importing data from csv file

wbcd <- read.csv("C:/Users/Justice2/Desktop/Machine Learning & Data Science/R/data/wisc_bc_data.csv")
#attach(wbcd)
names(wbcd)
##  [1] "id"                      "diagnosis"              
##  [3] "radius_mean"             "texture_mean"           
##  [5] "perimeter_mean"          "area_mean"              
##  [7] "smoothness_mean"         "compactness_mean"       
##  [9] "concavity_mean"          "concave.points_mean"    
## [11] "symmetry_mean"           "fractal_dimension_mean" 
## [13] "radius_se"               "texture_se"             
## [15] "perimeter_se"            "area_se"                
## [17] "smoothness_se"           "compactness_se"         
## [19] "concavity_se"            "concave.points_se"      
## [21] "symmetry_se"             "fractal_dimension_se"   
## [23] "radius_worst"            "texture_worst"          
## [25] "perimeter_worst"         "area_worst"             
## [27] "smoothness_worst"        "compactness_worst"      
## [29] "concavity_worst"         "concave.points_worst"   
## [31] "symmetry_worst"          "fractal_dimension_worst"
str(wbcd)
## 'data.frame':    569 obs. of  32 variables:
##  $ id                     : int  842302 842517 84300903 84348301 84358402 843786 844359 84458202 844981 84501001 ...
##  $ diagnosis              : Factor w/ 2 levels "B","M": 2 2 2 2 2 2 2 2 2 2 ...
##  $ radius_mean            : num  18 20.6 19.7 11.4 20.3 ...
##  $ texture_mean           : num  10.4 17.8 21.2 20.4 14.3 ...
##  $ perimeter_mean         : num  122.8 132.9 130 77.6 135.1 ...
##  $ area_mean              : num  1001 1326 1203 386 1297 ...
##  $ smoothness_mean        : num  0.1184 0.0847 0.1096 0.1425 0.1003 ...
##  $ compactness_mean       : num  0.2776 0.0786 0.1599 0.2839 0.1328 ...
##  $ concavity_mean         : num  0.3001 0.0869 0.1974 0.2414 0.198 ...
##  $ concave.points_mean    : num  0.1471 0.0702 0.1279 0.1052 0.1043 ...
##  $ symmetry_mean          : num  0.242 0.181 0.207 0.26 0.181 ...
##  $ fractal_dimension_mean : num  0.0787 0.0567 0.06 0.0974 0.0588 ...
##  $ radius_se              : num  1.095 0.543 0.746 0.496 0.757 ...
##  $ texture_se             : num  0.905 0.734 0.787 1.156 0.781 ...
##  $ perimeter_se           : num  8.59 3.4 4.58 3.44 5.44 ...
##  $ area_se                : num  153.4 74.1 94 27.2 94.4 ...
##  $ smoothness_se          : num  0.0064 0.00522 0.00615 0.00911 0.01149 ...
##  $ compactness_se         : num  0.049 0.0131 0.0401 0.0746 0.0246 ...
##  $ concavity_se           : num  0.0537 0.0186 0.0383 0.0566 0.0569 ...
##  $ concave.points_se      : num  0.0159 0.0134 0.0206 0.0187 0.0188 ...
##  $ symmetry_se            : num  0.03 0.0139 0.0225 0.0596 0.0176 ...
##  $ fractal_dimension_se   : num  0.00619 0.00353 0.00457 0.00921 0.00511 ...
##  $ radius_worst           : num  25.4 25 23.6 14.9 22.5 ...
##  $ texture_worst          : num  17.3 23.4 25.5 26.5 16.7 ...
##  $ perimeter_worst        : num  184.6 158.8 152.5 98.9 152.2 ...
##  $ area_worst             : num  2019 1956 1709 568 1575 ...
##  $ smoothness_worst       : num  0.162 0.124 0.144 0.21 0.137 ...
##  $ compactness_worst      : num  0.666 0.187 0.424 0.866 0.205 ...
##  $ concavity_worst        : num  0.712 0.242 0.45 0.687 0.4 ...
##  $ concave.points_worst   : num  0.265 0.186 0.243 0.258 0.163 ...
##  $ symmetry_worst         : num  0.46 0.275 0.361 0.664 0.236 ...
##  $ fractal_dimension_worst: num  0.1189 0.089 0.0876 0.173 0.0768 ...
wbcd<-wbcd[,-1]

converting the Classifier “Diagnosis” into a factor

wbcd$diagnosis<- factor(wbcd$diagnosis, levels = c("B", "M"),
labels = c("Benign", "Malignant"))
round(prop.table(table(wbcd$diagnosis)) * 100,digits=1)
## 
##    Benign Malignant 
##      62.7      37.3
summary(wbcd[,c(2,5,6)])
##   radius_mean       area_mean      smoothness_mean  
##  Min.   : 6.981   Min.   : 143.5   Min.   :0.05263  
##  1st Qu.:11.700   1st Qu.: 420.3   1st Qu.:0.08637  
##  Median :13.370   Median : 551.1   Median :0.09587  
##  Mean   :14.127   Mean   : 654.9   Mean   :0.09636  
##  3rd Qu.:15.780   3rd Qu.: 782.7   3rd Qu.:0.10530  
##  Max.   :28.110   Max.   :2501.0   Max.   :0.16340

