cluster_modules.py

#!/usr/bin/python
import csv
import collections

def get_data(filename):
    '''function to read the data form the input csv file to use in the analysis'''
    reader = [] # Just in case the file open fails
    with open(filename, 'rb') as f:
        reader = csv.reader(f,delimiter=',')                      
        #returns all the data from the csv file in list form
        #f.close() # May need to close the file when done
        return list(reader)  # only return the reader when you have finished.

your_list = []
your_list += get_data('modules-anselm.csv')
your_list += get_data('modules-salomon.csv')
#print your_list

a=[["python/2.8.1",1],["python/2.9.1",2],["python/2.8.1",4],["python/3.0.1",4]]
counts = dict()
for i in your_list:
  #print i[0]
  #print int(i[1])
  counts[i[0]]=counts.get(i[0], 0) + int(i[1])

#print sorted(counts.items())

c=[
"---",
"--A",
"-S-",
"-SA",
"U--",
"U-A",
"US-",
"USA",
]

print "| Module | Versions | Clusters |"
print "| ------ | -------- | -------- |"

software = dict()
versions = ''
clusters = ''
prev = ''

for m,i in sorted(counts.items()):
  split =  m.split('/')
  if len(split) > 1:
    a = split[0]
    b = split[1]
    if split[0] <> prev:
      software[a] = {}
    software[a][b] = c[i]
    prev = a

#print software.items()

for m in sorted(software.items()):
  software = m[0]
  versions = ''
  clusters = ''
  #print '</br>'.join(m[1].keys())
  #print '</br>'.join(m[1].values())
  print "| %s | %s | %s |" % (software, '</br>'.join(m[1].keys()), '</br>'.join(m[1].values()))