101 lines
2.7 KiB
Plaintext
101 lines
2.7 KiB
Plaintext
|
---
|
||
|
|
title: "predictive_model"
|
||
|
|
output: pdf_document
|
||
|
|
---
|
||
|
|
|
||
|
|
```{r setup, include=FALSE}
|
||
|
|
knitr::opts_chunk$set(echo = TRUE)
|
||
|
|
```
|
||
|
|
|
||
|
|
# Data
|
||
|
|
```{r}
|
||
|
|
library(caret)
|
||
|
|
library(pROC)
|
||
|
|
library(daDoctoR)
|
||
|
|
```
|
||
|
|
|
||
|
|
Import
|
||
|
|
```{r}
|
||
|
|
trainData<-read.csv("/Users/au301842/PhysicalActivityandStrokeOutcome/data/trainData.csv",)
|
||
|
|
testData<-read.csv("/Users/au301842/PhysicalActivityandStrokeOutcome/data/testData.csv",)
|
||
|
|
```
|
||
|
|
|
||
|
|
|
||
|
|
# Prediction
|
||
|
|
Inspiration: https://stackoverflow.com/questions/30366143/how-to-compute-roc-and-auc-under-roc-after-training-using-caret-in-r and https://www.machinelearningplus.com/machine-learning/caret-package/
|
||
|
|
|
||
|
|
## Early visualisation
|
||
|
|
|
||
|
|
```{r}
|
||
|
|
featurePlot(x = trainData %>% select(!matches("pase_drop")),
|
||
|
|
y = factor(trainData$pase_drop),
|
||
|
|
plot = "box",
|
||
|
|
strip=strip.custom(par.strip.text=list(cex=.7)),
|
||
|
|
scales = list(x = list(relation="free"),
|
||
|
|
y = list(relation="free")))
|
||
|
|
|
||
|
|
featurePlot(x = trainData %>% select(!matches("pase_drop")),
|
||
|
|
y = factor(trainData$pase_drop),
|
||
|
|
plot = "density",
|
||
|
|
strip=strip.custom(par.strip.text=list(cex=.7)),
|
||
|
|
scales = list(x = list(relation="free"),
|
||
|
|
y = list(relation="free")))
|
||
|
|
```
|
||
|
|
|
||
|
|
|
||
|
|
```{r}
|
||
|
|
subsets <- c(1:10, 15, 18,33)
|
||
|
|
|
||
|
|
ctrl <- rfeControl(functions = rfFuncs,
|
||
|
|
method = "repeatedcv",
|
||
|
|
repeats = 5,
|
||
|
|
verbose = FALSE)
|
||
|
|
|
||
|
|
lmProfile <- rfe(x = trainData %>% select(!matches("pase_drop")),
|
||
|
|
y = trainData$pase_drop,
|
||
|
|
sizes = subsets,
|
||
|
|
rfeControl = ctrl)
|
||
|
|
|
||
|
|
lmProfile
|
||
|
|
```
|
||
|
|
|
||
|
|
|
||
|
|
```{r}
|
||
|
|
set.seed(1000)
|
||
|
|
|
||
|
|
forest.model <- train(pase_drop ~., trainData)
|
||
|
|
|
||
|
|
result.predicted.prob <- predict(forest.model, testData, type="prob") # Prediction
|
||
|
|
|
||
|
|
result.roc <- roc(factor(testData$pase_drop), result.predicted.prob$no) # Draw ROC curve.
|
||
|
|
|
||
|
|
plot(result.roc, print.thres="best", print.thres.best.method="closest.topleft")
|
||
|
|
|
||
|
|
result.coords <- coords(result.roc, "best", best.method="closest.topleft", ret=c("threshold", "accuracy"))
|
||
|
|
print(result.coords)#to get threshold and accuracy
|
||
|
|
```
|
||
|
|
|
||
|
|
```{r}
|
||
|
|
library(MLeval)
|
||
|
|
|
||
|
|
myTrainingControl <- trainControl(method = "cv",
|
||
|
|
number = 10,
|
||
|
|
savePredictions = TRUE,
|
||
|
|
classProbs = TRUE,
|
||
|
|
verboseIter = TRUE)
|
||
|
|
|
||
|
|
randomForestFit = train(x = trainData[,1:32],
|
||
|
|
y = as.factor(trainData$pase_drop),
|
||
|
|
method = "rf",
|
||
|
|
trControl = myTrainingControl,
|
||
|
|
preProcess = c("center","scale"),
|
||
|
|
ntree = 50)
|
||
|
|
|
||
|
|
x <- evalm(randomForestFit)
|
||
|
|
|
||
|
|
x$roc
|
||
|
|
|
||
|
|
x$stdres
|
||
|
|
```
|
||
|
|
|