# plot_points¶

class reliability.Probability_plotting.plot_points

Plots the failure points as a scatter plot based on the plotting positions. This is similar to a probability plot, just without the axes scaling or the fitted distribution. It may be used to overlay the failure points with a fitted distribution on either the PDF, CDF, SF, HF, or CHF. If you choose to plot the points for PDF or HF the points will not form a smooth curve as this process requires integration of discrete points which leads to a disjointed plot. The PDF and HF points are correct but not as useful as CDF, SF, and CHF.

Inputs: failures - an array or list of the failure times. Minimum number of points allowed is 1. right_censored - an array or list of the right censored failure times. func - The distribution function to plot. Choose either ‘PDF,’CDF’,’SF’,’HF’,’CHF’. Default is ‘CDF’ a - the heuristic constant for plotting positions of the form (k-a)/(n+1-2a). Default is a=0.3 which is the median rank method (same as the default in Minitab).

kwargs - keyword arguments for the scatter plot. Defaults are set for color=’k’ and marker=’.’ These defaults can be changed using kwargs.

Outputs: The scatter plot is the only output. Use plt.show to show it. It is recommended that plot_points be used in conjunction with one of the plotting methods from a distribution (see the example below).

Example usage: from reliability.Fitters import Fit_Lognormal_2P from reliability.Probability_plotting import plot_points import matplotlib.pyplot as plt data = [8.0, 10.2, 7.1, 5.3, 8.5, 15.4, 17.7, 5.4, 5.8, 11.7, 4.4, 18.1, 8.5, 6.6, 9.7, 13.7, 8.2, 15.3, 2.9, 4.3] fitted_dist = Fit_Lognormal_2P(failures=data,show_probability_plot=False,print_results=False) #fit the Lognormal distribution to the failure data plot_points(failures=data,func=’SF’) #plot the failure points on the scatter plot fitted_dist.distribution.SF() #plot the distribution plt.show()