when I run Arima/Sarima Model getting errors - ufunc 'isnan' not supported for the input types or Panda on numpy cast

Question

I am building ARIMA/Sarima Model in percentages but getting following error 1- model = SARIMAX(np.asarray(train), order = (0, 1, 1), seasonal_order =(1, 1, 1, 12))

TypeError: ufunc 'isnan' not supported for the input types, and the inputs could not be safely coerced to any supported types according to the casting rule ''safe''

2- If i don't covert pandas data frame to numpy array i get following error model = SARIMAX(train, order = (0, 1, 1), seasonal_order =(1, 1, 1, 12))

ValueError: Pandas data cast to numpy dtype of object. Check input data with np.asarray(data).

though few days back same code was working which I am using in step 2

Please also show us the data you are using. – Arne Decker Jan 05 '22 at 11:51 — Arne Decker, Jan 05 '22 at 11:51
issue was with input data :) it is working fine now – Ashish Jan 06 '22 at 08:15 — Ashish, Jan 06 '22 at 08:15

score 0 · Answer 1 · answered Jan 06 '22 at 08:14

0

issue was with the input data format, few rows had commas so it was reading it as string. Once i removed it is working fine.

answered Jan 06 '22 at 08:14

Ashish

115
3
15

when I run Arima/Sarima Model getting errors - ufunc 'isnan' not supported for the input types or Panda on numpy cast

1 Answers1