Navigation

• Main Page

• Random Page
• Create a new Page
• All Pages
• Categories

• Administration
• File Management

• Login/Logout
• Language Selection
• Your Profile
• Create Account

Assignment 1

The Task: Implement the Naive Bayes algorithm

• Implement the Naive Bayes methods for discrete attributes (Named as NBD)
• Implement the Naive Bayes methods for continuous attributes in two ways: 1. Discretize the continuous attributes and then apply NBD (Named as NBCD);2. Use Gaussian distribution to estimate the conditional probability (Named NBCG)
• Conduct 10 fold cross validation on the benchmark data with TF features by NBD, report the mean and standard variance of accuracy
• Conduct 10 fold cross validation on the benchmark data with TF-IDF features by NBCD and NBCG, report the mean and standard deviation of accuracy.
• Write a brief report to show your results, and think about the question: Among the three methods for the same task, which one is better? Can you give an analysis?

Benchmark Dataset

• Data: Forum Classification based on the posts (from the Lily BBS) [Download]

• Format: The zip file contains 10 txt files. Each file contains more than 100 lines, and each line represents a raw post, where the post is kept in the form of "title\tcontent", for example

• Preprocess: (For this step, you can use any language or any tool) You need to extract TF or TF-IDF features for yourself from the raw text data. A quick introduction can be found here. For our case, you also need to do the Tokenization job to get the words from the Chinese sentences. We recommend you to use some existing tools like jieba for python, or IKAnalyzer for java for the tokenization. When you encode the words to feature, you may also think about the Stop words. We provide a version of the Chinese stop words list here, while you may find some other ones better. There may be some noises in the data. However, in real data mining task, there are always noises. So try to deal with the noise by yourself, and DO NOT complain about that. Please finish the pre-processing job carefully since it will be also used in the following assignments.

Programming Language

• Python / Java / MATLAB
• Once you pick up one of them, the following assignments MUST be based on the SAME Language, otherwise you will NOT get the corresponding grades.

Submission

• Please use this MSWord template to report your results.
• Do NOT plagiarize, plagiarism will be seriously penalized: You should be careful on writing your report. Whenever you are using words and works of others, citations should be made clear such that one can tell which part is actually yours. Details about how to identify a plagiarism can be found in "Introduction to the Guidelines for Handling Plagiarism Complaints".
• Do NOT falsify results, data fraud will be even more seriously penalized: You should honestly record your results in the report, NEVER EVER modify the performance results manually.
• Pack your report and code into a zip file named with your student ID, e.g., 'MG1433001.zip'. If you have multiple submissions, add an extra '_' with a number, such as 'MG1433001_1.zip'. We will use the the version with the largest number as your final submission.
  
  
  • The file format should be zip, no other format is acceptable!
    
  • NO submission after the deadline is acceptable!
    
  • NO email submission will be accepted!

Evaluation

• Efficiency
• Performance
• Code style

• Technique: clearly explain all the component you used in your implementation
  
• Language: concise, precise, and logical.
  

Contact TA