对QQ聊天记录进行分析,由于每天产生的聊天记录比較多,所以选取的是从2月份整月的聊天记录数据。分析要产生的结果有三个,聊天记录中发消息的人前top15。统计24小时时间段那个时间段发贴人最多,还有对消息中的热词进行抽取。
对QQ用户发贴次数进行统计,须要注意QQ导出的聊天记录格式。【年月日时分秒 QQ账号相关信息】,须要对聊天记录做解析。另外对聊天内容也要做解析。
详细思路不做详解,仅仅贴结果和部分代码。相信大家一看就明确。
统计24小时时间段QQ消息数量
watermark/2/text/aHR0cDovL2Jsb2cuY3Nkbi5uZXQv/font/5a6L5L2T/fontsize/400/fill/I0JBQkFCMA==/dissolve/70/gravity/Center" alt="">
能够看出每天下午3点到5点大家都非常活跃
另一个就是对讨论的话题做分析,首先要对发的消息做分词处理。去掉一个停用词,然后按词频出现的次数统计,得到例如以下结果。
watermark/2/text/aHR0cDovL2Jsb2cuY3Nkbi5uZXQv/font/5a6L5L2T/fontsize/400/fill/I0JBQkFCMA==/dissolve/70/gravity/Center" alt="">
第一个表示出现的词,第二个表示在某个时间段内出现的次数,总的来说,我们这个群还算是一个技术群吧。
相关部分代码:
def userProcess():
userArray = []
contentArray = LoadUserInfo.loadUser()
for userInfo in contentArray:
if(len(userInfo)==3):
userArray.append(userInfo[2]) print(len(userArray))
#Counter(words).most_common(10)
userGroupInof = Counter(userArray).most_common(15)
#print(userGroupInof) userNameLable = []
postMessageNum = [] for key,value in userGroupInof:
userNameLable.append(key)
postMessageNum.append(value) #performance = 3 + 10 * np.random.rand(len(people))
#error = np.random.rand(len(people)) zh_font = matplotlib.font_manager.FontProperties(fname='C:\Windows\Fonts\simsun.ttc') plt.barh(np.arange(len(userNameLable)), postMessageNum, align='center', alpha=0.4)
plt.yticks(np.arange(len(userNameLable)), userNameLable,fontproperties=zh_font)
plt.xlabel('发贴数量',fontproperties=zh_font)
plt.title('java-Endless Space群(4881914)发贴最多的15个人',fontproperties=zh_font) plt.show()
def hourProcess():
hourArray = []
contentArray = LoadUserInfo.loadUser()
for userInfo in contentArray:
if(len(userInfo)==3):
messageDate = userInfo[1]
hourInfo = re.split('[:]',messageDate)
hourArray.append(hourInfo[0]) print(len(hourArray))
#Counter(words).most_common(10)
hour_counts = Counter(hourArray)
#对数据进行排序
sortByHour = sorted(hour_counts.items())
print(sortByHour) postMessageLable = []
postMessageNum = [] for key,value in sortByHour:
postMessageLable.append(key)
postMessageNum.append(value) print(postMessageLable)
print(postMessageNum) #生成发贴柱状图
N = len(postMessageNum) ind = np.arange(N)+0.5 # the x locations for the groups
#print(ind) #x轴上的数值
width = 0.35 # the width of the bars fig, ax = plt.subplots()
rects = ax.bar(ind, postMessageNum, width, color='r') # add some text for labels, title and axes ticks
ax.set_ylabel('message number')
ax.set_title('QQ message number of hour,total message ( '+ str(len(hourArray)) + ")")
ax.set_xticks(ind+width)
ax.set_xticklabels(postMessageLable) def autolabel(rects):
# attach some text labels
for rect in rects:
height = rect.get_height()
ax.text(rect.get_x()+rect.get_width()/2., height, '%d'%int(height), ha='center', va='bottom') autolabel(rects) plt.show()
#对导入的文件第四列做中文分词处理
#对用户发出的消息进行处理 def messageProcess():
wordArray = []
contentArray = LoadMessageInfo.loadMessage()
print("processing original data ........")
for messageInfo in contentArray:
#print(messageInfo[3])
word_list = jieba.cut(messageInfo, cut_all=False)
for word in word_list:
#过滤掉短词,仅仅有一个长度的词
if(len(word)>1):
wordArray.append(word) #print(wordArray)
print("remove stop word data ........")
jsonResource = open('./data/stopword.json','r',encoding='utf8')
stopwords = json.load(jsonResource)
#print(stopwords)
for word in wordArray:
print(word)
if (word in stopwords):
wordArray.remove(word) #print(wordArray)
print("text is processing.......")
word_counts = Counter(wordArray)
print(word_counts)
print("processing is over")