# HG changeset patch
# User Nicolas Saunier <nicolas.saunier@polymtl.ca>
# Date 1475012276 14400
# Node ID 2277ab1a81412bcbf9dc0098b6f4e950931a0c47
# Parent  33d296984dd8172ec935501b1a912cb4dc70f181
added utility for lognorm estimation

diff -r 33d296984dd8 -r 2277ab1a8141 python/utils.py
--- a/python/utils.py	Thu Sep 22 17:50:35 2016 -0400
+++ b/python/utils.py	Tue Sep 27 17:37:56 2016 -0400
@@ -5,10 +5,10 @@
 import matplotlib.pyplot as plt
 from datetime import time, datetime
 from math import sqrt, ceil, floor
-from scipy.stats import kruskal, shapiro
+from scipy.stats import kruskal, shapiro, lognorm
 from scipy.spatial import distance
 from scipy.sparse import dok_matrix
-from numpy import zeros, array, exp, sum as npsum, int as npint, arange, cumsum, median, isnan, ones, convolve,  dtype, isnan, NaN, mean, ma, isinf, savez, load as npload
+from numpy import zeros, array, exp, sum as npsum, int as npint, arange, cumsum, median, isnan, ones, convolve,  dtype, isnan, NaN, mean, ma, isinf, savez, load as npload, log
 
 
 datetimeFormat = "%Y-%m-%d %H:%M:%S"
@@ -46,6 +46,11 @@
     var = (exp(scale**2)-1)*exp(2*loc+scale**2)
     return mean, var
 
+def fitLogNormal(x):
+    'returns the fitted location and scale of the lognormal (general definition)'
+    shape, loc, scale = lognorm.fit(x, floc=0.)
+    return log(scale), shape
+
 def sampleSize(stdev, tolerance, percentConfidence, printLatex = False):
     from scipy.stats.distributions import norm
     k = round(norm.ppf(0.5+percentConfidence/200., 0, 1)*100)/100. # 1.-(100-percentConfidence)/200.