Created
January 17, 2010 17:41
-
-
Save russelnickson/279462 to your computer and use it in GitHub Desktop.
Generate a Tag Cloud
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import string,sys | |
| f1=open(sys.argv[1]) | |
| f2=open(sys.argv[2]) | |
| try: | |
| count=int(sys.argv[3]) | |
| except IndexError: | |
| count=20 | |
| content= string.lower(f1.read()) | |
| noisecontent= string.lower(f2.read()) | |
| workinglist =string.split(content) | |
| cleanlist =[] | |
| for item in workinglist: | |
| temp=item.strip(string.punctuation) | |
| cleanlist=cleanlist+[temp,] | |
| freq = {} | |
| for item in cleanlist: | |
| if item in noisecontent: | |
| continue | |
| else: | |
| try: | |
| freq[item] += 1 | |
| except KeyError: | |
| freq[item] = 1 | |
| print '\nWORD'+' \t '+'FREQUENCY' | |
| def most_common(h): | |
| t = [] | |
| for key, value in h.items(): | |
| t.append((value, key)) | |
| t.sort(reverse=True) | |
| return t | |
| freq = most_common(freq) | |
| for freque, word in freq[0:count]: | |
| print word,' \t', freque | |
| f=open('c:/tiny_projects/tagcloud.html','w') | |
| f.write('<html><body>') | |
| for freque, word in freq[0:count]: | |
| f.write('<font face="Times New Roman"size="'+str((freque*10)/freq[0][0])+'"color="#23bb07">'+word+'\t\t\t</font>') | |
| f.write('</body></html>') | |
| f.close() | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment