def send(self, receiver, P, maxNoise):
#Original Text
print('\nOriginal Size: {} bytes\nOriginal Text Entropy: {}'.format(
len(self.text),
calculateEntropy(self.text))) #Each character is 1 byte
print("\nCompressing with LZ78...")
#Compressed Text
compressed = compress(self.text)
print(
'\nCompressed Size: {} bytes\nCompressed Text Entropy: {}'.format(
len(compressed) / 8,
calculateEntropy(compressed))) #Each 8 bits are 1 byte
#Encoding with linear code
print("\nEncoding with Linear Code...\n")
L = LC(P, maxNoise)
encoded = L.encode(compressed)
print("\nEncoding with base64...\n")
base64encoded = b64encode(encoded)
json = dumps({
"compression_algorithm": "LZ78",
"code": {
"name": "linear",
"P": P
},
"base64encoded": base64encoded
})
print("Sending JSON...\n")
receiver.receive(json)
def getCompSizes(inFile,stringSize):
f = open(inFile)
eof = os.path.getsize(inFile)
i=0
l = []
while i<1000000 and eof-i>=stringSize:
f.seek(i)
l+=[compress(f.read(stringSize))]
i+=1
f.close()
return l
l=string.printable
for i in range(n):
s+=l[rand.randrange(len(l))]
return s
#f=open(sys.argv[1])
#s=f.read(1000)
l=string.printable
s=''
for j in range(10000):
s+=l[rand.randrange(len(l))]
res,x = [],[]
for i in range(1,10000):
res+=[compress(s[:i])]
x+=[i]
#f.close()
#plt.plot(x,x,'red',label='linear')
#plt.plot(x,res, label='random')
plt.plot(x,[x[i]/float(res[i]) for i in range(len(x))], label='random')
plt.xlabel('Uncompressed String Length')
plt.ylabel('Compression ratio')
plt.legend(bbox_to_anchor=(0.3,0.9))
plt.show()
from lz78 import compress
import sys, random as rand
import matplotlib.pyplot as plt
from math import log
f=open('genome.fa')
s,r=f.read(2),'ag'
randRes, res,x = [],[],[]
alpha='agct'
maxString = int(sys.argv[1])
for i in range(1,int(log(maxString,2))):
s+=f.read(2**i)
for j in range(2**i): r+=alpha[rand.randrange(4)]
res+=[compress(s)]
randRes+=[compress(r)]
x+=[len(s)]
f.close()
plt.plot(x,x,label='linear',color='red')
plt.plot(x,res)
plt.plot(x,randRes)
plt.xlabel('Uncompressed String Length')
plt.ylabel('Compressed Length')
plt.legend(bbox_to_anchor=(0.3,0.9))
f=open('englishText.txt')
g=open('genome.fa')
r,s,h ='&d','aa', 'ac'
compRand, compUni, genome, x = [],[],[],[]
l=string.printable
maxString = int(sys.argv[1])
for i in range(1,int(log(maxString,2))):
s+=f.read(2**i)
h+=g.read(2**i)
for j in range(2**i):
r+=l[rand.randrange(len(l))]
compUni+=[compress(s)]
compRand+=[compress(r)]
genome+=[compress(h)]
x+=[len(s)]
f.close()
g.close()
plt.plot(x, [float(x[i])/genome[i] for i in range(len(x))], label = 'genome')
plt.plot(x,[float(x[i])/compUni[i] for i in range(len(x))],label='average')
plt.plot(x,[float(x[i])/compRand[i] for i in range(len(x))],label='random')
#plt.plot(x,[sqrt(n/2) for n in x],label='best case')
#plt.plot(x,map(lambda z: sqrt(2*z),x), label='uniform')
plt.xlabel('String Length')
plt.ylabel('Compression Ratio')
from lz78 import compress
import string
import matplotlib.pyplot as plt
from math import sqrt
s = 'aa'
compUni, x = [], []
l = string.printable
for i in range(1, 13):
s += 2**i * 'a'
compUni += [compress(s)]
x += [len(s)]
plt.plot(map(lambda z: sqrt(2 * z), x), compUni)
plt.ylabel('Compressed Size')
plt.xlabel('sqrt(2n)')
plt.show()
from lz78 import compress import sys import matplotlib.pyplot as plt f = open(sys.argv[1]) s=f.read(2) y=[] for i in range(10000): s+=f.read(1) y+=[len(s)/float(compress(s))] f.close() plt.plot(y) plt.show()
import time,string, random as r
from lz78 import compress
import matplotlib.pyplot as plt
from math import log
l=string.printable
f=''
res=[]
for i in range(1000): # initialize f to a 1000 letter string
f+=l[r.randrange(len(l))]
x=[]
for i in range(12):
for j in range(2**i*1000):
f+=l[r.randrange(0,len(l))]
x+=[2**i*1000]
t = time.time()
compress(f)
t=time.time()-t
res+=[t]
plt.plot(x,res)
plt.ylabel('Time')
plt.xlabel('String Length')
#plt.plot(range(len(res)),map(lambda z: log(z,2),res))
plt.show()
import string
import random as r
from lz78 import compress
import matplotlib.pyplot as plt
from math import log
stringlength = 10000
l=string.printable
xaxis = []
res=[]
for i in range(1,21):
f=''
x=i*(len(l)//20)
xaxis+=[x]
