probplot

scikitplot.probscale.probplot(data, ax=None, plottype='prob', dist=None, probax='x', problabel=None, datascale='linear', datalabel=None, bestfit=False, return_best_fit_results=False, estimate_ci=False, ci_kws=None, pp_kws=None, scatter_kws=None, line_kws=None, **fgkwargs)

Probability, percentile, and quantile plots.

Parameters:

dataarray-like

1-dimensional data to be plotted

axmatplotlib axes, optional

The Axes on which to plot. If one is not provided, a new Axes will be created.

plottypestring (default = ‘prob’)

Type of plot to be created. Options are:

• ‘prob’: probability plot

• ‘pp’: percentile plot

• ‘qq’: quantile plot

distscipy distribution, optional

A distribution to compute the scale’s tick positions. If not specified, a standard normal distribution will be used.

probaxstring, optional (default = ‘x’)

The axis (‘x’ or ‘y’) that will serve as the probability (or quantile) axis.

problabel, datalabelstring, optional

Axis labels for the probability/quantile and data axes respectively.

datascalestring, optional (default = ‘log’)

Scale for the other axis that is not the probability (or quantile) axis.

bestfitbool, optional (default is False)

Specifies whether a best-fit line should be added to the plot.

return_best_fit_resultsbool (default is False)

If True a dictionary of results of is returned along with the figure.

estimate_cibool, optional (False)

Estimate and draw a confidence band around the best-fit line using a percentile bootstrap.

ci_kwsdict, optional

Dictionary of keyword arguments passed directly to viz.fit_line when computing the best-fit line.

pp_kwsdict, optional

Dictionary of keyword arguments passed directly to viz.plot_pos when computing the plotting positions.

scatter_kws, line_kwsdict, optional

Dictionary of keyword arguments passed directly to ax.plot when drawing the scatter points and best-fit line, respectively.

Returns:

figmatplotlib.Figure

The figure on which the plot was drawn.

resultdict of linear fit results, optional

Keys are:

• q : array of quantiles

• x, y : arrays of data passed to function

• xhat, yhat : arrays of modeled data plotted in best-fit line

• res : array of coefficients of the best-fit line.

Other Parameters:

colorstring, optional

A directly-specified matplotlib color argument for both the data series and the best-fit line if drawn. This argument is made available for compatibility for the seaborn package and is not recommended for general use. Instead colors should be specified within scatter_kws and line_kws.

Note

Users should not specify this parameter. It is intended to only be used by seaborn when operating within a FacetGrid.

labelstring, optional

A directly-specified legend label for the data series. This argument is made available for compatibility for the seaborn package and is not recommended for general use. Instead the data series label should be specified within scatter_kws.

Note

Users should not specify this parameter. It is intended to only be used by seaborn when operating within a FacetGrid.

See also

viz.plot_pos

viz.fit_line

numpy.polyfit

scipy.stats.probplot

scipy.stats.mstats.plotting_positions

Examples

Probability plot with the probabilities on the y-axis

>>> import numpy; numpy.random.seed(0)
>>> from matplotlib import pyplot
>>> from scipy import stats
>>> import scikitplot.probscale as probscale
>>> data = numpy.random.normal(loc=5, scale=1.25, size=37)
>>> fig = probscale.probplot(data, plottype='prob', probax='y',
...          problabel='Non-exceedance probability',
...          datalabel='Observed values', bestfit=True,
...          line_kws=dict(linestyle='--', linewidth=2),
...          scatter_kws=dict(marker='o', alpha=0.5))

(Source code, png)

Quantile plot with the quantiles on the x-axis

>>> import scikitplot.probscale as probscale
>>> data = numpy.random.normal(loc=5, scale=1.25, size=37)
>>> fig = probscale.probplot(data, plottype='qq', probax='x',
...          problabel='Theoretical Quantiles',
...          datalabel='Observed values', bestfit=True,
...          line_kws=dict(linestyle='-', linewidth=2),
...          scatter_kws=dict(marker='s', alpha=0.5))

(Source code, png)