Dates in timeseries models

python

import matplotlib.pyplot as plt
import pandas as pd
import statsmodels.api as sm
from statsmodels.tsa.ar_model import AutoReg, ar_select_order

plt.rc("figure", figsize=(16, 8))
plt.rc("font", size=14)

Getting started

python

data = sm.datasets.sunspots.load()

Right now an annual date series must be datetimes at the end of the year.

python

from datetime import datetime

dates = pd.date_range("1700-1-1", periods=len(data.endog), freq="YE-DEC")

Using Pandas

Make a pandas TimeSeries or DataFrame

python

data.endog.index = dates
endog = data.endog
endog

Instantiate the model

python

selection_res = ar_select_order(endog, 9, old_names=False, seasonal=True, period=11)
pandas_ar_res = selection_res.model.fit()

Out-of-sample prediction

python

pred = pandas_ar_res.predict(start="2005", end="2027")
print(pred)

python

fig = pandas_ar_res.plot_predict(start="2005", end="2027")