1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
| import pandas as pd
import pyecharts as pc
from pyecharts import options as opts
import jieba
##数据预处理
def data_process(url):
df=pd.read_csv(url)
df = df[df['Type'] == 1] # 只保留文本聊天
##保留特定群员信息
df=df[(df['NickName']=="你的名字")| (df['NickName']=='她的名字')] ##这里换成你想保留人的群聊名字
selected_columns = ['IsSender', 'StrContent', 'StrTime']
df = df[selected_columns] # 只取'IsSender','StrContent','StrTime'列
df['StrTime'] = pd.to_datetime(df['StrTime'])
df['Date'] = df['StrTime'].dt.date
return df
##读取群聊文件的地址，这里改成你导出的群聊文件地址
fileurl=r"你的群聊文件地址"
df=data_process(fileurl)
def zhuzhuangtu():
# 每天聊天频率柱状图
chat_frequency = df['Date'].value_counts().sort_index()
total_messages = len(df)
date_labels = [date.strftime('%m-%d') for date in chat_frequency.index]
bar = pc.charts.Bar()
bar.add_xaxis(date_labels)
bar.add_yaxis('频率', list(chat_frequency))
bar.render("./data/zhuzhuantu.html")
return bar
# 双方信息数量对比
def pie():
sent_by_me = df[df['IsSender'] == 1]['StrContent']
sent_by_others = df[df['IsSender'] == 0]['StrContent']
count_sent_by_me = len(sent_by_me)
count_sent_by_others = len(sent_by_others)
labels = ['你的名字', '她的名字']
sizes = [count_sent_by_me, count_sent_by_others]
pie=pc.charts.Pie()
pie.add("",[list(z) for z in zip(labels,sizes)])
# 添加标签
pie.set_series_opts(label_opts=opts.LabelOpts(formatter="{b}: {c}"))
return pie
##每小时聊天记录
# 根据一天中的每一个小时进行统计聊天频率，并生成柱状图
def xiaoshitu():
df['DateTime'] = pd.to_datetime(df['StrTime'])
df['Hour'] = df['DateTime'].dt.hour
hourly_counts = df['Hour'].value_counts().sort_index().reset_index()
hourly_counts.columns = ['Hour', 'Frequency']
bar1=pc.charts.Bar()
bar1.add_xaxis(hourly_counts['Hour'].to_list())
bar1.add_yaxis('频率',hourly_counts['Frequency'].to_list())
return bar1
##绘制词云
def ciyun():
# 获取词云内容
words = df['StrContent'].to_string()
##分词
# 定义要去除的词列表
filter_list = ['的', '了', '是', '在', '和', '我', '之','我们', '你们', '他们', '有', '也', '不', '人', '这', '个', '你',
'上', '到', '们','小','中', '为', '上', '们', '都', '会', '他', '地', '那', '要', '就', '以', '说', '来', '可以', '对',
'出', '从', '到', '……', '呀', '吧']
words = jieba.cut(words,cut_all=False)
filtered_words = [word for word in words if word not in filter_list and word.isalpha()]
# words=' '.join(filtered_words )
# print(type(filtered_words))
#计算词频
word_dict = {}
for word in filtered_words:
if len(word) > 1:
if word in word_dict:
word_dict[word] += 1
else:
word_dict[word] = 1
# 将词频统计结果转换为列表
word_list = [(word, value) for word, value in word_dict.items()]
# print(word_list)
# 绘制词云
wordcloud = pc.charts.WordCloud()
wordcloud.add("", word_list, word_size_range=[20,100])
return wordcloud
#主函数
if __name__=='__main__':
zhuzhuang=zhuzhuangtu()
pietu=pie()
xiaoshi=xiaoshitu()
ciyuntu=ciyun()
#
zhuzhuang.set_global_opts(title_opts={"text": "聊天月份频率图"})
pietu.set_global_opts(title_opts={"text": "聊天数量饼图"})
xiaoshi.set_global_opts(title_opts={"text": "聊天全天分布图"})
ciyuntu.set_global_opts(title_opts={"text": "词云"})
page = pc.charts.Page(layout=pc.charts.Page.SimplePageLayout)
page.add(zhuzhuang)
page.add(pietu)
page.add(xiaoshi)
page.add(ciyuntu)
# 设置页面标题
page.page_title="聊天信息总结"
# 保存页面
page.render("你要保存的地址+文件名.html")
|
