1. Introduction
8 minStep 1 of 15
EDA and regression on CPCB air quality data — predict AQI from pollutant concentrations
What you'll need
- •Needs pandas, numpy, matplotlib, seaborn, scikit-learn. Use unicode_escape when reading the CSV (course encoding).
Why this matters
Environmental ML is a real applied domain — you practice the full pipeline from messy government CSV to a sklearn model.
What you'll have at the end
A notebook that loads data.csv, explores pollutants (SO₂, NO₂, RSPM, SPM, PM2.5), trains a regressor, and reports error metrics.
pandassklearnregressionLabelEncodertrain_test_split
