def soh_predict(self, df): IndentationError: unexpected indent

这个错误通常是由于代码缩进不正确导致的。在Python中，缩进非常重要，因为它用于表示代码块。如果缩进不正确，Python解释器将无法正确解析代码。在这种情况下，错误消息指出在缩进处有一个意外的缩进。

要解决此错误，请检查代码中缩进的位置是否正确。确保所有代码行的缩进级别相同，并且使用相同数量的空格或制表符进行缩进。建议使用四个空格进行缩进，而不是制表符。

以下是一个示例，演示了如何使用四个空格进行缩进：

def soh_predict(self, df):
    if some_condition:
        # do something
    else:
        # do something else

相关问题

优化代码 def fault_classification_wrapper(vin, main_path, data_path, log_path, done_path): start_time = time.time() isc_path = os.path.join(done_path, vin, 'isc_cal_result', f'{vin}_report.xlsx') if not os.path.exists(isc_path): print('No isc detection input!') else: isc_input = isc_produce_alarm(isc_path, vin) ica_path = os.path.join(done_path, vin, 'ica_cal_result', f'ica_detection_alarm_{vin}.csv') if not os.path.exists(ica_path): print('No ica detection input!') else: ica_input = ica_produce_alarm(ica_path) soh_path = os.path.join(done_path, vin, 'SOH_cal_result', f'{vin}_sohAno.csv') if not os.path.exists(soh_path): print('No soh detection input!') else: soh_input = soh_produce_alarm(soh_path, vin) alarm_df = pd.concat([isc_input, ica_input, soh_input]) alarm_df.reset_index(drop=True, inplace=True) alarm_df['alarm_cell'] = alarm_df['alarm_cell'].apply(lambda _: str(_)) print(vin) module = AutoAnalysisMain(alarm_df, main_path, data_path, done_path) module.analysis_process() flags = os.O_WRONLY | os.O_CREAT modes = stat.S_IWUSR | stat.S_IRUSR with os.fdopen(os.open(os.path.join(log_path, 'log.txt'), flags, modes), 'w') as txt_file: for k, v in module.output.items(): txt_file.write(k + ':' + str(v)) txt_file.write('\n') for x, y in module.output_sub.items(): txt_file.write(x + ':' + str(y)) txt_file.write('\n\n') fc_result_path = os.path.join(done_path, vin, 'fc_result') if not os.path.exists(fc_result_path): os.makedirs(fc_result_path) pd.DataFrame(module.output).to_csv( os.path.join(fc_result_path, 'main_structure.csv')) df2 = pd.DataFrame() for subs in module.output_sub.keys(): sub_s = pd.Series(module.output_sub[subs]) df2 = df2.append(sub_s, ignore_index=True) df2.to_csv(os.path.join(fc_result_path, 'sub_structure.csv')) end_time = time.time() print("time cost of fault classification:", float(end_time - start_time) * 1000.0, "ms") return

Here are some suggestions to optimize the code:

1. Use list comprehension to simplify the code:

   alarm_df = pd.concat([isc_input, ica_input, soh_input]).reset_index(drop=True)
   alarm_df['alarm_cell'] = alarm_df['alarm_cell'].apply(str)

2. Use context manager to simplify file operation:

   with open(os.path.join(log_path, 'log.txt'), 'w') as txt_file:
       for k, v in module.output.items():
           txt_file.write(f"{k}:{v}\n")
       for x, y in module.output_sub.items():
           txt_file.write(f"{x}:{y}\n\n")

3. Use `Pathlib` to simplify path operation:

   fc_result_path = Path(done_path) / vin / 'fc_result'
   fc_result_path.mkdir(parents=True, exist_ok=True)
   pd.DataFrame(module.output).to_csv(fc_result_path / 'main_structure.csv')
   pd.DataFrame(module.output_sub).to_csv(fc_result_path / 'sub_structure.csv')

4. Use f-string to simplify string formatting:

   print(f"time cost of fault classification: {(end_time - start_time) * 1000.0} ms")

Here's the optimized code:

def fault_classification_wrapper(vin, main_path, data_path, log_path, done_path):
    start_time = time.time()

    isc_path = Path(done_path) / vin / 'isc_cal_result' / f'{vin}_report.xlsx'
    if not isc_path.exists():
        print('No isc detection input!')
        isc_input = pd.DataFrame()
    else:
        isc_input = isc_produce_alarm(isc_path, vin)

    ica_path = Path(done_path) / vin / 'ica_cal_result' / f'ica_detection_alarm_{vin}.csv'
    if not ica_path.exists():
        print('No ica detection input!')
        ica_input = pd.DataFrame()
    else:
        ica_input = ica_produce_alarm(ica_path)

    soh_path = Path(done_path) / vin / 'SOH_cal_result' / f'{vin}_sohAno.csv'
    if not soh_path.exists():
        print('No soh detection input!')
        soh_input = pd.DataFrame()
    else:
        soh_input = soh_produce_alarm(soh_path, vin)

    alarm_df = pd.concat([isc_input, ica_input, soh_input]).reset_index(drop=True)
    alarm_df['alarm_cell'] = alarm_df['alarm_cell'].apply(str)

    print(vin)
    module = AutoAnalysisMain(alarm_df, main_path, data_path, done_path)
    module.analysis_process()

    with open(Path(log_path) / 'log.txt', 'w') as txt_file:
        for k, v in module.output.items():
            txt_file.write(f"{k}:{v}\n")
        for x, y in module.output_sub.items():
            txt_file.write(f"{x}:{y}\n\n")

    fc_result_path = Path(done_path) / vin / 'fc_result'
    fc_result_path.mkdir(parents=True, exist_ok=True)
    pd.DataFrame(module.output).to_csv(fc_result_path / 'main_structure.csv')
    pd.DataFrame(module.output_sub).to_csv(fc_result_path / 'sub_structure.csv')

    end_time = time.time()
    print(f"time cost of fault classification: {(end_time - start_time) * 1000.0} ms")

    return

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。