ensemble

Ensemble/ensemble.r

@@ -0,0 +1,32 @@
+install.packages("randomForest")
+library(randomForest)
+
+head(iris)
+
+# iris 개수만큼의 1 or 2의 70% : 30% 확률로 랜덤한 값을 생성
+idx = sample(2, nrow(iris), replace = T, prob = c(0.7, 0.3))
+
+trainData = iris[idx == 1,]
+testData = iris[idx == 2,]
+
+# 의사결정 트리 100개 생성
+model = randomForest(Species~., data=trainData, ntree=100, proximity=T)
+model
+
+# Call:
+#  randomForest(formula = Species ~ ., data = trainData, ntree = 100,      proximity = T)
+#                Type of random forest: classification
+#                      Number of trees: 100
+# No. of variables tried at each split: 2
+
+#         OOB estimate of  error rate: 6.36%
+# Confusion matrix:
+#            setosa versicolor virginica class.error
+# setosa         36          0         0  0.00000000
+# versicolor      0         34         3  0.08108108
+# virginica       0          4        33  0.10810811
+
+# OOB: Out Of Bag
+
+table(trainData$Species, predict(model))
+importance(model) # 지니계수: 값이 높은 변수가 클래스를 분류하는데 가장 큰 영향을 줌