Amazon_Review_数据处理与分析

import numpy as np 
import pandas as pd

import matplotlib.pyplot as plt
from matplotlib.colors import LinearSegmentedColormap
import seaborn as sns

import re
import string

import nltk
nltk.download('punkt')
nltk.download('averaged_perceptron_tagger')
nltk.download('wordnet')
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
from nltk.stem import SnowballStemmer
from nltk.corpus import wordnet
from nltk import pos_tag
from nltk.stem import WordNetLemmatizer

from wordcloud import WordCloud, STOPWORDS, ImageColorGenerator

from collections import Counter

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.model_selection import cross_validate
from sklearn.model_selection import train_test_split
from sklearn.model_selection import StratifiedKFold
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
from sklearn.metrics import roc_auc_score
from sklearn.utils import shuffle
from sklearn.naive_bayes import MultinomialNB


import warnings
warnings.filterwarnings('ignore')

review_df = pd.read_excel('amazon_review.xlsx','Sheet1',index_col=None)
review_df.head(3)

data = review_df[['reviews.rating','reviews.text']]
#只筛选需要分析的评分值和评论内容

data.info()

data.isnull().sum()

data.dropna(inplace=True)

import random
samples=4
for i in range(samples):
    n=random.choice(range(data.shape[0]))
    print(n)
    print('text:{}\n rating:{}\n'.format(data['reviews.text'][n],data['reviews.rating'][n]))
#随机查看4行数据

data.describe()

data2 = data[data['reviews.rating'].isin([1,2,3,4,5]) ]

data2['reviews.rating'].value_counts()
#查看该列的值以及值对应的数量

data2['reviews.rating'].value_counts().sort