Introduction

Multi-Modal Data: Combining Different Data Types

Learn to work with multi-modal data in Python. Combine tabular, text, image, and audio data for richer ML models. Master feature fusion, late fusion, joint embeddings, and practical integration patterns.

Video Data: Challenges and Opportunities

Learn to work with video data in Python. Understand video as image sequences, frame extraction, optical flow, scene detection, action recognition, and practical video analytics with OpenCV.

Understanding Audio Data for Analysis

Learn to work with audio data in Python. Master waveforms, sample rate, spectrograms, MFCCs, Librosa, feature extraction, audio classification, and speech-to-text for data science.

Working with Image Data in Python

Learn to work with image data in Python. Master Pillow, OpenCV, image arrays, preprocessing, augmentation, feature extraction, and when to use CNNs vs. pre-trained models for computer vision.

Introduction to Text Data and Natural Language

Learn to work with text data in Python. Master tokenization, cleaning, TF-IDF, word embeddings, sentiment analysis, topic modeling, and when to use classical NLP vs. transformer models.

Working with Geospatial Data in Python

Learn to work with geospatial data in Python. Master coordinate systems, Shapely geometries, GeoPandas, spatial joins, choropleth maps, distance calculations, and common geospatial analysis patterns.

Introduction to Data Catalogs

Learn what data catalogs are and why they matter for data science. Understand metadata management, data discovery, business glossaries, ownership, and how to build a lightweight catalog in Python.

Understanding Data Provenance and Lineage

Learn what data provenance and data lineage mean for data science. Understand how to track data origins, transformations, column-level lineage, and why it matters for debugging, compliance, and trust.