评论文本挖掘

from nltk.stem.wordnet import WordNetLemmatizer

# 创建词形还原器对象
lemmatizer = WordNetLemmatizer()

# 要进行词形还原的单词列表
words = ['running', 'dogs', 'better']

# 对每个单词进行词形还原
lemmatized_words = [lemmatizer.lemmatize(word) for word in words]

# 打印词形还原后的结果
for word, lemma in zip(words, lemmatized_words):
    print(f"{word} -> {lemma}")

import pandas as pd

import matplotlib.pyplot as plt
import seaborn as sns
plt.style.use('fivethirtyeight')
import warnings

warnings.filterwarnings('ignore')
%matplotlib inline

import pandas as pd
# nltk：文本处理的包
from nltk.stem.wordnet import WordNetLemmatizer 
from collections import Counter

import matplotlib.pyplot as plt
from nltk.corpus import wordnet as wn

import pyecharts.options as opts
from pyecharts.charts import WordCloud

def stars_cat(n):
    
    if n<=2:
        return '差评'  
    elif n ==3:
        return '中评' 
    else:
        return '好评'

# 获取评论中的日期信息，转换成日期时间格式
def get_date(x):
    
    x = x.split('on ')[1] # 把数据拆分成两部分 ['Reviewed in the United States on ','June 24, 2020']
    x = x.split(', ') 
    y= x[1]
    x = x[0].split(' ')
    m,d = x[0],x[1]
    if m=='January' or m=='Jan':
        on_date='01-'+d+'-'+y
    elif m=='February' or m=='Feb':
        on_date='02-'+d+'-'+y
    elif m=='March' or m=='Mar':
        on_date='03-'+d+'-'+y
    elif  m=='April' or m=='Apr':
        on_date='04-'+d+'-'+y
    elif  m=='May':
        on_date='05-'+d+'-'+y
    elif  m=='June' or m=='Jun':
        on_date='06-'+d+'-'+y
    elif  m=='July' or m=='Jul':
        on_date='07-'+d+'-'+y
    elif m=='August' or m=='Aug':
        on_date='08-'+d+'-'+y
    elif m=='September' or m=='Sep':
        on_date='09-'+d+'-'+y
    elif m=='October' or m=='Oct':
        on_date='10-'+d+'-'+y
    elif m=='November' or m=='Nov':
        on_date='11-'+d+'-'+y
    elif m=='December' or m=='Dec':
        on_date='12-'+d+'-'+y    
    on_date=datetime.datetime.strptime(on_date, '%m-%d-%Y').strftime('%Y-%m-%d')
    return on_date

def replace_abbreviations(text):
    new_text = text
    #则表达式过滤特殊符号用空格符占位，双引号、单引号、句点、逗号
    new_text = re.sub(r'[^a-zA-Z.,?! \']+',' ', text).strip().lower()
    # 还原常见缩写单词还原,i'm i'd he's
    new_text = re.sub(r"(it|he|she|that|this|there|here)(\'s)",r"\1 is", new_text,re.I)
    # (?<=pattern)xxx，就是捕获以pattern开头的内容xxx
    new_text = re.sub(r"(?<=[a-zA-Z])n\'t"," not", new_text) # not的缩写 aren't-- are not
    new_text = re.sub(r"(?<=[a-zA-Z])\'d"," would", new_text) # would的缩写i'd -->i would--> 'i' 'would'
    new_text = re.sub(r"(?<=[a-zA-Z])\'ll"," will", new_text) # will的缩写
    new_text = re.sub(r"(?<=[I|i])\'m"," am", new_text) # am的缩写
    new_text = re.sub(r"(?<=[a-zA-Z])\'re"," are", new_text) # are的缩写
    new_text = re.sub(r"(?<=[a-zA-Z])\'ve"," have", new_text) # have的缩写
    new_text = new_text.replace('\'', ' ').replace('.', '. ')
    return new_text

def get_words(clean_text):
    words_all = [] 
    for words in clean_text:
        for word in words:
            words_all.append(word) 
    total_words = list(set(words_all)) 
    all_words = Counter(words_all) 
    content_mean = len(words_all)/len(clean_text)  
    words_cap =  len(total_words)/len(words_all) 
    return all_words,content_mean,total_words,words_cap
    
(WordCloud()
    .add(series_name="好评词云",
         data_pair=positive_words_wordcloud,  #传入绘制词云图的数据
         word_size_range=[16, 80])  #word_size_range 字号大小取值范围
    .set_global_opts(
        title_opts=opts.TitleOpts(
            title="好评词云", 
            title_textstyle_opts=opts.TextStyleOpts(font_size=23) # 设置标题字号
        ),
        tooltip_opts=opts.TooltipOpts(is_show=True),  # 设置为True 鼠标滑过文字会弹出提示框
    )
    .render_notebook()
)