ARIMA in Python

Order (p, d, q), a fit, and a forecast with an interval.

import numpy as np
import pandas as pd
from statsmodels.tsa.arima.model import ARIMA

rng = np.random.default_rng(14)
values = np.zeros(200)
for i in range(1, 200):
    values[i] = 0.6 * values[i - 1] + rng.normal()
series = pd.Series(values + 90)

model = ARIMA(series, order=(1, 0, 0)).fit()
print(model.params.round(4).to_dict())
print(round(model.aic, 2), round(model.bic, 2))

forecast = model.get_forecast(steps=3)
print(forecast.predicted_mean.round(2).tolist())
print(forecast.conf_int(alpha=0.05).round(2).to_numpy()[0])

How it works

1. d is how many times the series is differenced.
2. get_forecast gives the interval, forecast only the point.
3. AIC is what you compare when choosing an order.

Keywords and builtins used here

• as
• for
• print
• range
• round

The run, in numbers

Lines

17

Characters to type

525

Tokens

178

Three-star pace

115 tpm

At the three-star pace of 115 tokens a minute, this run takes about 93 seconds.

Type this snippet

Step 4 of 6 in Time series, step 16 of 19 in Statistics with statsmodels.

← Previous Next →