Here is a function which takes any list and creates a freq table,
which can be printed unsorted, sorted by cases or items. It's supposed
to mirror the proc freq in SAS.
Dirk
def freq(seq,order='unsorted',prin=True):
#order can be unsorted, cases, items
freq={}
for s in seq:
if s in freq:
freq[s]+=1
else:
freq[s]=1
if prin==True:
print 'Items=',len(seq),'Cases=',len(freq)
print '------------------------'
if order=='unsorted':
for k in freq.keys():
print k,freq[k],float(freq[k])/len(seq)
elif order=='cases':
#http://blog.client9.com/2007/11/sorting-python-dict-by-
value.html
freq2=sorted(freq.iteritems(), key=lambda (k,v):
(v,k),reverse=True)
for f in freq2:
print f[0],f[1],float(f[1])/len(seq)
elif order=='items':
for k in sorted(freq.iterkeys()):
print k,freq[k],float(freq[k])/len(seq)
print '------------------------'
return freq
#test
import random
rand=[]
for i in range(10000):
rand.append(str(int(100*random.random())))
fr=freq(rand)
fr2=freq(rand,order='items')
fr2=freq(rand,order='cases')
