This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
Note that the echo = FALSE parameter was added to the
code chunk to prevent printing of the R code that generated the
plot.
#install.packages(c("vroom", "readr"), dependencies = TRUE)
library(readr)
wisc_bc_data <- read_csv("/Users/bezatilahun/Desktop/Datamining /R folders/RPractice/wisc_bc_data.csv")## Rows: 569 Columns: 32
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (1): diagnosis
## dbl (31): id, radius_mean, texture_mean, perimeter_mean, area_mean, smoothne...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.#View(wisc_bc_data)
#Step-1 Import Data through readr
wd <- wisc_bc_data
str(wd)## spc_tbl_ [569 × 32] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
## $ id : num [1:569] 842302 842517 84300903 84348301 84358402 ...
## $ diagnosis : chr [1:569] "M" "M" "M" "M" ...
## $ radius_mean : num [1:569] 18 20.6 19.7 11.4 20.3 ...
## $ texture_mean : num [1:569] 10.4 17.8 21.2 20.4 14.3 ...
## $ perimeter_mean : num [1:569] 122.8 132.9 130 77.6 135.1 ...
## $ area_mean : num [1:569] 1001 1326 1203 386 1297 ...
## $ smoothness_mean : num [1:569] 0.1184 0.0847 0.1096 0.1425 0.1003 ...
## $ compactness_mean : num [1:569] 0.2776 0.0786 0.1599 0.2839 0.1328 ...
## $ concavity_mean : num [1:569] 0.3001 0.0869 0.1974 0.2414 0.198 ...
## $ concave points_mean : num [1:569] 0.1471 0.0702 0.1279 0.1052 0.1043 ...
## $ symmetry_mean : num [1:569] 0.242 0.181 0.207 0.26 0.181 ...
## $ fractal_dimension_mean : num [1:569] 0.0787 0.0567 0.06 0.0974 0.0588 ...
## $ radius_se : num [1:569] 1.095 0.543 0.746 0.496 0.757 ...
## $ texture_se : num [1:569] 0.905 0.734 0.787 1.156 0.781 ...
## $ perimeter_se : num [1:569] 8.59 3.4 4.58 3.44 5.44 ...
## $ area_se : num [1:569] 153.4 74.1 94 27.2 94.4 ...
## $ smoothness_se : num [1:569] 0.0064 0.00522 0.00615 0.00911 0.01149 ...
## $ compactness_se : num [1:569] 0.049 0.0131 0.0401 0.0746 0.0246 ...
## $ concavity_se : num [1:569] 0.0537 0.0186 0.0383 0.0566 0.0569 ...
## $ concave points_se : num [1:569] 0.0159 0.0134 0.0206 0.0187 0.0188 ...
## $ symmetry_se : num [1:569] 0.03 0.0139 0.0225 0.0596 0.0176 ...
## $ fractal_dimension_se : num [1:569] 0.00619 0.00353 0.00457 0.00921 0.00511 ...
## $ radius_worst : num [1:569] 25.4 25 23.6 14.9 22.5 ...
## $ texture_worst : num [1:569] 17.3 23.4 25.5 26.5 16.7 ...
## $ perimeter_worst : num [1:569] 184.6 158.8 152.5 98.9 152.2 ...
## $ area_worst : num [1:569] 2019 1956 1709 568 1575 ...
## $ smoothness_worst : num [1:569] 0.162 0.124 0.144 0.21 0.137 ...
## $ compactness_worst : num [1:569] 0.666 0.187 0.424 0.866 0.205 ...
