orbit.diagnostics package

Submodules

orbit.diagnostics.plot module

orbit.diagnostics.plot.metric_horizon_barplot(df, model_col='model', pred_horizon_col='pred_horizon', metric_col='smape', bar_width=0.1, path=None, figsize=None, fontsize=None, is_visible=False)
orbit.diagnostics.plot.plot_posterior_params(mod, kind='density', n_bins=20, ci_level=0.95, pair_type='scatter', figsize=None, path=None, fontsize=None, incl_trend_params=False, incl_smooth_params=False, is_visible=True)

Data Viz for posterior samples

mod : orbit model object kind : str, {‘density’, ‘trace’, ‘pair’}

which kind of plot to be made. Currently, trace plot may not represent the actual sample process for different chainse since this information is not stored in orbit model objects.

n_binsint; default 20

number of bin, used in the histogram plotting

ci_levelfloat, between 0 and 1

confidence interval level

pair_typestr, {‘scatter’, ‘reg’}

dot plotting type for off-diagonal plots in pair plot

figsizetuple; optional

figure size

pathstr; optional

dir path to save the chart

fontsize: int; optional

fontsize of the title

incl_trend_paramsbool

if plot trend parameters; default False

incl_smooth_paramsbool

if plot smoothing parameters; default False

is_visible: boolean

whether we want to show the plot. If called from unittest, is_visible might = False.

Returns

fig

Return type

plt object

orbit.diagnostics.plot.plot_predicted_components(predicted_df, date_col, prediction_percentiles=None, plot_components=None, title='', figsize=None, path=None, fontsize=None, is_visible=True)
Plot predicted componenets with the data frame of decomposed prediction where components

has been pre-defined as trend, seasonality and regression. Parameters ———- predicted_df: pd.DataFrame

predicted data response data frame. two columns required: actual_col and pred_col. If user provide pred_percentiles_col, it needs to include them as well.

date_col: str

the date column name

prediction_percentiles: list

a list should consist exact two elements which will be used to plot as lower and upper bound of confidence interval

plot_components: list

a list of strings to show the label of components to be plotted; by default, it uses values in orbit.constants.constants.PredictedComponents.

title: str; optional

title of the plot

figsize: tuple; optional

figsize pass through to matplotlib.pyplot.figure()

path: str; optional

path to save the figure

fontsize: int; optional

fontsize of the title

is_visible: boolean

whether we want to show the plot. If called from unittest, is_visible might = False.

Returns

None

orbit.diagnostics.plot.plot_predicted_data(training_actual_df, predicted_df, date_col, actual_col, pred_col='prediction', prediction_percentiles=None, title='', test_actual_df=None, is_visible=True, figsize=None, path=None, fontsize=None)

plot training actual response together with predicted data; if actual response of predicted data is there, plot it too. :param training_actual_df: training actual response data frame. two columns required: actual_col and date_col :type training_actual_df: pd.DataFrame :param predicted_df: predicted data response data frame. two columns required: actual_col and pred_col. If

user provide prediction_percentiles, it needs to include them as well in such prediction_{x} where x is the correspondent percentiles

Parameters

  • prediction_percentiles (list) – list of two elements indicates the lower and upper percentiles

  • date_col (str) – the date column name

  • actual_col (str) –

  • pred_col (str) –

  • title (str) – title of the plot

  • test_actual_df (pd.DataFrame) – test actual response dataframe. two columns required: actual_col and date_col

  • is_visible (boolean) – whether we want to show the plot. If called from unittest, is_visible might = False.

  • figsize (tuple) – figsize pass through to matplotlib.pyplot.figure()

  • path (str) – path to save the figure

  • fontsize (int) – fontsize of the title

Returns

Return type

None.

Module contents