###
#Bailey 7/19/2018
#written for bmc bioinformatics redo
#generates the 50% off data for the bmc bioinformatics paper (maintains balance but 50% less input data)
import random
import os

####
#change these values
fName = "sep24_featSelected_50PercentOff.txt" #output feature file name
featureFile = "sep24_featSelected.txt"

####
outFile = None
pos = []
neg = []
randNeg = []
randPos = []
choice = [0, 1]
lc = 0
sampSize = 185900 #outFile file will have 2 times this number of examples (equal pos/neg) (make sure there is enough in the input file)

if not os.path.isfile(fName):
    outFile = open(fName, 'w')

with open(featureFile) as feats:
    for line in feats:
        lc = lc + 1
        if line[0] == '1':
            pos.append(line)
        if line[0] != '1':
            neg.append(line)

lc = 0

randNeg = random.sample(neg, sampSize)
randPos = random.sample(pos, sampSize)

for j in range(0, len(randNeg)):
    outFile.write(randNeg[j])

for j in range(0, len(randPos)):
    outFile.write(randPos[j])

outFile.close()
print ("finished")