From b56db38ffe628748d14079bf88e7240813baf826 Mon Sep 17 00:00:00 2001
From: Enzo De Carvalho Bittencourt <enzo.decarvalhobittencourt@ensiie.eu>
Date: Thu, 28 Sep 2023 17:38:04 +0200
Subject: [PATCH] prepared pipeline
---
Random/__pycache__/stats.cpython-311.pyc | Bin 1115 -> 773 bytes
Random/graph.py | 2 +
Random/main.py | 53 ++++++++++++++++++-----
Random/stats.py | 11 ++---
4 files changed, 48 insertions(+), 18 deletions(-)
diff --git a/Random/__pycache__/stats.cpython-311.pyc b/Random/__pycache__/stats.cpython-311.pyc
index 99b30e77125b8e59c18d27673114aa526b93eba2..8fbafb1507b9d7c92e33b0c08d6980c068386049 100644
GIT binary patch
delta 441
zcmcc3(aOfRoR^o20SJU<iKbdIPUM?a&jI8y1M%lsKw>&W2_uk#f-E?@234F1rXqzg
zg{g*d8BqUfkQrdGhItuKel=W843JgJRLfk#22;Vnki`OHYb{`fF_GySre#3OSHm3;
z%%I6KS(Hgjw+LkJOOUuG<1Ln?%)DYvwp&bj1-CdeGK)*{(~A;wZ*k-Rg$ojsQzuVk
zl2T&1#hh4Fbc;F2HTV{9eo}F2QCVtAd|FXz;Vs7aVvs{7KVfq969h6qVNvV|BpMjL
zaxh3r&*51RytZgf^$x=wfjf#X>N{W2cfKIua#6zN3Xo(GY4Dw3c$ZtC$ND<A!X<8n
z1+o{p^{;U2UtrOne3n^44dme>P7nbyd?iDX5Qr@RBz|$&<mRW8=A_yciB0BaF_B?q
MH2A=PNq}_#0K~Fe$^ZZW
literal 1115
zcmZ`&%}X0W6rbIl#AIWt#Avl3jy)7pj3H3;&=M&`GzW#&o<ixe?oM#SW;gDKG$DZ$
zdgwu+g@RrR9$IVBL;nQ(A7slyWx!J@#alpn@zmMX4aU;9Gw*}<@q06G_H#VW14_TQ
zhw%stz)#Nzh}u4#BPw=)42nQzWL9O0tS`ADCv&es5z6c;NWuCdzpTr)ijk!wNmM0U
z6)lW5MMKeTlS<XbNY{`^mtlxCe(H%WYL=qnX;i_YHjS_)&CI0uGY@q|3gA5}OgBgO
z`3uHt#iBf*a#wHA_Kw(nns?aEeNMF|+vFNtgQ>@;4tsLDaSd4Z>iZ;L#U8=lTFsCZ
z4PpRjz<r8**hTO0g?fD@mI2rOJw1einvEM-|B1SR+uI|>=@04wQ0@!#y-1*4mkmfU
zd+v)4GE|@95hZC|F*j_{z%nZ72C_AUiVBhy(=wDbKjc}8A#np+wxJ1<Zfll#=G{k%
zB_VTNtYX5K6jc@c(Wjz>)v6>+>ulJVz>=-11e!`6lTg)AG>dSiU7?ARQms*8iIz#C
z-6m3D!qI0#m=(eZBz%cR;`*A2jZG{IB?E7eIDT2hl67U8-mCFWg3!hN%(`B|nX;&*
zMa|SR3oEOI!a`=Xuvo}E6*XC}WPHRKik;|!%EHyDjZs?4yFzn^vKIIg0fULH+V0Rn
zzCDn22D0uz_SI7BajSHaytA8qx71qxl^l7$xR-YCJ~(EMC%<v+WZp^U-DJMCd<vs)
z(heMT;pm6q-KH~^cE{3f=q>8nzPokr?YP5FxctPY#K)0?xHCEHPR=@T&V_SrICmNw
z+<N#UhQ7zp-uTzJ6U(`=TpQ-jX=`+Rq)!lJT@nNm((FpLW_W!Yw>;*Z;tMdwJpDFh
z7m-I5|Ch}f<J9zKXU<dB;TVSLup9$Bz+(}>47EYxa-D$wmj87i&&+qgzsv{t3&r3A
A^Z)<=
diff --git a/Random/graph.py b/Random/graph.py
index ad5d45e..38f1c6a 100644
--- a/Random/graph.py
+++ b/Random/graph.py
@@ -33,6 +33,8 @@ def ecdf_graph(N,RESOLUTION,seed,data):
xlabel= "Value"
ylabel="Cumulative Probability"
title_name= name +"\n N = "+str(N)+"\n seed = "+str(seed)
+ if N==0:
+ title_name= name +"\n seed = "+str(seed)
graph=sns.displot(data[name], kind="ecdf")
graph.set(title=title_name)
graph.set_axis_labels(xlabel,ylabel)
diff --git a/Random/main.py b/Random/main.py
index 4af1704..5d330c9 100755
--- a/Random/main.py
+++ b/Random/main.py
@@ -57,9 +57,9 @@ def write_stats(data, name):
skew = scipy.stats.skew(data)
exckurt = scipy.stats.kurtosis(data) - 3
#write file
- with open(name+'.csv', 'w', newline='') as csvfile:
+ with open('stats.csv', 'a', newline='') as csvfile:
