1 개요[ | ]
- R 분류 모형 비교, R 분류 모델 비교
- R 이진분류 모형 비교, R 이진분류 모델 비교
2 에시 1[ | ]
set.seed(42) # 랜덤값 고정
#### 데이터 준비
df = read.csv("https://stats.idre.ucla.edu/stat/data/binary.csv")
df$y = df$admit
df$admit = NULL
# 데이터 분할
library(caret)
idx = createDataPartition(df$y, p=0.5, list=F)
Train = df[ idx,]
Test = df[-idx,]
# 모델 적합
library(rpart)
library(xgboost)
library(neuralnet)
library(randomForest, warn.conflicts=F)
x_columns = c("gre","gpa","rank")
formula = as.formula("y ~ gre + gpa + rank")
Train_forest = Train
Train_forest$y = as.factor(as.character(Train$y))
Train_xgboost = as.matrix(Train[,names(df) %in% x_columns])
model_tree = rpart (formula, Train)
model_forest = randomForest(formula, Train_forest)
model_xgboost = xgboost (data=Train_xgboost, label=Train$y, nround=2, verbose=0, objective="binary:logistic")
model_logistic = glm (formula, Train, family="binomial")
model_neuralnet = neuralnet (formula, Train, hidden=2)
#### 모델 평가 1 - ROC 곡선
library(ROCR, warn.conflicts=F)
Test_xgboost = as.matrix(Test[,names(df) %in% x_columns])
Test_neuralnet = Test[,names(df) %in% x_columns]
TestResult = Test
TestResult$pred_tree = predict(model_tree , Test)
TestResult$pred_forest = predict(model_forest , Test, type="prob")[,2]
TestResult$pred_xgboost = predict(model_xgboost , Test_xgboost)
TestResult$pred_logistic = predict(model_logistic , Test)
TestResult$pred_neuralnet = predict(model_neuralnet, Test)
pred_tree = prediction( TestResult$pred_tree , Test$y )
pred_forest = prediction( TestResult$pred_forest , Test$y )
pred_xgboost = prediction( TestResult$pred_xgboost , Test$y )
pred_logistic = prediction( TestResult$pred_logistic , Test$y )
pred_neuralnet = prediction( TestResult$pred_neuralnet, Test$y )
perf_tree = performance(pred_tree , "tpr", "fpr")
perf_forest = performance(pred_forest , "tpr", "fpr")
perf_xgboost = performance(pred_xgboost , "tpr", "fpr")
perf_logistic = performance(pred_logistic , "tpr", "fpr")
perf_neuralnet = performance(pred_neuralnet, "tpr", "fpr")
methods = c("tree" , "forest", "xgboost", "logistic", "neuralnet")
colors = c("black", "green" , "blue" , "orange" , "red" )
plot(perf_tree , lwd=2, add=F, col=colors[1])
plot(perf_forest , lwd=2, add=T, col=colors[2])
plot(perf_xgboost , lwd=2, add=T, col=colors[3])
plot(perf_logistic , lwd=2, add=T, col=colors[4])
plot(perf_neuralnet, lwd=2, add=T, col=colors[5])
title("ROC curve")
legend("bottomright", methods, lwd=2, col=colors)
#### 모델 평가 2 - Confusion Matrix
# cutoff 0.5로 판정
TestResult$y_tree = ifelse(TestResult$pred_tree >0.5, 1, 0)
TestResult$y_forest = ifelse(TestResult$pred_forest >0.5, 1, 0)
TestResult$y_xgboost = ifelse(TestResult$pred_xgboost >0.5, 1, 0)
TestResult$y_logistic = ifelse(TestResult$pred_logistic >0.5, 1, 0)
TestResult$y_neuralnet = ifelse(TestResult$pred_neuralnet>0.5, 1, 0)
cat( "분류표" )
table(TestResult$y_tree , Test$y)
table(TestResult$y_forest , Test$y)
table(TestResult$y_xgboost , Test$y)
table(TestResult$y_logistic , Test$y)
table(TestResult$y_neuralnet, Test$y)
#### 모델 평가 3 - 각종 지표
evaluation = data.frame(Name=c("tree","forest","xgboost","logistic","neuralnet"))
# Accuracy 계산
evaluation$Accuracy = c(
sum(TestResult$y_tree ==Test$y)/nrow(Test),
sum(TestResult$y_forest ==Test$y)/nrow(Test),
sum(TestResult$y_xgboost ==Test$y)/nrow(Test),
sum(TestResult$y_logistic ==Test$y)/nrow(Test),
sum(TestResult$y_neuralnet==Test$y)/nrow(Test)
)
# Precision 계산
evaluation$Precision = c(
sum(TestResult$y_tree ==T & Test$y==T)/sum(TestResult$y_tree ==T),
sum(TestResult$y_forest ==T & Test$y==T)/sum(TestResult$y_forest ==T),
sum(TestResult$y_xgboost ==T & Test$y==T)/sum(TestResult$y_xgboost ==T),
sum(TestResult$y_logistic ==T & Test$y==T)/sum(TestResult$y_logistic ==T),
sum(TestResult$y_neuralnet==T & Test$y==T)/sum(TestResult$y_neuralnet==T)
)
# Recall 계산
evaluation$Recall = c(
sum(TestResult$y_tree ==T & Test$y==T)/sum(Test$y==T),
sum(TestResult$y_forest ==T & Test$y==T)/sum(Test$y==T),
sum(TestResult$y_xgboost ==T & Test$y==T)/sum(Test$y==T),
sum(TestResult$y_logistic ==T & Test$y==T)/sum(Test$y==T),
sum(TestResult$y_neuralnet==T & Test$y==T)/sum(Test$y==T)
)
# F1 Score 계산
evaluation$F1_Score = 2 * evaluation$Precision * evaluation$Recall / ( evaluation$Precision + evaluation$Recall )
