Assignment 5- Nave Bayes The Car Evaluation Dataset is a collection of data derived from a hierarchical decision model developed for the purpose of demonstrating an expert system for decision making. The original model was created by M. Bohanec and V. Rajkovic in 1990 and was used to showcase the capabilities of the DEX system. The dataset includes examples that have been stripped of their structural information, focusing solely on the relationship between cars and six input attributes: buying, maint, doors, persons, lug_boot, and safety. By removing the structural information, the dataset becomes a valuable resource for testing constructive induction and structure discovery methods. Due to its well-defined underlying concept structure, the Car Evaluation Database provides a suitable environment for evaluating and developing algorithms and techniques that aim to uncover patterns, relationships, and decision rules within the data. Researchers and practitioners can utilize this dataset to assess the effectiveness of various approaches in dealing with classification and decision-making tasks related to car evaluations. Overall, the Car Evaluation Dataset serves as a valuable resource for those interested in exploring constructive induction, structure discovery, and decision-making methodologies within the context of car evaluation and related domains. You can read more about it here. Attribute Information: Variable Name Description buying Buying price (Very high:4, High: 3, Medium:2, Low:1) maint Price of Maintenance (Very high:4, High: 3, Medium:2, Low:1) doors Number of doors (2, 3, 4 , 5 or more:5) persons Capacity in terms of person to carry (2, 4, more:5) Lug_boot The size of luggage boot (Small: 1, Medium: 2, Big:3) safety Estimated safety of car (low: 1, Medium:2, High: 3) class This shows the value of the car in 5 classes (unacceptable:1, Acceptable:2, Good:3, Very good:4) Here are the tasks: 0) As you see some of the data in the dataset are in form of the text. Your job is to convert them into numerical value because sometimes the coding cannot handle this. You can simply use Excel for this job. 1)Assign y to the "class" variable and X to the rest of the variables. 2) Split the data into 80% for training and 20% for test use random_state=1 3) Create a Nave Bayes classifier using training data 4) Test the model using Test data, show confusion matrix and measure the accuracy 5) Now, answer to this question, based on your analysis, which class of your predictions had no misclassification? What is your conclusion from this finding? You are free to use either R or Python for this assignment, but the submission should be in HTML format. Note that if the variable is in the wrong data type. Make sure to convert the target variable into the appropriate type. This assignment contains two files: 1) Instructions (this file) 2) cars.csv