In [1]:

    

import numpy
import pandas


    

In [3]:

    

def gini_index(groups, classes):
	# count all samples at split point
	n_instances = float(sum([len(group) for group in groups]))
	# sum weighted Gini index for each group
	gini = 0.0
	for group in groups:
		size = float(len(group))
		# avoid divide by zero
		if size == 0:
			continue
		score = 0.0
		# score the group based on the score for each class
		for class_val in classes:
			p = [row[-1] for row in group].count(class_val) / size
			score += p * p
		# weight the group score by its relative size
		gini += (1.0 - score) * (size / n_instances)
	return gini


    

In [6]:

    

def test_split(index, value, dataset):
    left, right = [], []
    for row in dataset:
        if row[index] < value:
            left.append(row)
        else:
            right.append(row)
    return left, right


    

In [7]:

    

pwd


    

    
Out[7]:





'C:\\Users\\gsim\\repos\\jupyter-notebooks\\decision-tree'

In [ ]:

    

pandas.read_csv('data')