際際滷

際際滷Share a Scribd company logo

Adopting data8 at a two year college

Download as PPTX, PDF
A
Ava Meredith

This document summarizes adopting the Data8 introductory data science course at two-year colleges. Data8 was designed to be accessible to a broad range of students without typical prerequisites. It combines inferential thinking, computational thinking, and a focus on social issues. The goals are diversity, equity, pedagogical clarity, scalability, and depth without computational barriers. Core concepts include critical thinking, experimentation, and understanding data limitations and uncertainty. The course uses Jupyter notebooks and Python and focuses on hands-on work and understanding concepts rather than package details.

1 of 13
Adopting Data8 at a Two-year College Presented by: Ava Meredith, Seattle Central College
What is Data 8? Data 8 is a popular introductory Data Science class at UC Berkeley Designed to be accessible to a broad range of students without the typical prerequisites for a data science class Data 8's unique model combines inferential thinking, computatianl thinking, and focus on social issues into a single, introductory course All materials for the course are available for free online under a CC license.
Data 8 Goals Diversity Equity Pedagogical Clarity Scalability Depth No computational barrier to entry
Core Concepts Critical thinking Don't take your data for granted Use the combination of CS + Stats as a feature, not a bug Focus on hands on work Determine if your inference is sound Experiment Know the right statistical tools for the job
Learn about data limitations Quantify and understand uncertainty in data Turn your data analysis into a decision Think of ways that you could be wrong Consider edge-cases
Focus on main ideas (shield the students from non essential topics) Use the data science module rather than many package APIs Use JupyterHub (no need for students to setup environment)
Observation and Visualization
Abstract cleaning data by providing pre-collected/cleaned data Provide further resources Aim the course for anybody, not just statistics or CS majors.
Intersections of Topics Intersectionality is a feature, not a bug Connect CS and statistics concepts Use interactivity to let people explore
Topics covered Programming fundamentals Statistics, sampling, and hypothesis testing Inference, prediction, and models Comparing distributions
Connector courses Connector courses offer the ways in which data science is applied in a domain knowledge field
Tech Stack Managing course content - Jupyter notebooks Programming language - Python 3 Primary data object and functions - Use of data analytics packages in Python (Data 8 wraps several) Handling the Python environment - Python dev environment managed with miniconda
Next Steps View the course online http://data8.org/ Free online textbook: https://www.inferentialthinking.com/chapters/intro Data Science Academic Resource Kit: https://data.berkeley.edu/education/ark

More Related Content

Adopting data8 at a two year college

  • 1. Adopting Data8 at a Two-year College Presented by: Ava Meredith, Seattle Central College
  • 2. What is Data 8? Data 8 is a popular introductory Data Science class at UC Berkeley Designed to be accessible to a broad range of students without the typical prerequisites for a data science class Data 8's unique model combines inferential thinking, computatianl thinking, and focus on social issues into a single, introductory course All materials for the course are available for free online under a CC license.
  • 3. Data 8 Goals Diversity Equity Pedagogical Clarity Scalability Depth No computational barrier to entry
  • 4. Core Concepts Critical thinking Don't take your data for granted Use the combination of CS + Stats as a feature, not a bug Focus on hands on work Determine if your inference is sound Experiment Know the right statistical tools for the job
  • 5. Learn about data limitations Quantify and understand uncertainty in data Turn your data analysis into a decision Think of ways that you could be wrong Consider edge-cases
  • 6. Focus on main ideas (shield the students from non essential topics) Use the data science module rather than many package APIs Use JupyterHub (no need for students to setup environment)
  • 8. Abstract cleaning data by providing pre-collected/cleaned data Provide further resources Aim the course for anybody, not just statistics or CS majors.
  • 9. Intersections of Topics Intersectionality is a feature, not a bug Connect CS and statistics concepts Use interactivity to let people explore
  • 10. Topics covered Programming fundamentals Statistics, sampling, and hypothesis testing Inference, prediction, and models Comparing distributions
  • 11. Connector courses Connector courses offer the ways in which data science is applied in a domain knowledge field
  • 12. Tech Stack Managing course content - Jupyter notebooks Programming language - Python 3 Primary data object and functions - Use of data analytics packages in Python (Data 8 wraps several) Handling the Python environment - Python dev environment managed with miniconda
  • 13. Next Steps View the course online http://data8.org/ Free online textbook: https://www.inferentialthinking.com/chapters/intro Data Science Academic Resource Kit: https://data.berkeley.edu/education/ark