代码更新

公共代码/产品重复型号分析.py

@@ -33,6 +33,7 @@ def product_washing(filepath, category, thre=1, a=0):
     for param in other_parameters_fetch:
         other_parameters.append(param[0])
 
+    point_category_list = ['台式机', '笔记本', '一体电脑', '复印纸']
     related_product = []
     brand_grouped = df.groupby(by='产品品牌')
     for brand in brand_grouped:
@@ -41,6 +42,15 @@ def product_washing(filepath, category, thre=1, a=0):
         tempo_dict = {}
         # 每个品牌提取产品型号关键字，放入tempo_dict
         for i in brand[1].index:
+            if category in point_category_list:
+                if category == '复印纸':
+                    k = brand[1].loc[i, '*产品系列']
+                else:
+                    k = brand[1].loc[i, '*产品子系列']
+                k.replace(' ','').replace('系列','').replace('_','').replace('-','').upper()
+                tempo_dict[i] = [k]
+
+            else:
                 k = brand[1].loc[i, '*产品型号']
                 if k in invalid_list:
                     continue
@@ -119,7 +129,10 @@ def product_washing(filepath, category, thre=1, a=0):
                     if count != 0:
                         tested_product.append(set([i, j]))
                         break  # 如果出现了必须相等但不相等的参数，则退出到上一层循环。如果没有出现，则对比型号
-
+                    if category in point_category_list:
+                        if tempo_dict[i][0] == tempo_dict[j][0]:
+                            related_product.append(set([i, j]))
+                    else:
                         accuracy_i=0
                         accuracy_j=0
                         for word_i in tempo_dict[i][0]:
@@ -179,6 +192,6 @@ def product_washing(filepath, category, thre=1, a=0):
 
 
 if __name__ == '__main__':
-    filepath = "E:\\ZDZC\\激光打印机参数确认.xlsx"
-    category = '激光打印机'
+    filepath = "E:\\ZDZC\\Sourcetree_local\\公共代码\\一体电脑参数确认.xlsx"
+    category = '一体电脑'
     product_washing(filepath,category)