## $ concavity_worst : num [1:569] 0.712 0.242 0.45 0.687 0.4 ...
## $ concave points_worst : num [1:569] 0.265 0.186 0.243 0.258 0.163 ...
## $ symmetry_worst : num [1:569] 0.46 0.275 0.361 0.664 0.236 ...
## $ fractal_dimension_worst: num [1:569] 0.1189 0.089 0.0876 0.173 0.0768 ...
## - attr(*, "spec")=
## .. cols(
## .. id = col_double(),
## .. diagnosis = col_character(),
## .. radius_mean = col_double(),
## .. texture_mean = col_double(),
## .. perimeter_mean = col_double(),
## .. area_mean = col_double(),
## .. smoothness_mean = col_double(),
## .. compactness_mean = col_double(),
## .. concavity_mean = col_double(),
## .. `concave points_mean` = col_double(),
## .. symmetry_mean = col_double(),
## .. fractal_dimension_mean = col_double(),
## .. radius_se = col_double(),
## .. texture_se = col_double(),
## .. perimeter_se = col_double(),
## .. area_se = col_double(),
## .. smoothness_se = col_double(),
## .. compactness_se = col_double(),
## .. concavity_se = col_double(),
## .. `concave points_se` = col_double(),
## .. symmetry_se = col_double(),
## .. fractal_dimension_se = col_double(),
## .. radius_worst = col_double(),
## .. texture_worst = col_double(),
## .. perimeter_worst = col_double(),
## .. area_worst = col_double(),
## .. smoothness_worst = col_double(),
## .. compactness_worst = col_double(),
## .. concavity_worst = col_double(),
## .. `concave points_worst` = col_double(),
## .. symmetry_worst = col_double(),
## .. fractal_dimension_worst = col_double()
## .. )
## - attr(*, "problems")=<externalptr>#Step 2- Remove the "id" feature from column 1 as it is unrelated to the data and does not contribute to the training.
wd1 <- wd[-1]
#View(wd1)
#display values of diagnosis
wd1$diagnosis## [1] "M" "M" "M" "M" "M" "M" "M" "M" "M" "M" "M" "M" "M" "M" "M" "M" "M" "M"
## [19] "M" "B" "B" "B" "M" "M" "M" "M" "M" "M" "M" "M" "M" "M" "M" "M" "M" "M"
## [37] "M" "B" "M" "M" "M" "M" "M" "M" "M" "M" "B" "M" "B" "B" "B" "B" "B" "M"
## [55] "M" "B" "M" "M" "B" "B" "B" "B" "M" "B" "M" "M" "B" "B" "B" "B" "M" "B"
## [73] "M" "M" "B" "M" "B" "M" "M" "B" "B" "B" "M" "M" "B" "M" "M" "M" "B" "B"
## [91] "B" "M" "B" "B" "M" "M" "B" "B" "B" "M" "M" "B" "B" "B" "B" "M" "B" "B"
## [109] "M" "B" "B" "B" "B" "B" "B" "B" "B" "M" "M" "M" "B" "M" "M" "B" "B" "B"
## [127] "M" "M" "B" "M" "B" "M" "M" "B" "M" "M" "B" "B" "M" "B" "B" "M" "B" "B"
## [145] "B" "B" "M" "B" "B" "B" "B" "B" "B" "B" "B" "B" "M" "B" "B" "B" "B" "M"
## [163] "M" "B" "M" "B" "B" "M" "M" "B" "B" "M" "M" "B" "B" "B" "B" "M" "B" "B"
## [181] "M" "M" "M" "B" "M" "B" "M" "B" "B" "B" "M" "B" "B" "M" "M" "B" "M" "M"
