优化这段代码df_in_grown_ebv = pd.read_table(open(r"C:\Users\荆晓燕\Desktop\20230515分品种计算育种值\生长性能育种值N72分组 (7).txt"), delim_whitespace=True, encoding="gb18030", header=None) df_in_breed_ebv = pd.read_table(open(r"C:\Users\荆晓燕\Desktop\20230515分品种计算育种值\繁殖性能育种值N72分组 (7).txt"), delim_whitespace=True, encoding="gb18030", header=None) # df_in_grown_Phenotype.columns = ['个体号', '活仔EBV', '21d窝重EBV', '断配EBV'] # df_in_breed_Phenotype.columns = ['个体号', '115EBV', '饲料转化率EBV', '瘦肉率EBV', '眼肌EBV', '背膘EBV'] df_in_breed_ebv.columns = ['个体号', '活仔EBV', '21d窝重EBV', '断配EBV'] df_in_grown_ebv.columns = ['个体号', '115daysEBV', '饲料转化率EBV', '瘦肉率EBV', '眼肌EBV', '背膘EBV'] NBA_mean = np.mean(df_in_breed_ebv['活仔EBV']) NBA_std = np.std(df_in_breed_ebv['活仔EBV']) days_mean = np.mean(df_in_grown_ebv['115daysEBV']) days_std = np.std(df_in_grown_ebv['115daysEBV']) fcr_mean = np.mean(df_in_grown_ebv['饲料转化率EBV']) fcr_std = np.std(df_in_grown_ebv['饲料转化率EBV']) output = pd.merge(df_in_grown_ebv, df_in_breed_ebv, how='inner', left_on='个体号', right_on='个体号') # output['计算长白母系指数'] = 0.3 * (NBA - NBA_mean)/NBA_std - 0.3 * (days - days_mean)/days_std - 0.3 * (fcr-fcr_mean)/fcr_std + 0.1 * (pcl-pcl_mean)/pcl_std output['计算长白母系指数'] = 0.29 * (df_in_breed_ebv['活仔EBV'] - NBA_mean)/NBA_std - 0.58 * (df_in_grown_ebv['115daysEBV']- days_mean)/days_std - 0.13 * (df_in_grown_ebv['饲料转化率EBV']-fcr_mean)/fcr_std MLI_mean = np.mean(output['计算长白母系指数']) MLI_std = np.std(output['计算长白母系指数']) output['校正长白母系指数'] = 25 * ((output['计算长白母系指数'] - MLI_mean)/MLI_std) + 100

可以优化的地方有：

1. 重复的路径可以抽象成一个变量，避免代码重复。

2. 可以使用 with 语句来处理文件读取，避免忘记关闭文件。

3. 可以在读取文件时指定列名，避免后续需要重新指定列名。

4. 可以将计算指数和计算校正指数的代码分成两个函数，提高代码的可读性和可维护性。

优化后的代码如下：

import pandas as pd
import numpy as np

# 定义文件路径
breed_file = r"C:\Users\荆晓燕\Desktop\20230515分品种计算育种值\繁殖性能育种值N72分组 (7).txt"
grown_file = r"C:\Users\荆晓燕\Desktop\20230515分品种计算育种值\生长性能育种值N72分组 (7).txt"

def read_file(file_path, columns):
    with open(file_path, encoding="gb18030") as f:
        df = pd.read_table(f, delim_whitespace=True, header=None)
        df.columns = columns
    return df

# 读取文件并指定列名
df_in_breed_ebv = read_file(breed_file, ['个体号', '活仔EBV', '21d窝重EBV', '断配EBV'])
df_in_grown_ebv = read_file(grown_file, ['个体号', '115daysEBV', '饲料转化率EBV', '瘦肉率EBV', '眼肌EBV', '背膘EBV'])

def calculate_index(df_in_breed_ebv, df_in_grown_ebv):
    # 计算指数
    NBA_mean = np.mean(df_in_breed_ebv['活仔EBV'])
    NBA_std = np.std(df_in_breed_ebv['活仔EBV'])
    days_mean = np.mean(df_in_grown_ebv['115daysEBV'])
    days_std = np.std(df_in_grown_ebv['115daysEBV'])
    fcr_mean = np.mean(df_in_grown_ebv['饲料转化率EBV'])
    fcr_std = np.std(df_in_grown_ebv['饲料转化率EBV'])
    
    df = pd.merge(df_in_grown_ebv, df_in_breed_ebv, how='inner', on='个体号')
    df['计算长白母系指数'] = 0.29 * (df['活仔EBV'] - NBA_mean) / NBA_std - 0.58 * (df['115daysEBV'] - days_mean) / days_std - 0.13 * (df['饲料转化率EBV'] - fcr_mean) / fcr_std
    return df

def calculate_correction_index(df):
    # 计算校正指数
    MLI_mean = np.mean(df['计算长白母系指数'])
    MLI_std = np.std(df['计算长白母系指数'])
    df['校正长白母系指数'] = 25 * ((df['计算长白母系指数'] - MLI_mean) / MLI_std) + 100
    return df

# 计算指数和校正指数
df_index = calculate_index(df_in_breed_ebv, df_in_grown_ebv)
df_correction_index = calculate_correction_index(df_index)