In this problem, you will build classifiers based on Gaussian discriminant analysis. Unlike Home-work 1, you are NOT allowed to use any libraries for out-of-the-box classification (e. g.sklearn).You may use anything innumpyandscipy. The training and test data can be found on in the post corresponding to this homework. Don’t usethe training/test data from Homework 1, as they have changed for this homework. Submit yourpredicted class labels for the test data on the Kaggle competition website and be sure to includeyour Kaggle display name and scores in your writeup. Also be sure to include an appendix of yourcode at the end of your writeup.(a) Taking pixel values as features (no new features yet, please), fit a Gaussian distribution toeach digit class using maximum likelihood estimation. This involves computing a mean and acovariance matrix for each digit class, as discussed in lecture. Hint:You may, and probably should, contrast-normalize the images before using their pixelvalues. One way to normalize is to divide the pixel values of an image by thel2-norm of itspixel values.(b) (Written answer) Visualize the covariance matrix for a particular class (digit). How do thediagonal terms compare with the off-diagonal terms? What do you conclude from this?(c) Classify the digits in the test set on the basis of posterior probabilities with two different ap-proaches.

For a typical middle-income family, what is the estimated cost of raising a child to the age of 18? $145,500 $245,340 $304,340 $455,500

3.11.3 quiz: comparing and analyzing function typesquestion 4 of 102 pointswhat can you say about the y-values of the two functions f(x) = 3x2-3 andg(x)=2* - 3?

Create a class hand in its own module. one object of class hand represents a hand of cards and so one object stores a number of card objects. for this assignment you will submit three separate modules, one with the definition of class card, one with the definition of class hand and one with the main application that thoroughly tests class hand.class hand must contain the following four methods: 1) , numcardsinhand) takes an integer as parameter and initializes a hand object with numcardsinhand card objects inside it. these card objects are generated randomly. for simplicity, assume an infinite number of decks of cards.2) bjvalue(self) returns the blackjack value for the whole hand of cards3) ) returns a string containing all the cards in the hand4) hitme(self) adds one randomly generated card to the handcreate a main program in its own module that thoroughly tests class hand. you will have three modules/files to upload to your etudes assignment submission: card.py, hand.py and the module that contains your main program.two alternatives for extra credit - you cannot get credit for both! (+1 point): after you have thoroughly tested the class hand and all of its methods, add code to your main program that stores one hand object as a pickle file and reads it back into a new hand object. you are only eligible for this extra credit if class hand has all four of the methods above working.or(+2 points): after you have thoroughly tested the class hand and all of its methods, add code to your main program that stores one hand object as a text file on the disk and reads it back into a new hand object. you are only eligible for this extra credit if class hand has all four of the methods above working.notes: -start by making any and all modifications suggested by my comments to your previous submission of class card from assignment #6 "a robust card object"-once your class card is tested and working well, you will not make any further modifications to it for the purposes of class hand.-you can keep the test code for class card intact. if it is indented inside an if __name__ == "__main__", then it will not be executed when your main program's module imports it.-to save time, write and test one method for class hand at a time.-under no circumstances are you to attempt the extra credit until you are completely finished with writing and testing all the methods in class hand.