first draft of allowed filter

This commit is contained in:
=
2025-08-21 17:15:34 -04:00
parent e56d6c36b0
commit d018c72820
3 changed files with 380 additions and 0 deletions
+16
View File
@@ -0,0 +1,16 @@
import pandas as pd
def filter_and_drop(approved, eligiblepaths, min_hashes):
"""
Filters eligiblepaths to rows where all hashes are in approved,
then drops rows with fewer than min_hashes hashes.
"""
approved_hashes = set(approved['sha256'])
def all_hashes_approved(row):
return all(h in approved_hashes for h in row['sha256'])
filtered = eligiblepaths[eligiblepaths.apply(all_hashes_approved, axis=1)]
filtered = filtered[filtered['sha256'].apply(len) >= min_hashes]
return filtered