datawriter = csv.DictWriter(csvfile, fieldnames=fields)
- datawriter.writeheader()
+ #datawriter.writeheader()
datawriter.writerow({
"name" : name,
"quantil25" : str(quantil25),
@@ -71,10 +71,26 @@ def write_stats(data, name):
"exckurt" : str(exckurt)})
return
+def write_stats_chi(data, name, RES):
+ fields=["chi","p"]
+ val = stats.chisquared_uniform(data,RES)
+ chi = val[0]
+ p = val[1]
+ #write file
+ with open('chi.csv', 'a', newline='') as csvfile:
+ datawriter = csv.DictWriter(csvfile, fieldnames=fields)
+ #datawriter.writeheader()
+ datawriter.writerow({
+ "name" : name,
+ "chi" : str(chi),
+ "p" : str(p)})
+ return
+
if __name__=="__main__":
##INIT PARAMS##
- N = 100
- RESOLUTION = 1000
+ N = 1000000
+ RESOLUTION = 100
+ iterN = [100, 1000000, 100000000]
#init generators
generators = [ParkMiller(), KnuthLewis(), Marsaglia()
@@ -87,7 +103,7 @@ if __name__=="__main__":
#set seaborn params
sns.set_theme(style="darkgrid")
- #generate all diagrams
+ #generate N random values for each RNG
data = values(N,seed,generators)
#graph.hist_distributivity_graph(N,RESOLUTION,seed,data)
@@ -96,8 +112,25 @@ if __name__=="__main__":
#graph.ecdf_graph(N,RESOLUTION,seed,data)
- graph.compare(0, RESOLUTION, seed
- , iteratives([1000, 10, 100], seed, ParkMiller()))
- print(stats.chisquared_uniform(data["ParkMiller"],N))
- print(np.quantile(data["ParkMiller"],0.25))
- write_stats(data["ParkMiller"],"ParkMiller")
+ #graph.compare(0, RESOLUTION, seed
+ # , iteratives([1000, 10, 100], seed, ParkMiller()))
+ #print(stats.chisquared_uniform(data["ParkMiller"],RESOLUTION))
+ #print(np.quantile(data["ParkMiller"],0.25))
+ #write_stats(data["ParkMiller"],"ParkMiller")
+ #write_stats_chi(data["ParkMiller"], "ParkMiller", RESOLUTION)
+
+ #generate a lot of diagrams
+ graph.hist_distributivity_graph(N,RESOLUTION,seed,data)
+
+ for name in data:
+ write_stats(data[name],name)
+ write_stats_chi(data[name],name)
+
+ for name in generators:
+ data_iter = iteratives(iterN, seed, name)
+
+ graph.ecdf_graph(0, RESOLUTION, seed, data_iter)
+ graph.compare(0, RESOLUTION, seed, data_iter)
+
+
+
diff --git a/Random/stats.py b/Random/stats.py
index 6b1b11d..31cb2d1 100644
--- a/Random/stats.py
+++ b/Random/stats.py
@@ -5,15 +5,10 @@ Module to calculate various value on an array
import numpy as np
import scipy
-def chisquared_uniform(arr, N):
+def chisquared_uniform(arr,RES):
"""
chisquared for uniform distrib
"""
- _,counts = np.unique(arr, return_counts=True)
- observed_freq = counts/N
- #print(observed_freq)
- expected_freq = np.full(shape=observed_freq.size,fill_value=1/N)
- print(observed_freq),print(expected_freq)
- print(np.sum(expected_freq), np.sum(observed_freq))
- return scipy.stats.chisquare(observed_freq, expected_freq)
+ observed_freq, _ = np.histogram(arr, bins=np.linspace(0,1,RES))
+ return scipy.stats.chisquare(observed_freq)
--
GitLab