Mercurial Hosting > traffic-intelligence
comparison python/utils.py @ 854:33d296984dd8
rework and more info on speed probabilities for classification
author | Nicolas Saunier <nicolas.saunier@polymtl.ca> |
---|---|
date | Thu, 22 Sep 2016 17:50:35 -0400 |
parents | 36c5bee9a887 |
children | 2277ab1a8141 |
comparison
equal
deleted
inserted
replaced
853:95e7622b11be | 854:33d296984dd8 |
---|---|
37 # Simple statistics | 37 # Simple statistics |
38 ######################### | 38 ######################### |
39 | 39 |
40 def logNormalMeanVar(loc, scale): | 40 def logNormalMeanVar(loc, scale): |
41 '''location and scale are respectively the mean and standard deviation of the normal in the log-normal distribution | 41 '''location and scale are respectively the mean and standard deviation of the normal in the log-normal distribution |
42 https://en.wikipedia.org/wiki/Log-normal_distribution''' | 42 https://en.wikipedia.org/wiki/Log-normal_distribution |
43 | |
44 same as lognorm.stats(scale, 0, exp(loc))''' | |
43 mean = exp(loc+(scale**2)/2) | 45 mean = exp(loc+(scale**2)/2) |
44 var = (exp(loc**2)-1)*exp(2*loc+scale**2) | 46 var = (exp(scale**2)-1)*exp(2*loc+scale**2) |
45 return mean, var | 47 return mean, var |
46 | 48 |
47 def sampleSize(stdev, tolerance, percentConfidence, printLatex = False): | 49 def sampleSize(stdev, tolerance, percentConfidence, printLatex = False): |
48 from scipy.stats.distributions import norm | 50 from scipy.stats.distributions import norm |
49 k = round(norm.ppf(0.5+percentConfidence/200., 0, 1)*100)/100. # 1.-(100-percentConfidence)/200. | 51 k = round(norm.ppf(0.5+percentConfidence/200., 0, 1)*100)/100. # 1.-(100-percentConfidence)/200. |