Python Pandas实现数据分组求平均值并填充nan的示例

factordatafillna = pd.DataFrame()industrys = newfactordata1.industryName1.unique()for ind in industrys:  t = newfactordata1.industryName1 == ind  a = newfactordata1[t].fillna(newfactordata1[t].mean())  factordatafillna = factordatafillna.append(a)

df = pd.DataFrame({'code':[1,2,3,4,5,6,7,8],          'value':[np.nan,5,7,8,9,10,11,12],                    'value2':[5,np.nan,7,np.nan,9,10,11,12],          'indstry':['农业1','农业1','农业1','农业2','农业2','农业4','农业2','农业3']},          columns=['code','value','value2','indstry'],          index=list('ABCDEFGH'))# 只留下需要处理的列cols = [col for col in df.columns if col not in['code','indstry']]# 分组的列gp_col = 'indstry'# 查询nan的列df_na = df[cols].isna()# 根据分组计算平均值df_mean = df.groupby(gp_col)[cols].mean()print(df)# 依次处理每一列for col in cols:  na_series = df_na[col]  names = list(df.loc[na_series,gp_col])     t = df_mean.loc[names,col]  t.index = df.loc[na_series,col].index  # 相同的index进行赋值     df.loc[na_series,col] = tprint(df)

code value value2 indstryA   1  NaN   5.0   农业1B   2  5.0   NaN   农业1C   3  7.0   7.0   农业1D   4  8.0   NaN   农业2E   5  9.0   9.0   农业2F   6  10.0  10.0   农业4G   7  11.0  11.0   农业2H   8  12.0  12.0   农业3  code value value2 indstryA   1  6.0   5.0   农业1B   2  5.0   6.0   农业1C   3  7.0   7.0   农业1D   4  8.0  10.0   农业2E   5  9.0   9.0   农业2F   6  10.0  10.0   农业4G   7  11.0  11.0   农业2H   8  12.0  12.0   农业3