about summary refs log tree commit diff
path: root/wqflask/maintenance
diff options
context:
space:
mode:
Diffstat (limited to 'wqflask/maintenance')
-rwxr-xr-xwqflask/maintenance/gen_select_dataset.py34
-rwxr-xr-xwqflask/maintenance/generate_probesetfreeze_file.py2
-rwxr-xr-xwqflask/maintenance/get_group_samplelists.py8
-rwxr-xr-xwqflask/maintenance/print_benchmark.py16
4 files changed, 30 insertions, 30 deletions
diff --git a/wqflask/maintenance/gen_select_dataset.py b/wqflask/maintenance/gen_select_dataset.py
index 489d291f..b1459bf3 100755
--- a/wqflask/maintenance/gen_select_dataset.py
+++ b/wqflask/maintenance/gen_select_dataset.py
@@ -21,7 +21,7 @@ It needs to be run manually when database has been changed.
 # (sourceforge.net/projects/genenetwork/).
 #
 # Contact Drs. Robert W. Williams
-# at rwilliams@uthsc.edu 
+# at rwilliams@uthsc.edu
 #
 #
 #
@@ -60,15 +60,15 @@ from pprint import pformat as pf
 
 def parse_db_uri(db_uri):
     """Converts a database URI to the db name, host name, user name, and password"""
-    
+
     parsed_uri = urlparse.urlparse(zach_settings.DB_URI)
-    
+
     db_conn_info = dict(
                         db = parsed_uri.path[1:],
                         host = parsed_uri.hostname,
                         user = parsed_uri.username,
                         passwd = parsed_uri.password)
-    
+
     return db_conn_info
 
 
@@ -149,12 +149,12 @@ def genotypes_exist(group_name):
 
 def build_types(species, group):
     """Fetches tissues
-    
+
     Gets the tissues with data for this species/group
     (all types except phenotype/genotype are tissues)
-     
+
     """
-    
+
     Cursor.execute("""select distinct Tissue.Name
                        from ProbeFreeze, ProbeSetFreeze, InbredSet, Tissue, Species
                        where Species.Name = %s and Species.Id = InbredSet.SpeciesId and
@@ -164,14 +164,14 @@ def build_types(species, group):
                        ProbeSetFreeze.ProbeFreezeId = ProbeFreeze.Id and
                        ProbeSetFreeze.public > 0
                        order by Tissue.Name""", (species, group))
-    
+
     results = []
     for result in Cursor.fetchall():
         if len(result):
             these_datasets = build_datasets(species, group, result[0])
             if len(these_datasets) > 0:
                 results.append((result[0], result[0]))
-    
+
     return results
 
 def get_datasets(types):
@@ -196,10 +196,10 @@ def build_datasets(species, group, type_name):
     if type_name == "Phenotypes":
         print("GROUP:", group)
         Cursor.execute("""select InfoFiles.GN_AccesionId from InfoFiles, PublishFreeze, InbredSet where
-                    InbredSet.Name = %s and 
+                    InbredSet.Name = %s and
                     PublishFreeze.InbredSetId = InbredSet.Id and
                     InfoFiles.InfoPageName = PublishFreeze.Name and
-                    PublishFreeze.public > 0 and 
+                    PublishFreeze.public > 0 and
                     PublishFreeze.confidentiality < 1 order by
                     PublishFreeze.CreateTime desc""", (group))
 
@@ -216,10 +216,10 @@ def build_datasets(species, group, type_name):
 
     elif type_name == "Genotypes":
         Cursor.execute("""select InfoFiles.GN_AccesionId from InfoFiles, GenoFreeze, InbredSet where
-                    InbredSet.Name = %s and 
+                    InbredSet.Name = %s and
                     GenoFreeze.InbredSetId = InbredSet.Id and
                     InfoFiles.InfoPageName = GenoFreeze.ShortName and
-                    GenoFreeze.public > 0 and 
+                    GenoFreeze.public > 0 and
                     GenoFreeze.confidentiality < 1 order by
                     GenoFreeze.CreateTime desc""", (group))
 
