Mercurial > repos > rliterman > csp2

comparison CSP2/bin/saveSNPDiffs.py @ 39:93393808f415

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload"
author rliterman
date Thu, 12 Dec 2024 13:53:15 -0500
parents 893a6993efe3
children
comparison
equal deleted inserted replaced
38:ee512a230a1e 39:93393808f415
56 with open(snpdiffs_file, 'r') as file: 56 with open(snpdiffs_file, 'r') as file:
57 top_line = file.readline().lstrip('#').strip().split('\t') 57 top_line = file.readline().lstrip('#').strip().split('\t')
58 header_rows.append(processHeader(top_line,snpdiffs_file,trim_name)) 58 header_rows.append(processHeader(top_line,snpdiffs_file,trim_name))
59 59
60 output_data = pd.concat(header_rows, ignore_index=True) 60 output_data = pd.concat(header_rows, ignore_index=True)
61 output_data.to_csv(summary_file, sep='\t', index=False) 61 with open(summary_file,"w") as f:
62 output_data.to_csv(f, sep='\t', index=False)
62 63
63 # If ref_ids is empty, save isolate data 64 # If ref_ids is empty, save isolate data
64 ref_header = ['Reference_ID','Reference_Assembly','Reference_Contig_Count','Reference_Assembly_Bases','Reference_N50','Reference_N90','Reference_L50','Reference_L90','Reference_SHA256'] 65 ref_header = ['Reference_ID','Reference_Assembly','Reference_Contig_Count','Reference_Assembly_Bases','Reference_N50','Reference_N90','Reference_L50','Reference_L90','Reference_SHA256']
65 query_header = ['Query_ID','Query_Assembly','Query_Contig_Count','Query_Assembly_Bases','Query_N50','Query_N90','Query_L50','Query_L90','Query_SHA256'] 66 query_header = ['Query_ID','Query_Assembly','Query_Contig_Count','Query_Assembly_Bases','Query_N50','Query_N90','Query_L50','Query_L90','Query_SHA256']
66 isolate_header = ["Isolate_ID","Assembly_Path","Contig_Count","Assembly_Bases","N50","N90","L50","L90","SHA256"] 67 isolate_header = ["Isolate_ID","Assembly_Path","Contig_Count","Assembly_Bases","N50","N90","L50","L90","SHA256"]
77 combined_df['Isolate_Type'] = np.where(combined_df['Isolate_ID'].isin(ref_ids), 'Reference', 'Query') 78 combined_df['Isolate_Type'] = np.where(combined_df['Isolate_ID'].isin(ref_ids), 'Reference', 'Query')
78 combined_df = combined_df.drop_duplicates() 79 combined_df = combined_df.drop_duplicates()
79 cols = combined_df.columns.tolist() 80 cols = combined_df.columns.tolist()
80 cols = cols[:1] + cols[-1:] + cols[1:-1] 81 cols = cols[:1] + cols[-1:] + cols[1:-1]
81 combined_df = combined_df[cols] 82 combined_df = combined_df[cols]
82 combined_df.to_csv(isolate_data_file, sep='\t', index=False) 83 with open(isolate_data_file,"w") as f:
84 combined_df.to_csv(f, sep='\t', index=False)
83 85