word2vec训练词向量

word2vec训练词向量

import os
import re
import numpy as np
import pandas as pd
from bs4 import BeautifulSoup
import nltk.data
#nltk.download()
#from nltk.corpus import stopwords
from gensim.models.word2vec import Word2Vec

#加载数据
def load_dataset(name, nrows=None):
    datasets = {
        'unlabeled_train': 'unlabeledTrainData.tsv',
        'labeled_train': 'labeledTrainData.tsv',
        'test': 'testData.tsv'
    }
    if name not in datasets:
        raise ValueError(name)
    data_file = os.path.join('..', 'data', datasets[name])
    df = pd.read_csv(data_file, sep='\t', escapechar='\\', nrows=nrows)
    print('Number of reviews: {}'.format(len(df)))
return df
df = load_dataset('unlabeled_train')
df.head()
数据的预处理
#留了个候选，可以去除停用词，也可以不去除停用词。
#eng_stopwords = set(stopwords.words('english'))
eng_stopwords = {}.fromkeys([ line.rstrip() for line in open('../stopwords.txt')])
#定义清理数据的信息。
def clean_text(text, remove_stopwords=False):
    text = BeautifulSoup(text, 'html.parser').get_text()
    text = re.sub(r'[^a-zA-Z]', ' ', text)
    words = text.lower().split()
    if remove_stopwords:
        words = [w for w in words if w not in eng_stopwords]
    return words

tokenizer = nltk.data.load('tokenizers/punkt/english.pickle')
#每去调用一次split——sentences就输出一下。
def print_call_counts(f):
    n = 0
    def wrapped(*args, **kwargs):
        nonlocal n
        n += 1
        if n % 1000 == 1:
            print('method {} called {} times'.format(f.__name__, n))
        return f(*args, **kwargs)
    return wrapped

@print_call_counts
def split_sentences(review):
    raw_sentences = tokenizer.tokenize(review.strip())
    sentences = [clean_text(s) for s in raw_sentences if s]
return sentences
time sentences = sum(df.review.apply(split_sentences), [])
import logging
logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO)

# 设定词向量训练的参数
num_features = 300    # Word vector dimensionality，建议300，或者500
min_word_count = 40   # Minimum word count     至少出现40ci
num_workers = 4       # Number of threads to run in parallel，线程
context = 10          # Context window size  上下文，窗口大小
downsampling = 1e-3   # Downsample setting for frequent words gensuim，要用的，下采样的。
# nnlm 有投射层，4个窗口，用前3个预测第四个，有10W个词库，，三个 one-hot, 就是 1*10w
# 下一次，投影层。初始化权重，稠密向量。
# C=300*10W，C与one-hot,相乘。变成300*1，三个加起来，就变成了 900*1
# Hidden layer  ：900*500。900*1，变成了500*1，也有Wx+b  最后10W的维度。
# 
# Cbow（连续词库）
# 用 我喜欢 机器学习  
# 预测  学习
# 我喜欢机器学习，就是四个词向量。
# 直接求和，来预测词的概率。
# Window就是 滑动窗口。。滑动窗口开着，把所有为4 的窗口 扫描出来。
# Min_word=40:  出现次数至少 40次。
# 
# Toma模型：
# 学习，来预测：  我喜欢 机器学习。

model_name = '{}features_{}minwords_{}context.model'.format(num_features, min_word_count, context)

print('Training model...')
#初始化
model = word2vec.Word2Vec(sentences, workers=num_workers, \
            size=num_features, min_count = min_word_count, \
            window = context, sample = downsampling)

# If you don't plan to train the model any further, calling init_sims will make the model much more #memory-efficient.
model.init_sims(replace=True)

# It can be helpful to create a meaningful model name and 
# save the model for later use. You can load it later using Word2Vec.load()
model.save(os.path.join('..', 'models', model_name))

print(model.doesnt_match("man woman child kitchen".split()))
print(model.doesnt_match('france england germany berlin'.split()))
print(model.most_similar("man"))#关联度最高的。