Comments (1)
I'm not sure why you think the parameters are switched. The histogram plot with fitted PDF just peaks really high. If you let reliability plot it using results.best_distribution.PDF()
then the ylim will be set automatically.
Just because the PDF of the Gamma 3P doesn't follow the histogram does not mean that the fit is incorrect. Mathematically is is better than all the others so it should be chosen, but it is only the best of the 12 distributions in this package. It may just be that none of the available distributions are suited to the data. "But Gamma_3P is the best fitting distribution" I hear you say. That is true from a log likelihood perspective, but that doesn't mean that there isn't some other distribution out there that's better than Gamma_3P.
Out of interest, look at how well the Weibull Mixture models the histogram:
The dataset is interesting because of the non-zero start point, the few large peaks in the middle and the small peak in the tail.
Not many software packages implement Gamma 3P so I understand benchmarking it against other software is difficult. If you want to verify the accuracy of the Gamma_3P fit, then try drawing samples from a known distribution and refitting it like is done here.
Lastly, before I close this issue for not being a bug, I would like to point out that there is a much better way to access the parameters than using iloc and rebuilding the distribution. Do this instead:
results = Fit_Everything(data, show_histogram_plot=False,show_probability_plot=False,show_best_distribution_probability_plot=False,show_PP_plot=False)
results.best_distribution.PDF()
print("Alpha =",results.best_distribution.alpha)
The best fitting distribution is already built for you and you can extract parameters by name. Have a read of the API reference for Fit_Everything.
If you'd like to know more, please feel free to email [email protected].
from reliability.
Related Issues (20)
- [BUG] - Cannot replicate the results from example - Fitting all available distributions to data HOT 1
- [BUG] - Proportions sum to 1 Mixture_model HOT 1
- How to use reliability package to answer if test time can be reduced or should be augmented HOT 2
- [BUG] - force_beta is inversed when using RRX in Fit_Weibull_2P HOT 1
- [BUG] - Problem with matplotlib-3.7.0 HOT 1
- [BUG] - AttributeError: 'Line2D' object has no property 'ci_y' HOT 3
- [BUG] - AttributeError: 'Line2D' object has no property 'quantiles' HOT 1
- BUG about accelerated life experiment module HOT 10
- [BUG] - ALT_fitters.py IndexError: list index out of range HOT 3
- [BUG] - float128 and complex256 HOT 2
- RankAdjustment HOT 1
- [BUG] - A minor problem in Reliability_testing.chi2test related to numpy.histogram HOT 1
- [BUG] - Stress - Strength Interference Erroneous Result HOT 3
- FitEverything example error HOT 1
- [BUG] - Stress-Strength Mixture_Model and Loglogistic errors HOT 1
- Lognormal_Distribution.CDF does not return tuple HOT 1
- Extract confidence bounds HOT 1
- [BUG] - Lognormal_Distribution.random_samples give wrong values HOT 1
- [BUG] - Complex Distributions (Mixture, Competing Risks, DSZI) quantile and inverse_SF functions error when input is array-like
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from reliability.