diff --git a/T7_server.py b/T7_server.py index 8a25055..7aeecee 100644 --- a/T7_server.py +++ b/T7_server.py @@ -67,16 +67,23 @@ def server(): adrss = ("", 8191) myserver.bind(adrss) myserver.listen(5) - while True: - try: - myclient, adddr = myserver.accept() - recv_content, chipnum = recvdata(myclient, os.path.join(basedir, 'example')) - layout = T7(recv_content, chipnum) - outputpath = layout.run() - senddata(myclient, outputpath) - except Exception as e: - print(e) - continue + + myclient, adddr = myserver.accept() + recv_content, chipnum = recvdata(myclient, os.path.join(basedir, 'example')) + layout = T7(recv_content, chipnum) + outputpath = layout.run() + senddata(myclient, outputpath) + + # while True: + # try: + # myclient, adddr = myserver.accept() + # recv_content, chipnum = recvdata(myclient, os.path.join(basedir, 'example')) + # layout = T7(recv_content, chipnum) + # outputpath = layout.run() + # senddata(myclient, outputpath) + # except Exception as e: + # print(e) + # continue if __name__ == '__main__': diff --git a/tools/t7.py b/tools/t7.py index 6916fd1..d63cd6b 100644 --- a/tools/t7.py +++ b/tools/t7.py @@ -13,7 +13,7 @@ class AutoLayout: 自动化派样 """ - def __init__(self, path, chipnum, output=basedir, data_limit=1520): + def __init__(self, path, chipnum, output=basedir, data_limit=1800): self.path = path self.output = output self.chipnum = int(chipnum) @@ -78,39 +78,39 @@ class AutoLayout: self.chip_customer[chipname].add(library_data['customer']) self.chip_classification[chipname].add(library_data['classification']) - def add_new_chip(self, library_data): - """ - 要新增到芯片上的数据 - :param library_data: - :return: - """ - chip_num_tmp = self.loc_chip_num - while True: - chip_num_tmp += 1 - chipname_tmp = f'chip{chip_num_tmp}' - library = library_data['library'] - if chipname_tmp not in self.index_assignments: - self.logger.error(f'{library} {chipname_tmp} 常规添加') - self.add_new_data(chipname_tmp, library_data) - break - else: - is_same_barcode = self.chip_barcode_recode[chipname_tmp].intersection( - {item['barcode'] for item in library_data['data']}) - # 没有从重复的index,并且也不互斥的 - if ((self.chip_size[chipname_tmp] + library_data['size']) > self.data_limit): - self.logger.error(f'{library} {chipname_tmp} 文库相加大于设定限制') - if ((self.chip_speciallib_size[chipname_tmp] + library_data['size']) >= 200): - self.logger.error(f'{library} {chipname_tmp} 不平衡文库相加大于设定限制') - if is_same_barcode: - self.logger.error(f'{library} {chipname_tmp} 文库有barcode重复') - if self.use_rule(chipname_tmp, library_data['customer']): - self.logger.error(f'{library} {chipname_tmp} 有互斥单位') - if ((self.chip_size[chipname_tmp] + library_data['size']) <= self.data_limit) \ - and ((self.chip_speciallib_size[chipname_tmp] + library_data['size']) < 200) \ - and (not is_same_barcode) \ - and (not self.use_rule(chipname_tmp, library_data['customer'])): - self.add_new_data(chipname_tmp, library_data, newer=False) - break + # def add_new_chip(self, library_data): + # """ + # 要新增到芯片上的数据 + # :param library_data: + # :return: + # """ + # chip_num_tmp = self.loc_chip_num + # while True: + # chip_num_tmp += 1 + # chipname_tmp = f'chip{chip_num_tmp}' + # library = library_data['library'] + # if chipname_tmp not in self.index_assignments: + # self.logger.error(f'{library} {chipname_tmp} 常规添加') + # self.add_new_data(chipname_tmp, library_data) + # break + # else: + # is_same_barcode = self.chip_barcode_recode[chipname_tmp].intersection( + # {item['barcode'] for item in library_data['data']}) + # # 没有从重复的index,并且也不互斥的 + # if ((self.chip_size[chipname_tmp] + library_data['size']) > self.data_limit): + # self.logger.error(f'{library} {chipname_tmp} 文库相加大于设定限制') + # if ((self.chip_speciallib_size[chipname_tmp] + library_data['size']) >= 200): + # self.logger.error(f'{library} {chipname_tmp} 不平衡文库相加大于设定限制') + # if is_same_barcode: + # self.logger.error(f'{library} {chipname_tmp} 文库有barcode重复') + # if self.use_rule(chipname_tmp, library_data['customer']): + # self.logger.error(f'{library} {chipname_tmp} 