for j in range(stringlength):
f+=l[r.randrange(x)]
res+=[stringlength/float(compress(f))]
plt.plot(xaxis,res)
plt.xlabel('Alphabet Size')
plt.ylabel('Compression Ratio')
#plt.yscale('log')
plt.show()
import string
import random as r
from lz78 import compress
import matplotlib.pyplot as plt
from math import log
stringlength = 10000
l = string.printable
xaxis = []
res = []
for i in range(1, 21):
f = ''
x = i * (len(l) // 20)
xaxis += [x]
for j in range(stringlength):
f += l[r.randrange(x)]
res += [stringlength / float(compress(f))]
plt.plot(xaxis, res)
plt.xlabel('Alphabet Size')
plt.ylabel('Compression Ratio')
#plt.yscale('log')
plt.show()
from lz78 import compress
import string
import matplotlib.pyplot as plt
from math import sqrt
s='aa'
compUni, x = [],[]
l=string.printable
for i in range(1,13):
s+=2**i*'a'
compUni+=[compress(s)]
x+=[len(s)]
plt.plot(map(lambda z: sqrt(2*z),x),compUni)
plt.ylabel('Compressed Size')
plt.xlabel('sqrt(2n)')
plt.show()
f = open('englishText.txt')
g = open('genome.fa')
r, s, h = '&d', 'aa', 'ac'
compRand, compUni, genome, x = [], [], [], []
l = string.printable
maxString = int(sys.argv[1])
for i in range(1, int(log(maxString, 2))):
s += f.read(2**i)
h += g.read(2**i)
for j in range(2**i):
r += l[rand.randrange(len(l))]
compUni += [compress(s)]
compRand += [compress(r)]
genome += [compress(h)]
x += [len(s)]
f.close()
g.close()
plt.plot(x, [float(x[i]) / genome[i] for i in range(len(x))], label='genome')
plt.plot(x, [float(x[i]) / compUni[i] for i in range(len(x))], label='average')
plt.plot(x, [float(x[i]) / compRand[i] for i in range(len(x))], label='random')
#plt.plot(x,[sqrt(n/2) for n in x],label='best case')
#plt.plot(x,map(lambda z: sqrt(2*z),x), label='uniform')
plt.xlabel('String Length')
plt.ylabel('Compression Ratio')
import matplotlib.pyplot as plt
from math import log,sqrt
f=open('englishText.txt')
r,s='&d','aa'
compRand, compUni, x = [],[],[]
l=string.printable
maxString = int(sys.argv[1])
for i in range(1,int(log(maxString,2))):
s+=f.read(2**i)
for j in range(2**i):
r+=l[rand.randrange(len(l))]
compUni+=[compress(s)]
compRand+=[compress(r)]
x+=[len(s)]
f.close()
plt.plot(x,compUni,'g--', label='average')
plt.plot(x,compRand,'b-.',label='random')
plt.plot(x,x,label='linear',color='red')
plt.plot(x,map(lambda z: sqrt(2*z),x), 'k:',label='optimal',markersize=20)
plt.xlabel('Uncompressed String Length')
plt.ylabel('Compressed Length')
plt.legend(bbox_to_anchor=(0.3,0.9))
import sys, random as rand
import matplotlib.pyplot as plt
from math import log
f = open('genome.fa')
s, r = f.read(2), 'ag'
randRes, res, x = [], [], []
alpha = 'agct'
maxString = int(sys.argv[1])
for i in range(1, int(log(maxString, 2))):
s += f.read(2**i)
for j in range(2**i):
r += alpha[rand.randrange(4)]
res += [compress(s)]
randRes += [compress(r)]
x += [len(s)]
f.close()
plt.plot(x, x, label='linear', color='red')
plt.plot(x, res)
plt.plot(x, randRes)
plt.xlabel('Uncompressed String Length')
plt.ylabel('Compressed Length')
plt.legend(bbox_to_anchor=(0.3, 0.9))
plt.show()
import matplotlib.pyplot as plt
from math import log, sqrt
f = open('englishText.txt')
r, s = '&d', 'aa'
compRand, compUni, x = [], [], []
l = string.printable
maxString = int(sys.argv[1])
for i in range(1, int(log(maxString, 2))):
s += f.read(2**i)
for j in range(2**i):
r += l[rand.randrange(len(l))]
compUni += [compress(s)]
compRand += [compress(r)]
x += [len(s)]
f.close()
plt.plot(x, compUni, 'g--', label='average')
plt.plot(x, compRand, 'b-.', label='random')
plt.plot(x, x, label='linear', color='red')
plt.plot(x,
map(lambda z: sqrt(2 * z), x),
'k:',
label='optimal',
markersize=20)
plt.xlabel('Uncompressed String Length')
import string, sys,random as rand
import matplotlib.pyplot as plt
from math import log,sqrt
g=open('genome.fa')
r='ac'
genome, x = [],[]
maxString = int(sys.argv[1])
for i in range(1,maxString):
r+=g.read(1)
genome+=[compress(r)]
x+=[len(r)]
g.close()
plt.plot(x, [float(x[i])/genome[i] for i in range(len(x))], label = 'genome')
#plt.plot(x,[sqrt(n/2) for n in x],label='uniform')
plt.xlabel('String Length')
plt.ylabel('Compression Ratio')
plt.legend(bbox_to_anchor=(0.3,0.9))