Auto.Arima() Equivalent for Python

auto.arima() equivalent for python

You can implement a number of approaches:

1. ARIMAResults include aic and bic. By their definition, (see here and here), these criteria penalize for the number of parameters in the model. So you may use these numbers to compare the models. Also scipy has optimize.brute which does grid search on the specified parameters space. So a workflow like this should work:

    def objfunc(order, exog, endog):
        from statsmodels.tsa.arima.model import ARIMA
        fit = ARIMA(endog, order, exog).fit()
        return fit.aic()
   
    from scipy.optimize import brute
    grid = (slice(1, 3, 1), slice(1, 3, 1), slice(1, 3, 1))
    brute(objfunc, grid, args=(exog, endog), finish=None)
   

Make sure you call brute with finish=None.

2. You may obtain pvalues from ARIMAResults. So a sort of step-forward algorithm is easy to implement where the degree of the model is increased across the dimension which obtains lowest p-value for the added parameter.

3. Use ARIMAResults.predict to cross-validate alternative models. The best approach would be to keep the tail of the time series (say most recent 5% of data) out of sample, and use these points to obtain the test error of the fitted models.

What is the equivalent of R forecast:auto.arima in Python

A simple solution is to call your R function from Python. One way to do that is to use the interface rpy2. The repository is here and the Python Package Index (PyPI) page is here.

Updated links on 3/18/2022.

auto arima: r and python suggest different arima models for same data, why?

I have moved around the web and found this python code very useful

# import package
import itertools

# Define the p, d and q parameters to take any value between 0 and 2
p = d = q = range(0, 3)

# Generate all different combinations of p, q and q triplets
pdq = list(itertools.product(p, d, q))

# Generate all different combinations of seasonal p, q and q 
triplets
seasonal_pdq = [(x[0], x[1], x[2], 12) for x in 
list(itertools.product(p, d, q))]

print('Examples of parameter combinations for Seasonal ARIMA...')
print('SARIMAX: {} x {}'.format(pdq[1], seasonal_pdq[1]))
print('SARIMAX: {} x {}'.format(pdq[1], seasonal_pdq[2]))
print('SARIMAX: {} x {}'.format(pdq[2], seasonal_pdq[3]))
print('SARIMAX: {} x {}'.format(pdq[2], seasonal_pdq[4]))

And

warnings.filterwarnings("ignore") # specify to ignore warning messages

for param in pdq:
    for param_seasonal in seasonal_pdq:
        try:
            mod = sm.tsa.statespace.SARIMAX(ts,
                                     order=param,
                                     seasonal_order=param_seasonal,
                                     enforce_stationarity=False,
                                     enforce_invertibility=False)

            results = mod.fit()

            print('ARIMA{}x{}12 - AIC:{}'.format(param, param_seasonal, results.aic))
        except:
            continue

The variable tp imput here is the univiriate time series data which I indicate with tsin the python code. the result is the same as the auto.arima in R.

ARIMA prediction in a loop Python

Start and end are the starting and ending points you wish to forecast. So this might be start = '2012-07-31' and end = '2012-09-01'.

Regarding params - when .fit() is called, an ARIMAResults class is returned. This class' predict method does not require the params argument: start and end should be all that's needed.

For your second question, this answer should help. I was not actually able to get that code to work for myself, but I'm sure you could get a AIC/BIC grid search to work in that or a similar way. An alternative would be switching to R and using the auto.arima function, which also selects the best (p,d,q) order based on AIC/BIC (which is definitely more advisable than selecting based on p-values).

You should be able to get the coefficients from your fitted model using r.params

Is there a way to force seasonality from auto.arima

You can set the D parameter, which governs seasonal differencing, to a value greater than zero. (The default NA allows auto.arima() to use or not use seasonality.) For example:

> set.seed(1)
> foo <- ts(rnorm(60),frequency=12)
> auto.arima(foo)
Series: foo 
ARIMA(0,0,0) with zero mean     

sigma^2 estimated as 0.7307:  log likelihood=-75.72
AIC=153.45   AICc=153.52   BIC=155.54
> auto.arima(foo,D=1)
Series: foo 
ARIMA(0,0,0)(1,1,0)[12]                    

Coefficients:
         sar1
      -0.3902
s.e.   0.1478

sigma^2 estimated as 1.139:  log likelihood=-72.23
AIC=148.46   AICc=148.73   BIC=152.21

---

Related Topics