Day #317 - Ensemble Methods

Summary of Ensemble Techniques, Bagging, Boosting code snippets

	#https://scikit-learn.org/stable/modules/ensemble.html#forest
	#Ensemble - combine several techniques
	#averaging - baggining - randomforest
	#boosting - seqiential build, combine weak classifiers - Adaboost, Gradient boosting
	#voting classifier
	from sklearn.ensemble import RandomForestClassifier
	from sklearn.model_selection import cross_val_score
	from sklearn.tree import DecisionTreeClassifier
	x_data = [[0,0],[1,1],[1,2],[0,4]]
	y_data = [0,1,1,0]
	rfit = RandomForestClassifier(n_estimators = 10)
	rfit = rfit.fit(x_data,y_data)
	scores = cross_val_score(rfit,x_data,y_data,cv=2)
	print(scores.mean())
	# The minimum number of samples required to split an internal node:
	dtree = DecisionTreeClassifier(max_depth=None,min_samples_split=2,random_state=0)
	dtree = dtree.fit(x_data,y_data)
	scores = cross_val_score(dtree,x_data,y_data,cv=2)
	print(scores.mean())
	print(rfit.predict([[3,3]]))
	print(dtree.predict([[3,3]]))
	#boosting
	from sklearn.ensemble import AdaBoostClassifier
	adaboostmodel = AdaBoostClassifier(n_estimators = 10)
	adaboostmodel = adaboostmodel.fit(x_data,y_data)
	print(adaboostmodel.predict([[3,3]]))
	from sklearn.ensemble import GradientBoostingClassifier
	gbmodel = GradientBoostingClassifier(n_estimators = 10,learning_rate=1.0,max_depth=1,random_state=0)
	gbmodel = gbmodel.fit(x_data,y_data)
	print(gbmodel.predict([[3,3]]))
	#VotingClassifier (with voting='hard') would classify based on the majority class label.
	#If ‘hard’, uses predicted class labels for majority rule voting. Else if ‘soft’, predicts the class label based on the argmax of the sums of the predicted probabilities
	from sklearn.ensemble import VotingClassifier
	estimators = [('model1',rfit),('model2',dtree),('model3',adaboostmodel),('model4',gbmodel)]
	votinghardmodel = VotingClassifier(estimators=estimators, voting = 'hard')
	votinghardmodel = votinghardmodel.fit(x_data,y_data)
	print(votinghardmodel.predict([[3,3]]))
	votingsoftmodel = VotingClassifier(estimators=estimators, voting = 'soft')
	votingsoftmodel = votingsoftmodel.fit(x_data,y_data)
	print(votingsoftmodel.predict([[3,3]]))

view raw Ensemble_methods.py hosted with ❤ by GitHub

Happy Learning!!!