Question 3 - my take iris.txt contains 150 data points, each with four predictor variables and one categorical response PDF

Preview

Summary

my takeiris.txt contains 150 data points, each with four predictor variables and one categorical response...

Description

Question 3.1 Using the same data set (credit_card_data.txt or credit_card_data-headers.txt) as in Question 2.2, use the ksvm or kknn function to find a good classifier: using cross-validation (do this for the k-nearest-neighbors model; SVM is optional); and splitting the data into training, validation, and test data sets (pick either KNN or SVM; the other is optional). # Get the libraries kernlab and kvnn library(kernlab) library(kknn) # Load the datafiles and print the header cc_data = read.delim(file.choose(),header=F) head(cc_data,10)

#Set seed to ensure reproducability set.seed(1) # Create a mask for ensuring the Training , Validation and Test set are in 70%,15%,15% ratio # Training Set : 70% Data mask_cc_training = sample(nrow(cc_data), size = floor(nrow(cc_data) * 0.7)) # Training data set cc_trainingset = cc_data[mask_cc_training,] #Filter out the other data into validation and test sets other_data = cc_data[-mask_cc_training,] # 15% of total data (50% of the other data is test and rest is validation) mask_cc_validation = sample(nrow(other_data), size = floor(nrow(other_data)/2)) # Validation and Test Data sets cc_validationset = other_data[mask_cc_validation,] cc_testset = other_data[-mask_cc_validation,]

# There are 9 SVM models and 20 KNN models accuracy = rep(0,29) # 1-9 are SVM, 10-29 are KNN # there are certain c's to be put in place to test. amounts_c = c(0.00001, 0.0001, 0.001, 0.01, 0.1, 1, 10, 100, 1000)

for (i in 1:9) { #Fitting using training dataset using C classification and simple linear kernel (vanilladot) cc_scaledmodel = ksvm(as.matrix(cc_trainingset[,1:10]),as.factor(cc_trainingset[,11]), type = "C-svc",kernel = "vanilladot",C = amounts_c[i],scaled=TRUE) # Pridcting the Model predicted = predict(cc_scaledmodel,cc_validationset[,1:10]) # Matching the model prediction to actual classification accuracy[i] = (sum(predicted == cc_validationset$V11) / nrow(cc_validationset))*100 }

# Model Accuracy Percentage accuracy[1:9]

# Getting the best SVM model from the above exercise cat("Top SVM model is : ",which.max(accuracy[1:9]),"\n")

cat("Top C value is : ",amounts_c[which.max(accuracy[1:9])],"\n")

cat("Top validation set accuracy is (%)=",max(accuracy[1:9]),"\n")

# Keeping the best model using above training data cc_scaledmodel = ksvm(as.matrix(cc_trainingset[,1:10]),as.factor(cc_trainingset[,11]),type = "C-svc",kernel = "vanilladot",C = amounts_c[which.max(accuracy[1:9])],scaled=TRUE)

cat("Test data set accuracy = ",sum(predict(cc_scaledmodel,cc_testset[,1:10]) == cc_testset$V11) / nrow(cc_testset),"\n")

# Now, training SVM models for (k in 1:20) { # Fitting the k-nearest-neighbor models using the training dataset via kknn knn_model = kknn(V11~.,cc_trainingset,cc_validationset,k=k,scale=TRUE) # Comparing model with validation dataset

prediction = as.integer(fitted(knn_model)+0.5) # rounding off to 0 or 1 accuracy[k+9] = (sum(prediction == cc_validationset$V11) / nrow(cc_validationset))*100 } # Percentage of accuracy of the models accuracy[10:29]

# Now, we have to find the best KNN model with its accuracyracy % in validation data cat("Top KNN model number is :",which.max(accuracy[10:29]),"\n")

cat("Top Validation accuracy percentage is : ",max(accuracy[10:29]),"\n")

# Using test data to verify the actual results knn_model= kknn(V11~.,cc_trainingset,cc_testset,k=which.max(accuracy[10:29]),scale=TRUE) prediction = as.integer(fitted(knn_model)+0.5) cat("Test Data set accuracy = ",sum(prediction == cc_testset$V11) / nrow(cc_testset),"\n")

# The best model in evaluation data is below # Checking whether kvsm or kknn method is better if (which.max(accuracy)...