utility.py

def maxf(s):
    return s.max()

def minf(s):
    return s.min()

def uniqueValue(s):
    # are records in s the same? return true
    if s.nunique()['Class'] == 1:
        return False
    # otherwise false 
    else:
        return True


def maxPartition(maxInformationGain,maxThreshold,s,s1,s2):
    print(f'informationGain: {maxInformationGain}, threshold: {maxThreshold}')
    merged_partitions =  pd.merge(s1,s2)
    merged_partitions =  pd.merge(merged_partitions,s)
    print("Best Partition")
    print("***************")
    print(merged_partitions)
    print("***************")
    return merged_partitions



def information_gain(s1, s2, s):
    # calculate cardinality for s1
    cardinalityS1 = len(pd.Index(s1['Class']).value_counts())
    print(f'The Cardinality of s1 is: {cardinalityS1}')
    # calculate cardinality for s2
    cardinalityS2 = len(pd.Index(s2['Class']).value_counts())
    print(f'The Cardinality of s2 is: {cardinalityS2}')
    # calculate cardinality of s
    cardinalityS = len(pd.Index(s['Class']).value_counts())
    print(f'The Cardinality of s is: {cardinalityS}')
    # calculate informationGain
    informationGain = (cardinalityS1/cardinalityS) * entropy(s1) + (cardinalityS2/cardinalityS) * entropy(s2)
    print(f'The total informationGain is: {informationGain}')
    return informationGain