## [199] "M" "M" "B" "M" "M" "M" "B" "M" "B" "M" "B" "B" "M" "B" "M" "M" "M" "M"
## [217] "B" "B" "M" "M" "B" "B" "B" "M" "B" "B" "B" "B" "B" "M" "M" "B" "B" "M"
## [235] "B" "B" "M" "M" "B" "M" "B" "B" "B" "B" "M" "B" "B" "B" "B" "B" "M" "B"
## [253] "M" "M" "M" "M" "M" "M" "M" "M" "M" "M" "M" "M" "M" "M" "B" "B" "B" "B"
## [271] "B" "B" "M" "B" "M" "B" "B" "M" "B" "B" "M" "B" "M" "M" "B" "B" "B" "B"
## [289] "B" "B" "B" "B" "B" "B" "B" "B" "B" "M" "B" "B" "M" "B" "M" "B" "B" "B"
## [307] "B" "B" "B" "B" "B" "B" "B" "B" "B" "B" "B" "M" "B" "B" "B" "M" "B" "M"
## [325] "B" "B" "B" "B" "M" "M" "M" "B" "B" "B" "B" "M" "B" "M" "B" "M" "B" "B"
## [343] "B" "M" "B" "B" "B" "B" "B" "B" "B" "M" "M" "M" "B" "B" "B" "B" "B" "B"
## [361] "B" "B" "B" "B" "B" "M" "M" "B" "M" "M" "M" "B" "M" "M" "B" "B" "B" "B"
## [379] "B" "M" "B" "B" "B" "B" "B" "M" "B" "B" "B" "M" "B" "B" "M" "M" "B" "B"
## [397] "B" "B" "B" "B" "M" "B" "B" "B" "B" "B" "B" "B" "M" "B" "B" "B" "B" "B"
## [415] "M" "B" "B" "M" "B" "B" "B" "B" "B" "B" "B" "B" "B" "B" "B" "B" "M" "B"
## [433] "M" "M" "B" "M" "B" "B" "B" "B" "B" "M" "B" "B" "M" "B" "M" "B" "B" "M"
## [451] "B" "M" "B" "B" "B" "B" "B" "B" "B" "B" "M" "M" "B" "B" "B" "B" "B" "B"
## [469] "M" "B" "B" "B" "B" "B" "B" "B" "B" "B" "B" "M" "B" "B" "B" "B" "B" "B"
## [487] "B" "M" "B" "M" "B" "B" "M" "B" "B" "B" "B" "B" "M" "M" "B" "M" "B" "M"
## [505] "B" "B" "B" "B" "B" "M" "B" "B" "M" "B" "M" "B" "M" "M" "B" "B" "B" "M"
## [523] "B" "B" "B" "B" "B" "B" "B" "B" "B" "B" "B" "M" "B" "M" "M" "B" "B" "B"
## [541] "B" "B" "B" "B" "B" "B" "B" "B" "B" "B" "B" "B" "B" "B" "B" "B" "B" "B"
## [559] "B" "B" "B" "B" "M" "M" "M" "M" "M" "M" "B"#how many M and B in the data set?
table(wd1$diagnosis)##
## B M
## 357 212#the proportion of M and B?
prop.table(table(wd1$diagnosis))##
## B M
## 0.6274165 0.3725835#Examining numeric features
summary(wd1)## diagnosis radius_mean texture_mean perimeter_mean
## Length:569 Min. : 6.981 Min. : 9.71 Min. : 43.79
## Class :character 1st Qu.:11.700 1st Qu.:16.17 1st Qu.: 75.17
## Mode :character 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
## area_mean smoothness_mean compactness_mean concavity_mean
## Min. : 143.5 Min. :0.05263 Min. :0.01938 Min. :0.00000
## 1st Qu.: 420.3 1st Qu.:0.08637 1st Qu.:0.06492 1st Qu.:0.02956
## Median : 551.1 Median :0.09587 Median :0.09263 Median :0.06154
## Mean : 654.9 Mean :0.09636 Mean :0.10434 Mean :0.08880
## 3rd Qu.: 782.7 3rd Qu.:0.10530 3rd Qu.:0.13040 3rd Qu.:0.13070
## Max. :2501.0 Max. :0.16340 Max. :0.34540 Max. :0.42680
## concave points_mean symmetry_mean fractal_dimension_mean