aboutsummaryrefslogtreecommitdiff
path: root/scripts
diff options
context:
space:
mode:
Diffstat (limited to 'scripts')
-rwxr-xr-xscripts/maintenance/QTL_Reaper_v6.py6
-rw-r--r--scripts/maintenance/Update_Case_Attributes_MySQL_tab.py2
-rwxr-xr-xscripts/maintenance/delete_genotypes.py14
-rwxr-xr-xscripts/maintenance/delete_phenotypes.py14
-rwxr-xr-xscripts/maintenance/load_genotypes.py16
-rwxr-xr-xscripts/maintenance/load_phenotypes.py30
-rwxr-xr-xscripts/maintenance/readProbeSetMean_v7.py40
-rwxr-xr-xscripts/maintenance/readProbeSetSE_v7.py22
8 files changed, 72 insertions, 72 deletions
diff --git a/scripts/maintenance/QTL_Reaper_v6.py b/scripts/maintenance/QTL_Reaper_v6.py
index e50dbd40..7fb56eca 100755
--- a/scripts/maintenance/QTL_Reaper_v6.py
+++ b/scripts/maintenance/QTL_Reaper_v6.py
@@ -53,7 +53,7 @@ for ProbeSetFreezeId in ProbeSetFreezeIds:
#if InbredSetId==12:
# InbredSetId=2
- print ProbeSetFreezeId, InbredSets[InbredSetId]
+ print((ProbeSetFreezeId, InbredSets[InbredSetId]))
genotype_1.read(InbredSets[InbredSetId])
locuses = []
@@ -102,7 +102,7 @@ for ProbeSetFreezeId in ProbeSetFreezeIds:
kj += 1
if kj%1000==0:
- print ProbeSetFreezeId, InbredSets[InbredSetId],kj
+ print((ProbeSetFreezeId, InbredSets[InbredSetId],kj))
- print ProbeSetFreezeIds
+ print(ProbeSetFreezeIds)
diff --git a/scripts/maintenance/Update_Case_Attributes_MySQL_tab.py b/scripts/maintenance/Update_Case_Attributes_MySQL_tab.py
index 0f8602c9..bf796df4 100644
--- a/scripts/maintenance/Update_Case_Attributes_MySQL_tab.py
+++ b/scripts/maintenance/Update_Case_Attributes_MySQL_tab.py
@@ -24,4 +24,4 @@ for row in csv_data:
#close the connection to the database.
mydb.commit()
cursor.close()
-print "Done" \ No newline at end of file
+print("Done") \ No newline at end of file
diff --git a/scripts/maintenance/delete_genotypes.py b/scripts/maintenance/delete_genotypes.py
index fa693f0f..060640e1 100755
--- a/scripts/maintenance/delete_genotypes.py
+++ b/scripts/maintenance/delete_genotypes.py
@@ -8,13 +8,13 @@ import genotypes
def main(argv):
# config
config = utilities.get_config(argv[1])
- print "config:"
+ print("config:")
for item in config.items('config'):
- print "\t%s" % (str(item))
+ print(("\t%s" % (str(item))))
# var
- print "variable:"
+ print("variable:")
inbredsetid = config.get('config', 'inbredsetid')
- print "\tinbredsetid: %s" % inbredsetid
+ print(("\tinbredsetid: %s" % inbredsetid))
# datafile
datafile = open(config.get('config', 'datafile'), 'r')
datafile = csv.reader(datafile, delimiter='\t', quotechar='"')
@@ -25,9 +25,9 @@ def main(argv):
continue
genoname = row[0]
delrowcount += genotypes.delete(genoname, inbredsetid)
- print "deleted %d genotypes" % (delrowcount)
+ print(("deleted %d genotypes" % (delrowcount)))
if __name__ == "__main__":
- print "command line arguments:\n\t%s" % sys.argv
+ print(("command line arguments:\n\t%s" % sys.argv))
main(sys.argv)
- print "exit successfully"
+ print("exit successfully")
diff --git a/scripts/maintenance/delete_phenotypes.py b/scripts/maintenance/delete_phenotypes.py
index 326c466e..60dbec61 100755
--- a/scripts/maintenance/delete_phenotypes.py
+++ b/scripts/maintenance/delete_phenotypes.py
@@ -8,13 +8,13 @@ import phenotypes
def main(argv):
# config
config = utilities.get_config(argv[1])
- print "config:"
+ print("config:")
for item in config.items('config'):
- print "\t%s" % (str(item))
+ print(("\t%s" % (str(item))))
# var
- print "variable:"
+ print("variable:")
inbredsetid = config.get('config', 'inbredsetid')
- print "\tinbredsetid: %s" % inbredsetid
+ print(("\tinbredsetid: %s" % inbredsetid))
# datafile
datafile = open(config.get('config', 'datafile'), 'r')
datafile = csv.reader(datafile, delimiter='\t', quotechar='"')
@@ -27,9 +27,9 @@ def main(argv):
except:
continue
delrowcount += phenotypes.delete(publishxrefid=publishxrefid, inbredsetid=inbredsetid)
- print "deleted %d phenotypes" % (delrowcount)
+ print(("deleted %d phenotypes" % (delrowcount)))
if __name__ == "__main__":
- print "command line arguments:\n\t%s" % sys.argv
+ print(("command line arguments:\n\t%s" % sys.argv))
main(sys.argv)
- print "exit successfully"
+ print("exit successfully")
diff --git a/scripts/maintenance/load_genotypes.py b/scripts/maintenance/load_genotypes.py
index 338483f4..c235a31f 100755
--- a/scripts/maintenance/load_genotypes.py
+++ b/scripts/maintenance/load_genotypes.py
@@ -8,7 +8,7 @@ def main(argv):
config = utilities.get_config(argv[1])
print("config file:")
for item in config.items('config'):
- print("\t%s" % str(item))
+ print(("\t%s" % str(item)))
parse_genofile(config, fetch_parameters(config))
def fetch_parameters(config):
@@ -20,7 +20,7 @@ def fetch_parameters(config):
config_dic['genofile'] = config.get('config', 'genofile')
print("config dictionary:")
for k, v in config_dic.items():
- print("\t%s: %s" % (k, v))
+ print(("\t%s: %s" % (k, v)))
return config_dic
def parse_genofile(config, config_dic):
@@ -43,9 +43,9 @@ def parse_genofile(config, config_dic):
#
print("geno file meta dictionary:")
for k, v in meta_dic.items():
- print("\t%s: %s" % (k, v))
+ print(("\t%s: %s" % (k, v)))
#
- print("geno file head:\n\t%s" % line)
+ print(("geno file head:\n\t%s" % line))
strainnames = line.split()[4:]
config_dic['strains'] = datastructure.get_strains_bynames(inbredsetid=config_dic['inbredsetid'], strainnames=strainnames, updatestrainxref="yes")
continue
@@ -81,7 +81,7 @@ def check_or_insert_geno(config_dic, marker_dic):
result = cursor.fetchone()
if result:
genoid = result[0]
- print("get geno record: %d" % genoid)
+ print(("get geno record: %d" % genoid))
else:
sql = """
INSERT INTO Geno
@@ -95,7 +95,7 @@ def check_or_insert_geno(config_dic, marker_dic):
cursor.execute(sql, (config_dic['speciesid'], marker_dic['locus'], marker_dic['locus'], marker_dic['chromosome'], marker_dic['mb']))
rowcount = cursor.rowcount
genoid = con.insert_id()
- print("INSERT INTO Geno: %d record: %d" % (rowcount, genoid))
+ print(("INSERT INTO Geno: %d record: %d" % (rowcount, genoid)))
return genoid
def check_genoxref(config_dic, marker_dic):
@@ -146,9 +146,9 @@ def insert_genoxref(config_dic, marker_dic):
"""
cursor.execute(sql, (config_dic['genofreezeid'], marker_dic['genoid'], config_dic['dataid'], marker_dic['cm'], 'N'))
rowcount = cursor.rowcount
- print("INSERT INTO GenoXRef: %d record" % (rowcount))
+ print(("INSERT INTO GenoXRef: %d record" % (rowcount)))
if __name__ == "__main__":
- print("command line arguments:\n\t%s" % sys.argv)
+ print(("command line arguments:\n\t%s" % sys.argv))
main(sys.argv)
