$1.$ The following table consists of training data from an employee database. $"\backslash (31\backslash$ldots $35\backslash )"$ for age represents the age range of $31$ to $35.$ For a given row entry, count represents the number of data tuples having the values for department, status, age, and salary given in that row. There are a total of $\backslash (\backslash$mathbf$\{165\}\backslash )$ data records.

Let status be the class label attribute.

Design a multilayer neural network $($MLP$)$ for the given data.

$($a$)$ How to encode the categorical data, ordinal data in geneal? And specifically how are you going to code department, age, salary? $(10$pts$)$

$($b$)$ How many hidden layers, how many nodes in hidden layers do you want to design? $(10$pts$)$

c$)$ Draw your ANN model, and label the nodes in the input and output layers. $(10$pts$)$

d$)$ Implement the multilayer neural network obtained above, show the code to train the model with selection of parameters like activation, initialization, the learning rate, optimizer, etc. $($Just for home work purposes, you can assume this is the training data, you have another set of data for testing $)(10$pts$)$

$```$

Ex: X$\_$train$=...$

Y$\_$train$=...$

myANN$=$MLPClassifier $(...)$

myANN.fit$($X$\_$train, Y$\_$train$)$;

y$\_$pred $=$ myANN.predict$($X$\_$train$)$;

$```$