优化代码 def module_split(self, save_on=True): """ split module data :param save_on: :return: """ for ms in range(self.mod_num): m_sn = self.module_list[ms] module_path = os.path.join(self.result_path_down, m_sn) cols_obj = ChuNengPackMustCols(ms, self.mod_cell_num, self.mod_cell_num) # 传入当前的module序号（如0,1,2,3,4），电芯电压个数，温度NTC个数。 aim_cols = [i for i in cols_obj.total_cols if i in self.df.columns] print(m_sn, aim_cols) self.modules[m_sn] = rename_cols_normal(self.df.loc[:, aim_cols], ms, self.mod_cell_num) print("after change cols name:", ms, m_sn, self.modules[m_sn].columns.tolist()) self.modules[m_sn].dropna(axis=0, how='any', subset=['soc'], inplace=True) volt_col = [f'volt{i}' for i in range(self.mod_cell_num)] temp_col = [f'temp{i}' for i in range(self.mod_cell_num)] self.modules[m_sn].dropna(axis=0, how='any', subset=volt_col, inplace=True) self.modules[m_sn] = stat(self.modules[m_sn], volt_col, temp_col) self.modules[m_sn].reset_index(drop=True, inplace=True) print(self.modules[m_sn]['discharge_ah'].iloc[-1]) self.module_cap[m_sn] = [self.modules[m_sn]['discharge_ah'].iloc[-1], self.modules[m_sn]['charge_ah'].iloc[-1], self.modules[m_sn]['soh'].iloc[-1]] self.module_peaks[m_sn] = list(quick_report(self.modules[m_sn], module_path, f'quick_report_{m_sn[:8]}')) # check soc status mod_soc = self.modules[m_sn]['soc'] self.module_soc_sig[m_sn] = [np.nanmedian(mod_soc), np.max(mod_soc), np.min(mod_soc)] if save_on: single_variables_plot(mod_soc, module_path, f'{m_sn[:8]}_soc_distribution_box.png', 'box', 'SOC') single_variables_plot(mod_soc, module_path, f'{m_sn[:8]}_soc_distribution_violin.png', 'violin', 'SOC')

以下是代码优化后的版本：

def module_split(self, save_on=True):
    """
    Split module data
    :param save_on:
    :return:
    """
    for ms in range(self.mod_num):
        m_sn = self.module_list[ms]
        module_path = os.path.join(self.result_path_down, m_sn)
        cols_obj = ChuNengPackMustCols(ms, self.mod_cell_num, self.mod_cell_num)
        aim_cols = [i for i in cols_obj.total_cols if i in self.df.columns]
        print(m_sn, aim_cols)
        self.modules[m_sn] = rename_cols_normal(self.df.loc[:, aim_cols], ms, self.mod_cell_num)
        print("after change cols name:", ms, m_sn, self.modules[m_sn].columns.tolist())
        
        # Drop rows with NaN values in 'soc' and voltage columns
        volt_col = [f'volt{i}' for i in range(self.mod_cell_num)]
        temp_col = [f'temp{i}' for i in range(self.mod_cell_num)]
        self.modules[m_sn].dropna(axis=0, how='any', subset=['soc'] + volt_col, inplace=True)
        
        # Compute statistics on remaining data
        self.modules[m_sn] = stat(self.modules[m_sn], volt_col, temp_col)
        self.modules[m_sn].reset_index(drop=True, inplace=True)
        
        print(self.modules[m_sn]['discharge_ah'].iloc[-1])
        self.module_cap[m_sn] = [
            self.modules[m_sn]['discharge_ah'].iloc[-1],
            self.modules[m_sn]['charge_ah'].iloc[-1],
            self.modules[m_sn]['soh'].iloc[-1]
        ]
        self.module_peaks[m_sn] = list(quick_report(self.modules[m_sn], module_path, f'quick_report_{m_sn[:8]}'))
        
        # Compute SOC statistics and save plots
        mod_soc = self.modules[m_sn]['soc']
        self.module_soc_sig[m_sn] = [
            np.nanmedian(mod_soc),
            np.max(mod_soc),
            np.min(mod_soc)
        ]
        if save_on:
            for plot_type in ['box', 'violin']:
                single_variables_plot(mod_soc, module_path, f'{m_sn[:8]}_soc_distribution_{plot_type}.png', plot_type, 'SOC')

优化后的代码主要做了以下几个方面的改进：

1. 将所有行删除操作合并为一步，同时删除了温度列中的 NaN 值；
2. 统计数据前，只保留了保留了 'soc' 和电压列的非 NaN 行；
3. 在保存 SOC 分布图像时，避免了重复的代码。