模式回归到多个sheet,包lane列出

new_sanwei
chaopower 2024-05-22 11:29:11 +08:00
parent 796b2deef4
commit 7909d015bf
1 changed files with 32 additions and 25 deletions

View File

@ -76,6 +76,9 @@ class AutoLayout:
self.return_log = list() self.return_log = list()
self.no_assign_data = list() self.no_assign_data = list()
# 包lane处理
self.order_assign_data = list()
self.need_cols = self.read_cols() self.need_cols = self.read_cols()
self.is_use_balance = is_use_balance self.is_use_balance = is_use_balance
@ -483,8 +486,6 @@ class AutoLayout:
def assign_samples(self): def assign_samples(self):
# if '未测' not in self.ori_data.keys():
# raise UserWarning('提供excel没有 未测 sheet ,请核查!')
ori_library_df = pd.DataFrame(self.ori_data) ori_library_df = pd.DataFrame(self.ori_data)
# 数据标准格式 # 数据标准格式
@ -494,18 +495,23 @@ class AutoLayout:
# 非正常barcode # 非正常barcode
barcode_mask = ori_library_df['indexi5i7'].str.len() != 16 barcode_mask = ori_library_df['indexi5i7'].str.len() != 16
ori_library_df.loc[barcode_mask, 'indexi5i7'] = ori_library_df.loc[barcode_mask, 'indexi5'].str[-8:] + \ ori_library_df.loc[barcode_mask, 'indexi5i7'] = ori_library_df.loc[barcode_mask, 'indexi5'].str[-8:] + \
ori_library_df.loc[barcode_mask, 'indexi7'].str[-8:] ori_library_df.loc[barcode_mask, 'indexi7'].str[-8:]
ori_library_df['note'] = '' ori_library_df['note'] = ''
ori_library_df.loc[~numeric_mask, 'note'] = 'data_needed 列非数字' ori_library_df.loc[~numeric_mask, 'note'] = 'data_needed 列非数字'
ori_library_df.loc[~time_mask, 'note'] = 'time 列非日期' ori_library_df.loc[~time_mask, 'note'] = 'time 列非日期'
# ori_library_df.loc[barcode_mask, 'note'] = '非16位barcode' ori_library_df.loc[barcode_mask, 'note'] = '非16位barcode已修改'
no_ori_data = ori_library_df[~(numeric_mask & time_mask)] no_ori_data = ori_library_df[~(numeric_mask & time_mask)]
self.no_assign_data.extend(no_ori_data.to_dict('records')) self.no_assign_data.extend(no_ori_data.to_dict('records'))
# 包lane的剔除
orderlane_mask = ori_library_df['productname'].str.contains('包lane')
self.order_assign_data = ori_library_df[orderlane_mask].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, 以及非16位置barcode # 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) & ~barcode_mask] ori_library_df = ori_library_df[(numeric_mask & time_mask) & (~orderlane_mask)]
# 时间格式化 # 时间格式化
ori_library_df['receivedtime'] = pd.to_datetime(ori_library_df['receivedtime'], errors='coerce') ori_library_df['receivedtime'] = pd.to_datetime(ori_library_df['receivedtime'], errors='coerce')
@ -539,6 +545,7 @@ class AutoLayout:
self.ori_lib_data.append(dict( self.ori_lib_data.append(dict(
library=library, library=library,
sample_code=library_df['sampleCode'].values[0],
is_balance_lib=library_df['librarybalancedflag'].values[0], is_balance_lib=library_df['librarybalancedflag'].values[0],
size=library_df['orderdatavolume'].sum(), size=library_df['orderdatavolume'].sum(),
split_method=library_df['cycletype'].values[0], split_method=library_df['cycletype'].values[0],
@ -557,6 +564,7 @@ class AutoLayout:
self.return_log.append(f'文库{library} 已做拆分处理, 请注意!!! ') self.return_log.append(f'文库{library} 已做拆分处理, 请注意!!! ')
self.ori_lib_data.append(dict( self.ori_lib_data.append(dict(
library=library, library=library,
sample_code=library_df['sampleCode'].values[0],
is_balance_lib=library_df['librarybalancedflag'].values[0], is_balance_lib=library_df['librarybalancedflag'].values[0],
size=library_df['orderdatavolume'].sum(), size=library_df['orderdatavolume'].sum(),
split_method=library_df['cycletype'].values[0], split_method=library_df['cycletype'].values[0],
@ -569,6 +577,7 @@ class AutoLayout:
self.ori_lib_data.append(dict( self.ori_lib_data.append(dict(
library=library, library=library,
sample_code=library_df['sampleCode'].values[0],
is_balance_lib=library_df['librarybalancedflag'].values[0], is_balance_lib=library_df['librarybalancedflag'].values[0],
size=library_df['orderdatavolume'].sum(), size=library_df['orderdatavolume'].sum(),
split_method=library_df['cycletype'].values[0], split_method=library_df['cycletype'].values[0],
@ -581,7 +590,6 @@ class AutoLayout:
self.combinations_same_barcode() self.combinations_same_barcode()
