Make sure to load the source code files within the package.
The data set items examples that that you may use in your project attached here:
[login to view URL] the document
The item data sets includes a list of items and a several transactions combining these item sets.
All datasets should be distinct from each other. Some overlapping items are ok. The idea is your program should work for different data sets.
You must run the code in an IDE editor or command line terminal to show that it's fully working
In addition, use GitHub and Jupyter Notebook to load and run your project. And add your GitHub repository link.
If you are working on Jupyter as IDE, save your code as "Python" to include it. Jupyter source code is not accepted.
Your final project file that you will submit must be a one file with the naming convention, and should be zip or tar so that you have all of your artifacts included in one compressed file.
Use several support and confidence values for each dataset to show and prove that your program works for any database. Of course, not expecting same result from different dataset even with same input parameters.
The class TA. This is also the email you will use to add her to your GitHub repository along with mine.
The final report which is a zip file should include
1. Report file explaining your implementation, code usage, screen shots, etc... (that is a PDF or doc file).2. The source code ready to run.3. The data sets you used.
I added a pdf example (that is equivalent to number 1 above).