KNN classification

knn for iris data

library(class)
library(tidyverse)

package <U+393C><U+3E31>tidyverse<U+393C><U+3E32> was built under R version 3.3.2Loading tidyverse: ggplot2
Loading tidyverse: tibble
Loading tidyverse: tidyr
Loading tidyverse: readr
Loading tidyverse: purrr
Loading tidyverse: dplyr
package <U+393C><U+3E31>ggplot2<U+393C><U+3E32> was built under R version 3.3.2package <U+393C><U+3E31>tidyr<U+393C><U+3E32> was built under R version 3.3.2package <U+393C><U+3E31>readr<U+393C><U+3E32> was built under R version 3.3.2package <U+393C><U+3E31>purrr<U+393C><U+3E32> was built under R version 3.3.2Conflicts with tidy packages -----------------------------------------------------------------------
filter(): dplyr, stats
lag():    dplyr, stats

summary(iris)

  Sepal.Length    Sepal.Width     Petal.Length    Petal.Width          Species  
 Min.   :4.300   Min.   :2.000   Min.   :1.000   Min.   :0.100   setosa    :50  
 1st Qu.:5.100   1st Qu.:2.800   1st Qu.:1.600   1st Qu.:0.300   versicolor:50  
 Median :5.800   Median :3.000   Median :4.350   Median :1.300   virginica :50  
 Mean   :5.843   Mean   :3.057   Mean   :3.758   Mean   :1.199                  
 3rd Qu.:6.400   3rd Qu.:3.300   3rd Qu.:5.100   3rd Qu.:1.800                  
 Max.   :7.900   Max.   :4.400   Max.   :6.900   Max.   :2.500                  

normalize the data

iris_n%>%dim

[1] 150   4

create test and train dataset

library(caret)
train_index=createDataPartition(iris$Species,p=0.8,list=FALSE)
iris_train=iris_n[train_index,]
iris_test=iris_n[-train_index,]
train_label=iris$Species[train_index]
test_label=iris$Species[-train_index]

use the knn algorithm

confusionMatrix(model,test_label)

Confusion Matrix and Statistics

            Reference
Prediction   setosa versicolor virginica
  setosa         10          0         0
  versicolor      0         10         0
  virginica       0          0        10

Overall Statistics
                                     
               Accuracy : 1          
                 95% CI : (0.8843, 1)
    No Information Rate : 0.3333     
    P-Value [Acc > NIR] : 4.857e-15  
                                     
                  Kappa : 1          
 Mcnemar's Test P-Value : NA         

Statistics by Class:

                     Class: setosa Class: versicolor Class: virginica
Sensitivity                 1.0000            1.0000           1.0000
Specificity                 1.0000            1.0000           1.0000
Pos Pred Value              1.0000            1.0000           1.0000
Neg Pred Value              1.0000            1.0000           1.0000
Prevalence                  0.3333            0.3333           0.3333
Detection Rate              0.3333            0.3333           0.3333
Detection Prevalence        0.3333            0.3333           0.3333
Balanced Accuracy           1.0000            1.0000           1.0000

working with data from UCI

download it into your current working directory and import it into your Rstudio using fread from data.table or just read.csv

summary(bc)

