ds-modules/data88-sp22

Data 88 - Environmental Data Analysis

Environmental Data Analysis (Data 88 Spring 2022)

Developer Team: Aaron Moore, Caitlin Yee, Kinsey Long, Peter Flo Grinde-Hollevik, Hans Ocampo

Environmental Data Analysis, taught by Dan Hammer, will teach practical skills to address climate change and environmental conservation using data and building on what you've learned in DATA 8.

The main branch of this Github repository will reflect the most recent Lecture notes. Note that the Datahub links will not be live until Wednesday at 10am PT, following the Tuesday lecture. In fact, all Lecture notes and topics are subject to change until the day of lecture. Additional resources for the course can be found on bcourses. You will need to be enrolled in the class to see the additional resources, but the Lectures will remain public.

Please contact Head TA Peter F. Grinde-Hollevik with any questions. He knows everything.

Lecture	Date	Summary	Topic	Datahub Link
Lecture1	01/18	Course overview & Introduction to Python	Environmental Justice	launch DataHub
Lecture2	01/25	Sort, merge, and aggregate tables	Environmental Justice	launch DataHub
Lecture3	02/01	Finding correlations	Environmental Justice	launch DataHub
Lecture4	02/08	HTTP Requests & emissions monitoring	Emissions monitoring	launch DataHub
Lecture5	02/15	Simple mapping	Emissions monitoring	launch DataHub
Lecture6	02/22	Clustering and mapping	Environmental policy	launch DataHub
Lecture7	03/01	Omitted variables & simulations	Environmental quality	launch DataHub
Lecture8	03/08	Fitting a curve	Emissions vs growth	launch DataHub
Lecture9	03/15	Data visualization	Emissions vs growth	launch DataHub
Lecture10	03/22	Web API interactions	City-level emissions	launch DataHub
Panel	03/29	(5pm PT) Newton Distinguished Innovator Lecture	Career trajectory	I-House Chevron Auditorium

data88-sp22's Issues

whej03

Need to:

• Clean up data to not have codes/encrypted labels
• Remove un-needed/duplicate columns

• Change names of columns to be either snake or camel case. The spaces break statsmodels

• Add segue before review
• Fix markdown size level in titles (some are ## and should ### and vice versa)
• Fix text referencing lecture
• Add in Data 8 textbook references

• Added in for existing sections, need to add in for future sections

• Check to see if the correlation image will be transparent on the final version (dark mode issue)
• What to do with NaNs - they break the code for some reason

• Seems to be an issue with the datascience package. I used np.nanstd() and np.nanmean() which worked but I feel like that is not an ideal solution.

• Probably more