실기 277
read.delim("titanic3.txt",header=TRUE,sep=',')->full
full %>% glimpse
set.seed(1357)
idx<-createDataPartition(y=full$survived,p=0.7,list=FALSE)
train<-full[idx,]
test<-full[-idx,]
train %>% mutate(index="train")->df_train
test %>% mutate(index="test")->df_test
bind_rows(df_train,df_test)->data
data %>% select(-boat,-body,-home.dest)->data
data %>% glimpse
data$survived<-ifelse(data$survived==0,"생존","사망")
data$survived<-as.factor(data$survived)
data$sex<-as.factor(data$sex)
data$pclass<-as.factor(data$pclass)
data$embarked<-as.factor(data$embarked)
colSums(is.na(data))
table(data$embarked)
levels(data$embarked)[1]<-NA
table(data$embarked,useNA="always")
data %>% filter(!is.na(age)&!is.na(embarked)&!is.na(fare))->data
colSums(is.na(data))
data %>% glimpse
recipe(survived~.,data=data) %>%
step_YeoJohnson(age,sibsp,fare,parch) %>%
step_center(age,sibsp,fare,parch) %>%
step_scale(age,sibsp,fare,parch) %>% prep() %>% juice()->data1
data1 %>% filter(index=="train") %>% dplyr::select(-index,-name,-ticket,-cabin)->train
data1 %>% filter(index=="test") %>% dplyr::select(-index,-name,-ticket,-cabin)->test
ctrl<-trainControl(method="cv",summaryFunction=twoClassSummary,
classProbs=TRUE)
train(survived~.,data=train,
method="rpart",metric="ROC",
trControl=ctrl)->rpfit
rpfit
confusionMatrix(rpfit)
predict(rpfit,data=test,type="prob")->predfit2
head(predfit2)
predict(rpfit,data=test,type="raw")->predfit3
head(predfit3)
confusionMatrix(predfit3,test$survived) 이렇게 했는데 갑자기 이런 코드가 뜨네요 모든인자들이 같은 길이를 가져야한다는데 중간에 갑자기 다른길이를 갖는이유가 뭐가있나요?
Error in table(data, reference, dnn = dnn, ...) :
댓글
안녕하세요 답변 드립니다.
타켓변수(목표변수) 모두 factor 인지 확인해주세요
댓글을 남기려면 로그인하세요.