P3_CS580_M23

.pdf

School

University of Maryland, College Park *

*We aren’t endorsed by this school

Course

580

Subject

Computer Science

Date

Dec 6, 2023

Type

pdf

Pages

2

Uploaded by whorelindsey on coursehero.com

CS 580: Introduction to Artificial Intelligence Project 3: Decision Tree Classifier for Wines INSTRUCTIONS This Project is considered individual effort and the honor code applies when reviewing the submission. Submit your solution as P3_<username>.py , and your report P3_<username>.pdf , where <username> is your Mason account (i.e., your email account). NOTES: For this project, you are allowed to use the referenced code of the video and make some few changes. You are NOT allowed to use any predefined tool for the main core of the implementation (e.g. the decision tree, metric for splitting, etc.) otherwise, the Project is penalized with -30 points. It is not a wise decision to wait until the last minute to submit your project , this action may cause you not to submit your work or submit a wrong file. Once the submission link is closed, we do not accept resubmissions or email submissions, so it is the responsibility of the student to verify that the files are the correct ones and not corrupted. Multiple submissions are allowed, and the last attempt is graded. E XTRA C REDIT Category Score The last attempt was at most 24 hours before due date/time +5 points P ENALTIES Category Score Wrong file name .py -3 points Wrong file name .pdf -3 points Wrong format (it's not a pdf file) -4 points Wrong template (it's not the IEEE article template for conferences) -10 points The .py implementation is using predefined tools for the decision tree, metrics, etc. -30 points
CS580: Introduction to Artificial Intelligence George Mason University Prof. Ana Loreto González Hernández loreto@gmu.edu 2/2 Introduction A classifier in machine learning is an algorithm that automatically orders or categorizes data into one or more of a set of classes. Supervised classifiers are fed training datasets, from which they learn to classify data according to predetermined categories. Implementation In this project you will implement in Python a decision tree classifier for wines. The classifier must show how the decision tree was built, i.e., the attributes used for the classification and how were splitted. The attributes are specified in the header of the wines.cvs file, where the type of wine in each example is indicated. NOTE: The header was included in the original wines.cvs file only to indicate the attributes in each column, when implementing your classifier, remove the first line (header) from the wines.cvs file and overwrite the original file . Access the following link to watch the video that explains the code used for this project: https://www.youtube.com/watch?v=sgQAhG5Q7iY Deliverables Submit two files: the code P3_<username>.py and a report P3_<username>.pdf . After your implementation, run the classifier using the dataset for training. Perform a parameter tuning to determine values that will allow your classifier to achieve at least 85% accuracy . To get full credit on this aspect, it is not enough to just give the final values of the classifier parameters, but to explain in your report how the process was carried out to determine the parameter adjustment to obtain that precision, what values were tested and why you selected those values. Elaborate a report written in Latex using the IEEE article template for conferences and its format specifications. Include at least the following: Abstract and keywords Introduction Background Proposed Approach Experimental Results Conclusions References (at least three, including the textbook) At this point in the course, it is assumed that you are familiar with the information that each section should contain as a minimum requirement. Keep in mind that omitting basic information on your report may cause you to get partial credit. Note : Review the description of previous projects to remember the basic information that a conference document must contain.
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help