Week2ML
Lisa Szydziak
3/3/2022
#install.packages("caret")
#install.packages("caret", dependencies=c("Depends", "Suggests"))
library(caret)## Loading required package: ggplot2## Loading required package: lattice# attach the iris dataset to the environment
data(iris)
# rename the dataset
dataset <- iris
# define the filename-manual procedure
#filename <- "iris.csv"
# load the CSV file from the local directory
#dataset <- read.csv(filename, header=FALSE)
# set the column names in the dataset
colnames(dataset) <- c("Sepal.Length","Sepal.Width","Petal.Length","Petal.Width","Species")
#validation_index
# create a list of 80% of the rows in the original dataset we can use for training
validation_index <- createDataPartition(dataset$Species, p=0.80, list=FALSE)
# select 20% of the data for validation
validation <- dataset[-validation_index,]
# use the remaining 80% of data to training and testing the models
dataset <- dataset[validation_index,]
# dimensions of dataset
dim(dataset)## [1] 120 5# take a peek at the first 5 rows of the data
head(dataset)## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 2 4.9 3.0 1.4 0.2 setosa
## 3 4.7 3.2 1.3 0.2 setosa
## 4 4.6 3.1 1.5 0.2 setosa
## 5 5.0 3.6 1.4 0.2 setosa
## 6 5.4 3.9 1.7 0.4 setosa
## 7 4.6 3.4 1.4 0.3 setosa# list the levels for the class
levels(dataset$Species)## [1] "setosa" "versicolor" "virginica"# summarize the class distribution
percentage <- prop.table(table(dataset$Species)) * 100
cbind(freq=table(dataset$Species), percentage=percentage)## freq percentage
## setosa 40 33.33333
## versicolor 40 33.33333
## virginica 40 33.33333# summarize attribute distributions
summary(dataset)## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## Min. :4.30 Min. :2.000 Min. :1.000 Min. :0.100 setosa :40
## 1st Qu.:5.10 1st Qu.:2.800 1st Qu.:1.600 1st Qu.:0.300 versicolor:40
## Median :5.80 Median :3.000 Median :4.250 Median :1.300 virginica :40
## Mean :5.81 Mean :3.058 Mean :3.729 Mean :1.189
## 3rd Qu.:6.40 3rd Qu.:3.225 3rd Qu.:5.100 3rd Qu.:1.800
## Max. :7.90 Max. :4.400 Max. :6.700 Max. :2.500# split input and output
x <- dataset[,1:4]
y <- dataset[,5]
# boxplot for each attribute on one image
par(mfrow=c(1,4))
for(i in 1:4) {
boxplot(x[,i], main=names(iris)[i])
}
# barplot for class breakdown
plot(y)
# scatterplot matrix
featurePlot(x=x, y=y, plot="ellipse")
# box and whisker plots for each attribute
featurePlot(x=x, y=y, plot="box")
# density plots for each attribute by class value
scales <- list(x=list(relation="free"), y=list(relation="free"))
featurePlot(x=x, y=y, plot="density", scales=scales)
# Run algorithms using 10-fold cross validation
control <- trainControl(method="cv", number=10)
metric <- "Accuracy"
# a) linear algorithms
set.seed(7)
fit.lda <- train(Species~., data=dataset, method="lda", metric=metric, trControl=control)
# b) nonlinear algorithms
# CART
set.seed(7)
fit.cart <- train(Species~., data=dataset, method="rpart", metric=metric, trControl=control)
# kNN
set.seed(7)
fit.knn <- train(Species~., data=dataset, method="knn", metric=metric, trControl=control)
# c) advanced algorithms
# SVM
set.seed(7)
fit.svm <- train(Species~., data=dataset, method="svmRadial", metric=metric, trControl=control)
# Random Forest
set.seed(7)
fit.rf <- train(Species~., data=dataset, method="rf", metric=metric, trControl=control)
#Â summarize accuracy of models
results <- resamples(list(lda=fit.lda, cart=fit.cart, knn=fit.knn, svm=fit.svm, rf=fit.rf))
summary(results)##
## Call:
## summary.resamples(object = results)
##
## Models: lda, cart, knn, svm, rf
## Number of resamples: 10
##
## Accuracy
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## lda 0.8333333 1.0000000 1.0000000 0.9750000 1.0000000 1 0
## cart 0.8333333 0.9166667 0.9166667 0.9166667 0.9166667 1 0
## knn 0.9166667 0.9166667 1.0000000 0.9666667 1.0000000 1 0
## svm 0.8333333 0.9166667 0.9583333 0.9500000 1.0000000 1 0
## rf 0.8333333 0.9166667 0.9583333 0.9500000 1.0000000 1 0
##
## Kappa
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## lda 0.750 1.000 1.0000 0.9625 1.000 1 0
## cart 0.750 0.875 0.8750 0.8750 0.875 1 0
## knn 0.875 0.875 1.0000 0.9500 1.000 1 0
## svm 0.750 0.875 0.9375 0.9250 1.000 1 0
## rf 0.750 0.875 0.9375 0.9250 1.000 1 0# compare accuracy of models
dotplot(results)
