Generates a probability plot on Normal scaled probability paper so that the CDF of the distribution appears linear.
- failures (array, list) – The failure data. Must have at least 2 elements.
- right_censored (array, list, optional) – The right censored data. Optional input. Default = None.
- show_fitted_distribution (bool, optional) – If True, the fitted distribution will be plotted on the probability plot. Defaults = True.
- show_scatter_points (bool, optional) – If True, the plot will include the scatter points from the failure times. Defaults = True.
- downsample_scatterplot (bool, int, optional) – If True or None, and there are over 1000 points, then the scatterplot will be downsampled by a factor. The default downsample factor will seek to produce between 500 and 1000 points. If a number is specified, it will be used as the downsample factor. Default is False which will result in no downsampling. This functionality makes plotting faster when there are very large numbers of points. It only affects the scatterplot not the calculations.
- a (float, int, optional) – The heuristic constant for plotting positions of the form (k-a)/(n+1-2a). Default = 0.3 which is the median rank method (same as the default in Minitab). For more heuristics, see: https://en.wikipedia.org/wiki/Q%E2%80%93Q_plot#Heuristics
- CI (float, optional) – The confidence interval for the bounds. Must be between 0 and 1. Optional input. Default = 0.95 for 95% CI.
- CI_type (str, None, optional) – This is the confidence bounds on time or reliability shown on the plot. Use None to turn off the confidence intervals. Must be either ‘time’, ‘reliability’, or None. Default is ‘time’. Some flexibility in names is allowed (eg. ‘t’, ‘time’, ‘r’, ‘rel’, ‘reliability’ are all valid).
- kwargs – Plotting keywords that are passed directly to matplotlib (e.g. color, label, linestyle).
figure (object) – The figure handle of the probability plot is returned as an object
There is a hidden parameter called __fitted_dist_params which is used to specify the parameters of the distribution that has already been fitted. Passing a distribution object to this parameter will bypass the fitting process and use the parameters of the distribution provided. When this is done the minimum length of failures can be 1. The distribution object must contain the SE and Cov of the parameters so it needs to be generated by the Fitters module.
If your plot does not appear automatically, use plt.show() to show it.