Now calculates correlation values for traits, but not yet in template

2 files changed, 67 insertions, 34 deletions

diff --git a/wqflask/base/data_set.py b/wqflask/base/data_set.py
index 1520b180..89bbf03d 100755
--- a/wqflask/base/data_set.py
+++ b/wqflask/base/data_set.py
@@ -46,7 +46,7 @@ from pprint import pformat as pf
 DS_NAME_MAP = {}
 
 def create_dataset(dataset_name):
-    print("dataset_name:", dataset_name)
+    #print("dataset_name:", dataset_name)
 
     query = """
         SELECT DBType.Name
@@ -71,7 +71,7 @@ def create_dataset(dataset_name):
 def mescape(*items):
     """Multiple escape"""
     escaped = [escape(item) for item in items]
-    print("escaped is:", escaped)
+    #print("escaped is:", escaped)
     return escaped
 
 
@@ -235,6 +235,7 @@ class DataSet(object):
         self.retrieve_other_names()
         
         self.group = DatasetGroup(self)   # sets self.group and self.group_id and gets genotype
+        self.group.read_genotype_file()
         self.species = species.TheSpecies(self)
 
 
@@ -624,17 +625,34 @@ class MrnaAssayDataSet(DataSet):
         return trait_data
     
     def get_trait_data(self):
+        import pdb
+        pdb.set_trace()
+        #samplelist = []
+        #samplelist += self.group.samplelist
+        #samplelist += self.group.parlist
+        #samplelist += self.group.f1list
+        #self.samplelist = samplelist
+        
+        self.samplelist = self.group.samplelist + self.group.parlist + self.group.f1list
+        
         sample_ids = []
-        for sample in self.group.samplelist:
-            query = """
-                SELECT Strain.Id FROM Strain, Species
-                WHERE Strain.Name = '{}'
-                and Strain.SpeciesId=Species.Id
-                and Species.name = '{}'
-                """.format(*mescape(sample, self.group.species))
-            this_id = g.db.execute(query).fetchone()[0]
-            sample_ids.append('%d' % this_id)
-        print("sample_ids size: ", len(sample_ids))
+        
+        where_clause = ""
+        for sample in self.samplelist:
+            if len(where_clause):
+                where_clause += " or "
+            where_clause += """'{}'""".format(*mescape(sample))
+            
+        query = """
+            SELECT Strain.Id, Strain.Name FROM Strain, Species
+            WHERE Strain.Name = '{}'
+            and Strain.SpeciesId=Species.Id
+            and Species.name = '{}'
+            """.format(*mescape(where_clause, self.group.species))
+        result = g.db.execute(query).fetchall()
+        
+        print("[blueberry] result is:", pf(result))
+        #sample_ids.append('%d' % this_id)
 
         # MySQL limits the number of tables that can be used in a join to 61,
         # so we break the sample ids into smaller chunks
@@ -642,7 +660,6 @@ class MrnaAssayDataSet(DataSet):
         n = len(sample_ids) / chunk_count
         if len(sample_ids) % chunk_count:
             n += 1
-        print("n: ", n)
         #XZ, 09/24/2008: build one temporary table that only contains the records associated with the input GeneId 
         #tempTable = None
         #if GeneId and db.type == "ProbeSet": 
@@ -681,10 +698,9 @@ class MrnaAssayDataSet(DataSet):
                     order by {}.Id
                     """.format(*mescape(self.type, self.type, self.type, self.type,
                                self.name, self.type, self.type, self.type, self.type))
-            print("query: ", query)
             results = g.db.execute(query).fetchall()
             trait_sample_data.append(results)
-            
+
         trait_count = len(trait_sample_data[0])
         self.trait_data = collections.defaultdict(list)
         # put all of the separate data together into a dictionary where the keys are
diff --git a/wqflask/wqflask/correlation/show_corr_results.py b/wqflask/wqflask/correlation/show_corr_results.py
index 1d0368cc..ee732050 100644
--- a/wqflask/wqflask/correlation/show_corr_results.py
+++ b/wqflask/wqflask/correlation/show_corr_results.py
@@ -37,6 +37,7 @@ import time
 #import pyXLWriter as xl
 import pp
 import math
+import collections
 
 from pprint import pformat as pf
 
@@ -285,16 +286,15 @@ class CorrelationResults(object):
         #                               name=start_vars['trait_id'],
         #                               cellid=None)                
         
