#  數(shù)據(jù)導入
import pandas as pd
data = pd.read_csv('../data/京東評論數(shù)據(jù).csv')
data.head()

#  數(shù)據(jù)描述
data.describe()

#  數(shù)據(jù)預處理
#  取出sku_Id,content字段
data1 = data[['sku_id', 'content']]
data1.head(10)

#  情感分析
from snownlp import SnowNLP
data1['emotion'] = data1['content'].apply(lambda x: SnowNLP(x).sentiments)
data1.head()

#  情感數(shù)據(jù)描述
data1.describe()

#  繪制情感分直方圖
import matplotlib.pyplot as plt
import numpy as np
 
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
 
bins = np.arange(0, 1.1, 0.1)
plt.hist(data1['emotion'], bins, color = '#4F94CD', alpha=0.9)
plt.xlim(0, 1)
plt.xlabel('情感分')
plt.ylabel('數(shù)量')
plt.title('情感分直方圖')
plt.show()

#  繪制詞云圖（這兒沒有做停用詞處理）
from wordcloud import WordCloud
import jieba
 
myfont = myfont = r'C:\Windows\Fonts\simhei.ttf'
w = WordCloud(font_path=myfont)
text = ''
for i in data['content']:
    text += i
data_cut = ' '.join(jieba.lcut(text))
w.generate(data_cut)
image = w.to_file('詞云圖.png')
image

#  關(guān)鍵詞提取top10
#  這兒直接寫import jieba運行會顯示沒有analyse屬性
from jieba import analyse
 
key_words = jieba.analyse.extract_tags(sentence=text, topK=10, withWeight=True, allowPOS=())
key_words

#  計算積極評論與消極評論各自的數(shù)目
pos, neg = 0, 0
for i in data1['emotion']:
    if i >= 0.5:
        pos += 1
    else:
        neg += 1
print('積極評論數(shù)目為:', pos, '\n消極評論數(shù)目為：', neg)

#  積極消極評論占比
import matplotlib.pyplot as plt
 
plt.rcParams['font.sans-serif']=['SimHei']
plt.rcParams['axes.unicode_minus'] = False
 
pie_labels = 'positive', 'negative'
plt.pie([pos, neg], labels=pie_labels, autopct='%1.2f%%', shadow=True)
 
plt.show()

#  獲取消極評論的數(shù)據(jù)
data2 = data1[data1['emotion'] < 0.5]
data2.head()

#消極評論詞云圖（這兒沒有做停用詞處理）
text2 = ''
for s in data2['content']:
    text2 += s
data_cut2 = ' '.join(jieba.lcut(text2))
w.generate(data_cut2)
image = w.to_file('消極評論詞云.png')
image

#消極評論關(guān)鍵詞top10
key_words = jieba.analyse.extract_tags(sentence=text2, topK=10, withWeight=True, allowPOS=())
key_words