使用Python分析周杰伦《Mojito》豆瓣短评

源代码+数据集已上传至GitHub：https://github.com/zoe9698/Mojito_Douban_analysis

公众号博文：Python告诉你网友究竟如何看待周杰伦的《Mojito》

 

1.将数据集（包含我手动标注的情感倾向：{0:"不喜欢",1:"中立",2:"喜欢"}）转为dataframe格式

#coding:utf-8
import pandas as pd

fpath = "D://数据集大荟萃/周杰伦新歌《Mojito》豆瓣短评数据集/mojito6931/1Mojito豆瓣短评数据6.12.csv"

df = pd.read_csv(fpath,engine='python')

2.情感倾向分析

• snownlp库：为python版的文本分析工具。

简单举例：用它区分两句话的情感倾向，看起来还可以。但是很慢。

应用到本数据集中：只有38%的正确率。。

• 常规情感分析的方法：分词->构造训练集测试集->构建词向量->朴素贝叶斯 

 

 

 正确率70%以上还是可以的。

 

3.matplotlib绘制数据可视化图

统计不同情感倾向的评论获赞总数：

绘制饼图：

分析最高赞的10条评论：

 

绘制柱状图：

# 绘制柱状图
labels = maxvote_dict.values()
votes = maxvote_dict.keys()

x = np.arange(10)
width = 0.35

fig3,ax3 = plt.subplots()
rects = ax3.bar(x,votes,width,label = '投票数')

ax3.set_ylabel('votes')
ax3.set_title('前十名高赞评论')
ax3.set_xticks(x)
ax3.set_xticklabels(labels)
ax3.legend()

# 在柱顶加具体投票数
def autolabel(rects):
    """Attach a text label above each bar in *rects*, displaying its height."""
    for rect in rects:
        height = rect.get_height()
        ax3.annotate('{}'.format(height),
                    xy=(rect.get_x() + rect.get_width() / 2, height),
                    xytext=(0, 2),  # 3 points vertical offset
                    textcoords="offset points",
                    ha='center', va='bottom')



autolabel(rects)
    
fig3.tight_layout()

plt.savefig('D:/mojito/max10_zhu.jpg',dpi=300)
plt.show()

 

 绘制词云图1---所有评论整合在一起：

allcontent = ""
for index,row in df.iterrows():
    allcontent+=row['content']
    
# [所有content]绘制词云
from wordcloud import WordCloud as wc

text_cut = jieba.lcut(allcontent)
text_cut = ' '.join(text_cut)

stop_words_file = 'D:\文本数据预处理常用工具\stopwords-master\hit_stopwords.txt'
stop_words = open(stop_words_file,encoding="utf8").read().split("\n")

word_cloud = wc(font_path="simsun.ttc",
               background_color="white", stopwords=stop_words,scale=4)

word_cloud.generate(text_cut)

plt.subplots(figsize=(72,64))

plt.imshow(word_cloud)

plt.axis("off")

plt.savefig('D:/all_wordcloud.jpg')

绘制词云图-----前十名高赞评论：

max10_content = ""

for index,row in maxvote_df_10.iterrows():
    max10_content+=row["content"]

text_cut = jieba.lcut(max10_content)
text_cut = ' '.join(text_cut)

stop_words_file = 'D:\文本数据预处理常用工具\stopwords-master\hit_stopwords.txt'
stop_words = open(stop_words_file,encoding="utf8").read().split("\n")

word_cloud = wc(font_path="simsun.ttc",
               background_color="white", stopwords=stop_words,scale=4)

word_cloud.generate(text_cut)

plt.subplots(figsize=(72,64))

plt.imshow(word_cloud)

plt.axis("off")

plt.savefig('D:/max10_wordcloud.jpg')

 分析评星数据：

# 填充缺失值
df['rating_num'] = df['rating_num'].fillna(1)

绘制饼图：

# 绘制 星级 饼图
import matplotlib.pyplot as plt
import numpy as np
%matplotlib inline

#解决中文显示问题
plt.rcParams['font.sans-serif'] = ['KaiTi'] # 指定默认字体
plt.rcParams['axes.unicode_minus'] = False # 解决保存图像是负号'-'显示为方块的问题

fig4, ax4 = plt.subplots()

ax4.pie(y,labels=x,autopct='%1.2f%%')

# x,y轴长度相同
ax4.axis('equal')
plt.savefig('D:/mojito/rating_count_bing.jpg',dpi=300)

plt.show()

# 绘制柱状图
labels = x
votes = y

x = np.arange(1,6)
width = 0.35

fig5,ax5 = plt.subplots()
rects = ax5.bar(x,y,width,label = '星级统计')

ax5.set_ylabel('count')
ax5.set_title('星级统计')
ax5.set_xticks(x)
ax5.set_xticklabels(labels)
ax5.legend()

# 在柱顶加具体投票数
def autolabel(rects):
    """Attach a text label above each bar in *rects*, displaying its height."""
    for rect in rects:
        height = rect.get_height()
        ax5.annotate('{}'.format(height),
                    xy=(rect.get_x() + rect.get_width() / 2, height),
                    xytext=(0, 2),  # 3 points vertical offset
                    textcoords="offset points",
                    ha='center', va='bottom')



autolabel(rects)
    
fig5.tight_layout()

plt.savefig('D:/mojito/rating_count_zhu.jpg',dpi=300)

plt.show()