@@ -238,11 +238,11 @@ def build_datasets(species, group, type_name):
                     ProbeSetFreeze, ProbeFreeze, InbredSet, Tissue, Species where
                     Species.Name = %s and Species.Id = InbredSet.SpeciesId and
                     InbredSet.Name = %s and
-                    ProbeSetFreeze.ProbeFreezeId = ProbeFreeze.Id and Tissue.Name = %s and 
-                    ProbeFreeze.TissueId = Tissue.Id and ProbeFreeze.InbredSetId = InbredSet.Id and 
+                    ProbeSetFreeze.ProbeFreezeId = ProbeFreeze.Id and Tissue.Name = %s and
+                    ProbeFreeze.TissueId = Tissue.Id and ProbeFreeze.InbredSetId = InbredSet.Id and
                     ProbeSetFreeze.confidentiality < 1 and ProbeSetFreeze.public > 0 order by
                     ProbeSetFreeze.CreateTime desc""", (species, group, type_name))
- 
+
         dataset_results = Cursor.fetchall()
         datasets = []
         for dataset_info in dataset_results:
@@ -295,7 +295,7 @@ def _test_it():
     datasets = build_datasets("Mouse", "BXD", "Hippocampus")
     #print("build_datasets:", pf(datasets))
 
-if __name__ == '__main__':   
+if __name__ == '__main__':
     Conn = MySQLdb.Connect(**parse_db_uri(zach_settings.DB_URI))
     Cursor = Conn.cursor()
     main()
diff --git a/wqflask/maintenance/generate_probesetfreeze_file.py b/wqflask/maintenance/generate_probesetfreeze_file.py
index 91a2b8a1..84319a21 100755
--- a/wqflask/maintenance/generate_probesetfreeze_file.py
+++ b/wqflask/maintenance/generate_probesetfreeze_file.py
@@ -107,7 +107,7 @@ def write_data_matrix_file(strains, probeset_vals, filename):
 
 def main():
     filename = os.path.expanduser("~/gene/wqflask/maintenance/" +
-                "ProbeSetFreezeId_210_FullName_Eye_AXBXA_Illumina_V6.2" + 
+                "ProbeSetFreezeId_210_FullName_Eye_AXBXA_Illumina_V6.2" +
                 "(Oct08)_RankInv_Beta.txt")
     dataset_name = "Eye_AXBXA_1008_RankInv"
 
diff --git a/wqflask/maintenance/get_group_samplelists.py b/wqflask/maintenance/get_group_samplelists.py
index a9059fad..2d48ce78 100755
--- a/wqflask/maintenance/get_group_samplelists.py
+++ b/wqflask/maintenance/get_group_samplelists.py
@@ -28,7 +28,7 @@ def get_samplelist_from_geno(genofilename):
         genofile = gzip.open(genofilename)
     else:
         genofile = open(genofilename)
-        
+
     for line in genofile:
         line = line.strip()
         if not line:
@@ -36,9 +36,9 @@ def get_samplelist_from_geno(genofilename):
         if line.startswith(("#", "@")):
             continue
         break
-    
+
     headers = line.split()
-    
+
     if headers[3] == "Mb":
         samplelist = headers[4:]
     else:
@@ -47,7 +47,7 @@ def get_samplelist_from_geno(genofilename):
 
 def get_samplelist_from_plink(genofilename):
     genofile = open(genofilename)
-    
+
     samplelist = []
     for line in genofile:
         line = line.split(" ")
diff --git a/wqflask/maintenance/print_benchmark.py b/wqflask/maintenance/print_benchmark.py
index 540e0904..ae327cf3 100755
--- a/wqflask/maintenance/print_benchmark.py
+++ b/wqflask/maintenance/print_benchmark.py
@@ -9,34 +9,34 @@ from pprint import pformat as pf
 
 class TheCounter(object):
     Counters = {}
-    
+
     def __init__(self):
         start_time = time.time()
         for counter in range(170000):
             self.print_it(counter)
         self.time_took = time.time() - start_time
-        TheCounter.Counters[self.__class__.__name__] = self.time_took        
+        TheCounter.Counters[self.__class__.__name__] = self.time_took
 
-class PrintAll(TheCounter): 
+class PrintAll(TheCounter):
     def print_it(self, counter):
         print(counter)
-        
+
 class PrintSome(TheCounter):
     def print_it(self, counter):
         if counter % 1000 == 0:
             print(counter)
-            
+
 class PrintNone(TheCounter):
     def print_it(self, counter):
         pass
-    
-    
+
+
 def new_main():
     print("Running new_main")
     tests = [PrintAll, PrintSome, PrintNone]
     for test in tests:
         test()
-        
+
     print(pf(TheCounter.Counters))
 
 if __name__ == '__main__':