I have the following input:

startDate = "2013-01-01"
endDate = "2013-01-01"
knownTimestamps = ['2013-01-01 00:00','2013-01-01 01:00','2013-01-01 02:00','2013-01-01 03:00','2013-01-01 04:00', '2013-01-01 05:00','2013-01-01 06:00','2013-01-01 08:00','2013-01-01 10:00','2013-01-01 11:00', '2013-01-01 12:00','2013-01-01 13:00','2013-01-01 16:00','2013-01-01 17:00','2013-01-01 18:00', '2013-01-01 19:00','2013-01-01 20:00','2013-01-01 21:00','2013-01-01 23:00']
humidity = ['0.62','0.64','0.62','0.63','0.63','0.64','0.63','0.64','0.48','0.46','0.45','0.44','0.46','0.47','0.48','0.49','0.51','0.52','0.52']
timestamps = ['2013-01-01 07:00','2013-01-01 09:00','2013-01-01 14:00','2013-01-01 15:00','2013-01-01 22:00']

And I am using following function to predict the humidity values using AR model in python.

from statsmodels.tsa.arima_model import ARIMA
def predictMissingHumidity(startDate, endDate, knownTimestamps, humidity, timestamps):
data_prediction = pd.DataFrame({'knownTimestamps': knownTimestamps,'humidity': humidity})
print(data_prediction.head(10))
history = [float(x) for x in data_prediction.humidity]
predictions = []
test = timestamps
for t in range(len(test)): model = ARIMA(history, order=(2,2,0)) model_fit = model.fit(disp=0) output = model_fit.forecast() yhat = output[0] predictions.append(float(yhat)) obs = test[t] history.append(float(obs))
print(predictions)
return predictions

The model predict the same value of humidity for the values in time stamp list.

res = predictMissingHumidity(startDate, endDate, knownTimestamps, humidity, timestamps)
print(res)
output = [0.5287247355700563, 0.5287247355700563, 0.5287247355700563, 0.5287247355700563, 0.5287247355700563] 

Can someone tell me where I am wrong?

1 Answer

You are not updating your history. Presumably, this is the site where most of your code comes from

There you can see how, on line 23, the history is updated and used for the forecast at the next step on the test set:

history.append(obs)

3

Your Answer

Sign up or log in

Sign up using Google Sign up using Facebook Sign up using Email and Password Submit

Post as a guest

Post Your Answer Discard

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.