self.ori_lib_data = sorted(self.ori_lib_data, key=lambda x: (x['level'], x['time'])) self.ori_lib_data = sorted(self.ori_lib_data, key=lambda x: (x['level'], x['time']))
# self.ori_lib_data = sorted(self.ori_lib_data, key=lambda x: (x['level'] != 100000, -x['size']))
while self.ori_lib_data: while self.ori_lib_data:
library_data = self.ori_lib_data[0] library_data = self.ori_lib_data[0]
@ -694,8 +702,6 @@ class AutoLayout:
outputpath = os.path.join(self.output, 'result', outputname) outputpath = os.path.join(self.output, 'result', outputname)
writer = pd.ExcelWriter(outputpath) writer = pd.ExcelWriter(outputpath)
res = list()
sum_res = list()
chip_loc = 1 chip_loc = 1
librarynum = 0 librarynum = 0
for chip_idx, chip_assignments in self.index_assignments.items(): for chip_idx, chip_assignments in self.index_assignments.items():
@ -722,43 +728,44 @@ class AutoLayout:
self.dec_barcode_radio(chip_idx) self.dec_barcode_radio(chip_idx)
chipname = addname + chip_idx + other_name chipname = addname + chip_idx + other_name
df['lanepackcode'] = chipname
# df = pd.concat([pd.DataFrame(self.items), df]).reset_index(drop=True)
#
# df.to_excel(writer, sheet_name=chipname, index=False)
res.extend(df.to_dict('records'))
chip_loc += 1
sum_list = list() sum_list = list()
for library, library_df in df.groupby('samplename'): for library, library_df in df.groupby('samplename'):
sum_list.append(dict( sum_list.append(dict(
预排文库编号=library_df['sampleCode'].values[0],
二次拆分=library, 二次拆分=library,
客户=library_df['companynamea'].values[0], 客户=library_df['companynamea'].values[0],
类型=library_df['classification'].values[0], 类型=library_df['librarystructure'].values[0],
打折前=library_df['orderdatavolume'].sum() 打折前=library_df['orderdatavolume'].sum()
)) ))
df_sum = pd.DataFrame(sum_list) df_sum = pd.DataFrame(sum_list)
sum_res.append({'sheetname': chipname, 'data': df_sum}) res_df = pd.concat([df, df_sum], axis=1)
res_df.to_excel(writer, sheet_name=chipname, index=False)
chip_loc += 1
res_df = pd.DataFrame(res) # res_df = pd.DataFrame(res)
res_df = pd.concat([pd.DataFrame(self.items), res_df]).reset_index(drop=True) # res_df = pd.concat([pd.DataFrame(self.items), res_df]).reset_index(drop=True)
res_df.to_excel(writer, sheet_name='assignment', index=False) # res_df.to_excel(writer, sheet_name='assignment', index=False)
for sum_sheet in sum_res: # for sum_sheet in sum_res:
sheetname = sum_sheet.get('sheetname') # sheetname = sum_sheet.get('sheetname')
df_data = sum_sheet.get('data') # df_data = sum_sheet.get('data')
df_data.to_excel(writer, sheet_name=sheetname, index=False) # df_data.to_excel(writer, sheet_name=sheetname, index=False)
no_assign_df = pd.DataFrame(self.no_assign_data) no_assign_df = pd.DataFrame(self.no_assign_data)
if not no_assign_df.empty: if not no_assign_df.empty:
no_assign_df = no_assign_df.applymap(lambda x: format_date(x) if isinstance(x, pd.Timestamp) else x) no_assign_df = no_assign_df.applymap(lambda x: format_date(x) if isinstance(x, pd.Timestamp) else x)
no_assign_df_not_balance = ','.join(set([lib for lib in no_assign_df['samplename'] if lib in self.split_lib])) no_assign_df_not_balance = ','.join(
set([lib for lib in no_assign_df['samplename'] if lib in self.split_lib]))
if 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!') 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: # if not no_assign_df.empty:
# no_assign_df = no_assign_df[self.need_cols] # no_assign_df = no_assign_df[self.need_cols]
no_assign_df = pd.concat([pd.DataFrame(self.items), no_assign_df]).reset_index(drop=True) no_assign_df = pd.concat([pd.DataFrame(self.items), no_assign_df]).reset_index(drop=True)
no_assign_df.to_excel(writer, sheet_name='未测', index=False) no_assign_df.to_excel(writer, sheet_name='未测', index=False)
order_assign_df = pd.DataFrame(self.order_assign_data)
if not order_assign_df.empty:
order_assign_df = pd.concat([pd.DataFrame(self.items), order_assign_df]).reset_index(drop=True)
order_assign_df.to_excel(writer, sheet_name='包lane', index=False)
if self.return_log: if self.return_log:
pd.DataFrame(self.return_log).to_excel(writer, sheet_name='log', index=False) pd.DataFrame(self.return_log).to_excel(writer, sheet_name='log', index=False)
writer.close() writer.close()