install.packages(“class”) install.packages(“caret”) install.packages(“gmodels”)
wbcd <- read.csv("D:/Users/jayapate/Downloads/wbcd.csv")
#View(wbcd)
str(wbcd)## 'data.frame': 569 obs. of 32 variables:
## $ id : int 87139402 8910251 905520 868871 9012568 906539 925291 87880 862989 89827 ...
## $ diagnosis : Factor w/ 2 levels "B","M": 1 1 1 1 1 1 1 2 1 1 ...
## $ radius_mean : num 12.3 10.6 11 11.3 15.2 ...
## $ texture_mean : num 12.4 18.9 16.8 13.4 13.2 ...
## $ perimeter_mean : num 78.8 69.3 70.9 73 97.7 ...
## $ area_mean : num 464 346 373 385 712 ...
## $ smoothness_mean : num 0.1028 0.0969 0.1077 0.1164 0.0796 ...
## $ compactness_mean : num 0.0698 0.1147 0.078 0.1136 0.0693 ...
## $ concavity_mean : num 0.0399 0.0639 0.0305 0.0464 0.0339 ...
## $ points_mean : num 0.037 0.0264 0.0248 0.048 0.0266 ...
## $ symmetry_mean : num 0.196 0.192 0.171 0.177 0.172 ...
## $ dimension_mean : num 0.0595 0.0649 0.0634 0.0607 0.0554 ...
## $ radius_se : num 0.236 0.451 0.197 0.338 0.178 ...
## $ texture_se : num 0.666 1.197 1.387 1.343 0.412 ...
## $ perimeter_se : num 1.67 3.43 1.34 1.85 1.34 ...
## $ area_se : num 17.4 27.1 13.5 26.3 17.7 ...
## $ smoothness_se : num 0.00805 0.00747 0.00516 0.01127 0.00501 ...
## $ compactness_se : num 0.0118 0.03581 0.00936 0.03498 0.01485 ...
## $ concavity_se : num 0.0168 0.0335 0.0106 0.0219 0.0155 ...
## $ points_se : num 0.01241 0.01365 0.00748 0.01965 0.00915 ...
## $ symmetry_se : num 0.0192 0.035 0.0172 0.0158 0.0165 ...
## $ dimension_se : num 0.00225 0.00332 0.0022 0.00344 0.00177 ...
## $ radius_worst : num 13.5 11.9 12.4 11.9 16.2 ...
## $ texture_worst : num 15.6 22.9 26.4 15.8 15.7 ...
## $ perimeter_worst : num 87 78.3 79.9 76.5 104.5 ...
## $ area_worst : num 549 425 471 434 819 ...
## $ smoothness_worst : num 0.139 0.121 0.137 0.137 0.113 ...
## $ compactness_worst: num 0.127 0.252 0.148 0.182 0.174 ...
## $ concavity_worst : num 0.1242 0.1916 0.1067 0.0867 0.1362 ...
## $ points_worst : num 0.0939 0.0793 0.0743 0.0861 0.0818 ...
## $ symmetry_worst : num 0.283 0.294 0.3 0.21 0.249 ...
## $ dimension_worst : num 0.0677 0.0759 0.0788 0.0678 0.0677 ...dim(wbcd)## [1] 569 32#To remove the first column ID which is not required
wbcd <- wbcd [-1]
View(wbcd)
#Table format of Diagnosis
table(wbcd$diagnosis)##
## B M
## 357 212#To label B as "Benign" and M as "Malignant"
wbcd$diagnosis <- factor(wbcd$diagnosis, levels = c("B","M"), labels = c("Benign", "Malignant"))
# To calculate the % of Benign and Malignant in the dataset
round(prop.table(table(wbcd$diagnosis))*100,1)##
## Benign Malignant
## 62.7 37.3summary(wbcd[c("radius_mean","texture_mean","perimeter_mean")])## radius_mean texture_mean perimeter_mean
## Min. : 6.981 Min. : 9.71 Min. : 43.79
## 1st Qu.:11.700 1st Qu.:16.17 1st Qu.: 75.17
## Median :13.370 Median :18.84 Median : 86.24
## Mean :14.127 Mean :19.29 Mean : 91.97
## 3rd Qu.:15.780 3rd Qu.:21.80 3rd Qu.:104.10
## Max. :28.110 Max. :39.28 Max. :188.50#To Normanalize or standardize data
#wbcd <- wbcd [-1]
#View(wbcd)
#scaledata <- scale(wbcd, center = TRUE, scale = TRUE)
#wbcd_n <- as.data.frame(lapply(wbcd[2:31], scaledata))
#wbcd_n <- as.data.frame(lapply(wbcd[2:31], norm))
norm <- function(x){
return((x-min(x))/(max(x)-min(x)))
}
#Apply the normalization function to wbcd dataset
wbcd_n <- as.data.frame(lapply(wbcd[2:30], norm))
#View(wbcd_n)
#create training and test datasets
wbcd_train <- wbcd_n[1:469,]
wbcd_test <- wbcd_n[470:569,]
#Get labels for training and test datasets
wbcd_train_labels <- wbcd[1:469,1]
wbcd_test_labels <- wbcd[470:569,1]
# Build a KNN model on taining dataset
library("class")## Warning: package 'class' was built under R version 3.5.1library("caret")## Warning: package 'caret' was built under R version 3.5.1## Loading required package: lattice## Loading required package: ggplot2## Warning: package 'ggplot2' was built under R version 3.5.1# Building the KNN model on training dataset and also need labels which we are including c1. Once we build the preduction model
# we have to test on test dataset
wbcd_pred <- knn(train = wbcd_train, test = wbcd_test, cl = wbcd_train_labels, k=21)
class(wbcd_train)## [1] "data.frame"class(wbcd_test)## [1] "data.frame"## Now evualuation the model performance
# install package gmodels
#install.packages("gmodels")
library("gmodels")## Warning: package 'gmodels' was built under R version 3.5.1# Create cross table of predicted and actual
CrossTable( x = wbcd_test_labels, y = wbcd_pred)##
##
## Cell Contents
## |-------------------------|
## | N |
## | Chi-square contribution |
## | N / Row Total |
## | N / Col Total |
## | N / Table Total |
## |-------------------------|
##
##
## Total Observations in Table: 100
##
##
## | wbcd_pred
## wbcd_test_labels | Benign | Malignant | Row Total |
## -----------------|-----------|-----------|-----------|
## Benign | 61 | 0 | 61 |
## | 12.353 | 21.960 | |
## | 1.000 | 0.000 | 0.610 |
## | 0.953 | 0.000 | |
## | 0.610 | 0.000 | |
## -----------------|-----------|-----------|-----------|
## Malignant | 3 | 36 | 39 |
## | 19.321 | 34.348 | |
## | 0.077 | 0.923 | 0.390 |
## | 0.047 | 1.000 | |
## | 0.030 | 0.360 | |
## -----------------|-----------|-----------|-----------|
## Column Total | 64 | 36 | 100 |
## | 0.640 | 0.360 | |
## -----------------|-----------|-----------|-----------|
##
##