From df8386f75b0538075d72d52693836bb8878f505b Mon Sep 17 00:00:00 2001 From: KatolaZ Date: Mon, 19 Oct 2015 16:23:00 +0100 Subject: First commit of MAMMULT code --- structure/correlations/rank_occurrence.py | 45 +++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) create mode 100644 structure/correlations/rank_occurrence.py (limited to 'structure/correlations/rank_occurrence.py') diff --git a/structure/correlations/rank_occurrence.py b/structure/correlations/rank_occurrence.py new file mode 100644 index 0000000..6339d5d --- /dev/null +++ b/structure/correlations/rank_occurrence.py @@ -0,0 +1,45 @@ +#### +## +## Get two rankings and compute the size of the k-intersection, +## i.e. the number of elements which are present in the first k +## positions of both rankings, as a function of k +## +## + + +import sys + + +if len(sys.argv)< 4: + print "Usage: %s " % sys.argv[0] + sys.exit(1) + +incr = int(sys.argv[3]) + +rank1 = [] +rank2 = [] + +lines = open(sys.argv[1], "r").readlines() + +for l in lines: + n= l.strip(" \n").split(" ")[0] + rank1.append(n) + +lines = open(sys.argv[2], "r").readlines() + +for l in lines: + n= l.strip(" \n").split(" ")[0] + rank2.append(n) + + +N = len(rank1) + +i = incr + +while i < N+incr: + l = len(set(rank1[:i]) & set(rank2[:i])) + print i, l + i += incr + + + -- cgit v1.2.3