OLS回归存储问题：零大小数组到归约操作最大值，没有身份

Question

I have a problem with this for loop in python. I'm trying to iterate the OLS command in a cross-section data where I'have multiple id observed during the same period. I want to do a regression for each id of each year, of each month.

When i try to run singurlarly the commands they works but in the loop the output is always the same: zero-size array to reduction operation maximum which has no identity . I have no idea where is the problem in the for loop. The problem is in the last 8 rows (i have uploaded the other only to make sense to them). Thanks in advance for your support.

import pandas as pd\\
import statsmodels.api as sm
import statsmodels.formula.api as smf
from datetime import datetime as dt
from sklearn import linear_model as lm
import numpy as np
data=pd.DataFrame()
data=pd.read_excel('gggg.xlsx', sheet_name='Foglio1')
data['Data']=pd.to_datetime(data['Data'])
data["year"]=data['Data'].dt.year
data["month"]=data['Data'].dt.month

sl=pd.wide_to_long(data, ['R','RM','V','MktCap'], i="Data", j="group_id")


sl["month1"]=sl["month"].shift(-1)
sl['monthindicator'] = np.where(sl['month']!=sl['month1'], 1, 0)
sl["year1"]=sl["year"].shift(-1)
sl['yearindicator'] = np.where(sl['year']!=sl['year1'], 1, 0)


sl['AdjVol']=sl['V']/sl['MktCap']
sl['id']=sl.index.get_level_values('group_id')

for i in range(1,11): 
    for y in range(2012,2020):
        for m in range(1,13):
            Y=sl.loc[(sl['id']==i) & (sl["year"]==y) & (sl["month"]==m), "R"]
            X=sl.loc[(sl['id']==i) & (sl["year"]==y) & (sl["month"]==m), "RM"]
            result = sm.OLS(Y, sm.add_constant(X))
            result=result.fit()
            sl["prediction"] = result.predict()  ```

Answer 1

it usually happens when there is missing value in dataset, you better try df.dropna(how='all') and test it