bug

tools/t7.py

@@ -186,6 +186,12 @@ class AutoLayout:
             self.return_log.append(f'芯片{chipname}有碱基不平衡:\n{desc}')
             print(f'芯片{chipname}有碱基不平衡:\n{desc}')
 
+    def dec_lib_data_scatter(self, data):
+        """
+
+        """
+        pass
+
     @staticmethod
     def level(row):
 
@@ -194,19 +200,19 @@ class AutoLayout:
         if 'nextera' in row['classification'].lower():
             return 1000
 
-        if '华大' in row['classification']:
+        if '华大' in row['classification'] and 'NN' in row['i5']:
             return 1100
 
-        if '超加急' in row['priority']:
+        if '超加急' in str(row['priority']):
             return 1500
 
         if row['拆分方式'] == '极致周期' or '极致' in row['拆分方式']:
             return 2000
 
-        if '加急' in row['priority']:
+        if '加急' in str(row['priority']):
             return 3000
 
-        if '补测' in row['priority']:
+        if '补测' in str(row['priority']):
             return 4000
 
         mytime = row['time']
@@ -221,21 +227,6 @@ class AutoLayout:
         """
         barcode 有重复的极致样本 进行排列组合，汇集成新的可能性
         """
-        # 筛选有重复的行
-
-        # same_barcode_data = [data for data in self.ori_lib_data if data['level'] == 1900]
-        # same_barcode_sorted = sorted(same_barcode_data, key=lambda x: (-x['size']))
-        #
-        # same_barcode_dict = dict()
-        # for index, data in enumerate(same_barcode_sorted):
-        #     same_barcode_dict[data['library']] = data['level'] + index + 1
-        # correct_data = list()
-        # for data in self.ori_lib_data:
-        #     if data in same_barcode_sorted:
-        #         data['level'] = same_barcode_dict[data['library']]
-        #     correct_data.append(data)
-        # self.ori_lib_data = correct_data
-
         same_barcode_df = pd.DataFrame(
             [spdata for data in self.ori_lib_data if data['level'] == 1900 for spdata in data['data']])
 
@@ -323,13 +314,17 @@ class AutoLayout:
                 # print(library_data['data'][0]['barcode'])
                 self.chip_size_N[chipname] += library_data['size']
 
-    def use_rule(self, chipname, classfication):
+    def use_rule_exclusive_classfication(self, chipname, classfication):
+        """
+        文库不能排在一起
+        """
         may_classfic = set(self.rule[self.rule['c1'] == classfication]['c2'])
         if self.chip_customer[chipname].intersection(may_classfic):
             return True
         return False
 
     def use_rule_exclusive_customer(self, chipname, customer):
+        """文库不能排在一起"""
         may_classfic = set(
             self.rule_exclusive_customer[self.rule_exclusive_customer['customer1'] == customer]['customer2'])
         if self.chip_customer[chipname].intersection(may_classfic):
@@ -347,7 +342,7 @@ class AutoLayout:
         classification = library_data['classification']
         customer = library_data['customer']
         is_balance_lib = library_data['is_balance_lib']
-        library = library_data['library']
+        # library = library_data['library']
 
         # 芯片大小不能超过设定限制
         sizelimit = True
@@ -367,7 +362,7 @@ class AutoLayout:
 
         # 互斥的文库
         exclusive_classific = True
-        if self.use_rule(chipname, classification):
+        if self.use_rule_exclusive_classfication(chipname, classification):
             exclusive_classific = False
             # print(chipname, library, '互斥的文库')
 
@@ -500,7 +495,6 @@ class AutoLayout:
             self.loc_chip_num += 1
 
     def assign_samples(self):
-        # ori_library_data = list()
 
         if '未测' not in self.ori_data.keys():
             raise UserWarning('提供excel没有 未测 sheet ,请核查！')
@@ -512,7 +506,7 @@ class AutoLayout:
 
         if unhave_col:
             unhave_from = '; '.join(unhave_col)
-            raise UserWarning(f'未测表里没有{unhave_from}  表头,请核查！')
+            raise UserWarning(f'未测表里没有 {unhave_from} 表头,请核查！')
 
