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:

library(mlbench)
library(caret)
## Loading required package: ggplot2
## Loading required package: lattice
data(PimaIndiansDiabetes)
View(PimaIndiansDiabetes)
#Prepare training scheme
trainControl <- trainControl(method='repeatedcv', number=10, repeats=3)

#CART
set.seed(7)
fit.cart <- train(diabetes~., data=PimaIndiansDiabetes, method='rpart', trControl=trainControl)

# LDA
set.seed(7)
fit.lda <- train(diabetes~., data=PimaIndiansDiabetes, method='lda', trControl=trainControl)

# SVM
set.seed(7)
fit.svm <- train(diabetes~., data=PimaIndiansDiabetes, method='svmRadial', trControl=trainControl)

# KNN
set.seed(7)
fit.knn <- train(diabetes~., data=PimaIndiansDiabetes, method='knn', trControl=trainControl)

# Random Forest
set.seed(7)
fit.rf <- train(diabetes~., data=PimaIndiansDiabetes, method='rf', trControl=trainControl)

# Collect resamples



results <- resamples(list(CART=fit.cart, LDA=fit.lda, SVM=fit.svm, KNN=fit.knn, RF=fit.rf))
summary(results)
## 
## Call:
## summary.resamples(object = results)
## 
## Models: CART, LDA, SVM, KNN, RF 
## Number of resamples: 30 
## 
## Accuracy 
##           Min.   1st Qu.    Median      Mean   3rd Qu.      Max. NA's
## CART 0.6753247 0.7272727 0.7532468 0.7469697 0.7662338 0.7922078    0
## LDA  0.7142857 0.7508117 0.7662338 0.7791069 0.8000256 0.9078947    0
## SVM  0.7236842 0.7508117 0.7631579 0.7712919 0.7915243 0.8947368    0
## KNN  0.6753247 0.7036056 0.7272727 0.7369503 0.7662338 0.8311688    0
## RF   0.6842105 0.7305195 0.7662338 0.7638528 0.8019481 0.8421053    0
## 
## Kappa 
##           Min.   1st Qu.    Median      Mean   3rd Qu.      Max. NA's
## CART 0.2762566 0.3620724 0.4241878 0.4151867 0.4861107 0.5250000    0
## LDA  0.3011551 0.4192537 0.4662541 0.4862025 0.5308596 0.7812500    0
## SVM  0.3391908 0.3997116 0.4460612 0.4621585 0.5234605 0.7475083    0
## KNN  0.2553191 0.3406000 0.3841761 0.3984995 0.4539789 0.6195363    0
## RF   0.2951613 0.3682680 0.4685583 0.4620226 0.5447483 0.6426332    0
# box and whisker plots to compare models
scales <- list(x = list(relation='free'),  y = list(relation='free'))
bwplot(results, scales=scales)

# density plots of accuracy
scales <- list(x = list(relation='free'), y = list(relation='free'))
densityplot(results, scales=scales, pch = '|')

# dot  plots of accuracy
scales <- list(x = list(relation='free'), y = list(relation='free'))
dotplot(results, scales=scales)

# pairwise scatter plots of predictions to compare models   
splom(results)

# difference in model predictions      
diffs <- diff(results)
# summarize p-values for pairwise comparisons
summary(diffs)
## 
## Call:
## summary.diff.resamples(object = diffs)
## 
## p-value adjustment: bonferroni 
## Upper diagonal: estimates of the difference
## Lower diagonal: p-value for H0: difference = 0
## 
## Accuracy 
##      CART      LDA       SVM       KNN       RF       
## CART           -0.032137 -0.024322  0.010019 -0.016883
## LDA  0.0011862            0.007815  0.042157  0.015254
## SVM  0.0116401 0.9156892            0.034342  0.007439
## KNN  1.0000000 6.68e-05  0.0002941           -0.026902
## RF   0.2521949 0.3914281 1.0000000 0.0101387          
## 
## Kappa 
##      CART      LDA        SVM        KNN        RF        
## CART           -0.0710158 -0.0469717  0.0166872 -0.0468359
## LDA  0.0008086             0.0240440  0.0877029  0.0241799
## SVM  0.0258079 0.3562734              0.0636589  0.0001359
## KNN  1.0000000 0.0003858  0.0040823             -0.0635230
## RF   0.0250500 1.0000000  1.0000000  0.0099222
# Run algorithms using 10-fold cross-validation
trainControl <- trainControl(method='cv', number=10)
metric <-  'Accuracy'


# compare accuracy of models
dotplot(results)

# summarize Best Model
print(fit.lda)
## Linear Discriminant Analysis 
## 
## 768 samples
##   8 predictor
##   2 classes: 'neg', 'pos' 
## 
## No pre-processing
## Resampling: Cross-Validated (10 fold, repeated 3 times) 
## Summary of sample sizes: 691, 691, 691, 691, 691, 691, ... 
## Resampling results:
## 
##   Accuracy   Kappa    
##   0.7791069  0.4862025
# estimate skill of LDA on the validation dataset
predictions <- predict(fit.lda, PimaIndiansDiabetes)
confusionMatrix(predictions, PimaIndiansDiabetes$diabetes)
## Confusion Matrix and Statistics
## 
##           Reference
## Prediction neg pos
##        neg 446 112
##        pos  54 156
##                                          
##                Accuracy : 0.7839         
##                  95% CI : (0.753, 0.8125)
##     No Information Rate : 0.651          
##     P-Value [Acc > NIR] : 7.051e-16      
##                                          
##                   Kappa : 0.4992         
##                                          
##  Mcnemar's Test P-Value : 9.686e-06      
##                                          
##             Sensitivity : 0.8920         
##             Specificity : 0.5821         
##          Pos Pred Value : 0.7993         
##          Neg Pred Value : 0.7429         
##              Prevalence : 0.6510         
##          Detection Rate : 0.5807         
##    Detection Prevalence : 0.7266         
##       Balanced Accuracy : 0.7370         
##                                          
##        'Positive' Class : neg            
##

Including 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.