Transformation - normalizing numeric data

normalize <- function(x) {
return ((x - min(x)) / (max(x) - min(x)))
}
wbcd_n <- as.data.frame(lapply(wbcd[2:31], normalize))
hist(wbcd_n$area_mean,col=2)

Data preparation - creating training and test datasets

wbcd_train <- wbcd_n[1:469, ]
wbcd_test <- wbcd_n[470:569, ]
wbcd_train_labels <- wbcd[1:469, 1]
wbcd_test_labels <- wbcd[470:569, 1]

Training a model on the data

library(class)
wbcd_test_pred<-knn(train=wbcd_train,test=wbcd_test,cl=wbcd_train_labels,k=27)

Evaluating model performance

library(gmodels)
CrossTable(x = wbcd_test_labels, y = wbcd_test_pred,prop.chisq=TRUE)
## 
##  
##    Cell Contents
## |-------------------------|
## |                       N |
## | Chi-square contribution |
## |           N / Row Total |
## |           N / Col Total |
## |         N / Table Total |
## |-------------------------|
## 
##  
## Total Observations in Table:  100 
## 
##  
##                  | wbcd_test_pred 
## wbcd_test_labels |    Benign | Malignant | Row Total | 
## -----------------|-----------|-----------|-----------|
##           Benign |        77 |         0 |        77 | 
##                  |     4.298 |    16.170 |           | 
##                  |     1.000 |     0.000 |     0.770 | 
##                  |     0.975 |     0.000 |           | 
##                  |     0.770 |     0.000 |           | 
## -----------------|-----------|-----------|-----------|
##        Malignant |         2 |        21 |        23 | 
##                  |    14.390 |    54.134 |           | 
##                  |     0.087 |     0.913 |     0.230 | 
##                  |     0.025 |     1.000 |           | 
##                  |     0.020 |     0.210 |           | 
## -----------------|-----------|-----------|-----------|
##     Column Total |        79 |        21 |       100 | 
##                  |     0.790 |     0.210 |           | 
## -----------------|-----------|-----------|-----------|
## 
##

Improving model performance thus transformation into z-score standardization

library(gmodels)
library(class)
wbcd_z <- as.data.frame(scale(wbcd[-1]))
summary(wbcd_z$area_mean)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
## -1.4530 -0.6666 -0.2949  0.0000  0.3632  5.2460
wbcd_train_z <- wbcd_z[1:469, ]
wbcd_test_z <- wbcd_z[470:569, ]
wbcd_train_labels <- wbcd[1:469, 1]
wbcd_test_labels <- wbcd[470:569, 1]
wbcd_test_pred <- knn(train = wbcd_train_z, test = wbcd_test_z,cl = wbcd_train_labels, k = 5)
CrossTable(x = wbcd_test_labels, y = wbcd_test_pred,prop.chisq = TRUE)
## 
##  
##    Cell Contents
## |-------------------------|
## |                       N |
## | Chi-square contribution |
## |           N / Row Total |
## |           N / Col Total |
## |         N / Table Total |
## |-------------------------|
## 
##  
## Total Observations in Table:  100 
## 
##  
##                  | wbcd_test_pred 
## wbcd_test_labels |    Benign | Malignant | Row Total | 
## -----------------|-----------|-----------|-----------|
##           Benign |        73 |         4 |        77 | 
##                  |     5.015 |    13.560 |           | 
##                  |     0.948 |     0.052 |     0.770 | 
##                  |     1.000 |     0.148 |           | 
##                  |     0.730 |     0.040 |           | 
## -----------------|-----------|-----------|-----------|
##        Malignant |         0 |        23 |        23 | 
##                  |    16.790 |    45.395 |           | 
##                  |     0.000 |     1.000 |     0.230 | 
##                  |     0.000 |     0.852 |           | 
##                  |     0.000 |     0.230 |           | 
## -----------------|-----------|-----------|-----------|
##     Column Total |        73 |        27 |       100 | 
##                  |     0.730 |     0.270 |           | 
## -----------------|-----------|-----------|-----------|
## 
##