cat( "\n평가지표\n" )
print( evaluation )
3 예시 2[ | ]
library(caret) # createDataPartition()
library(hash) # hash()
library(e1071) # svm()
library(rpart) # rpart()
library(xgboost) # xgboost()
library(neuralnet) # neuralnet()
library(randomForest) # randomForest()
library(ROCR) # performance()
set.seed(42) # 랜덤값 고정
#### 데이터 준비
df = read.csv("https://stats.idre.ucla.edu/stat/data/binary.csv")
df$y = df$admit
df$admit = NULL
# 데이터 분할
idx = createDataPartition(df$y, p=0.5, list=F)
Train = df[ idx,]
Test = df[-idx,]
# 모델 적합
x_columns = c("gre","gpa","rank")
formula = as.formula("y ~ gre + gpa + rank")
Train_forest = Train
Train_forest$y = as.factor(as.character(Train$y))
Train_xgboost = as.matrix(Train[,names(df) %in% x_columns])
Test_xgboost = as.matrix(Test[,names(df) %in% x_columns])
Test_neuralnet = Test[,names(df) %in% x_columns]
names = c("svm","tree","forest","xgboost","logistic","neuralnet")
lst = list()
for(i in 1:length(names)) {
lst[[i]] = hash(name=names[i])
}
lst[[1]]$model = svm (formula, Train)
lst[[2]]$model = rpart (formula, Train)
lst[[3]]$model = randomForest(formula, Train_forest)
lst[[4]]$model = xgboost (data=Train_xgboost, label=Train$y, nround=2, verbose=0, objective="binary:logistic")
lst[[5]]$model = glm (formula, Train, family="binomial")
lst[[6]]$model = neuralnet (formula, Train, hidden=2)
lst[[1]]$predict = predict(lst[[1]]$model, Test)
lst[[2]]$predict = predict(lst[[2]]$model, Test)
lst[[3]]$predict = predict(lst[[3]]$model, Test, type="prob")[,2]
lst[[4]]$predict = predict(lst[[4]]$model, Test_xgboost)
lst[[5]]$predict = predict(lst[[5]]$model, Test)
lst[[6]]$predict = predict(lst[[6]]$model, Test)
for (i in 1:length(names)) {
lst[[i]]$predictedY = ifelse(lst[[i]]$predict>.5, 1, 0)
lst[[i]]$performance = performance(prediction(lst[[i]]$predict, Test$y), "tpr", "fpr")
lst[[i]]$confusionMatrix = confusionMatrix(factor(lst[[i]]$predictedY), factor(Test$y), positive='1')
}
## 모델 평가표
evaluation = data.frame(Name=names)
evaluation$Accuracy = sapply(lst, function(x){x$confusionMatrix$overall['Accuracy']})
evaluation$Sensitivity = sapply(lst, function(x){x$confusionMatrix$byClass['Sensitivity']})
evaluation$Specificity = sapply(lst, function(x){x$confusionMatrix$byClass['Specificity']})
evaluation$Precision = sapply(lst, function(x){x$confusionMatrix$byClass['Precision']})
evaluation
## ROC 곡선
colors = c("black", "green", "blue", "orange", "red", "gray")
for (i in 1:length(names)) {
plot(lst[[i]]$performance, lwd=2, add=(i!=1), col=colors[i])
}
title("ROC curve")
legend("bottomright", legend=names, lwd=2, col=colors)
4 예시 3[ | ]
library(caret) # createDataPartition()
library(hash) # hash()
library(rpart) # rpart()
library(randomForest) # randomForest()
library(e1071) # svm()
set.seed(42) # 랜덤값 고정
# 데이터 준비
df <- read.csv("https://stats.idre.ucla.edu/stat/data/binary.csv")
df$y <- df$admit
df$admit <- NULL
# 데이터 분할
idx <- createDataPartition(df$y, p=.5, list=F)
Train <- df[ idx,]
Test <- df[-idx,]
# 리스트 생성
names <- c("logistic","tree","forest","svm")
lst <- list()
for(i in 1:length(names)) { lst[[i]] <- hash() }
# 모델 적합
lst[[1]]$model <- glm (y ~ ., Train, family="binomial")
lst[[2]]$model <- rpart (y ~ ., Train)
lst[[3]]$model <- randomForest(y ~ ., Train)
lst[[4]]$model <- svm (y ~ ., Train)
# 예측값 구하기
lst[[1]]$predictedY <- ifelse(predict(lst[[1]]$model, Test) > .5, 1, 0)
lst[[2]]$predictedY <- ifelse(predict(lst[[2]]$model, Test) > .5, 1, 0)
lst[[3]]$predictedY <- ifelse(predict(lst[[3]]$model, Test, type="response") > .5, 1, 0)
lst[[4]]$predictedY <- ifelse(predict(lst[[4]]$model, Test) > .5, 1, 0)
# 혼동행렬 구하기
for(i in 1:length(names)) { lst[[i]]$confusionMatrix = confusionMatrix(factor(lst[[i]]$predictedY), factor(Test$y), positive='1') }
# 모델 평가표 작성
evaluation <- data.frame(Name=names)
evaluation$Accuracy <- sapply(lst, function(x){x$confusionMatrix$overall['Accuracy']})
evaluation$Sensitivity <- sapply(lst, function(x){x$confusionMatrix$byClass['Sensitivity']})
evaluation$Specificity <- sapply(lst, function(x){x$confusionMatrix$byClass['Specificity']})
evaluation$Precision <- sapply(lst, function(x){x$confusionMatrix$byClass['Precision']})
evaluation
5 같이 보기[ | ]
