AI assignment

gistfile1.txt

import numpy as np
import pandas as pd
eps = np.finfo(float).eps
from numpy import log2, log

df = pd.read_csv('data.csv', sep = ',')
#this code I used for only values of entropy of target and all features of data.

entropy_node = 0 #initilaize entropy
values = df.Target.unique()
for value in values:
    fraction = df.Target.value_counts()[value]/len(df.Target)
    entropy_node += -fraction*np.log2(fraction)
    
    
    
def ent(df,attribute): #entropy for each feature in the given data
    target_variables = df.Target.unique()  
    variables = df[attribute].unique()   


    entropy_attribute = 0
    for variable in variables:
        entropy_each_feature = 0
        for target_variable in target_variables:
            num = len(df[attribute][df[attribute]==variable][df.Target ==target_variable]) #numerator
            den = len(df[attribute][df[attribute]==variable])  #denominator
            fraction = num/(den+eps)  #pi
            entropy_each_feature += -fraction*log(fraction+eps) 
        fraction2 = den/len(df)
        entropy_attribute += -fraction2*entropy_each_feature   

    return(abs(entropy_attribute))
    
    
def info_gain(e_dataset, e_attr):
    return e_dataset - e_attr
    
    
ig = {i:info_gain(entropy_node, a_entropy[i]) for i in a_entropy}