注释补充

barrage/handleData.py

@@ -14,11 +14,13 @@ import pandas as pd
 from collections import Counter
 from openpyxl import Workbook
 
+# 读取弹幕文件
 def ReadXlsx(filePath=''):
     df = pd.read_excel(filePath, sheet_name=0)
     df.dropna(axis=1, how='all')
     return df
 
+# 将dataframe类型转为string类型
 def ChangeDfToString(df,sep=',', isSave=False, filePath=''):
     string_data = df.to_string(index=False, header=False, na_rep='')
     string = string_data.replace('\n', ' ')
@@ -28,6 +30,7 @@ def ChangeDfToString(df,sep=',', isSave=False, filePath=''):
             file.write(str)
     return str
 
+# 根据关键词进行检索
 def GetKeyFromList(keyWords, origin_list):
     filtered_list = [item for item in origin_list if any(keyword in item for keyword in keyWords)]
     counter_list = Counter(filtered_list)

barrage/wordCloud.py

@@ -16,6 +16,7 @@ from PIL import Image
 from wordcloud import WordCloud, ImageColorGenerator
 from sklearn.feature_extraction.text import TfidfVectorizer
 
+# 将弹幕文本分隔成易于处理的字词
 def ReadAndCutWords(filePath):
     with open(filePath, 'r', encoding='utf-8') as file:
         text = file.read()
@@ -23,6 +24,7 @@ def ReadAndCutWords(filePath):
     word_list = ' '.join(words)
     return word_list
 
+# 利用TF-IDF将字词按频率划分
 def ChangeToFreq(word_list):
     documents = [word_list]
     vectorizer = TfidfVectorizer()
@@ -31,6 +33,7 @@ def ChangeToFreq(word_list):
     word_freq = dict(zip(feature_names, tfidf_matrix.toarray().sum(axis=0)))
     return word_freq
 
+# 根据字词频率来生成图云
 def CreateWordCloud(word_freq, width, height, maskImgPath, saveImgPath, save=False):
     if maskImgPath == '':
         mask = None