first corrections on the init table

jass/models/worktable.py

@@ -117,13 +117,13 @@ def create_inittable_file(input_data_path: str, init_covariance_path: str, regio
     # Read summary statistics
     covariance = read_csv(init_covariance_path, sep='\t', index_col=0)
     # Read description file
-    description = read_csv(description_file_path, sep='\t', index_col=0)
+    description = read_csv(description_file_path, sep='\t')
     
     # gwas_list = list(set([os.path.basename(x).split("_")[0] for x in glob.glob(input_data_path)]))
     
     gwas_dict = {}
     
-    for x in glob.glob(input_data_path)]):
+    for x in glob.glob(input_data_path):
         gwas_name = os.path.basename(x).split("_")[0]
         if gwas_name in gwas_dict:
             gwas_dict[gwas_name].append(x)
@@ -134,18 +134,20 @@ def create_inittable_file(input_data_path: str, init_covariance_path: str, regio
 
     for meta_index, meta_row in description.iterrows():        # READ GWAS
        
+        print(meta_row.keys()) 
         # create an ID from the GWAS consortia + outcome columns
-        study_name = 'z_' + meta_row['consortia'].upper() + '_' + meta_row['outcome'].upper()
+        study_name = 'z_' + meta_row['Consortium'].upper() + '_' + meta_row['Outcome'].upper()
         
-        print('**** PARSING %s ******' % my_study)
+        print('**** PARSING %s ******' % study_name)
         
-        for gwas_file_chri in gwas_dict[meta_row['outcome']]:
-            
-            chrom = int(os.path.splitext(os.path.basename(gwas_file_chri[0]))[0].split("_chr")[1])
+        for gwas_file_chri in gwas_dict[meta_row['Outcome']]:
+            print(gwas_file_chri) 
+            chrom = int(os.path.splitext(os.path.basename(gwas_file_chri))[0].split("_chr")[1])
             print('Working on Chromosome %d' % chrom)
             
             # Load summary statistics file for CHR i
-            z_gwas = read_csv(gwas_file_chri, sep = "\t", index_col= [0, 1, 4])
+            z_gwas = read_csv(gwas_file_chri, sep = "\t", usecols= [0, 1, 4])
+            print(z_gwas.columns)
             z_gwas.columns = ['snp_ids', 'position', 'z_score']
             # CAUTION: handle duplicates (whenever there are multiple values for a single SNP)
             z_gwas = z_gwas[~z_gwas.index.duplicated(keep='first')]
@@ -155,7 +157,7 @@ def create_inittable_file(input_data_path: str, init_covariance_path: str, regio
 
             # Add chromosome and study name columns
             z_gwas['CHR'] = [chrom] * N
-            merge_GWAS['study_name'] = [study_name] * N
+            z_gwas['study_name'] = [study_name] * N
 
             # Add region and middle position columns
             z_gwas['Region'] = np.zeros(len(z_gwas), dtype=np.int)