** Problem **

Seeking to have return values from ARIMA model fit / forecast; namely 'fc', 'se', 'conf' from '= model_fit.forecast()'.

** ARIMA Model Works **

from statsmodels.tsa.arima_model import ARIMA
import statsmodels.api as sm

model = sm.tsa.arima.ARIMA(wd.weather_data['prcp'], order=(2,1,1))

** Model fit provides **

model_fit = model.fit()

SARIMAX Results
Dep. Variable:  prcp    No. Observations:   151802
Model:  ARIMA(2, 1, 1)  Log Likelihood  -516358.209
Date:   Tue, 29 Mar 2022    AIC 1032724.419
Time:   23:13:35    BIC 1032764.140
Sample: 0   HQIC    1032736.251
- 151802        
Covariance Type:    opg     
coef    std err z   P>|z|   [0.025  0.975]
ar.L1   0.1559  0.001   158.370 0.000   0.154   0.158
ar.L2   -0.0030 0.001   -2.195  0.028   -0.006  -0.000
ma.L1   -0.9916 0.000   -3414.610   0.000   -0.992  -0.991
sigma2  52.7300 0.026   2008.147    0.000   52.679  52.781
Ljung-Box (L1) (Q): 0.00    Jarque-Bera (JB):   81680638.75
Prob(Q):    1.00    Prob(JB):   0.00
Heteroskedasticity (H): 0.89    Skew:   7.35
Prob(H) (two-sided):    0.00    Kurtosis:   115.68


Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).

** Model fit forecast(5, alpha=05) **

This give forecasts ok. Set fc, se, conf

fc, se, conf = model_fit.forecast(5, alpha=0.05)

Then run time error, too many variables, expected 3. Well, I applied fc, se, conf = model_fit.forecast() has prediction values.

ValueError                                Traceback (most recent call last)
<ipython-input-31-b0971fda8955> in <module>()
----> 1 fc, se, conf = model_fit.forecast(5, alpha=0.05)
      2 results

ValueError: too many values to unpack (expected 3)