radius_se
## Min. :0.00000 Min. :0.1060 Min. :0.04996 Min. :0.1115
## 1st Qu.:0.02031 1st Qu.:0.1619 1st Qu.:0.05770 1st Qu.:0.2324
## Median :0.03350 Median :0.1792 Median :0.06154 Median :0.3242
## Mean :0.04892 Mean :0.1812 Mean :0.06280 Mean :0.4052
## 3rd Qu.:0.07400 3rd Qu.:0.1957 3rd Qu.:0.06612 3rd Qu.:0.4789
## Max. :0.20120 Max. :0.3040 Max. :0.09744 Max. :2.8730
## texture_se perimeter_se area_se smoothness_se
## Min. :0.3602 Min. : 0.757 Min. : 6.802 Min. :0.001713
## 1st Qu.:0.8339 1st Qu.: 1.606 1st Qu.: 17.850 1st Qu.:0.005169
## Median :1.1080 Median : 2.287 Median : 24.530 Median :0.006380
## Mean :1.2169 Mean : 2.866 Mean : 40.337 Mean :0.007041
## 3rd Qu.:1.4740 3rd Qu.: 3.357 3rd Qu.: 45.190 3rd Qu.:0.008146
## Max. :4.8850 Max. :21.980 Max. :542.200 Max. :0.031130
## compactness_se concavity_se concave points_se symmetry_se
## Min. :0.002252 Min. :0.00000 Min. :0.000000 Min. :0.007882
## 1st Qu.:0.013080 1st Qu.:0.01509 1st Qu.:0.007638 1st Qu.:0.015160
## Median :0.020450 Median :0.02589 Median :0.010930 Median :0.018730
## Mean :0.025478 Mean :0.03189 Mean :0.011796 Mean :0.020542
## 3rd Qu.:0.032450 3rd Qu.:0.04205 3rd Qu.:0.014710 3rd Qu.:0.023480
## Max. :0.135400 Max. :0.39600 Max. :0.052790 Max. :0.078950
## fractal_dimension_se radius_worst texture_worst perimeter_worst
## Min. :0.0008948 Min. : 7.93 Min. :12.02 Min. : 50.41
## 1st Qu.:0.0022480 1st Qu.:13.01 1st Qu.:21.08 1st Qu.: 84.11
## Median :0.0031870 Median :14.97 Median :25.41 Median : 97.66
## Mean :0.0037949 Mean :16.27 Mean :25.68 Mean :107.26
## 3rd Qu.:0.0045580 3rd Qu.:18.79 3rd Qu.:29.72 3rd Qu.:125.40
## Max. :0.0298400 Max. :36.04 Max. :49.54 Max. :251.20
## area_worst smoothness_worst compactness_worst concavity_worst
## Min. : 185.2 Min. :0.07117 Min. :0.02729 Min. :0.0000
## 1st Qu.: 515.3 1st Qu.:0.11660 1st Qu.:0.14720 1st Qu.:0.1145
## Median : 686.5 Median :0.13130 Median :0.21190 Median :0.2267
## Mean : 880.6 Mean :0.13237 Mean :0.25427 Mean :0.2722
## 3rd Qu.:1084.0 3rd Qu.:0.14600 3rd Qu.:0.33910 3rd Qu.:0.3829
## Max. :4254.0 Max. :0.22260 Max. :1.05800 Max. :1.2520
## concave points_worst symmetry_worst fractal_dimension_worst
## Min. :0.00000 Min. :0.1565 Min. :0.05504
## 1st Qu.:0.06493 1st Qu.:0.2504 1st Qu.:0.07146
## Median :0.09993 Median :0.2822 Median :0.08004
## Mean :0.11461 Mean :0.2901 Mean :0.08395
## 3rd Qu.:0.16140 3rd Qu.:0.3179 3rd Qu.:0.09208
## Max. :0.29100 Max. :0.6638 Max. :0.20750#based on the code in line 14. We observed that the numbers are all over the place.
#Consequently, we need to implement scaling to rectify this issue.
