There should be no additional libraries to run the code beyond the Anaconda distribution of Python (versions 3.*). The code was tested on local Mac.
The code has printed out the version for important libraries for future reference.
I am personally interested in building and maintaining good habits. I took reading as an example, and chose Reading habit Dataset to better understand:
- What factors about an individual contributed to number of books to read?
- Which media (printed books, e-books, audiobooks) results in more books to be read?
- How do the book lovers differentiate themselves from others?
The ipynb notebook includes all code to reproduce exploratory data analysis. (In case GitHub preview does not show some tables correctly, please download to check the correct content.)
The reading-habit-dataset/ directory is where dataset should be stored as csv.
Please find the summary of the data analysis results in 3 Tips to Build a Good Reading Habit blog post.
- Reading habit Dataset
- Japanese version of the book "Introduction to Machine Learning with Python"
- Kaggle competition House Prices: Advanced Regression Techniques shows many ideas related to data analysis
- Stratified sampling for regression LB: 1.4627