def getMinString(inFile, stringSize):
l = getCompSizes(inFile, stringSize)
i = l.index(min(l))
f = open(inFile)
f.seek(i)
s = f.read(stringSize)
f.close()
return s
def getMinString(inFile, stringSize): l= getCompSizes(inFile,stringSize) i = l.index(min(l)) f=open(inFile) f.seek(i) s=f.read(stringSize) f.close() return s
def main():
t=time.time()
l = getCompSizes(sys.argv[1],int(sys.argv[2]))
t=time.time()-t
plt.plot(l,'green')#,marker=u'.')
plt.plot(len(l)*[mean(l)],label='mean')
plt.plot(len(l)*[median(l)], 'r--',label='median')
plt.legend()
plt.ylabel('Compressed Size')
plt.xlabel('Position')
plt.show()
print t
return
import matplotlib.pyplot as plt
from getStats import *
from varyGraph import getCompSizes
import matplotlib.mlab as mlab
import sys,math
l = getCompSizes(sys.argv[1],int(sys.argv[2]))
n, bins, patches = plt.hist(l,50,normed=True)
#y = mlab.normpdf(bins, mean(l),deviation(l))
plt.xlabel('Compressed string length')
#plt.plot(bins, y, 'r')
plt.show()
import sys
from getStats import *
from varyGraph import getCompSizes
import matplotlib.pyplot as plt
import matplotlib.mlab as mlab
stringSize=int(sys.argv[1])
l = getCompSizes('englishText.txt', stringSize)
n = getCompSizes('spanishText.txt', stringSize)
m, bins, p = plt.hist(l,50,normed=True,visible=False)
m1, bins1, p1 = plt.hist(n,50,normed=True,visible=False)
y = mlab.normpdf(bins, mean(l),deviation(l))
y1 = mlab.normpdf(bins1, mean(n),deviation(n))
plt.plot(bins,y,label='English')
plt.plot(bins1,y1,'b--',label='Spanish')
plt.xlabel('Compressed Size')
plt.legend()
plt.show()
import sys
from getStats import deviation
from varyGraph import getCompSizes
f = open('standardDeviations.csv', 'a')
for i in range(2, 8):
f.write(
str(i) + ',' + str(deviation(getCompSizes(sys.argv[1], 2**i))) + '\n')
f.close()
import sys
from getStats import *
from varyGraph import getCompSizes
import matplotlib.pyplot as plt
import matplotlib.mlab as mlab
stringSize = int(sys.argv[1])
l = getCompSizes('englishText.txt', stringSize)
n = getCompSizes('spanishText.txt', stringSize)
m, bins, p = plt.hist(l, 50, normed=True, visible=False)
m1, bins1, p1 = plt.hist(n, 50, normed=True, visible=False)
y = mlab.normpdf(bins, mean(l), deviation(l))
y1 = mlab.normpdf(bins1, mean(n), deviation(n))
plt.plot(bins, y, label='English')
plt.plot(bins1, y1, 'b--', label='Spanish')
plt.xlabel('Compressed Size')
plt.legend()
plt.show()
from varyGraph import getCompSizes
import matplotlib.pyplot as plt
from getStats import mean
x,res=[],[]
for i in range(1,100):
l = getCompSizes('genome.fa',i)
print i,mean(l)
res+=[i/mean(l)]
x+=[i]
plt.plot(x,res)
plt.ylabel('Mean Compression Rate')
plt.xlabel('String Length')
plt.show()
import matplotlib.pyplot as plt
from getStats import *
from varyGraph import getCompSizes
import matplotlib.mlab as mlab
import sys, math
l = getCompSizes(sys.argv[1], int(sys.argv[2]))
n, bins, patches = plt.hist(l, 50, normed=True)
#y = mlab.normpdf(bins, mean(l),deviation(l))
plt.xlabel('Compressed string length')
#plt.plot(bins, y, 'r')
plt.show()