printcommonsubsets.py

rawdata = [["age","workclass","capital_loss"],["age","capital_gain","capital_loss"],["age","workclass","capital_loss","x"],["age","capital_gain","capital_loss","x"],["workclass","hours_per_week","native_country"],["age","capital_loss","native_country"],["workclass","hours_per_week","native_country","x"],["age","capital_loss","native_country","x"],["age","capital_loss","x"],["age","capital_gain","native_country"],["age","workclass","capital_gain"],["age","workclass","capital_gain","x"],["age","capital_gain","native_country","x"],["age","capital_gain","x"]]
print("how many sets", len(rawdata))
sdata = map(set,rawdata)
#print(len(sdata))
total = len(sdata)
allkeys = reduce(lambda x,y :x.union(y),sdata)
print("how many attributes ", len(allkeys))
l = set()
d = []
for k1 in allkeys:
    for k2 in allkeys:
        for k3 in allkeys:
          ts = set([k1,k2,k3])
          c = sum([ts.issubset(s)  for s in sdata])
          tss = list(ts)
          tss.sort()
          if(c >= total / 2): 
            if((c,str(tss)) in l):
                pass
            else:
                l.add((c,str(tss))) 
                d.append(ts)
l = list(l)
l.sort()
l.reverse()
for x in l:
  print(x)

d2 = filter(lambda x: len(x) > 1,d)
print("all sets contain at least two of the following sets (except for some exceptions)")
print(d2)
for r in sdata:
    c = sum([td.issubset(r) and len(d) > 1 for td in d])
    if( c <= 1 ):
        print(r, " has count ", c)

('how many sets', 14)
('how many attributes ', 7)
(12, "['age']")
(8, "['x']")
(7, "['capital_loss']")
(7, "['capital_gain']")
(7, "['age', 'x']")
(7, "['age', 'capital_loss']")
(7, "['age', 'capital_gain']")
all sets contain at least two of the following sets (except for some exceptions)
[set(['x', 'age']), set(['age', 'capital_loss']), set(['age', 'capital_gain'])]
(set(['native_country', 'hours_per_week', 'workclass']), ' has count ', 0)
(set(['native_country', 'hours_per_week', 'workclass', 'x']), ' has count ', 1)