Introduction to Data Science

Overview

You will start with an overview of the course and then an introduction to statistics and data science. You will learn some of the tools of the trade in scientific python, particularly numerical python, Jupyter nodebooks, and handling data.

Goals

• Getting overview of the course, activities and policies

• Setting up your environment on Google Colab

• Gain familiarity with Jupyter Notebooks and Numerical python

• Learn about handling and describing data

• Learn about the importance of clustering data in physics

• Learn how to find structure in data (clustering)

  • KMeans, Spectral Clustering, DBSCAN

• Measure and reduce dimensionality

• Adapt linear models to nonlinear problems

• Learn about Kernel functions

Lecture Materials

• Slides

• Jupyter Notebooks and Numerical Python

• Handling Data

• Visualizing Data

• Finding Structure in Data

• Measuring and Reducing Dimensionality

• Adapting Linear Methods to Non-Linear Data and Kernel Functions

Homework Assignment

• Homework 01: Introduction to Data Science

Supplemental Readings

• A Whirlwind Tour of Python, Jake VanderPlas: free PDF, notebooks online.

• IPython: Beyond Normal Python

• Python Data Science Handbook

• Introduction to NumPy

• Data Manipulation with Pandas

• Scikit-learn

• Whitening transformation

• Eigenvalue/Eignvector refresher

• Principle Component Analysis

• PCA Step-by-Step

• Blind Signal Separation

• Kernel Method

• Mercer’s Theorem

• Similarity Measure

• Nonlinear Dimensionality Reduction by Locally Linear Embedding