Import the necessary libraries
Read the Dataset and do descriptive analysis
DF <- read_excel('/Users/salahkaf/Downloads/labW9.xlsx') #Read the excel file as a tibble
head(DF) #Shows top 6 rows
# A tibble: 6 × 9
Pregnancies Glucose BloodPressure SkinThickness Insulin BMI
<dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 6 148 72 35 0 33.6
2 1 85 66 29 0 26.6
3 8 183 64 0 0 23.3
4 1 89 66 23 94 28.1
5 0 137 40 35 168 43.1
6 5 116 74 0 0 25.6
# … with 3 more variables: DiabetesPedigreeFunction <dbl>, Age <dbl>,
# Outcome <dbl>tail(DF) #Shows last 6 rows
# A tibble: 6 × 9
Pregnancies Glucose BloodPressure SkinThickness Insulin BMI
<dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 9 89 62 0 0 22.5
2 10 101 76 48 180 32.9
3 2 122 70 27 0 36.8
4 5 121 72 23 112 26.2
5 1 126 60 0 0 30.1
6 1 93 70 31 0 30.4
# … with 3 more variables: DiabetesPedigreeFunction <dbl>, Age <dbl>,
# Outcome <dbl>dim(DF) #Shows number of columns and rows
[1] 768 9str(DF) #Presents DF structure
tibble [768 × 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(DF) #Presents DF summary
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
Min. : 0.0 Min. : 0.00 Min. :0.0780
1st Qu.: 0.0 1st Qu.:27.30 1st Qu.:0.2437
Median : 30.5 Median :32.00 Median :0.3725
Mean : 79.8 Mean :31.99 Mean :0.4719
3rd Qu.:127.2 3rd Qu.:36.60 3rd Qu.:0.6262
Max. :846.0 Max. :67.10 Max. :2.4200
Age Outcome
Min. :21.00 Min. :0.000
1st Qu.:24.00 1st Qu.:0.000
Median :29.00 Median :0.000
Mean :33.24 Mean :0.349
3rd Qu.:41.00 3rd Qu.:1.000
Max. :81.00 Max. :1.000 Checking for any missing values
# Total number of missing values in the data set:
cat("The total number of missing values in the dataset is" , sum(is.na(DF)))
The total number of missing values in the dataset is 0 Pregnancies Glucose
0 0
BloodPressure SkinThickness
0 0
Insulin BMI
0 0
DiabetesPedigreeFunction Age
0 0
Outcome
0 Changing the “outcome” column (Target value) into categorical data to apply classification
DF$Outcome<-gsub(1,"diabetic", as.character(DF$Outcome)) #Changing 1 to diabetic
DF$Outcome<-gsub(0,"Non-diabetic", as.character(DF$Outcome)) #Changing 0 to Non-diabetic
DF$Outcome <- as.factor(DF$Outcome) #Make it as a factor in order to apply classification
Checking the final form of the DF
head(DF)
# A tibble: 6 × 9
Pregnancies Glucose BloodPressure SkinThickness Insulin BMI
<dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 6 148 72 35 0 33.6
2 1 85 66 29 0 26.6
3 8 183 64 0 0 23.3
4 1 89 66 23 94 28.1
5 0 137 40 35 168 43.1
6 5 116 74 0 0 25.6
# … with 3 more variables: DiabetesPedigreeFunction <dbl>, Age <dbl>,
# Outcome <fct>Splitting the dataset into 70/30
split = 0.7
trainIndex <- createDataPartition(DF$Outcome, p = split, list = F)
data_train <- DF[trainIndex,]
data_test <- DF[-trainIndex,]
Checking the training and testing subsets
dim(data_train)
[1] 538 9dim(data_test)
[1] 230 9#### Equal number of columns (9), rows with 70% & 30% split
Apply cross validation
train_control <- trainControl(method="cv", number=10) #10 subsets
Train the data using K nearest neighbor
model <- train(Outcome~., data = data_train, trControl=train_control, method="knn")
Ploting the model
plot(model)
Predict the values of test data
predictions <- predict(model, newdata = data_test)
#Evaluate the outcome by using confusion Matrix
cm <-confusionMatrix(predictions, data_test$Outcome)
cm
Confusion Matrix and Statistics
Reference
Prediction diabetic Non-diabetic
diabetic 46 16
Non-diabetic 34 134
Accuracy : 0.7826
95% CI : (0.7236, 0.8341)
No Information Rate : 0.6522
P-Value [Acc > NIR] : 1.156e-05
Kappa : 0.4943
Mcnemar's Test P-Value : 0.01621
Sensitivity : 0.5750
Specificity : 0.8933
Pos Pred Value : 0.7419
Neg Pred Value : 0.7976
Prevalence : 0.3478
Detection Rate : 0.2000
Detection Prevalence : 0.2696
Balanced Accuracy : 0.7342
'Positive' Class : diabetic