# summarize Best Model
print(fit.lda)## Linear Discriminant Analysis
##
## 120 samples
## 4 predictor
## 3 classes: 'setosa', 'versicolor', 'virginica'
##
## No pre-processing
## Resampling: Cross-Validated (10 fold)
## Summary of sample sizes: 108, 108, 108, 108, 108, 108, ...
## Resampling results:
##
## Accuracy Kappa
## 0.975 0.9625# estimate skill of LDA on the validation dataset
predictions <- predict(fit.lda, validation)
confusionMatrix(predictions, validation$Species)## Confusion Matrix and Statistics
##
## Reference
## Prediction setosa versicolor virginica
## setosa 10 0 0
## versicolor 0 10 0
## virginica 0 0 10
##
## Overall Statistics
##
## Accuracy : 1
## 95% CI : (0.8843, 1)
## No Information Rate : 0.3333
## P-Value [Acc > NIR] : 4.857e-15
##
## Kappa : 1
##
## Mcnemar's Test P-Value : NA
##
## Statistics by Class:
##
## Class: setosa Class: versicolor Class: virginica
## Sensitivity 1.0000 1.0000 1.0000
## Specificity 1.0000 1.0000 1.0000
## Pos Pred Value 1.0000 1.0000 1.0000
## Neg Pred Value 1.0000 1.0000 1.0000
## Prevalence 0.3333 0.3333 0.3333
## Detection Rate 0.3333 0.3333 0.3333
## Detection Prevalence 0.3333 0.3333 0.3333
## Balanced Accuracy 1.0000 1.0000 1.0000
#install.packages(“caret”)
#install.packages(“caret”, dependencies=c(“Depends”, “Suggests”))
library(caret)
attach the iris dataset to the environment
data(iris) # rename the dataset dataset <- iris
define the filename-manual procedure
#filename <- “iris.csv” # load the CSV file from the local directory #dataset <- read.csv(filename, header=FALSE)
set the column names in the dataset
colnames(dataset) <- c(“Sepal.Length”,“Sepal.Width”,“Petal.Length”,“Petal.Width”,“Species”) validation_index # create a list of 80% of the rows in the original dataset we can use for training validation_index <- createDataPartition(dataset$Species, p=0.80, list=FALSE) # select 20% of the data for validation validation <- dataset[-validation_index,] # use the remaining 80% of data to training and testing the models dataset <- dataset[validation_index,]
dimensions of dataset
dim(dataset)
take a peek at the first 5 rows of the data
head(dataset)
list the levels for the class
levels(dataset$Species)
summarize the class distribution
percentage <- prop.table(table(dataset\(Species)) * 100 cbind(freq=table(dataset\)Species), percentage=percentage)
summarize attribute distributions
summary(dataset)
split input and output
x <- dataset[,1:4] y <- dataset[,5]
boxplot for each attribute on one image
par(mfrow=c(1,4)) for(i in 1:4) { boxplot(x[,i], main=names(iris)[i]) }
barplot for class breakdown
plot(y)
scatterplot matrix
featurePlot(x=x, y=y, plot=“ellipse”)
box and whisker plots for each attribute
featurePlot(x=x, y=y, plot=“box”)
density plots for each attribute by class value
scales <- list(x=list(relation=“free”), y=list(relation=“free”)) featurePlot(x=x, y=y, plot=“density”, scales=scales)
Run algorithms using 10-fold cross validation
control <- trainControl(method=“cv”, number=10) metric <- “Accuracy”
a) linear algorithms
set.seed(7) fit.lda <- train(Species~., data=dataset, method=“lda”, metric=metric, trControl=control) # b) nonlinear algorithms # CART set.seed(7) fit.cart <- train(Species~., data=dataset, method=“rpart”, metric=metric, trControl=control) # kNN set.seed(7) fit.knn <- train(Species~., data=dataset, method=“knn”, metric=metric, trControl=control) # c) advanced algorithms # SVM set.seed(7) fit.svm <- train(Species~., data=dataset, method=“svmRadial”, metric=metric, trControl=control) # Random Forest set.seed(7) fit.rf <- train(Species~., data=dataset, method=“rf”, metric=metric, trControl=control)
#Â summarize accuracy of models results <- resamples(list(lda=fit.lda, cart=fit.cart, knn=fit.knn, svm=fit.svm, rf=fit.rf)) summary(results)
compare accuracy of models
dotplot(results)
summarize Best Model
print(fit.lda)
estimate skill of LDA on the validation dataset
predictions <- predict(fit.lda, validation) confusionMatrix(predictions, validation$Species) ## R Markdown
This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
summary(cars)## speed dist
## Min. : 4.0 Min. : 2.00
## 1st Qu.:12.0 1st Qu.: 26.00
## Median :15.0 Median : 36.00
## Mean :15.4 Mean : 42.98
## 3rd Qu.:19.0 3rd Qu.: 56.00
## Max. :25.0 Max. :120.00Including Plots
You can also embed plots, for example:
Note that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot.