aboutsummaryrefslogtreecommitdiff
path: root/wqflask/maintenance/dataset/specials3.py
diff options
context:
space:
mode:
authorzsloan2016-01-26 19:08:13 +0000
committerzsloan2016-01-26 19:08:13 +0000
commitfca37195705ac68f21a1f725cf1fe3c59e0d1800 (patch)
tree6263853824e4b9abefdcb2351ee8a25cfb5aa853 /wqflask/maintenance/dataset/specials3.py
parent3078d459efda0f4805fbf3cb18297bcdc74dc420 (diff)
downloadgenenetwork2-fca37195705ac68f21a1f725cf1fe3c59e0d1800.tar.gz
Removed a bunch of files/directories/packages that are no longer used and some corresponding imports
Diffstat (limited to 'wqflask/maintenance/dataset/specials3.py')
-rw-r--r--wqflask/maintenance/dataset/specials3.py117
1 files changed, 0 insertions, 117 deletions
diff --git a/wqflask/maintenance/dataset/specials3.py b/wqflask/maintenance/dataset/specials3.py
deleted file mode 100644
index 237df27e..00000000
--- a/wqflask/maintenance/dataset/specials3.py
+++ /dev/null
@@ -1,117 +0,0 @@
-import utilities
-import datastructure
-import genotypes
-import probesets
-import calculate
-
-def correlations(outputdir, genos, probesetfreeze):
- print probesetfreeze
- probesetfreezeid = probesetfreeze[0]
- probesetfreezename = probesetfreeze[1]
- probesetfreezefullname = probesetfreeze[2]
- #
- outputfile = open("%s/%d_%s.txt" % (outputdir, probesetfreezeid, probesetfreezename), "w+")
- outputfile.write("%s\t" % "ProbeSet Id")
- outputfile.write("%s\t" % "ProbeSet Name")
- outputfile.write("%s\t" % "Geno Name")
- outputfile.write("%s\t" % "Overlap Number")
- outputfile.write("%s\t" % "Pearson r")
- outputfile.write("%s\t" % "Pearson p")
- outputfile.write("%s\t" % "Spearman r")
- outputfile.write("%s\t" % "Spearman p")
- outputfile.write("\n")
- outputfile.flush()
- #
- probesetxrefs = probesets.get_probesetxref(probesetfreezeid)
- print "Get %d probesetxrefs" % (len(probesetxrefs))
- #
- for probesetxref in probesetxrefs:
- #
- probesetid = probesetxref[0]
- probesetdataid = probesetxref[1]
- probeset = probesets.get_probeset(probesetid)
- probesetname = probeset[1]
- probesetdata = probesets.get_probesetdata(probesetdataid)
- probesetdata = zip(*probesetdata)
- probesetdata = utilities.to_dic([strain.lower() for strain in probesetdata[1]], probesetdata[2])
- #
- for geno in genos:
- genoname = geno['locus']
- outputfile.write("%s\t" % probesetid)
- outputfile.write("%s\t" % probesetname)
- outputfile.write("%s\t" % genoname)
- #
- dic1 = geno['dicvalues']
- dic2 = probesetdata
- keys, values1, values2 = utilities.overlap(dic1, dic2)
- rs = calculate.correlation(values1, values2)
- #
- outputfile.write("%s\t" % len(keys))
- outputfile.write("%s\t" % rs[0][0])
- outputfile.write("%s\t" % rs[0][1])
- outputfile.write("%s\t" % rs[1][0])
- outputfile.write("%s\t" % rs[1][1])
- outputfile.write("\n")
- outputfile.flush()
- #
- outputfile.close()
-
-"""
-For: Ash
-Date: 2014-02-12
-Function:
- Generate probeset data files.
- given probesetfreeze list.
-"""
-def generate_probesets(probesetfreezesfile, outputdir):
- file = open(probesetfreezesfile, 'r')
- for line in file:
- line = line.strip()
- cells = line.split()
- probesetfreezeid = cells[0]
- probesetfreeze = datastructure.get_probesetfreeze(probesetfreezeid)
- probesetfreezeid = probesetfreeze[0]
- probesetfreezename = probesetfreeze[1]
- inbredset = datastructure.get_inbredset(probesetfreezeid)
- inbredsetid = inbredset[0]
- strains = datastructure.get_strains(inbredsetid)
- #
- outputfile = open("%s/%d_%s.txt" % (outputdir, probesetfreezeid, probesetfreezename), "w+")
- outputfile.write("%s\t" % "ProbeSet Id")
- outputfile.write("%s\t" % "ProbeSet Name")
- outputfile.write('\t'.join([strain[1].upper() for strain in strains]))
- outputfile.write("\n")
- outputfile.flush()
- #
- probesetxrefs = probesets.get_probesetxref(probesetfreezeid)
- print probesetfreeze
- print len(probesetxrefs)
- for probesetxref in probesetxrefs:
- probesetid = probesetxref[0]
- probesetdataid = probesetxref[1]
- probeset = probesets.get_probeset(probesetid)
- probesetname = probeset[1]
- probesetdata = probesets.get_probesetdata(probesetdataid)
- probesetdata = zip(*probesetdata)
- probesetdata = utilities.to_dic([strain.lower() for strain in probesetdata[1]], probesetdata[2])
- #
- outputfile.write("%s\t" % probesetid)
- outputfile.write("%s\t" % probesetname)
- #
- for strain in strains:
- strainname = strain[1]
- strainname = strainname.lower()
- if strainname in probesetdata:
- value = probesetdata[strainname]
- else:
- value = 'x'
- outputfile.write("%s\t" % value)
- outputfile.write("\n")
- outputfile.flush()
- #
- outputfile.close()
- file.close()
-
-probesetfreezesfile = "/home/leiyan/gn2/wqflask/maintenance/dataset/datadir/20140205_Ash_correlations/output2/probesetfreezes_filter.txt"
-outputdir = "/home/leiyan/gn2/wqflask/maintenance/dataset/datadir/20140205_Ash_correlations/output2"
-generate_probesets(probesetfreezesfile, outputdir)