<pre><code>from collections import defaultdict
import statistics
import itertools
import scipy.stats
import heapq
#Please add a filename here and use a .csv format.
F=open('filename','r').readlines();
F[0].strip().split(',');
HEADER=[r.strip() for r in F[0].strip().split(',')[2:]];
DDF={};
DDP={};
DDN={};
DDG={};
#Please replace missing values using Excel into "NAA". I have replaced the "NAA"/missing values with average of the column. You may also consider ignoring missing rows before doing correlation between 2 columns.
for f in F[1:]:
DATA=f.strip().split(',');
ATAD=[[i.strip(),j.strip()] for i,j in zip(HEADER,DATA[2:])];
for atad in ATAD:
if atad[0].strip() in DDF.keys():
DDF[atad[0].strip()].append(atad[1].strip());
else:
DDF[atad[0].strip()]=[atad[1].strip()];
if F[0].strip().split(',')[1].strip() in DDG.keys():
DDG[F[0].strip().split(',')[1].strip()].append(float(DATA[1].strip()));
else:
DDG[F[0].strip().split(',')[1].strip()]=[float(DATA[1].strip())];
for ke in DDF.keys():
AVGP=statistics.mean([float(u) for u in DDF[ke.strip()] if u.strip()!='NAA']);
NEWP=[float(nr.strip()) if nr.strip()!='NAA' else AVGP for nr in DDF[ke.strip()]];
if ke in DDP.keys():
DDP[ke.strip()]=NEWP;
else:
DDP[ke.strip()]=NEWP;
AVGN=statistics.mean([-1*float(e) for e in DDF[ke.strip()] if e.strip()!='NAA']);
NEWN=[-1*float(ne.strip()) if ne.strip()!='NAA' else AVGN for ne in DDF[ke.strip()]];
if 'minus_'+ke.strip() in DDN.keys():
DDN['minus_'+ke.strip()]=NEWN;
else:
DDN['minus_'+ke.strip()]=NEWN;
U=0;
L1=DDP.keys()+DDN.keys();
N=range(1,len(L1));
U=[0,0,-1];
for n in N:
DDU=[];
for subset in itertools.combinations(L1,n):
S=[];
SSET=[sset.strip().replace('minus_','') if sset.strip().startswith('minus_') else sset.strip() for sset in list(subset)];
if len(set(SSET))>=len(subset):
TMP=[DDN[p.strip()] if p.strip().startswith('minus_') else DDP[p.strip()] for p in subset];
for y in range(0,len(TMP[0])):
for x in TMP:
S.append(x[y]);
SUM=[sum(S[w:w + n]) for w in range(0, len(S),n)];
K=['+'.join(list(subset)).strip()]+[' vs Cq TREC']+list(scipy.stats.pearsonr(SUM,DDG['Cq TREC']));
if str(K[-2])!='nan':
DDU.append([K[-2],K]);
DDU.sort(key=lambda x: x[0],reverse=True);
for ea in DDU[0:3]:
print repr(n).strip()+','+ea[1][0].strip().replace('+minus_','-').replace('minus_','-')+' '+ea[1][1].strip()+','+repr(ea[1][-2]).strip();
</code></pre>