comparison accuracy.R @ 0:4547b5a5169d draft

Uploaded
author testtool
date Fri, 13 Oct 2017 10:09:29 -0400
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:4547b5a5169d
1 require(caret, quietly = TRUE)
2
3 args <- commandArgs(trailingOnly = TRUE)
4
5 input = args[1]
6 p = args[2]
7 output1 = args[3]
8 output2 = args[4]
9
10 dataset <- read.csv(input, header=TRUE)
11
12 validation_index <- createDataPartition(dataset$Species, p=p, list=FALSE)
13
14 validation <- dataset[-validation_index,]
15
16 validdataset <- dataset[validation_index,]
17
18 percentage <- prop.table(table(validdataset$Species)) * 100
19 cbind(freq=table(validdataset$Species), percentage=percentage)
20
21 output_summary <- summary(validdataset)
22 write.csv(output_summary,output1)
23
24 control <- trainControl(method="cv", number=10)
25 metric <- "Accuracy"
26
27 # a) linear algorithms
28 set.seed(7)
29 fit.lda <- train(Species~., data=validdataset, method="lda", metric=metric, trControl=control)
30 # b) nonlinear algorithms
31 # CART
32 set.seed(7)
33 fit.cart <- train(Species~., data=validdataset, method="rpart", metric=metric, trControl=control)
34 # kNN
35 set.seed(7)
36 fit.knn <- train(Species~., data=validdataset, method="knn", metric=metric, trControl=control)
37 # c) advanced algorithms
38 # SVM
39 set.seed(7)
40 fit.svm <- train(Species~., data=validdataset, method="svmRadial", metric=metric, trControl=control)
41 # Random Forest
42 set.seed(7)
43 fit.rf <- train(Species~., data=validdataset, method="rf", metric=metric, trControl=control)
44
45 results <- resamples(list(lda=fit.lda, cart=fit.cart, knn=fit.knn, svm=fit.svm, rf=fit.rf))
46 output_results <- summary(results)
47
48 write.csv(as.matrix(output_results),output2)