In [16]:
import numpy as np

In [17]:
f = open ('supermarket.txt')
lines = f.readlines()

In [18]:
breakpoint = 20
t = set()
def AddElements(line):
    elements = line.split(" ")
    for element in elements:
        t.add(element.strip())
def AllElementsinSet(line):
    elements = line.split(" ")
    for element in elements:
        if not element.strip() in t:
            return False
    return True

In [19]:
np.random.shuffle(lines)
outputfile=[]
def WriteToFile():
    output = open('supermarket.dat','w')
    for l in outputfile:
        output.write(l)

In [20]:
for line in lines:
    #outputfile.append(line)
    AddElements(line)
    if len(t)>breakpoint:
        break

In [22]:
for line in lines:
    if AllElementsinSet(line):
        outputfile.append(line)

In [40]:
WriteToFile()

In [24]:
len(outputfile)


Out[24]:
48