#Importing Data #we are also looking at the data, and seeing if what needs to be altared for proper preprocessing for machine learning #things such as removal of comma’s, or making everything numeric are common changes
# import the CSV file
wbcd <- read.csv("wisc_bc_data.csv", stringsAsFactors = FALSE)
# examine the structure of the wbcd data frame
str(wbcd)
'data.frame': 569 obs. of 32 variables:
$ id : int 87139402 8910251 905520 868871 9012568 906539 925291 87880 862989 89827 ...
$ diagnosis : chr "B" "B" "B" "B" ...
$ 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 ...
#we are dropping one of the columns from the dataset here #we are telling it which one, to do so it will no longer appear
# drop the id feature
wbcd <- wbcd[-1]
#Table of diagnosis
# table of diagnosis
table(wbcd$diagnosis)
B M
357 212
#this is making the table appear better instead of just B, & M #this will make it easier to read, and understand for people who may not be staring directly at the dataset itself
# recode diagnosis as a factor
wbcd$diagnosis <- factor(wbcd$diagnosis, levels = c("B", "M"),
labels = c("Benign", "Malignant"))
#Once agian, just making some easy fundamental changes, so that it can be understood in an easier manner
# table or proportions with more informative labels
round(prop.table(table(wbcd$diagnosis)) * 100, digits = 1)
Benign Malignant
62.7 37.3
#summary of three particular mean’s #this shows specified data, rather than the summarys for the entire dataset #this can be used as a point of emphasis / focus
# summarize three numeric features
summary(wbcd[c("radius_mean", "area_mean", "smoothness_mean")])
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
#normilzation function basics #this will be used later, but is being set up now
# create normalization function
normalize <- function(x) {
return ((x - min(x)) / (max(x) - min(x)))
}
#making sure normilization functions works #if these numbers weren’t to be identitical than you would know the function was coded incorrectly #this is an important step to remember
# test normalization function - result should be identical
normalize(c(1, 2, 3, 4, 5))
[1] 0.00 0.25 0.50 0.75 1.00
normalize(c(10, 20, 30, 40, 50))
[1] 0.00 0.25 0.50 0.75 1.00
#applying the normalize function to our data we have inputted
# normalize the wbcd data
wbcd_n <- as.data.frame(lapply(wbcd[2:31], normalize))
#nsummary of the function from earlier to ensure it works properly #if this were to not work you would get error codes, or crazy data numbers back #important to pay attention to these steps as it can altar future outcomes
# confirm that normalization worked
summary(wbcd_n$area_mean)
Min. 1st Qu. Median Mean 3rd Qu. Max.
0.0000 0.1174 0.1729 0.2169 0.2711 1.0000
#training data, we are giving it different values to use, for different results
# create training and test data
wbcd_train <- wbcd_n[1:469, ]
wbcd_test <- wbcd_n[470:569, ]
#Label creation is important to ensure that every data point is clear and understandables #while we are the one’s creating it, othes need to be able to identify what it is we are breaking down
# create labels for training and test data
wbcd_train_labels <- wbcd[1:469, 1]
wbcd_test_labels <- wbcd[470:569, 1]
#load new liabrary
# load the "class" library
library(class)
#knn test train #this is to setup KNN neighbors using the existing data
wbcd_test_pred <- knn(train = wbcd_train, test = wbcd_test,
cl = wbcd_train_labels, k = 21)
#Gmodels will not load or work #I have been forced to comment it out, I have tried everything in my power #This is going to force me to potentially have to comment out key steps, I will do my best #I have commented it out, I have restarted, re downloaded and every other tip possible online, and it will not load it gives the same error code
#install.packages(gmodels)
# load the "gmodels" library
#library(gmodels)
# Create the cross tabulation of predicted vs. actual
#CrossTable(x = wbcd_test_labels, y = wbcd_test_pred,
#prop.chisq = FALSE)
#overview of key data points #this helps us understand unity and what can be looked at further in detail
## Step 5: Improving model performance
# use the scale() function to z-score standardize a data frame
wbcd_z <- as.data.frame(scale(wbcd[-1]))
# confirm that the transformation was applied correctly
summary(wbcd_z$area_mean)
Min. 1st Qu. Median Mean 3rd Qu. Max.
-1.4532 -0.6666 -0.2949 0.0000 0.3632 5.2459
#continue with training preprocesses #this is a neccessary step to get positive results for machine learning #im worried gmodels is going to mess me up, but onward we go.
# create training and test datasets
wbcd_train <- wbcd_z[1:469, ]
wbcd_test <- wbcd_z[470:569, ]
# re-classify test cases
wbcd_test_pred <- knn(train = wbcd_train, test = wbcd_test,
cl = wbcd_train_labels, k = 21)
#Having to comment out because of gmodels error, it is saying this cannot be found. #function wont work because of this #If this were to work, it would show a comparison between actual results, and predicted results #This helps show the accuracy and precision of machine learning
# Create the cross tabulation of predicted vs. actual
#CrossTable(x = wbcd_test_labels, y = wbcd_test_pred,
# prop.chisq = FALSE)
# try several different values of k
wbcd_train <- wbcd_n[1:469, ]
wbcd_test <- wbcd_n[470:569, ]
#Had to comment this out as well… #this i another comparison using the crosstable function in order to, further compare it using our new values for K
#K=1
wbcd_test_pred <- knn(train = wbcd_train, test = wbcd_test, cl = wbcd_train_labels, k=1)
#CrossTable(x = wbcd_test_labels, y = wbcd_test_pred, prop.chisq=FALSE)
#Each of these, next several chunks would result in different numbers of accuracy and precision when it comes to overall machine learning results #this is because we are continously changing the K value, and giving it opportunity to understand more data #It is a happy balance that will give the best possible results
#k=5
wbcd_test_pred <- knn(train = wbcd_train, test = wbcd_test, cl = wbcd_train_labels, k=5)
#CrossTable(x = wbcd_test_labels, y = wbcd_test_pred, prop.chisq=FALSE)
wbcd_test_pred <- knn(train = wbcd_train, test = wbcd_test, cl = wbcd_train_labels, k=11)
#CrossTable(x = wbcd_test_labels, y = wbcd_test_pred, prop.chisq=FALSE)
wbcd_test_pred <- knn(train = wbcd_train, test = wbcd_test, cl = wbcd_train_labels, k=15)
#CrossTable(x = wbcd_test_labels, y = wbcd_test_pred, prop.chisq=FALSE)
wbcd_test_pred <- knn(train = wbcd_train, test = wbcd_test, cl = wbcd_train_labels, k=21)
#CrossTable(x = wbcd_test_labels, y = wbcd_test_pred, prop.chisq=FALSE)
wbcd_test_pred <- knn(train = wbcd_train, test = wbcd_test, cl = wbcd_train_labels, k=27)
#CrossTable(x = wbcd_test_labels, y = wbcd_test_pred, prop.chisq=FALSE)