Lecture 3: Structured Data Processing (Part I)

(Last updated: Feb 2, 2024)

This lecture gives a tutorial about the Smell Pittsburgh project using a Jupyter Notebook. The learning goals can be found on this link.

Preparation

Do the preparation for the structured data processing module.

Materials

Below is the link to the online notebook:

• Structured Data Processing Tutorial Online Notebook

Follow the steps below to set up the notebook:

• Have the JupyterLab environment ready.
• Download the structured data processing module from the GitHub repository. Or you can also download the zip file from this link.
• Open the notebook file (docs/tutorial-structured-data.ipynb) and start working on the tasks.

Additional Resources

Below are the videos that students found useful in understanding more about the course materials:

• [Pandas Resample

  pd.DataFrame.resample()](https://www.youtube.com/watch?v=l4dvMiSDBzs)

• Python Rolling Window Functions explained in 4 minutes

Below are websites related to this tutorial:

• The Smell Pittsburgh Dataset
• The scikit-learn API
• The seaborn API
• The plotly API
• The pandas API
• The numpy API

Below are papers related to this tutorial:

• Quinlan, J. R. (1986). Induction of decision trees. Machine learning.
• Breiman, L. (2001). Random forests. Machine learning.