       id            diagnosis  radius_mean      texture_mean   perimeter_mean     area_mean     
 Min.   :     8670   B:357     Min.   : 6.981   Min.   : 9.71   Min.   : 43.79   Min.   : 143.5  
 1st Qu.:   869218   M:212     1st Qu.:11.700   1st Qu.:16.17   1st Qu.: 75.17   1st Qu.: 420.3  
 Median :   906024             Median :13.370   Median :18.84   Median : 86.24   Median : 551.1  
 Mean   : 30371831             Mean   :14.127   Mean   :19.29   Mean   : 91.97   Mean   : 654.9  
 3rd Qu.:  8813129             3rd Qu.:15.780   3rd Qu.:21.80   3rd Qu.:104.10   3rd Qu.: 782.7  
 Max.   :911320502             Max.   :28.110   Max.   :39.28   Max.   :188.50   Max.   :2501.0  
 smoothness_mean   compactness_mean  concavity_mean    concave.points_mean symmetry_mean   
 Min.   :0.05263   Min.   :0.01938   Min.   :0.00000   Min.   :0.00000     Min.   :0.1060  
 1st Qu.:0.08637   1st Qu.:0.06492   1st Qu.:0.02956   1st Qu.:0.02031     1st Qu.:0.1619  
 Median :0.09587   Median :0.09263   Median :0.06154   Median :0.03350     Median :0.1792  
 Mean   :0.09636   Mean   :0.10434   Mean   :0.08880   Mean   :0.04892     Mean   :0.1812  
 3rd Qu.:0.10530   3rd Qu.:0.13040   3rd Qu.:0.13070   3rd Qu.:0.07400     3rd Qu.:0.1957  
 Max.   :0.16340   Max.   :0.34540   Max.   :0.42680   Max.   :0.20120     Max.   :0.3040  
 fractal_dimension_mean   radius_se        texture_se      perimeter_se       area_se       
 Min.   :0.04996        Min.   :0.1115   Min.   :0.3602   Min.   : 0.757   Min.   :  6.802  
 1st Qu.:0.05770        1st Qu.:0.2324   1st Qu.:0.8339   1st Qu.: 1.606   1st Qu.: 17.850  
 Median :0.06154        Median :0.3242   Median :1.1080   Median : 2.287   Median : 24.530  
 Mean   :0.06280        Mean   :0.4052   Mean   :1.2169   Mean   : 2.866   Mean   : 40.337  
 3rd Qu.:0.06612        3rd Qu.:0.4789   3rd Qu.:1.4740   3rd Qu.: 3.357   3rd Qu.: 45.190  
 Max.   :0.09744        Max.   :2.8730   Max.   :4.8850   Max.   :21.980   Max.   :542.200  
 smoothness_se      compactness_se      concavity_se     concave.points_se   symmetry_se      
 Min.   :0.001713   Min.   :0.002252   Min.   :0.00000   Min.   :0.000000   Min.   :0.007882  
 1st Qu.:0.005169   1st Qu.:0.013080   1st Qu.:0.01509   1st Qu.:0.007638   1st Qu.:0.015160  
 Median :0.006380   Median :0.020450   Median :0.02589   Median :0.010930   Median :0.018730  
 Mean   :0.007041   Mean   :0.025478   Mean   :0.03189   Mean   :0.011796   Mean   :0.020542  
 3rd Qu.:0.008146   3rd Qu.:0.032450   3rd Qu.:0.04205   3rd Qu.:0.014710   3rd Qu.:0.023480  
 Max.   :0.031130   Max.   :0.135400   Max.   :0.39600   Max.   :0.052790   Max.   :0.078950  
 fractal_dimension_se  radius_worst   texture_worst   perimeter_worst    area_worst    
 Min.   :0.0008948    Min.   : 7.93   Min.   :12.02   Min.   : 50.41   Min.   : 185.2  
 1st Qu.:0.0022480    1st Qu.:13.01   1st Qu.:21.08   1st Qu.: 84.11   1st Qu.: 515.3  
 Median :0.0031870    Median :14.97   Median :25.41   Median : 97.66   Median : 686.5  
 Mean   :0.0037949    Mean   :16.27   Mean   :25.68   Mean   :107.26   Mean   : 880.6  
 3rd Qu.:0.0045580    3rd Qu.:18.79   3rd Qu.:29.72   3rd Qu.:125.40   3rd Qu.:1084.0  
 Max.   :0.0298400    Max.   :36.04   Max.   :49.54   Max.   :251.20   Max.   :4254.0  
 smoothness_worst  compactness_worst concavity_worst  concave.points_worst symmetry_worst  
 Min.   :0.07117   Min.   :0.02729   Min.   :0.0000   Min.   :0.00000      Min.   :0.1565  
 1st Qu.:0.11660   1st Qu.:0.14720   1st Qu.:0.1145   1st Qu.:0.06493      1st Qu.:0.2504  
 Median :0.13130   Median :0.21190   Median :0.2267   Median :0.09993      Median :0.2822  
 Mean   :0.13237   Mean   :0.25427   Mean   :0.2722   Mean   :0.11461      Mean   :0.2901  
 3rd Qu.:0.14600   3rd Qu.:0.33910   3rd Qu.:0.3829   3rd Qu.:0.16140      3rd Qu.:0.3179  
 Max.   :0.22260   Max.   :1.05800   Max.   :1.2520   Max.   :0.29100      Max.   :0.6638  
 fractal_dimension_worst
 Min.   :0.05504        
 1st Qu.:0.07146        
 Median :0.08004        
 Mean   :0.08395        
 3rd Qu.:0.09208        
 Max.   :0.20750        

get data partition for training and test (createDataPartition from caret package)

index=createDataPartition(bc$diagnosis,p=0.8,list=FALSE,times=1)
train_bc=bc_n[index,]
test_bc=bc_n[-index,]
train_bc_cl=bc$diagnosis[index]
test_bc_cl=bc$diagnosis[-index]

apply knn

bc_model_5=knn(train=train_bc,test=test_bc,cl=train_bc_cl,k=5)
bc_model_10=knn(train=train_bc,test=test_bc,cl=train_bc_cl,k=10)
bc_model_100=knn(train=train_bc,test=test_bc,cl=train_bc_cl,k=100)
bc_model_200=knn(train=train_bc,test=test_bc,cl=train_bc_cl,k=200)
## access model performance
table(bc_model_5,test_bc_cl)

          test_bc_cl
bc_model_5  B  M
         B 69  2
         M  2 40

table(bc_model_10,test_bc_cl)

           test_bc_cl
bc_model_10  B  M
          B 69  2
          M  2 40

table(bc_model_100,test_bc_cl)

            test_bc_cl
bc_model_100  B  M
           B 70  2
           M  1 40

table(bc_model_200,test_bc_cl)

            test_bc_cl
bc_model_200  B  M
           B 70  9
           M  1 33

it seems that k=100 is a better model among those k variations.