Dinesh Ramachandran
Load the dataset and appropriate packages
library(readxl)
library(caret)
## Loading required package: ggplot2
## Loading required package: lattice
dataset<-read_excel('labW9.xlsx', 1)
Conduct data exploration and checking and cleaning if necessary
str(dataset)
## tibble [768 x 9] (S3: tbl_df/tbl/data.frame)
## $ Pregnancies : num [1:768] 6 1 8 1 0 5 3 10 2 8 ...
## $ Glucose : num [1:768] 148 85 183 89 137 116 78 115 197 125 ...
## $ BloodPressure : num [1:768] 72 66 64 66 40 74 50 0 70 96 ...
## $ SkinThickness : num [1:768] 35 29 0 23 35 0 32 0 45 0 ...
## $ Insulin : num [1:768] 0 0 0 94 168 0 88 0 543 0 ...
## $ BMI : num [1:768] 33.6 26.6 23.3 28.1 43.1 25.6 31 35.3 30.5 0 ...
## $ DiabetesPedigreeFunction: num [1:768] 0.627 0.351 0.672 0.167 2.288 ...
## $ Age : num [1:768] 50 31 32 21 33 30 26 29 53 54 ...
## $ Outcome : num [1:768] 1 0 1 0 1 0 1 0 1 1 ...
summary(dataset)
## Pregnancies Glucose BloodPressure SkinThickness
## Min. : 0.000 Min. : 0.0 Min. : 0.00 Min. : 0.00
## 1st Qu.: 1.000 1st Qu.: 99.0 1st Qu.: 62.00 1st Qu.: 0.00
## Median : 3.000 Median :117.0 Median : 72.00 Median :23.00
## Mean : 3.845 Mean :120.9 Mean : 69.11 Mean :20.54
## 3rd Qu.: 6.000 3rd Qu.:140.2 3rd Qu.: 80.00 3rd Qu.:32.00
## Max. :17.000 Max. :199.0 Max. :122.00 Max. :99.00
## Insulin BMI DiabetesPedigreeFunction Age
## Min. : 0.0 Min. : 0.00 Min. :0.0780 Min. :21.00
## 1st Qu.: 0.0 1st Qu.:27.30 1st Qu.:0.2437 1st Qu.:24.00
## Median : 30.5 Median :32.00 Median :0.3725 Median :29.00
## Mean : 79.8 Mean :31.99 Mean :0.4719 Mean :33.24
## 3rd Qu.:127.2 3rd Qu.:36.60 3rd Qu.:0.6262 3rd Qu.:41.00
## Max. :846.0 Max. :67.10 Max. :2.4200 Max. :81.00
## Outcome
## Min. :0.000
## 1st Qu.:0.000
## Median :0.000
## Mean :0.349
## 3rd Qu.:1.000
## Max. :1.000
dim(dataset)
## [1] 768 9
colSums(is.na(dataset))
## Pregnancies Glucose BloodPressure
## 0 0 0
## SkinThickness Insulin BMI
## 0 0 0
## DiabetesPedigreeFunction Age Outcome
## 0 0 0
dataset$Outcome <- as.factor(dataset$Outcome)
Partition data 70/30 check both training and test subsets
split = 0.70
trainIndex <- createDataPartition(dataset$Outcome, p=split, list=FALSE)
data_train <- dataset[trainIndex,]
data_test <- dataset[-trainIndex,]
dim(data_train)
## [1] 538 9
dim(data_test)
## [1] 230 9
Check for cross validation if the model allows for it
train_cont <- trainControl(method = "cv", number = 7)
Train the model
model <- train(Outcome~., data = data_train, trControl = train_cont, method = "knn")
model
## k-Nearest Neighbors
##
## 538 samples
## 8 predictor
## 2 classes: '0', '1'
##
## No pre-processing
## Resampling: Cross-Validated (7 fold)
## Summary of sample sizes: 461, 461, 461, 462, 461, 461, ...
## Resampling results across tuning parameters:
##
## k Accuracy Kappa
## 5 0.7174836 0.3575802
## 7 0.7434577 0.4172214
## 9 0.7546138 0.4404962
##
## Accuracy was used to select the optimal model using the largest value.
## The final value used for the model was k = 9.
Plot model
plot(model)
Predit using your test data onto your model
pred <- predict(model, data_test)
pred
## [1] 0 1 0 0 1 1 0 0 0 1 1 0 0 0 1 0 0 0 0 0 0 0 0 1 0 0 0 1 0 0 0 0 0 0 0 0 0
## [38] 0 0 1 0 0 0 0 0 1 0 0 0 1 1 0 0 0 0 0 0 0 1 1 0 0 1 1 0 0 0 1 1 0 0 1 0 0
## [75] 0 0 1 0 0 0 0 1 1 0 0 1 0 0 0 0 0 0 1 0 1 0 1 0 0 0 0 1 0 0 0 0 0 0 0 1 0
## [112] 0 0 0 1 1 0 1 0 0 0 1 0 0 0 0 1 1 1 1 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 1
## [149] 0 0 0 0 0 0 0 0 1 1 1 1 1 0 0 0 0 0 0 1 0 0 0 1 0 0 0 0 1 1 1 0 0 0 1 0 1
## [186] 1 0 1 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 1 0 0 0 1 0 0 0 0 0 1 1 1 1 0 0 1 0 0
## [223] 0 0 0 0 1 0 0 0
## Levels: 0 1
Evaluating outcome
confusionMatrix(pred, data_test$Outcome)
## Confusion Matrix and Statistics
##
## Reference
## Prediction 0 1
## 0 129 40
## 1 21 40
##
## Accuracy : 0.7348
## 95% CI : (0.6728, 0.7906)
## No Information Rate : 0.6522
## P-Value [Acc > NIR] : 0.004551
##
## Kappa : 0.3811
##
## Mcnemar's Test P-Value : 0.021185
##
## Sensitivity : 0.8600
## Specificity : 0.5000
## Pos Pred Value : 0.7633
## Neg Pred Value : 0.6557
## Prevalence : 0.6522
## Detection Rate : 0.5609
## Detection Prevalence : 0.7348
## Balanced Accuracy : 0.6800
##
## 'Positive' Class : 0
##