schaunwheeler

from numpy.random import RandomState
import pyspark.sql.functions as f
from pyspark import StorageLevel


def hashmin_jaccard_spark(
    sdf, node_col, edge_basis_col, suffixes=('A', 'B'), 
    n_draws=100, storage_level=None, seed=42, verbose=False):
    """
    Calculate a sparse Jaccard similarity matrix using MinHash.