ccmcc · December 15, 2015 13:29
diff --git a/outfinal.csv b/outfinal.csv
diff --git a/pair_match.py b/pair_match.py
 import csv


 delim = ','

 columns = ['tag1', 'tag2', 'Book', 'Topic']

 reader = csv.DictReader(open('outfinal.csv', 'rbU'), delimiter=delim,fieldnames=columns)

 topiclist = dict()  
 taglist = dict()
 multiple = dict()

 #Make a dictionary of the topics
 for row in reader:
   # topic = row["Topic"]
    if row['Topic'] not in topiclist:
        topiclist[row['Topic']] = []
         
    
 #seems dumb that this happens again
 reader2 = csv.DictReader(open('outfinal.csv', 'rbU'), delimiter=delim,fieldnames=columns)

 #Populate an array of the unique tags for each topic
 for row in reader2:

    if row['tag1'] not in topiclist[row['Topic']]:
        topiclist[row['Topic']].append(row['tag1'])
        if row['tag1'] not in taglist:
            taglist[row['tag1']]= 1
        else:
            taglist[row['tag1']] += 1
      
    if row['tag2'] not in topiclist[row['Topic']]:
        topiclist[row['Topic']].append(row['tag2'])
        if row['tag2'] not in taglist:
            taglist[row['tag2']]= 1
        else:
            taglist[row['tag2']] += 1  

 # see where there multiples
 for tag in taglist:
    if taglist[tag] > 1:
     multiple[tag] =  taglist[tag]

 list = topiclist.keys()
 numtopics = len(list)
 #print list
 n = 0

 RESULT= [1, 2, 3]
 with open('topicmatch.csv', 'wb') as test_file:
    file_writer = csv.writer(test_file)
    while n <= (numtopics-1):
        t1 = topiclist[list[n]]
        p = n+1
        while p < numtopics:
            t2 = topiclist[list[p]]
            matches = set(t1) & set(t2)
            #print matches
            RESULT[0] = list[n]
            RESULT[1] = list[p]
            RESULT[2] = len(matches)
            #print RESULT
            file_writer.writerow(RESULT)
            p = p+1
        n = n+1
	import csv


	delim = ','

	columns = ['tag1', 'tag2', 'Book', 'Topic']

	reader = csv.DictReader(open('outfinal.csv', 'rbU'), delimiter=delim,fieldnames=columns)

	topiclist = dict()
	taglist = dict()
	multiple = dict()

	#Make a dictionary of the topics
	for row in reader:
	# topic = row["Topic"]
	if row['Topic'] not in topiclist:
	topiclist[row['Topic']] = []


	#seems dumb that this happens again
	reader2 = csv.DictReader(open('outfinal.csv', 'rbU'), delimiter=delim,fieldnames=columns)

	#Populate an array of the unique tags for each topic
	for row in reader2:

	if row['tag1'] not in topiclist[row['Topic']]:
	topiclist[row['Topic']].append(row['tag1'])
	if row['tag1'] not in taglist:
	taglist[row['tag1']]= 1
	else:
	taglist[row['tag1']] += 1

	if row['tag2'] not in topiclist[row['Topic']]:
	topiclist[row['Topic']].append(row['tag2'])
	if row['tag2'] not in taglist:
	taglist[row['tag2']]= 1
	else:
	taglist[row['tag2']] += 1

	# see where there multiples
	for tag in taglist:
	if taglist[tag] > 1:
	multiple[tag] = taglist[tag]

	list = topiclist.keys()
	numtopics = len(list)
	#print list
	n = 0

	RESULT= [1, 2, 3]
	with open('topicmatch.csv', 'wb') as test_file:
	file_writer = csv.writer(test_file)
	while n <= (numtopics-1):
	t1 = topiclist[list[n]]
	p = n+1
	while p < numtopics:
	t2 = topiclist[list[p]]
	matches = set(t1) & set(t2)
	#print matches
	RESULT[0] = list[n]
	RESULT[1] = list[p]
	RESULT[2] = len(matches)
	#print RESULT
	file_writer.writerow(RESULT)
	p = p+1
	n = n+1