#create normalization function
normalize <- function(x){
return((x - min(x))/ (max(x) - min(x)))
}
#Test 1 normalize(c(1,2,3,4,5))
#Test 2 normalize(c(10,20,30,40,50))
#Test 3 normalize(c(100,200,300,400,500))
#normalize all the columns except the diagnosis column
wd_n <- as.data.frame(lapply(wd1 [2:31], normalize))
summary(wd_n)## radius_mean texture_mean perimeter_mean area_mean
## Min. :0.0000 Min. :0.0000 Min. :0.0000 Min. :0.0000
## 1st Qu.:0.2233 1st Qu.:0.2185 1st Qu.:0.2168 1st Qu.:0.1174
## Median :0.3024 Median :0.3088 Median :0.2933 Median :0.1729
## Mean :0.3382 Mean :0.3240 Mean :0.3329 Mean :0.2169
## 3rd Qu.:0.4164 3rd Qu.:0.4089 3rd Qu.:0.4168 3rd Qu.:0.2711
## Max. :1.0000 Max. :1.0000 Max. :1.0000 Max. :1.0000
## smoothness_mean compactness_mean concavity_mean concave.points_mean
## Min. :0.0000 Min. :0.0000 Min. :0.00000 Min. :0.0000
## 1st Qu.:0.3046 1st Qu.:0.1397 1st Qu.:0.06926 1st Qu.:0.1009
## Median :0.3904 Median :0.2247 Median :0.14419 Median :0.1665
## Mean :0.3948 Mean :0.2606 Mean :0.20806 Mean :0.2431
## 3rd Qu.:0.4755 3rd Qu.:0.3405 3rd Qu.:0.30623 3rd Qu.:0.3678
## Max. :1.0000 Max. :1.0000 Max. :1.00000 Max. :1.0000
## symmetry_mean fractal_dimension_mean radius_se texture_se
## Min. :0.0000 Min. :0.0000 Min. :0.00000 Min. :0.0000
## 1st Qu.:0.2823 1st Qu.:0.1630 1st Qu.:0.04378 1st Qu.:0.1047
## Median :0.3697 Median :0.2439 Median :0.07702 Median :0.1653
## Mean :0.3796 Mean :0.2704 Mean :0.10635 Mean :0.1893
## 3rd Qu.:0.4530 3rd Qu.:0.3404 3rd Qu.:0.13304 3rd Qu.:0.2462
## Max. :1.0000 Max. :1.0000 Max. :1.00000 Max. :1.0000
## perimeter_se area_se smoothness_se compactness_se
## Min. :0.00000 Min. :0.00000 Min. :0.0000 Min. :0.00000
## 1st Qu.:0.04000 1st Qu.:0.02064 1st Qu.:0.1175 1st Qu.:0.08132
## Median :0.07209 Median :0.03311 Median :0.1586 Median :0.13667
## Mean :0.09938 Mean :0.06264 Mean :0.1811 Mean :0.17444
## 3rd Qu.:0.12251 3rd Qu.:0.07170 3rd Qu.:0.2187 3rd Qu.:0.22680
## Max. :1.00000 Max. :1.00000 Max. :1.0000 Max. :1.00000
## concavity_se concave.points_se symmetry_se fractal_dimension_se
## Min. :0.00000 Min. :0.0000 Min. :0.0000 Min. :0.00000
## 1st Qu.:0.03811 1st Qu.:0.1447 1st Qu.:0.1024 1st Qu.:0.04675
## Median :0.06538 Median :0.2070 Median :0.1526 Median :0.07919
## Mean :0.08054 Mean :0.2235 Mean :0.1781 Mean :0.10019
## 3rd Qu.:0.10619 3rd Qu.:0.2787 3rd Qu.:0.2195 3rd Qu.:0.12656
## Max. :1.00000 Max. :1.0000 Max. :1.0000 Max. :1.00000
## radius_worst texture_worst perimeter_worst area_worst
## Min. :0.0000 Min. :0.0000 Min. :0.0000 Min. :0.00000
## 1st Qu.:0.1807 1st Qu.:0.2415 1st Qu.:0.1678 1st Qu.:0.08113
## Median :0.2504 Median :0.3569 Median :0.2353 Median :0.12321
## Mean :0.2967 Mean :0.3640 Mean :0.2831 Mean :0.17091
## 3rd Qu.:0.3863 3rd Qu.:0.4717 3rd Qu.:0.3735 3rd Qu.:0.22090
## Max. :1.0000 Max. :1.0000 Max. :1.0000 Max. :1.00000
## smoothness_worst compactness_worst concavity_worst concave.points_worst
## Min. :0.0000 Min. :0.0000 Min. :0.00000 Min. :0.0000
## 1st Qu.:0.3000 1st Qu.:0.1163 1st Qu.:0.09145 1st Qu.:0.2231
## Median :0.3971 Median :0.1791 Median :0.18107 Median :0.3434
## Mean :0.4041 Mean :0.2202 Mean :0.21740 Mean :0.3938
## 3rd Qu.:0.4942 3rd Qu.:0.3025 3rd Qu.:0.30583 3rd Qu.:0.5546
## Max. :1.0000 Max. :1.0000 Max. :1.00000 Max. :1.0000
## symmetry_worst fractal_dimension_worst
## Min. :0.0000 Min. :0.0000
## 1st Qu.:0.1851 1st Qu.:0.1077
## Median :0.2478 Median :0.1640
## Mean :0.2633 Mean :0.1896
## 3rd Qu.:0.3182 3rd Qu.:0.2429
## Max. :1.0000 Max. :1.0000#making the target variable a factor
wd1$diagnosis <- factor(wd1$diagnosis, levels = c("B", "M"),labels = c("Benign", "Malignant"))
str(wd1$diagnosis)## Factor w/ 2 levels "Benign","Malignant": 2 2 2 2 2 2 2 2 2 2 ...#divide the alogrithim in to the training and test datasets.
