Assignment 2: Machine Learning

Leveraging insights from EDA to build, train, and evaluate predictive Machine Learning models across three distinct data modalities.

Select a modality to view detailed ML work

1. Tabular Data

Structured data in table form (CSV, Excel). Analysis includes basic statistics, missing values handling, and feature distributions.

Dataset: Heart disease
View Tabular ML →

2. Text Data

Unstructured text (documents, reviews). Analysis includes word clouds, length distributions, and text preprocessing.

Dataset: PubMed-20k-rct
View Text ML →

3. Image Data

Image datasets (classification/detection). Analysis includes sample grids, resolution checks, and label distributions.

Dataset: Intel Image Classification
View Image ML →