statsmodels.tsa.holtwinters.HoltWintersResults

class statsmodels.tsa.holtwinters.HoltWintersResults(model, params, **kwargs)[source]

Holt Winter’s Exponential Smoothing Results

Parameters
  • model (ExponentialSmoothing instance) – The fitted model instance

  • params (dict) – All the parameters for the Exponential Smoothing model.

params

All the parameters for the Exponential Smoothing model.

Type

dict

params_formatted

DataFrame containing all parameters, their short names and a flag indicating whether the parameter’s value was optimized to fit the data.

Type

pd.DataFrame

fittedfcast

An array of both the fitted values and forecast values.

Type

array

fittedvalues

An array of the fitted values. Fitted by the Exponential Smoothing model.

Type

array

fcastvalues

An array of the forecast values forecast by the Exponential Smoothing model.

Type

array

sse

The sum of squared errors

Type

float

level

An array of the levels values that make up the fitted values.

Type

array

slope

An array of the slope values that make up the fitted values.

Type

array

season

An array of the seasonal values that make up the fitted values.

Type

array

aic

The Akaike information criterion.

Type

float

bic

The Bayesian information criterion.

Type

float

aicc

AIC with a correction for finite sample sizes.

Type

float

resid

An array of the residuals of the fittedvalues and actual values.

Type

array

k

the k parameter used to remove the bias in AIC, BIC etc.

Type

int

optimized

Flag indicating whether the model parameters were optimized to fit the data.

Type

bool

mle_retvals

Optimization results if the parameters were optimized to fit the data.

Type

{None, scipy.optimize.optimize.OptimizeResult}

Methods

forecast([steps])

Out-of-sample forecasts

initialize(model, params, **kwd)

predict([start, end])

In-sample prediction and out-of-sample forecasting

summary()

Summarize the fitted Model