The data set used in this assignment comes from the Car Evaluation Data Set that is available at http://archive.ics.uci.edu/ml/datasets/Car+Evaluation. The data set is donated by its creator Marko Bohanec at 1997.

The data set used in this assignment is stored in the csv file CarData.csv. There are 1728 instances in this data set.

There are 6 descriptive attributes in this data set:

• BUY: the buying price, with domain {vhigh, high, med, low}.
• MAINT: the maintenance price, with domain {vhigh, high, med, low}.
• DOORS: the number of doors, with domain {2, 3, 4, 5more}.
• PERSONS: the capacity in terms of persons to carry, with domain {2, 4, more}.
• LOG_BOOT: the size of luggage boot, with domain {small, med, big}.
• SAFETY: the estimated safety of the car, with domain {low, med, high}.

The target attribute, EVALUATION, provides a description of the car's value as unacceptable (unacc), acceptable (acc), good (good), or very good (vgood).

Your tasks:

Overall, your task is to build a Naive Bayes Classifier.

Specifically, you need to perform the following tasks and document the process along the way:

1. Generate and store all the probabilities that will be used by your Naive Bayes Classifier based on the given data in CarData.csv. If any of these probabilities is 0, use Laplace smoothing algorithm wih k=2 to smooth the noises. (You can use Your Lab 4 program and result with the extension of Laplace smoothing if needed.)
2. Design and implement the Naive Bayes Classifier, and generate the class labels for each data item that's in the training data set CarData.csv, regardless what target class label the data item actually has. Save your predication result to a csv or text file.
3. Implement a program to compare the class labels generated by your Naive Bayes Classfier and their given class labels, and fill the following table with corresponding counts or percentages:

   		Your Result
   		unacc	acc	good	vgood
   Given Result	unacc
   	acc
   	good
   	vgood

What to Submit:

Submit a document that explains the whole process of building, applying and evaluating the Naive Bayes Classifier using the given Car Data set. Your document should include at least the following sections:

• Explain how all the necessary probabilities used later in the Naive Bayes Classifier are generated from the Car Data set. Present these probabilities in the document in a format that's easy to understand and interpret. Attach either the souce code file or the algorithm used to generate these probabilities as an appendix file.
• Explain how to predict the class label for each data object in the given data set, that is, explain how your Naive Bayes Classifier works. Attach either the source code file or the algorithm to make the prediction as an appendix file. Also attach the prediction result as an appendix file. The prediction result should be presented in a format that's easy to understand in the attached result file.
• Compare your prediction result with the given class label result. Present the comparison conclusion in a tabular format in the document. Attach the source code file or the algorithm used to do the comparison as an appendex file.

How to submit:

Choose one of the following two ways to submit your work:

• Login to your VIU Learn account, find the CSCI 479 course page, click on the "Assessment" drop-down menu, click on the "Assignments" item, then click on the folder named "A3". Then you can click on the "Add a File" button to browse and upload your document and appendix files.
• On csci server, in the directory that holds all of your assignment solution files, enter the command
  ~liuh/bin/submit 479 A3 .
  This submit script currently accepts files with the names of *.pdf, *.txt, *.csv, *.h, *.cpp, *.py, makefile.
  If you need to submit any file with different extension names, please contact your instructor before submitting.