Introduction to Statistics and Basics of Mathematics for Data Science - The Hacker's Way
Jupyter Notebook Python
Switch branches/tags
Nothing to show
Clone or download
Latest commit d00b0d1 Nov 26, 2017
Permalink
Failed to load latest commit information.
data Workshop Jan 27, 2017
img Updated video link Nov 21, 2017
.gitignore minor edits Jul 26, 2016
.swp Post Workshop Committ Jul 30, 2016
LICENSE Initial commit May 23, 2016
Module_0_Introduction.ipynb workshop Sep 3, 2017
Module_0b_Learning_from_Data.ipynb workshop Sep 3, 2017
Module_1a_linear_algebra_inverse.ipynb workshop Sep 3, 2017
Module_1b_linear_regression_ols.ipynb Added linear model Sep 6, 2017
Module_1c_linear_regression_ridge.ipynb workshop Sep 3, 2017
Module_1d_linear_regression_gradient.ipynb workshop Sep 3, 2017
Module_1e_logistic_regression.ipynb Workshop Jan 27, 2017
Module_1f_Exercise_LinearRegression-Completed.ipynb Updated Post Workshop Jan 31, 2017
Module_1f_Exercise_LinearRegression.ipynb workshop Sep 3, 2017
Module_1g_Exercise_LogisticRegression-Completed.ipynb Workshop Jan 27, 2017
Module_1g_Exercise_LogisticRegression.ipynb exercises Dec 2, 2016
Module_2a_Basic_Stat_Metrics.ipynb New Order Dec 2, 2016
Module_2b_probability.ipynb a/b testing Dec 4, 2016
Module_2c_resampling.ipynb workshop Sep 3, 2017
Module_2d_Distributions.ipynb a/b testing Dec 4, 2016
Module_2e_HypothesisTesting.ipynb New Order Dec 2, 2016
Module_2f_ABTesting.ipynb Workshop Jan 27, 2017
Module_2g_HackerStats.ipynb A/B Sep 3, 2017
Module_3a_linear_algebra_eigenvectors.ipynb workshop Sep 3, 2017
Module_3b_principal_component_analysis.ipynb Workshop Jan 27, 2017
Module_3c_principle_component_analysis_example.ipynb Added Cluster Dec 4, 2016
Module_3d_cluster_analysis.ipynb workshop Sep 3, 2017
Module_4a_Terminologies.ipynb New Order Dec 2, 2016
Module_4b_References.ipynb New Order Dec 2, 2016
README.md Updated video link Nov 21, 2017
check_env.py minor edits Jul 26, 2016
installation.md minor edits Jul 26, 2016
modelvis.py Modelvis Nov 26, 2017
talk.md Workshop Jan 27, 2017
talk.pdf Added Talk Dec 3, 2016
tree.dot Workshop Jan 27, 2017

README.md

HackerMath for Machine Learning

“Study hard what interests you the most in the most undisciplined, irreverent and original manner possible.” ― Richard Feynman

Math literacy, including proficiency in Linear Algebra and Statistics,is a must for anyone pursuing a career in data science. The goal of this workshop is to introduce some key concepts from these domains that get used repeatedly in data science applications. Our approach is what we call the “Hacker’s way”. Instead of going back to formulae and proofs, we teach the concepts by writing code. And in practical applications. Concepts don’t remain sticky if the usage is never taught.

The focus will be on depth rather than breadth. Three areas are chosen - Hypothesis Testing, Supervised Learning and Unsupervised Learning. They will be covered to sufficient depth - 50% of the time will be on the concepts and 50% of the time will be spent coding them.

More details at http://amitkaps.com/hackermath

See it in action: Binder

Module #1: Hypothesis Testing

Math Concepts

  • Basic Metrics: Mean, Variance, Covariance, Correlation
  • Discrete Probability Distributions: Bernoulli, Binomial
  • Cumulative Mass Function, Probability Mass Function
  • Continuous Probability Distributions: Poisson, Uniform, Normal, Beta, Gamma
  • Cumulative Distribution Function, Probability Density Function

ML Applications

  • Direct Simulation
  • Shuffling
  • Bootstrapping
  • Application to A/B Testing

Module #2: Supervised Learning

Math Concepts

  • Basics of Matrix Operation
  • Matrix Determinant, Inverse
  • Basics of Linear Algebra
  • Solve for Ax=b for nxn
  • Solve for Ax=b for nxp+1

ML Applications

  • Linear Regression
  • L2 Regularization
  • Gradient Descent
  • Linear Classifier
  • Logistic Regression

Module #3: Unsupervised Learning

Math Concepts

  • Matrix Projections
  • Solve for Ax=λx for nxn
  • Eigenvectors & Eigenvalues
  • Distance in Vector Space

ML Applications

  • Dimensionality Reduction
  • Principle Component Analysis
  • Cluster Analysis

Target Audience

  • Someone with a background in programming who wants to pick the math needed for data science and get a flavor for different data science problems
  • Someone who is a beginner in data science or has been doing data analysis (at least using Excel at a minimum) and wants to pick skills to take the next step in their data science career

Pre-requisites

  • Having a basic understanding of linear algebra would help. And we know you may have forgotten all about it from your school or college days. So here is an amazing video playlist by @3blue1brown to learn The Essence of Linear Algebra in a very visual way.
  • Also, a touch of calculus knowledge would make it also easier. So if you want to brush up your basic calculus skills, then @3blue1brown has another amazing video playlist to learn The Essence of Calculus in a very visual way.
  • Programming knowledge is mandatory. You should, at the bare minimum, be able to write conditional statements, use loops, be comfortable writing functions and be able to understand code snippets and come up with programming logic. Since we will be using Python - brush up your basics there. Specifically, we expect you to know the first three sections from this: http://anandology.com/python-practice-book/

Software Requirements

You will require the Python data stack for the workshop. Please install Ananconda for Python 3.5 for the workshop. That has everything we need for the workshop. For attendees more curious, we will be using Jupyter Notebook as our IDE. We will be introducing numpy, scipy, seaborn, matplotlib, plotnine, statsmodel and scikit-learn.

The working repo for this workshop is at https://github.com/amitkaps/hackermath/


Authors:

Amit Kapoor

Bargava Subramanian