Needs to be in C++

Given the training data set Dtrain specified by TrainData.csv and the test data set Dtest specified by TestData.csv, where D = {< x [i] , y [i] > | i = 1...n}, s.t. each x =< x1, x2, ..., xL > with a class label y {1, 1}. Moreover, each of the xi , i = 1, ..., L might be either discrete or continues valued, s.t.

Features with continues values: x1, x3, x5, x11, x12, x13

Features with discrete values: x2, x4, x6, x7, x8, x9, x10, x14

Please complete the following tasks. 1. (2.5 points) Build a naive Bayes classifier by returning the sets of parameters (P(y), P(xi |y), i = 1, ..,L) based on the Naive Bayes Algorithm.

P(y|x) P(y)P(x|y) = P(y) Y L i=1 P(xi |y)

A feature xi takes m discrete values in class yk, a discrete distribution of P(x = xi |y = yk) can be learned by parameters i,k,1, i,k,2, ..., i,k,m, s.t. P(x = xi |y = yk) = Pm j=1 i,k,j = 1.

A feature xi takes continuous values in class yk, we can learn a one-dimensional Gaussian for that feature. P(x = xi |y = yk) = N (i,k, 2 i,k ), where i,k and 2 i,k are respectively the mean and variance of feature xi for the instances in class yk.

2. (2.5 points) Apply your classifier for assigning a class label for each of the new instances x =< x1, x2, ..., xL > in the testing set by

y argmaxyk P(y = yk) Y L i=1 P(xi |y = yk)

Evaluate your classifier by accuracy

ACC(x [i] )Dtest = 1 |Dtest| Xn i=1 L(y i , y i )

where y i is the assigned class label by the classifier and y i is the true class label.

L(y i , y i ) = ( 1 if y i = y i 0 if y i 6= y i

Submission:

Submit a report that contains the screen shots for each of the questions.

Show the detailed parameters

Show the accuracy value

Submit the program source code file.