Data cleaning and preprocessing using Pandas and Scikit-learn

On December 9, 2024, at 7:00 PM, UP Data Science Society held a mentorship workshop on Zoom about data cleaning and preprocessing using Pandas and Scikit-learn. The session showed how cleaning and preparation are automated with the two Python libraries so that a dataset is ready for visualization and for training a machine learning model, and why this stage matters in the data science lifecycle.

The speaker was Junel Alje Isanan, the society’s Logistics Co-Director. He is a Senior ICT Assistant at the Computational Science Research Center in UP Diliman, was a Full-Stack Developer at Bespoke Cloud, and worked as a freelance tutor in his early years at the university. His research interests are AI explainability and large language models.

MS Excel for data cleaning and preparation

Two weeks earlier, on November 25, 2024, at 7:00 PM, the society ran a related mentorship workshop, “MS Excel for Data Cleaning and Preparation,” on Zoom and Facebook Live. It had been announced on November 20 for Saturday, November 23, and was moved to November 25 on the day. Mr. Jomar M. Jordas taught the session, which went through the early stages of the data science lifecycle and treated intermediate cleaning and preparation in a spreadsheet as the groundwork for accurate preprocessing.

Jordas is an Analytics Engineer at Zeller Australia and an MS Finance candidate at the UP Diliman Virata School of Business. He has worked as a data professional since 2021, and his research interests are time series analysis and natural language processing.

The two sessions covered the same step of the pipeline with different tools, a spreadsheet first and then Python libraries.