print("exit successfully")
diff --git a/scripts/maintenance/load_phenotypes.py b/scripts/maintenance/load_phenotypes.py
index c3c6570b..61d527d4 100755
--- a/scripts/maintenance/load_phenotypes.py
+++ b/scripts/maintenance/load_phenotypes.py
@@ -7,31 +7,31 @@ import datastructure
def main(argv):
# config
config = utilities.get_config(argv[1])
- print "config:"
+ print("config:")
for item in config.items('config'):
- print "\t%s" % (str(item))
+ print(("\t%s" % (str(item))))
# var
inbredsetid = config.get('config', 'inbredsetid')
- print "inbredsetid: %s" % inbredsetid
+ print(("inbredsetid: %s" % inbredsetid))
species = datastructure.get_species(inbredsetid)
speciesid = species[0]
- print "speciesid: %s" % speciesid
+ print(("speciesid: %s" % speciesid))
dataid = datastructure.get_nextdataid_phenotype()
- print "next data id: %s" % dataid
+ print(("next data id: %s" % dataid))
cursor, con = utilities.get_cursor()
# datafile
datafile = open(config.get('config', 'datafile'), 'r')
phenotypedata = csv.reader(datafile, delimiter='\t', quotechar='"')
phenotypedata_head = phenotypedata.next()
- print "phenotypedata head:\n\t%s" % phenotypedata_head
+ print(("phenotypedata head:\n\t%s" % phenotypedata_head))
strainnames = phenotypedata_head[1:]
strains = datastructure.get_strains_bynames(inbredsetid=inbredsetid, strainnames=strainnames, updatestrainxref="yes")
# metafile
metafile = open(config.get('config', 'metafile'), 'r')
phenotypemeta = csv.reader(metafile, delimiter='\t', quotechar='"')
phenotypemeta_head = phenotypemeta.next()
- print "phenotypemeta head:\n\t%s" % phenotypemeta_head
- print
+ print(("phenotypemeta head:\n\t%s" % phenotypemeta_head))
+ print()
# load
for metarow in phenotypemeta:
#
@@ -67,7 +67,7 @@ def main(argv):
))
rowcount = cursor.rowcount
phenotypeid = con.insert_id()
- print "INSERT INTO Phenotype: %d record: %d" % (rowcount, phenotypeid)
+ print(("INSERT INTO Phenotype: %d record: %d" % (rowcount, phenotypeid)))
# Publication
publicationid = None # reset
pubmed_id = utilities.to_db_string(metarow[0], None)
@@ -81,7 +81,7 @@ def main(argv):
re = cursor.fetchone()
if re:
publicationid = re[0]
- print "get Publication record: %d" % publicationid
+ print(("get Publication record: %d" % publicationid))
if not publicationid:
sql = """
INSERT INTO Publication
@@ -109,7 +109,7 @@ def main(argv):
))
rowcount = cursor.rowcount
publicationid = con.insert_id()
- print "INSERT INTO Publication: %d record: %d" % (rowcount, publicationid)
+ print(("INSERT INTO Publication: %d record: %d" % (rowcount, publicationid)))
# data
for index, strain in enumerate(strains):
#
@@ -158,14 +158,14 @@ def main(argv):
cursor.execute(sql, (inbredsetid, phenotypeid, publicationid, dataid, ""))
rowcount = cursor.rowcount
publishxrefid = con.insert_id()
- print "INSERT INTO PublishXRef: %d record: %d" % (rowcount, publishxrefid)
+ print(("INSERT INTO PublishXRef: %d record: %d" % (rowcount, publishxrefid)))
# for loop next
dataid += 1
- print
+ print()
# release
con.close()
if __name__ == "__main__":
- print "command line arguments:\n\t%s" % sys.argv
+ print(("command line arguments:\n\t%s" % sys.argv))
main(sys.argv)
- print "exit successfully"
+ print("exit successfully")
diff --git a/scripts/maintenance/readProbeSetMean_v7.py b/scripts/maintenance/readProbeSetMean_v7.py