有互斥单位') + # if ((self.chip_size[chipname_tmp] + library_data['size']) <= self.data_limit) \ + # and ((self.chip_speciallib_size[chipname_tmp] + library_data['size']) < 200) \ + # and (not is_same_barcode) \ + # and (not self.use_rule(chipname_tmp, library_data['customer'])): + # self.add_new_data(chipname_tmp, library_data, newer=False) + # break def dec_barcode_radio(self, chipname): data = self.index_assignments[chipname] @@ -134,8 +134,6 @@ class AutoLayout: # is_need_base = col_df.index[col_df['ratio'] < 0.088] A, B, C, D = list(), list(), list(), list(), - - need_base_list = list() ratio = col_df['ratio'].to_dict() for decbase in ['A', 'T', 'C', 'G']: if decbase not in ratio: @@ -153,7 +151,7 @@ class AutoLayout: '%s 第%s位置,有碱基不平衡，算出结果为 %s' % (chipname, i, ratio) ) - if len(is_not_balance_list) > 2: + if len(is_not_balance_list): self.return_log.append('有碱基不平衡性！') self.return_log.extend(is_not_balance_list) print('有碱基不平衡性！\n', '\n'.join(is_not_balance_list)) @@ -193,7 +191,7 @@ class AutoLayout: return res.reset_index() def use_rule(self, chipname, classfication): - may_classfic= set(self.rule[self.rule['c1'] == classfication]['c2']) + may_classfic = set(self.rule[self.rule['c1'] == classfication]['c2']) if self.chip_customer[chipname].intersection(may_classfic): return True return False @@ -221,15 +219,15 @@ class AutoLayout: # self.logger.error(f'{library} {chipname} 有互斥单位') # 互斥的文库 - exclusive_classific= True + exclusive_classific = True if self.use_rule(chipname, classification): - exclusive_classific= False + exclusive_classific = False self.logger.error(f'{library} {chipname} 有互斥单位') # 不平衡文库大于200G 不能添加 splibrary = True if classification in ['扩增子', '不平衡文库', '单细胞文库', '甲基化'] \ - and self.chip_speciallib_size[chipname] + size > 200: + and self.chip_speciallib_size[chipname] + size > 250: splibrary = False self.logger.error(f'{library} {chipname} 不平衡文库相加大于设定限制') if sizelimit and notrepeatbarcode and exclusive_classific and splibrary: @@ -262,11 +260,12 @@ class AutoLayout: need_col.append('note') - self.no_assign_data.extend(ori_library_df[~(numeric_mask & time_mask)].to_dict('records')) - # 使用布尔索引筛选出不是数字和非日期的行 - ori_library_df = ori_library_df[numeric_mask & time_mask] - ori_library_df['level'] = ori_library_df.apply(self.level, axis=1) + no_ori_data = ori_library_df[~(numeric_mask & time_mask)] + 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 + ori_library_df = ori_library_df[(numeric_mask & time_mask)] + ori_library_df['level'] = ori_library_df.apply(self.level, axis=1) for library, library_df in ori_library_df.groupby('#library'): ori_library_data.append(dict( library=library, @@ -308,14 +307,13 @@ class AutoLayout: j += 1 else: self.loc_chip_num += 1 - if self.chip_size[chipname] > 1500: + if self.chip_size[chipname] > self.data_limit: self.loc_chip_num += 1 def assign_again(self): pass def run(self): - self.assign_samples() try: self.assign_samples() except Exception as e: @@ -328,17 +326,20 @@ class AutoLayout: chip_loc = 1 for chip_idx, chip_assignments in self.index_assignments.items(): df = pd.DataFrame(chip_assignments) - if df['data_needed'].sum() < 1400 or chip_loc > self.chipnum: + df['time'] = df['time'].dt.strftime('%Y-%m-%d') + if df['data_needed'].sum() < 1500 or chip_loc > self.chipnum: self.no_assign_data.extend(chip_assignments) continue - if '极致' in df['拆分方式'].values: + if [method for method in df['拆分方式'].values if '极致' in method]: addname = 'X' else: addname = '' self.dec_barcode_radio(chip_idx) df.to_excel(writer, sheet_name=addname + chip_idx, index=False) chip_loc += 1 - pd.DataFrame(self.no_assign_data).to_excel(writer, sheet_name='未测', index=False) + no_assign_df = pd.DataFrame(self.no_assign_data) + # no_assign_df['time'] = no_assign_df['time'].dt.strftime('%Y-%m-%d') + no_assign_df.to_excel(writer, sheet_name='未测', index=False) if self.return_log: pd.DataFrame(self.return_log).to_excel(writer, sheet_name='log', index=False) writer.close()