brotoskyj
ccbf716418
Co-authored-by: = <=> Co-authored-by: Driven-Element <129630760+Driven-Element@users.noreply.github.com> Reviewed-on: brotoskyj/AirlockTools#6 Co-authored-by: brotoskyj <jbrotosky@gmail.com> Co-committed-by: brotoskyj <jbrotosky@gmail.com>
17 lines
537 B
Python
17 lines
537 B
Python
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
|