优化代码 def cluster_format(self, start_time, end_time, save_on=True, data_clean=False, data_name=None): """ local format function is to format data from beihang. :param start_time: :param end_time: :return: """ # 户用簇级数据清洗 if data_clean: unused_index_col = [i for i in self.df.columns if 'Unnamed' in i] self.df.drop(columns=unused_index_col, inplace=True) self.df.drop_duplicates(inplace=True, ignore_index=True) self.df.reset_index(drop=True, inplace=True) dupli_header_lines = np.where(self.df['sendtime'] == 'sendtime')[0] self.df.drop(index=dupli_header_lines, inplace=True) self.df = self.df.apply(pd.to_numeric, errors='ignore') self.df['sendtime'] = pd.to_datetime(self.df['sendtime']) self.df.sort_values(by='sendtime', inplace=True, ignore_index=True) self.df.to_csv(data_name, index=False) # 调用基本格式化处理 self.df = super().format(start_time, end_time) module_number_register = np.unique(self.df['bat_module_num']) # if registered m_num is 0 and not changed, there is no module data if not np.any(module_number_register): logger.logger.warning("No module data!") sys.exit() if 'bat_module_voltage_00' in self.df.columns: volt_ref = 'bat_module_voltage_00' elif 'bat_module_voltage_01' in self.df.columns: volt_ref = 'bat_module_voltage_01' elif 'bat_module_voltage_02' in self.df.columns: volt_ref = 'bat_module_voltage_02' else: logger.logger.warning("No module data!") sys.exit() self.df.dropna(axis=0, subset=[volt_ref], inplace=True) self.df.reset_index(drop=True, inplace=True) self.headers = list(self.df.columns) # time duration of a cluster self.length = len(self.df) if self.length == 0: logger.logger.warning("After cluster data clean, no effective data!") raise ValueError("No effective data after cluster data clean.") self.cluster_stats(save_on) for m in range(self.mod_num): print(self.clusterid, self.mod_num) self.module_list.append(np.unique(self.df[f'bat_module_sn_{str(m).zfill(2)}'].dropna())[0])

Here are some possible optimizations for the given code:

1. Instead of using a list comprehension to find columns with 'Unnamed' in their names, you can use the `filter()` function along with a lambda function to achieve the same result in a more concise way:

   unused_index_col = list(filter(lambda x: 'Unnamed' in x, self.df.columns))

2. Instead of dropping duplicates and resetting the index separately, you can use the `drop_duplicates()` function with the `ignore_index` parameter set to `True` to achieve both in one step:

   self.df.drop_duplicates(inplace=True, ignore_index=True)

3. Instead of using `sys.exit()` to terminate the program when there is no module data, you can raise a `ValueError` with an appropriate error message:

   raise ValueError("No module data!")

4. Instead of using a series of `if` statements to find the voltage reference column, you can use the `loc` accessor with a boolean mask to select the first column that starts with 'bat_module_voltage':

   volt_ref_col = self.df.columns[self.df.columns.str.startswith('bat_module_voltage')][0]

5. Instead of using a loop to append a single item to a list, you can use the `append()` method directly:

   self.module_list.append(np.unique(self.df[f'bat_module_sn_{str(m).zfill(2)}'].dropna())[0])

By applying these optimizations, the code can become more concise and efficient.