Resources
Before Applied Data Science at Berkeley, if you don’t have a working knowledge of Python, you can update your skills with the on-line Python Bootcamp offered by UC Berkeley and the Institute of Data Science. We recommend that you understand the content of at least the first 6 video lectures.
- Bootcamp Website
- BIDS Website with training videos
- Python Bootcamp Videos on YouTube
- Code and notebooks on Github
To get started, first, install the Anaconda Environment which includes a Jupyter Notebook for interactive Python. Then, see this Github link for install instructions for all necessary tools including install examples in Jupyter Notebook format.
Suggestions for Data-X project may be submitted here:
https://goo.gl/forms/h6cAxZS3Il2F0k4F2
Visit Github for Lectures Materials (Click Here)
(Note: All lectures and code samples will be available at this Github Repository )
Ref ERC06: Google's Machine Learning for Devs Guide
Ref M01: Covariance and Correlation
Ref M02: Basic Matrix Math
Ref M03: Gradient Descent
Ref M04: Linear-vs-Logit
Ref M05: Regression Analysis
Ref M06: Markov Chains (simplified) (complete) (Wikipedia)
Ref CS01: Python 3 Quick Reference (download) (weblink), Python 2.7 Quick Reference
and Python Data Structures for 2.7.
Ref CS02: NumPy Getting Started v1-12
Ref CS03: Pandas in 10 Min
Ref CS04: Pandas-SciPy-Numpy-Cheatsheet
Ref CS05: TensorFlow Getting Started
Ref CS06: SciKitLearn Reference Guide, Algorithm Cheat Sheet
Ref CS07: MatPlotLib Guide
Ref CS08: JSON File Format, JSON Examples
Ref EROC01 (free): Book: Introduction to Statistical Learning
Ref EROC02: Book: Hands-On Machine Learning with Scikit-Learn and TensorFlow
Ref EROC03: MOOC: Machine Learning, Coursera
Ref EROC04: DataCamp -- Register for Data-X account (must use berkeley.edu domain): Link to Form
Ref ERC05: Artificial Intelligence — The Revolution Hasn’t Happened Yet
Ref ERC06: Google's Machine Learning for Devs Guide