index e9c8f25c..e7a4c826 100755
--- a/scripts/maintenance/readProbeSetMean_v7.py
+++ b/scripts/maintenance/readProbeSetMean_v7.py
@@ -42,9 +42,9 @@ try:
con = MySQLdb.Connect(db='db_webqtl',host='localhost', user='username',passwd=passwd)
db = con.cursor()
- print "You have successfully connected to mysql.\n"
+ print("You have successfully connected to mysql.\n")
except:
- print "You entered incorrect password.\n"
+ print("You entered incorrect password.\n")
sys.exit(0)
time0 = time.time()
@@ -55,7 +55,7 @@ time0 = time.time()
# generate the gene list of expression data here
#
#########################################################################
-print 'Checking if each line have same number of members'
+print('Checking if each line have same number of members')
GeneList = []
isCont = 1
@@ -70,7 +70,7 @@ while line:
line2 = string.split(string.strip(line),'\t')
line2 = map(string.strip, line2)
if len(line2) != nfield:
- print "Error : " + line
+ print(("Error : " + line))
isCont = 0
GeneList.append(line2[0])
@@ -78,7 +78,7 @@ while line:
kj+=1
if kj%100000 == 0:
- print 'checked ',kj,' lines'
+ print(('checked ',kj,' lines'))
GeneList = map(string.lower, GeneList)
GeneList.sort()
@@ -87,14 +87,14 @@ if isCont==0:
sys.exit(0)
-print 'used ',time.time()-time0,' seconds'
+print(('used ',time.time()-time0,' seconds'))
#########################################################################
#
# Check if each strain exist in database
# generate the string id list of expression data here
#
#########################################################################
-print 'Checking if each strain exist in database'
+print('Checking if each strain exist in database')
isCont = 1
fp.seek(0)
@@ -109,20 +109,20 @@ for item in header:
db.execute('select Id from Strain where Name = "%s"' % item)
Ids.append(db.fetchall()[0][0])
except:
- print item,'does not exist, check the if the strain name is correct'
+ print((item,'does not exist, check the if the strain name is correct'))
isCont=0
if isCont==0:
sys.exit(0)
-print 'used ',time.time()-time0,' seconds'
+print(('used ',time.time()-time0,' seconds'))
########################################################################
#
# Check if each ProbeSet exist in database
#
########################################################################
-print 'Check if each ProbeSet exist in database'
+print('Check if each ProbeSet exist in database')
##---- find PID is name or target ----##
line = fp.readline()
@@ -146,7 +146,7 @@ Names = []
for item in results:
Names.append(item[0])
-print Names
+print(Names)
Names = map(string.lower, Names)
@@ -170,7 +170,7 @@ while x<len(GeneList) and y<len(Names):
y += 1
if x%100000==0:
- print 'check Name, checked %d lines'%x
+ print(('check Name, checked %d lines'%x))
while x<len(GeneList):
GeneList2.append(GeneList[x])
@@ -180,20 +180,20 @@ isCont=1
ferror = open("ProbeSetError.txt", "wb")
for item in GeneList2:
ferror.write(item + " doesn't exist \n")
- print item, " doesn't exist, check if the ProbeSet name is correct"
+ print((item, " doesn't exist, check if the ProbeSet name is correct"))
isCont = 0
if isCont==0:
sys.exit(0)
-print 'used ',time.time()-time0,' seconds'
+print(('used ',time.time()-time0,' seconds'))
