File tree Expand file tree Collapse file tree 1 file changed +4
-4
lines changed
Expand file tree Collapse file tree 1 file changed +4
-4
lines changed Original file line number Diff line number Diff line change @@ -94,6 +94,10 @@ def _extract_species_name(classification: str) -> str:
9494 )
9595 return ""
9696
97+ # Filter out classifications we don't want
98+ if "phage" in species or "sp." in species :
99+ return ""
100+
97101 return species
98102
99103
@@ -171,10 +175,6 @@ def parse_mash_winning_sorted_tab(
171175 # Extract species names
172176 df ["species" ] = df ["full_classification" ].apply (_extract_species_name )
173177
174- # Filter out species names that include "phage"
175- df = df [~ df ["species" ].str .contains ("phage" , case = False , na = False )]
176- df = df [~ df ["species" ].str .contains ("sp." , case = False , na = False )]
177-
178178 # Filter by median multiplicity factor
179179 if df .empty :
180180 logger .debug ("No mash hits after species filtering" , extra = {"path" : str (fp )})
You can’t perform that action at this time.
0 commit comments