meridian.analysis.visualizer.ModelFit

Generates model fit plots from the Meridian model fitting.

meridian.analysis.visualizer.ModelFit(
    meridian: model.Meridian,
    use_kpi: bool = False,
    confidence_level: float = c.DEFAULT_CONFIDENCE_LEVEL
)

Calculates the expected versus actual outcome with the confidence level over time, and plots graphs to compare the values.

meridian Media mix model with the raw data from the model fitting.
use_kpi If True, plots the incremental KPI. Otherwise, plots the incremental revenue using the revenue per KPI (if available).
confidence_level Confidence level for expected outcome credible intervals represented as a value between zero and one. Default is 0.9.

model_fit_data Dataset holding the expected, actual, and baseline outcome over time.

The dataset contains the following:

  • Coordinates: geo, time, metric (mean, ci_hi, ci_lo)
  • Data variables: expected, baseline, actual (outcome)

Methods

plot_model_fit

View source

plot_model_fit(
    selected_times: (Sequence[str] | None) = None,
    selected_geos: (Sequence[str] | None) = None,
    n_top_largest_geos: (int | None) = None,
    show_geo_level: bool = False,
    include_baseline: bool = True,
    include_ci: bool = True
) -> alt.Chart

Plots the expected versus actual outcome over time.

Args
selected_times Optional list of a subset of time dimensions to include. By default, all times are included. Times should match the time dimensions from meridian.InputData.
selected_geos Optional list of a subset of geo dimensions to include. By default, all geos are included. Geos should match the geo dimension names from meridian.InputData. Set either selected_geos or n_top_largest_geos, do not set both.
n_top_largest_geos Optional number of largest geos by population to include. By default, all geos are included. Set either selected_geos or n_top_largest_geos, do not set both.
show_geo_level If True, plots at the geo-level instead of one national level plot. Only available if selected_geos or n_top_largest_geos is provided.
include_baseline If True, shows the expected baseline outcome without any media execution.
include_ci If True, shows the credible intervals for the expected outcome.

Returns
An Altair plot showing the model fit.

update_confidence_level

View source

update_confidence_level(
    confidence_level: float
)