Decision Trees - 5 Mins Tutorials

	# -*- coding: utf-8 -*-
	"""DecisionTrees.ipynb
	Automatically generated by Colaboratory.
	"""
	#Gini Index has values inside the interval [0, 0.5] whereas the interval of the Entropy is [0, 1].
	#Calculation of the Gini Index will be faster.
	import numpy as np
	import pandas as pd
	from sklearn.metrics import confusion_matrix
	from sklearn.model_selection import train_test_split
	from sklearn.tree import DecisionTreeClassifier
	from sklearn.metrics import accuracy_score
	from sklearn.metrics import classification_report
	dataset = pd.read_csv(r'/content/diabetes_dataset.csv',sep= ',', header =0)
	print(dataset.head())
	#list all column names
	print(dataset.columns.tolist())
	from sklearn.tree import DecisionTreeClassifier # Import Decision Tree Classifier
	from sklearn.model_selection import train_test_split # Import train_test_split function
	#Drop the Outcome column and assign dataframe to X
	x=dataset.drop(['Outcome'], axis=1)
	#Assign outcome Y
	y=dataset.Outcome
	#Divide into train test split
	x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=1)
	# Create Decision Tree classifer model
	model = DecisionTreeClassifier(criterion='gini', splitter='best', max_depth=10, min_samples_split=2)
	# Map Data
	model = model.fit(x_train,y_train)
	#Predict the response for test dataset
	y_pred = model.predict(x_test)
	#Evaluation using Accuracy score
	from sklearn import metrics #Import scikit-learn metrics module for accuracy calculation
	print("Accuracy:",metrics.accuracy_score(y_test, y_pred)*100)
	#from sklearn import tree
	#text_representation = tree.export_text(model)
	#print(text_representation)
	# Create Decision Tree classifer model
	model = DecisionTreeClassifier(criterion='entropy', splitter='random', max_depth=10, min_samples_split=2)
	# Map Data
	model = model.fit(x_train,y_train)
	#Predict the response for test dataset
	y_pred = model.predict(x_test)
	#Evaluation using Accuracy score
	from sklearn import metrics #Import scikit-learn metrics module for accuracy calculation
	print("Accuracy:",metrics.accuracy_score(y_test, y_pred)*100)
	#For Information gain purpose lets limit Pregnancy values = 0,1,2 only
	#Total Samples = 349, Outcome = 0 is 263, Outcome = 1 is 86
	#Pregnancy values 0, Outcome = 0, 73, Total Samples 111
	#Pregnancy values 0, Outcome = 1, 38, Total Samples 111
	#Pregnancy values 1, Outcome = 0, 106, Total Samples 135
	#Pregnancy values 1, Outcome = 1, 29, Total Samples 135
	#Pregnancy values 2, Outcome = 0, 84, Total Samples 103
	#Pregnancy values 2, Outcome = 1, 19, Total Samples 103
	#Total set
	import math
	A = ((263/349)*math.log((263/349),2))
	B = ((86/349)*math.log((86/349),2))
	TotalEntropy = -A-B
	print('Entropy of Pregnancy column')
	print(TotalEntropy)
	#For Pregnancy 0,[73,38], 111
	A = ((73/111)*math.log((73/111),2))
	B = ((38/111)*math.log((38/111),2))
	EntropyP0 = -A-B
	print('Entropy of Pregnancy 0')
	print(EntropyP0)
	#For Pregnancy 1,[106,29],135
	A = ((106/135)*math.log((106/135),2))
	B = ((29/135)*math.log((29/135),2))
	EntropyP1 = -A-B
	print('Entropy of Pregnancy 1')
	print(EntropyP1)
	#For Pregnancy 2,[84,19],103
	A = ((-84/103)*math.log((84/103),2))
	B = ((19/103)*math.log((19/103),2))
	EntropyP2 = -A-B
	print('Entropy of Pregnancy 2')
	print(EntropyP2)
	Gain_Pfeature= TotalEntropy - (111/349)*EntropyP0 - (135/349)*EntropyP1 - (103/349)*EntropyP2
	print('Gain on pregnancy feature')
	print(Gain_Pfeature)

view raw DecisionTrees.py hosted with ❤ by GitHub

Happy Learning!!!