zeros((200,),dtype="float32")
# print(trainDataVecs[4])
trainDataVecs[np.isnan(trainDataVecs)] = 0
print(trainDataVecs[3])

接下来看一下使用torchtext怎么处理数据，对比之后，我感觉，确实优雅了很多

读取数据

import pandas as pd
data=pd.read_csv(r'C:\Users\jwc19\Desktop\sentiment-analysis-on-movie-reviews\train.tsv',sep='\t')
test=pd.read_csv(r'C:\Users\jwc19\Desktop\sentiment-analysis-on-movie-reviews\test.tsv',sep='\t')
data.head()

使用sklearn对数据集进行分割

将训练集数据按照8:2的比例分割为训练集和验证集

from sklearn.model_selection import train_test_split
train,val=train_test_split(data,test_size=0.2)
train.to_csv("train.csv",index=False)
val.to_csv('val.csv',index=False)

构建分词器，定义Field

Torchtext采用了一种声明式的方法来加载数据：你来告诉Torchtext你希望的数据是什么样子的，剩下的由torchtext来处理。
实现这种声明的是Field，Field确定了一种你想要怎么去处理数据。

field在默认的情况下都期望一个输入是一组单词的序列，并且将单词映射成整数。
这个映射被称为vocab。如果一个field已经被数字化了并且不需要被序列化，
可以将参数设置为use_vocab=False以及sequential=False。

import spacy
import torch
from torchtext import data, datasets
from torchtext.vocab import Vectors
from torch.nn import init

device=torch.device("cuda")
spacy_en=spacy.load("en")
def tokenize_en(text):
    return [tok.text for tok in spacy_en.tokenizer(text)]

label=data.Field(sequential=False, use_vocab=False)
text=data.Field(sequential=True, tokenize=tokenize_en,lower=True)

定义Dataset

The fields知道当给定原始数据的时候要做什么。现在，我们需要告诉fields它需要处理什么样的数据。这个功能利用Datasets来实现。

Torchtext有大量内置的Datasets去处理各种数据格式。

TabularDataset官网介绍: Defines a Dataset of columns stored in CSV, TSV, or JSON format.

对于csv/tsv类型的文件，TabularDataset很容易进行处理，故我们选它来生成Dataset

train, val=data.TabularDataset.splits(
    path=r'C:\Users\jwc19\Desktop\2001_2018jszyfz\code',
    train='train.csv',
    validation='val.csv',
    format='csv',
    skip_header=True,
    fields=[
        ('PhraseId',None),
        ('SentenceId',None),
        ('Phrase',text),
        ('Sentiment',label)
    ]
)

test=data.TabularDataset.splits(
    path=r'C:\Users\jwc19\Desktop\sentiment-analysis-on-movie-reviews',
    test='test.tsv',
    format='tsv',
    skip_header=True,
    fields=[
        ('PhraseId',None),
        ('SentenceId',None),
        ('Phrase',text),
    ]
)

建立vocab

Torchtext可以将词转化为数字，但是它需要被告知需要被处理的全部范围的词，在这里使用的是glove，库会帮你下载好

text.build_vocab(train,vectors='glove.6B.100d')
text.vocab.vectors.unk_init = init.xavier_uniform

print(text.vocab.itos[1510])
print(text.vocab.stoi['bore'])
# 词向量矩阵: TEXT.vocab.vectors
print(text.vocab.vectors.shape)
word_vec = text.vocab.vectors[text.vocab.stoi['bore']]
print(word_vec.shape)
print(word_vec)