CS 91.3 Lab 6: Research Analysis

Due Tuesday, March 1st, by midnight (23:59 EST)

Goals

The goals for this lab assignment are:

  • Learn how to analyze your data

  • Get familiar with Classification

  • Get familiar with Supervised Learning

  • Get familiar with code of Nearest Neighbors

  • Get familiar with code of Ensemble methods

  • Get familiar with poster formatting with AAAI

  • Get familiar with paper formatting with NeurIPS

1. Nearest Neighbors (30 min)

  • Example 1: Comparing Nearest Neighbors …​

    1. Download Python source code: plot_nca_classification.py

  • For the example above:

    1. Download the existing code

    2. Set up the coding environment

    3. Run the existing code

    4. Track the execution time and write them down in your notes.txt file.

    5. Take the screenshots of your results after running the code.

  • Write in your own words what 'Nearest Neighbors' is in your notes.txt file in four to five sentences.

2. Ensemble methods (30 min)

  • Example 1: Plot the decision boundaries …​

    1. Download Python source code: plot_voting_decision_regions.py

  • For the example above:

    1. Download the existing code

    2. Set up the coding environment

    3. Run the existing code

    4. Track the execution time and write them down in your notes.txt file.

    5. Take the screenshots of your results after running the code.

  • Write in your own words what 'Voting Classifier' is, in four to five sentences, in your notes.txt file.

3. Your research project (SIX hours)

  • Finish the writing for your two-page poster. Your drafts should include:

    1. Title, Authors, and Abstract

    2. Introduction

    3. Method

    4. Result

    5. Discussion

    6. Conclusion

  • Add more details to your ten-page paper.

  • Graders and Reviewers will look for more details in your ten-page paper to better understand your two-page poster.

  • The ten-page paper will not be graded for this lab, but will get reviewers' feedback.

  • Submit your Python code, make sure the README is clear for recreating your results.

    1. Review Example Paper 1: 'Fast and Accurate Multiclass …​' in Lab 4

    2. Write your README instructions similar to the example README, in your notes.txt file.

    3. Create a GitHub link for your research project, similar to this 'Fast and Accurate …​' example.

    4. Test your Python code on both of your computers.

    5. Take the screenshots of your results after running the code.

    6. Please do NOT email me your dataset, instead, write a guide where to download it similar to README above.

4. Submission Guide

  • Each team only submits one file, lab_6_lastname1_lastname2.zip, including

    1. lab_6_poster_lastname1_lastname2.PDF for your two-page poster draft in AAAI format.

    2. lab_6_paper_lastname1_lastname2.PDF for your ten-page paper draft in NeurIPS format.

    3. notes_lab_6_lastname1_lastname2.txt for your notes, including the README.

    4. A screenshot folder for all the screenshots files (PNG or JPEG), total size less than 10 M.

    5. A code folder for ALL your Python Code and support files to recreate your results.

    6. Include A GitHub link for your research project in your notes.txt file.

5. Notes

  • Each team only needs to submit one ZIP file, with both names on it.

  • Email 'xqu1@swarthmore.edu' your Lab 6 files as lab_6_lastname1_lastname2.zip.

  • The team members from the same team may get the same score.

  • Lab assignments will typically be released on Wednesday and will be due by midnight on the following Tuesday. This lab was released on 02/23 and will be due by midnight on 03/01.