wd1_train <-wd_n[1:469, ]
wd1_test <- wd_n[470:569, ]
#saving the diagnosis column that was left out to a to a new train and test vector since it is needed for the KNN model
wd1_train_labels <- wd1[1:469,1]
wd1_test_labels <- wd1[470:569,1]
head(wd1_test_labels)## # A tibble: 6 × 1
## diagnosis
## <fct>
## 1 Benign
## 2 Benign
## 3 Benign
## 4 Benign
## 5 Benign
## 6 Benignhead(wd1_train_labels)## # A tibble: 6 × 1
## diagnosis
## <fct>
## 1 Malignant
## 2 Malignant
## 3 Malignant
## 4 Malignant
## 5 Malignant
## 6 Malignant#KNN, training the classifier
library(class)
wd1_test_pred <- knn(train = wd1_train, test = wd1_test, cl= wd1_train_labels$diagnosis, k= 21)
wd1_test_pred## [1] Benign Benign Benign Benign Benign Benign Benign
## [8] Benign Benign Benign Malignant Benign Benign Benign
## [15] Benign Benign Benign Benign Malignant Benign Benign
## [22] Benign Benign Malignant Benign Benign Benign Benign
## [29] Benign Malignant Malignant Benign Malignant Benign Malignant
## [36] Benign Benign Benign Benign Benign Malignant Benign
## [43] Benign Malignant Benign Benign Benign Malignant Malignant
## [50] Benign Benign Benign Malignant Benign Benign Benign
## [57] Benign Benign Benign Benign Benign Benign Benign
## [64] Benign Malignant Benign Malignant Malignant Benign Benign
## [71] Benign Benign Benign Benign Benign Benign Benign
## [78] Benign Benign Benign Benign Benign Benign Benign
## [85] Benign Benign Benign Benign Benign Benign Benign
## [92] Benign Benign Malignant Malignant Malignant Malignant Malignant
## [99] Malignant Benign
## Levels: Benign Malignantlibrary(gmodels)
#Evaluating model performance
CrossTable(x= wd1_test_labels$diagnosis, y = wd1_test_pred, prop.chisq = FALSE)##
##
## Cell Contents
## |-------------------------|
## | N |
## | N / Row Total |
## | N / Col Total |
## | N / Table Total |
## |-------------------------|
##
##
## Total Observations in Table: 100
##
##
## | wd1_test_pred
## wd1_test_labels$diagnosis | Benign | Malignant | Row Total |
## --------------------------|-----------|-----------|-----------|
## Benign | 77 | 0 | 77 |
## | 1.000 | 0.000 | 0.770 |
## | 0.975 | 0.000 | |
## | 0.770 | 0.000 | |
## --------------------------|-----------|-----------|-----------|
## Malignant | 2 | 21 | 23 |
## | 0.087 | 0.913 | 0.230 |
## | 0.025 | 1.000 | |
## | 0.020 | 0.210 | |
## --------------------------|-----------|-----------|-----------|
## Column Total | 79 | 21 | 100 |
## | 0.790 | 0.210 | |
## --------------------------|-----------|-----------|-----------|
##
##