Attribute Information:
PimaIndiansDiabetes.pca <- princomp(PimaIndiansDiabetes[,1:(length(PimaIndiansDiabetes)-1)],
center = TRUE,
scale. = TRUE)## Warning: In princomp.default(PimaIndiansDiabetes[, 1:(length(PimaIndiansDiabetes) -
## 1)], center = TRUE, scale. = TRUE) :
## extra arguments 'center', 'scale.' will be disregardedView(PimaIndiansDiabetes.pca$scores)
target.numeric <- ifelse (PimaIndiansDiabetes$diabetes == "neg", 0 ,1)
pca.sisense.result <- data.frame(PimaIndiansDiabetes.pca$scores[,1:2],target.numeric)
x <- pca.sisense.result$Comp.1
y <- pca.sisense.result$Comp.2
pca.sisense.result$class <- as.factor(pca.sisense.result$target.numeric)
ggplot(pca.sisense.result, aes(Comp.1, Comp.2)) +
geom_point(aes(colour = class)) 
ct <- ctree(diabetes ~ ., data = training)
svg(filename="Diabites_Decision_Tree.svg",
width=12,
height=10,
pointsize=12)
plot(as.simpleparty(ct))
dev.off()## png
## 2## Predict Diabites Risk on new patients
predictions.probs <- predict(ct, testing,type = c("prob"))
predictions.class <- predict(ct, testing,type = c("response"))
table(predictions.class, testing$diabetes )##
## predictions.class neg pos
## neg 122 20
## pos 28 60## confusion matrix stats on testing set
cm <- confusionMatrix(testing$diabetes, predictions.class, positive = NULL,
dnn = c("Prediction", "Reference"))
# printing confusion matrix
cm## Confusion Matrix and Statistics
##
## Reference
## Prediction neg pos
## neg 122 28
## pos 20 60
##
## Accuracy : 0.7913
## 95% CI : (0.733, 0.8419)
## No Information Rate : 0.6174
## P-Value [Acc > NIR] : 1.155e-08
##
## Kappa : 0.5505
## Mcnemar's Test P-Value : 0.3123
##
## Sensitivity : 0.8592
## Specificity : 0.6818
## Pos Pred Value : 0.8133
## Neg Pred Value : 0.7500
## Prevalence : 0.6174
## Detection Rate : 0.5304
## Detection Prevalence : 0.6522
## Balanced Accuracy : 0.7705
##
## 'Positive' Class : neg
## roc_pred <- prediction(predictions.probs[,2], testing$diabetes)
#png(filename=paste("decision_tree_roc.png"),width = 1200, height = 800)
plot(performance(roc_pred, measure="sens", x.measure="spec"), colorize=TRUE)
auc.perf = performance(roc_pred, measure = "auc")
title(unlist(auc.perf@y.values))
#dev.off()
Sisense Diabetes Widget
fit.rf <-randomForest(diabetes ~ ., data=training)
print(fit.rf)##
## Call:
## randomForest(formula = diabetes ~ ., data = training)
## Type of random forest: classification
## Number of trees: 500
## No. of variables tried at each split: 2
##
## OOB estimate of error rate: 25.84%
## Confusion matrix:
## neg pos class.error
## neg 299 51 0.1457143
## pos 88 100 0.4680851#importance(fit.rf)
rf.predictions.class <- predict(fit.rf, testing)
rf.predictions.probs <- predict(fit.rf, testing,type = c("prob"))
cm.rf <- confusionMatrix(testing$diabetes, rf.predictions.class, positive = NULL,
dnn = c("Prediction", "Reference"))
# printing confusion matrix
cm.rf## Confusion Matrix and Statistics
##
## Reference
## Prediction neg pos
## neg 134 16
## pos 30 50
##
## Accuracy : 0.8
## 95% CI : (0.7424, 0.8497)
## No Information Rate : 0.713
## P-Value [Acc > NIR] : 0.001687
##
## Kappa : 0.5404
## Mcnemar's Test P-Value : 0.055270
##
## Sensitivity : 0.8171
## Specificity : 0.7576
## Pos Pred Value : 0.8933
## Neg Pred Value : 0.6250
## Prevalence : 0.7130
## Detection Rate : 0.5826
## Detection Prevalence : 0.6522
## Balanced Accuracy : 0.7873
##
## 'Positive' Class : neg
## roc_pred.rf <- prediction(rf.predictions.probs[,2], testing$diabetes)
plot(performance(roc_pred.rf, measure="sens", x.measure="spec"), colorize=TRUE)
rf.auc.perf = performance(roc_pred.rf, measure = "auc")
title(unlist(rf.auc.perf@y.values))
- an AUC improvement of
unlist(rf.auc.perf@y.values) - unlist(auc.perf@y.values)## [1] 0.01833333NOT BAD !