arviz_stats.ecdf

Contents

arviz_stats.ecdf#

arviz_stats.ecdf(data, dim=None, group='posterior', var_names=None, filter_vars=None, coords=None, pit=False, **kwargs)[source]#

Compute the marginal empirical cumulative density functions (ECDF).

See the EABM chapter on Visualization of Random Variables with ArviZ for more details.

Parameters:
dataarray_like, xarray.DataArray, xarray.Dataset, xarray.DataTree, DataArrayGroupBy, DatasetGroupBy, or idata-like

Input data. It will have different pre-processing applied to it depending on its type:

  • array-like: call array layer within arviz-stats.

  • xarray object: apply dimension aware function to all relevant subsets

  • others: passed to arviz_base.convert_to_dataset then treated as xarray.Dataset. This option is discouraged due to needing this conversion which is completely automated and will be needed again in future executions or similar functions.

    It is recommended to first perform the conversion manually and then call arviz_stats.ecdf. This allows controlling the conversion step and inspecting its results.

dimsequence of hashable, optional

Dimensions to be reduced when computing the ECDF. Default rcParams["data.sample_dims"].

grouphashable, default “posterior”

Group on which to compute the ECDF

var_namesstr or list of str, optional

Names of the variables for which the ECDF should be computed.

filter_vars{None, “like”, “regex”}, default None
coordsdict, optional

Dictionary of dimension/index names to coordinate values defining a subset of the data for which to perform the computation.

pitbool, default False
**kwargsany, optional

Forwarded to the array or dataarray interface for ECDF.

Returns:
ndarray, xarray.DataArray, xarray.Dataset, xarray.DataTree

Requested ECDF of the provided input. It will have a quantile dimension and a plot_axis dimension with coordinate values “x” and “y”.

See also

arviz_stats.histogram, arviz_stats.kde, arviz_stats.qds

Alternative visual summaries for marginal distributions

arviz_plots.plot_dist

Examples

Calculate the ECDF of a Normal random variable:

In [1]: import arviz_stats as azs
   ...: import numpy as np
   ...: data = np.random.default_rng().normal(size=2000)
   ...: # not available yet in array interface azs.ecdf(data)
   ...:

Calculate the ECDF for specific variables:

In [2]: import arviz_base as azb
   ...: dt = azb.load_arviz_data("centered_eight")
   ...: azs.ecdf(dt.posterior.dataset, var_names=["mu", "theta"])
   ...: 
Out[2]: 
<xarray.Dataset> Size: 6kB
Dimensions:    (plot_axis: 2, quantile: 200)
Coordinates:
  * plot_axis  (plot_axis) <U1 8B 'x' 'y'
Dimensions without coordinates: quantile
Data variables:
    mu         (plot_axis, quantile) float64 3kB -7.509 -7.382 ... 0.9995 1.0
    theta      (plot_axis, quantile) float64 3kB -29.71 -29.33 ... 0.9999 1.0

Calculate the ECDF also over the school dimension (for variables where present):

In [3]: azs.ecdf(dt.posterior.dataset, dim=["chain", "draw", "school"])
Out[3]: 
<xarray.Dataset> Size: 10kB
Dimensions:    (plot_axis: 2, quantile: 200)
Coordinates:
  * plot_axis  (plot_axis) <U1 8B 'x' 'y'
Dimensions without coordinates: quantile
Data variables:
    mu         (plot_axis, quantile) float64 3kB -7.509 -7.382 ... 0.9995 1.0
    theta      (plot_axis, quantile) float64 3kB -29.71 -29.33 ... 0.9999 1.0
    tau        (plot_axis, quantile) float64 3kB 0.8965 0.9949 ... 0.9995 1.0
Contents