         # 数据标准格式
         numeric_mask = pd.to_numeric(ori_library_df['data_needed'], errors='coerce').notna()
@@ -532,20 +526,25 @@ class AutoLayout:
 
         no_ori_data = ori_library_df[~(numeric_mask & time_mask) | status_mask | barcode_mask]
 
+        # 某个客户的检测的数据超过1个T就单独处理
+        summary = ori_library_df.groupby('customer').agg({'data_needed': 'sum'})
+        summary_dict = summary['data_needed'].to_dict()
+        for customer_sum, data_needed_sum in summary_dict.items():
+            if not data_needed_sum:
+                continue
+            if float(data_needed_sum) > 2000 :
+                self.return_log.append(f'客户 {customer_sum} 本次排样超过 2000G 建议包lane 处理')
+
         self.no_assign_data.extend(no_ori_data.to_dict('records'))
 
-        # 使用布尔索引筛选出不是数字和非日期的行，并且不是暂不排样的行
+        # 使用布尔索引筛选出不是数字和非日期的行，并且不是暂不排样的行, 以及非16位置barcode
         ori_library_df = ori_library_df[(numeric_mask & time_mask) & ~status_mask & ~barcode_mask]
 
-        # 某个客户的检测的数据超过1个T就单独处理
-        # summary = ori_library_df.groupby('customer').agg({'data_needed': 'sum'})
-        # print(summary)
-
         # 时间格式化
         ori_library_df['time'] = pd.to_datetime(ori_library_df['time'], errors='coerce')
         ori_library_df['level'] = ori_library_df.apply(self.level, axis=1)
 
-        # 极致客户有重复的，把等级调到19，防止放到了最后，到了未测里
+        # 极致客户有重复的，把等级调到1900，防止放到了最后，到了未测里
         must_lib_df = ori_library_df[ori_library_df['level'] == 2000]
         must_lib = set(must_lib_df[must_lib_df.duplicated(subset='barcode', keep=False)]['#library'].to_list())
         ori_library_df.loc[ori_library_df['#library'].isin(must_lib), 'level'] = 1900
@@ -586,7 +585,7 @@ class AutoLayout:
                 continue
 
             # 拆分处理 分为了2个大文库
-            if size > (self.data_limit) / 2:
+            if size > self.data_limit / 2:
                 library_df['data_needed'] = library_df['data_needed'] / 2
                 self.return_log.append(f'文库{library} 已做拆分处理, 请注意！！！ ')
                 self.ori_lib_data.append(dict(
@@ -685,7 +684,7 @@ class AutoLayout:
         self.loc_chip_num = 100
         while ori_lib_data:
             library_data = ori_lib_data[0]
-            chipname = f'chipB{self.loc_chip_num}_{max_barcode}' if max_barcode != 'all' else f'chipB{self.loc_chip_num}'
+            chipname = f'chip{self.loc_chip_num}_{max_barcode}' if max_barcode != 'all' else f'chip{self.loc_chip_num}'
 
             # 空白芯片直接添加
             if chipname not in self.index_assignments:
@@ -720,7 +719,6 @@ class AutoLayout:
             self.assign_again_size()
             # self.assign_again_size(max_barcode='i7')
             # self.assign_again_size(max_barcode='i5')
-            # self.assign_again_size()
         except Exception as e:
             self.return_log.append(f'T7排样出错， 请联系！{e}')
             self.index_assignments = {}
@@ -740,6 +738,7 @@ class AutoLayout:
                 addname = 'X'
             else:
                 addname = ''
+
             other_name = ''
             # if 'chipB' in chip_idx and df['barcode'].duplicated().any():
             #     other_name = '_i7'
@@ -772,7 +771,10 @@ class AutoLayout:
 
         no_assign_df = pd.DataFrame(self.no_assign_data)
         no_assign_df = no_assign_df.applymap(lambda x: format_date(x) if isinstance(x, pd.Timestamp) else x)
+        if not no_assign_df.empty:
             no_assign_df_not_balance = ','.join(set([lib for lib in no_assign_df['#library'] if lib in self.split_lib]))
+        else:
+            no_assign_df_not_balance = ''
         if no_assign_df_not_balance:
             self.return_log.append(f'文库{no_assign_df_not_balance}有做不平衡文库拆分处理，并且没有排完，请核查！')
         if not no_assign_df.empty: