YuuMJ1997/EukPhylo
1
0
Fork 0
mirror of http://43.156.76.180:8026/YuuMJ/EukPhylo.git synced 2025-12-27 07:10:25 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update headers

Browse Source
This commit is contained in:
Godwin Ani 2024-01-12 11:19:16 -05:00 committed by GitHub
parent 316f7620ed
commit d55b87f1d9
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 9 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
Utilities/for_taxonomy/get_unique_taxa.py
View File

@ -1,20 +1,15 @@
'''
#Author, date: Elinor Sterner Jan-26-2023, updated Feb-12-2023.
#Intent: To get the unique taxa from a taxonomic classification.
#Dependencies: Python3
#Inputs: text file of taxonomies. make sure each taxonomic level is separated with '; ' (semicolon space).
#Outputs: Spreadsheet with unique taxa. If you run the script multiple times, DELETE THE PREVIOUS OUTPUT.
#Example: python get_unique_taxa.py
'''
import os import os
from pathlib import Path from pathlib import Path
'''
Written by Elinor 1/26, updated 2/12
Input: text file of taxonomies. make sure each taxonomic level is separated with '; ' (semicolon space) or the
script will not parse the names right
This cuts off the genus (and species if there is one), uniquifies the list and writes them out to files by the first
word of the taxonomy
WARNING: if you run the script multiple times, DELETE THE PREVIOUS OUTPUT. this is because it appends lines to the
end of files so you will have many duplicates
'''
Path(f'unique_taxon_lists').mkdir(parents=True, exist_ok=True)#makes output folder Path(f'unique_taxon_lists').mkdir(parents=True, exist_ok=True)#makes output folder
with open ('all_taxa.txt') as t: with open ('all_taxa.txt') as t: