几乎无改动

公共代码/产品品牌分析.py

@@ -8,7 +8,7 @@ import re
 import xlsxwriter
 
 
-def brand_washing(filepath,thre=0.5,inner_thre=0.5,a=1,sheet_name=0):
+def brand_washing(filepath,thre=0.5,inner_thre=0.8,a=1,sheet_name=0):
     # filepath:文件路径，thre为两个品牌下型号重合率阈值，inner_thre为两个品牌下某条型号内关键词重合率阈值，a为权重调整，sheet_name为表单名
     df = pd.read_excel(filepath, sheet_name=sheet_name, converters = {'产品编码':str})
     # 处理缺失值
@@ -244,6 +244,6 @@ def brand_washing(filepath,thre=0.5,inner_thre=0.5,a=1,sheet_name=0):
     workbook.close()
 
 if __name__ == '__main__':
-    filepath = 'E:\\ZDZC\\扫描仪参数确认.xlsx'
+    filepath = 'E:\\ZDZC\\激光打印机参数确认.xlsx'
     brand_washing(filepath)
 

公共代码/产品类别分析.py

@@ -227,10 +227,10 @@ def class_washing(category, filepath, c_list,a=0.02, b=0.01):
 
 
 if __name__ == '__main__':
-    #category='激光打印机'
-    #filepath="E:\\ZDZC\\激光打印机参数确认.xlsx"
-    #c_list=[6,7,-4,-3]
-    category = '扫描仪'
-    filepath="E:\\ZDZC\\扫描仪参数确认.xlsx"
-    c_list=[7,8,9]
+    category='激光打印机'
+    filepath="E:\\ZDZC\\激光打印机参数确认.xlsx"
+    c_list=[6,7,-4,-3]
+    # category = '扫描仪'
+    # filepath="E:\\ZDZC\\扫描仪参数确认.xlsx"
+    # c_list=[7,8,9]
     class_washing(category, filepath, c_list)

公共代码/产品重复型号分析.py

@@ -149,5 +149,5 @@ def product_washing(filepath, thre=1, a=0):
 
 
 if __name__ == '__main__':
-    filepath = "E:\\ZDZC\\扫描仪参数确认.xlsx"
+    filepath = "E:\\ZDZC\\激光打印机参数确认.xlsx"
     product_washing(filepath)