PatternDistance

gistfile1.txt

# DB is dictionary with tuple of pattern as key and support as value
# P1 and P2 are lists or arrays of the keys to compare
# this will only work if one of P1 and P2 is a subset of the other
def pattern_distance(P1, P2, db):
    P1_support = db[tuple(P1)]
    P2_support = db[tuple(P2)]
        
    # if P1 is a subset of P2 then we just use their supports
    if set(P1).issubset(set(P2)):
        return 1 - (P2_support / P1_support)
    
    # else if P2 is a subset of P1 we flip it around
    elif set(P2).issubset(set(P1)):
        return 1 - (P1_support / P2_support)
    
    else:
        return 0
        
# takes two patterns and a complete DB and returns the
# pattern distance, calculating the supports from the db
def pattern_distance2(P1, P2, db):
    # initialize our counts
    P1orP2_count = 0
    P1andP2_count = 0
    
    # convert P1 and P2 to sets so we can do subset testing
    P1 = set(P1)
    P2 = set(P2)
    
    # loop through the DB getting the support for (P1 and P2) and (P1 or P2)
    for transaction in db:
        trans_set = set(transaction)
        # if both P1 and P2 are in the transaction then we increment both counts
        if P1.issubset(trans_set) and P2.issubset(trans_set):
            P1andP2_count += 1
            P1orP2_count += 1
        # else if only one of them is we increment the intersect count
        elif P1.issubset(trans_set) or P2.issubset(trans_set):
            P1orP2_count += 1
            
    return 1 - (P1andP2_count / P1orP2_count)