working

19_blastomatic/solution1_manual.py

@@ -6,6 +6,8 @@
 import os
 from typing import NamedTuple, TextIO
 
+from pprint import pprint
+
 
 class Args(NamedTuple):
     """ Command-line arguments """
@@ -73,14 +75,14 @@ def main():
     """ Make a jazz noise here """
 
     args = get_args()
-
     annots_reader = csv.DictReader(args.annotations, delimiter=',')
     annots = {}
     for row in annots_reader:
         if acc := row.get('seq_id'):
             annots[acc] = row
+        break
 
-    headers = ['qseqid', 'pident', 'latitude', 'longitude']
+    headers = ['qseqid', 'pident', 'depth', 'lat_lon']
     args.outfile.write(args.delimiter.join(headers) + '\n')
     # print(args.delimiter.join(headers), file=args.outfile)
 
@@ -104,8 +106,8 @@ def main():
                     args.delimiter.join([
                         seq_id,
                         hit.get('pident'),
-                        info.get('latitude'),
-                        info.get('longitude'),
+                        info.get('depth'),
+                        info.get('lat_lon'),
                     ]) + '\n')
 
                 # print(args.delimiter.join([

19_blastomatic/solution2_dict_writer.py

@@ -78,7 +78,7 @@ def main():
 
     writer = csv.DictWriter(
         args.outfile,
-        fieldnames=['qseqid', 'pident', 'genus', 'species'],
+        fieldnames=['qseqid', 'pident', 'depth', 'lat_lon'],
         delimiter=args.delimiter)
     writer.writeheader()
 
@@ -101,8 +101,8 @@ def main():
                 writer.writerow({
                     'qseqid': seq_id,
                     'pident': hit.get('pident', 'NA'),
-                    'genus': info.get('genus') or 'NA',
-                    'species': info.get('species') or 'NA',
+                    'depth': info.get('depth') or 'NA',
+                    'lat_lon': info.get('lat_lon') or 'NA',
                 })
 
     print(f'Exported {num_written:,} to "{args.outfile.name}".')

19_blastomatic/solution3_pandas.py

@@ -90,8 +90,8 @@ def main():
                 data.append({
                     'qseqid': hit['qseqid'],
                     'pident': hit['pident'],
-                    'latitude': info['latitude'] or 'NA',
-                    'longitude': info['longitude'] or 'NA',
+                    'depth': info['depth'] or 'NA',
+                    'lat_lon': info['lat_lon'] or 'NA',
                 })
 
     df = pd.DataFrame.from_records(data=data)

19_blastomatic/solution4_pandas_join.py

@@ -92,7 +92,7 @@ def main():
 
     joined.to_csv(args.outfile,
                   index=False,
-                  columns=['qseqid', 'pident', 'latitude', 'longitude'],
+                  columns=['qseqid', 'pident', 'depth', 'lat_lon'],
                   sep=args.delimiter)
 
     print(f'Exported {joined.shape[0]:,} to "{args.outfile.name}".')

19_blastomatic/tests/blastomatic_test.py

@@ -70,6 +70,8 @@ def test_good_input() -> None:
         assert os.path.isfile(outfile)
 
         reader = csv.DictReader(open(outfile), delimiter=',')
+        assert set(reader.fieldnames
+                   or '') == set(['qseqid', 'pident', 'depth', 'lat_lon'])
         records = list(reader)
         assert len(records) == 500
         assert records[0]['qseqid'] == 'CAM_READ_0234442157'
@@ -96,6 +98,8 @@ def test_delimiter() -> None:
         assert os.path.isfile(outfile)
 
         reader = csv.DictReader(open(outfile), delimiter=delim)
+        assert set(reader.fieldnames
+                   or '') == set(['qseqid', 'pident', 'depth', 'lat_lon'])
         records = list(reader)
         assert len(records) == 500
         assert records[0]['qseqid'] == 'CAM_READ_0234442157'
@@ -124,6 +128,8 @@ def test_guess_delimiter() -> None:
         assert os.path.isfile(outfile)
 
         reader = csv.DictReader(open(outfile), delimiter=delim)
+        assert set(reader.fieldnames
+                   or '') == set(['qseqid', 'pident', 'depth', 'lat_lon'])
         records = list(reader)
         assert len(records) == 252
         assert records[-1]['qseqid'] == 'JCVI_READ_1100018174123'
@@ -148,9 +154,12 @@ def test_pctid() -> None:
         assert os.path.isfile(outfile)
 
         reader = csv.DictReader(open(outfile), delimiter='\t')
+        assert set(reader.fieldnames
+                   or '') == set(['qseqid', 'pident', 'depth', 'lat_lon'])
         records = list(reader)
         assert len(records) == 101
         assert records[-1]['qseqid'] == 'JCVI_READ_1092343670678'
+        assert all(map(lambda r: float(r['pident']) >= 90, records))
     finally:
         if os.path.isfile(outfile):
             os.remove(outfile)