python-scipyHow can I use Python and SciPy to implement an ARIMA model?

Python and SciPy can be used to implement an ARIMA model. ARIMA stands for Autoregressive Integrated Moving Average and is a popular statistical model for time series forecasting.

Example code

from statsmodels.tsa.arima_model import ARIMA

# fit model
model = ARIMA(ts_data, order=(2,1,0))
model_fit = model.fit(disp=0)

# make prediction
yhat = model_fit.predict()

The code above fits the ARIMA model to the time series data in ts_data using an autoregressive order of 2, a differencing order of 1, and a moving average order of 0. The model is then used to make a prediction, which is stored in the variable yhat.

The list below contains parts of the code and a brief explanation of each part:

• from statsmodels.tsa.arima_model import ARIMA - imports the ARIMA model from the statsmodels library
• model = ARIMA(ts_data, order=(2,1,0)) - creates an ARIMA model object with the time series data and the specified order
• model_fit = model.fit(disp=0) - fits the model to the data
• yhat = model_fit.predict() - makes a prediction using the fitted model

Helpful links

• Statsmodels ARIMA Documentation
• Time Series Forecasting with Python

Edit this code on GitHub