-        print("start_vars: ", pf(start_vars))
+        #print("start_vars: ", pf(start_vars))
         
         helper_functions.get_species_dataset_trait(self, start_vars)
         self.dataset.group.read_genotype_file()
-        
-        self.samples = []   # Want only ones with values
-        self.vals = []
 
         corr_samples_group = start_vars['corr_samples_group']
 
+        self.sample_data = {}
+
         #The two if statements below append samples to the sample list based upon whether the user
         #selected Primary Samples Only, Other Samples Only, or All Samples
 
@@ -310,16 +310,24 @@ class CorrelationResults(object):
                                    self.dataset.group.f1list +
                                    self.dataset.group.samplelist)
             self.process_samples(start_vars, self.this_trait.data.keys(), primary_samples)
-
-        #for i, sample in enumerate(self.samples):
-        #    print("{} : {}".format(sample, self.vals[i]))
-    
         self.target_dataset = data_set.create_dataset(start_vars['corr_dataset'])
         self.target_dataset.get_trait_data()
-        print("trait_list: {}".format(pf(self.target_dataset.trait_data)))
         # Lei Yan todo
+        import pdb
+        pdb.set_trace()
+        correlation_data = collections.defaultdict(list)
         for trait, values in self.target_dataset.trait_data.iteritems():
-            correlation = calCorrelation(values, )
+            values_1 = []
+            values_2 = []
+            for index,sample in enumerate(self.target_dataset.samplelist):
+                target_value = values[index]
+                if sample in self.sample_data.keys():
+                    this_value = self.sample_data[sample]
+                    values_1.append(this_value)
+                    values_2.append(target_value)
+            correlation = calCorrelation(values_1, values_2)
+            correlation_data[trait] = correlation
+            print ('%s %s' % (trait, correlation))
 
         #XZ, 09/18/2008: get all information about the user selected database.
         #target_db_name = fd.corr_dataset
@@ -779,19 +787,28 @@ makeWebGestaltTree(thisForm, '%s', %d, 'edag_only.php');
         """
 
 
+    #def process_samples(self, start_vars, sample_names, excluded_samples):
+    #    for sample in sample_names:
+    #        if sample not in excluded_samples:
+    #            value = start_vars['value:' + sample]
+    #            variance = start_vars['variance:' + sample]
+    #            if variance.strip().lower() == 'x':
+    #                variance = 0
+    #            else:
+    #                variance = float(variance)
+    #            if value.strip().lower() != 'x':
+    #                self.samples.append(str(sample))
+    #                self.vals.append(float(value))
+    #                #self.variances.append(variance)
+
     def process_samples(self, start_vars, sample_names, excluded_samples):
         for sample in sample_names:
             if sample not in excluded_samples:
                 value = start_vars['value:' + sample]
-                variance = start_vars['variance:' + sample]
-                if variance.strip().lower() == 'x':
-                    variance = 0
+                if value.strip().lower() == 'x':
+                    self.sample_data[str(sample)] = None
                 else:
-                    variance = float(variance)
-                if value.strip().lower() != 'x':
-                    self.samples.append(str(sample))
-                    self.vals.append(float(value))
-                    #self.variances.append(variance)    
+                    self.sample_data[str(sample)] = float(value)
 
     def getSortByValue(self, calculationMethod):
 
@@ -2134,7 +2151,7 @@ Resorting this table <br>
 
 
 def calCorrelation(values_1, values_2):
-    N = Math.min(len(values_1), len(values_2))
+    N = min(len(values_1), len(values_2))
     X = []
     Y = []
     for i in range(N):