pointwise.py

#! /usr/bin/env python
# -*- coding: utf-8 -*-
import os
import string
import random
import math
import sys

def main():
	
	fold_num = ['1','2','3','4','5']
	fold1 = ['1','2','3','4']
	fold2 = ['1','2','3','5']
	fold3 = ['1','2','4','5']
	fold4 = ['1','3','4','5']
	fold5 = ['2','3','4','5']
	
	# Covert original data file to train data file
	for l in fold_num:
		train_file = open('train'+'fold'+l+'.txt', 'w')
		for n in fold_num:
			if n == l:
				continue
			orig_file = open('S'+n+'.txt', 'r')
			tmp_docs = orig_file.readline()
			while tmp_docs != '':
				if tmp_docs[0] == '0':
					train_file.write('-1')
				else:
					train_file.write('+1')
				train_file.write(tmp_docs[1:])
				tmp_docs = orig_file.readline()	
			orig_file.close()
		train_file.close()
	

	#print len(dict)
	#print dict
	#if '中国' in dict:
	#	print '中国'	
	# read original file
	#orig_file = open('RenMinData.txt','r')
	#lines = orig_file.readlines()
	#orig_file.close()
		
	#for ll in lines:
	#	tmp = ll[0:4]
	#	print tmp
		#break
	#print len(lines)

__comment__ = """
	contents = raw_input("Input a sentence: ")
	print "You typed '%s'" % (contents)
	contents = list(contents.strip(' \n'))
	#tmp = contents[-4*3:]
	#print tmp
	
	result = []
	while len(contents) >= 2*3:
		#tmp = contents[-4*3:]
		for i in range(-4,-1,1):
			tmp = list(contents[i*3:])
			#print tmp
			if tmp in dict:
				print tmp
				result.append(tmp)
				#del contents[i*3:]
				contents.remove(tmp)
				print contents
				break;
		#print contents
		#tmp = contents[i*3:]
		#break;
	print result
"""

main ()