#########################################################################
#
# Insert data into database
#
#########################################################################
-print 'getting ProbeSet/Id'
+print('getting ProbeSet/Id')
#---- get Name/Id map ----#
@@ -202,16 +202,16 @@ results = db.fetchall()
NameIds = {}
for item in results:
NameIds[item[0]] = item[1]
-print 'used ',time.time()-time0,' seconds'
+print(('used ',time.time()-time0,' seconds'))
-print 'inserting data'
+print('inserting data')
##---- get old max dataId ----##
db.execute('select max(Id) from ProbeSetData')
maxDataId = int(db.fetchall()[0][0])
bmax = maxDataId
-print "old_max = %d\n" % bmax
+print(("old_max = %d\n" % bmax))
##---- insert data ----##
fp.seek(0)
@@ -255,8 +255,8 @@ while line:
values1=[]
values2=[]
- print 'Inserted ', kj,' lines'
- print 'used ',time.time()-time0,' seconds'
+ print(('Inserted ', kj,' lines'))
+ print(('used ',time.time()-time0,' seconds'))
line = fp.readline()
diff --git a/scripts/maintenance/readProbeSetSE_v7.py b/scripts/maintenance/readProbeSetSE_v7.py
index 0b15ce09..79ed455f 100755
--- a/scripts/maintenance/readProbeSetSE_v7.py
+++ b/scripts/maintenance/readProbeSetSE_v7.py
@@ -82,14 +82,14 @@ while line:
line2 = map(string.strip, line2)
if len(line2) != nfield:
isCont = 0
- print("Error : " + line)
+ print(("Error : " + line))
GeneList.append(line2[0])
line = fp.readline()
kj += 1
if kj % 100000 == 0:
- print('checked ', kj, ' lines')
+ print(('checked ', kj, ' lines'))
GeneList = map(string.lower, GeneList)
GeneList.sort()
@@ -98,7 +98,7 @@ if isCont == 0:
sys.exit(0)
-print('used ', time.time()-time0, ' seconds')
+print(('used ', time.time()-time0, ' seconds'))
#########################################################################
#
# Check if each strain exist in database
@@ -121,13 +121,13 @@ for item in header:
Ids.append(db.fetchall()[0][0])
except:
isCont = 0
- print(item, 'does not exist, check the if the strain name is correct')
+ print((item, 'does not exist, check the if the strain name is correct'))
if isCont == 0:
sys.exit(0)
-print('used ', time.time()-time0, ' seconds')
+print(('used ', time.time()-time0, ' seconds'))
########################################################################
#
# Check if each ProbeSet exist in database
@@ -178,7 +178,7 @@ while x < len(GeneList) and y < len(Names):
y += 1
if x % 100000 == 0:
- print('check Name, checked %d lines' % x)
+ print(('check Name, checked %d lines' % x))
while x < len(GeneList):
GeneList2.append(GeneList[x])
@@ -190,12 +190,12 @@ for item in GeneList2:
ferror.write(item + " doesn't exist \n")
isCont = 0
- print(item, " doesn't exist")
+ print((item, " doesn't exist"))
if isCont == 0:
sys.exit(0)
-print('used ', time.time()-time0, ' seconds')
+print(('used ', time.time()-time0, ' seconds'))
#############################
# Insert new Data into SE
############################
@@ -244,9 +244,9 @@ while line:
DataValues = []
line = fp.readline()
- print(CellId, " doesn't exist")
- print('inserted ', kj, ' lines')
- print('used ', time.time()-time0, ' seconds')
+ print((CellId, " doesn't exist"))
+ print(('inserted ', kj, ' lines'))
+ print(('used ', time.time()-time0, ' seconds'))
if len(DataValues) > 0:
DataValues = ','.join(DataValues)