def _fit_forecaster(self, y, X=None):
"""Fit forecaster to training data.
Wraps Statsmodel's VAR fit method.
Parameters
----------
y : pd.DataFrame
Target time series to which to fit the forecaster.
fh : int, list, np.array or ForecastingHorizon, optional (default=None)
The forecasters horizon with the steps ahead to to predict.
X : pd.DataFrame, optional (default=None)
Returns
-------
self : returns an instance of self.
"""
self._forecaster = _VAR(endog=y, exog=X, missing=self.missing)
self._fitted_forecaster = self._forecaster.fit(
trend=self.trend,
maxlags=self.maxlags,
method=self.method,
verbose=self.verbose,
)
return self
def VAR(ts, max_order=15):
"""Vector Autoregressive Baseline Generator."""
# VAR model
if isinstance(ts, pd.DataFrame):
var = _VAR(ts.values)
elif isinstance(ts, np.ndarray):
var = _VAR(ts)
# optimal order
order = var.select_order(max_order)['aic']
# fit model
model = var.fit(order)
# simulation
ts_gen = var_util.varsim(model.coefs,
model.intercept,
model.sigma_u,
steps=len(ts.values))
return ts_gen
def VAR(df, max_order=15, return_model=False):
"""Vector Autoregressive Baseline Generator."""
# VAR model
var = _VAR(df)
# fit model
model = var.fit(maxlags=max_order, ic='aic')
# simulation
ts_gen = model.simulate_var(len(df.values))
# Create pandas DataFrame
df_gen = pd.DataFrame(ts_gen,
columns=df.columns,
index=df.index[-len(ts_gen):])
if return_model:
return df_gen, model
else:
return df_gen
def test_VAR_against_statsmodels():
"""Compares Sktime's and Statsmodel's VAR."""
train, test = temporal_train_test_split(df)
sktime_model = VAR()
fh = ForecastingHorizon([1, 3, 4, 5, 7, 9])
sktime_model.fit(train)
y_pred = sktime_model.predict(fh=fh)
stats = _VAR(train)
stats_fit = stats.fit()
fh_int = fh.to_relative(train.index[-1])
lagged = stats_fit.k_ar
y_pred_stats = stats_fit.forecast(train.values[-lagged:], steps=fh_int[-1])
new_arr = []
for i in fh_int:
new_arr.append(y_pred_stats[i - 1])
assert_allclose(y_pred, new_arr)