This repo is forked from the single repo we used to collaborate for our project.
Project 1 Group 5
Betul Akbas
Priya Durai Arasan
Lori Bradshaw
Elizabeth Dworkin
Celestee Williams
This was our first group project so the guidelines were very broad to enable us to demonstrate our skills more creatively. These were the primary requirements:
-Professional quality presentation
-Ample and complete README file
-6-8 visualizations with accurate labeling, supported with ample and precise explanations
-Professional quality write up to summarize major findings and their implications
-Presentation answer all questions from the original project proposal and are strongly supported with numbers and visualizations
-Use of statistical analysis from lessons including any of the following: aggregation, correlation, comparison, summary statistics, sentiment analysis, and time series analysis
-All group members must speak during the oral presentation
-Slides presented must be visually clean, professional, relevant to the material, and must effectively demonstrate the project
Our topic began as an exploration of the effects of climate change. Because we have group members with experience in the industry, we chose to explore the subject by relating it to the cattle industry. We began by looking at milk production and beef production.
Analysis Questions:
1.Impact of temperature on beef production?
2.Impact of rainfall on beef production?
3.Impact of wheat production on beef production?
Our data is sourced from the USDA website. We chose this organization as our source because we felt it would have sufficient and accurate information and because the source would be considered reputable by the audience of the final presentation.
Temperature and precipitation data: https://www.ncei.noaa.gov/access/monitoring/climate-at-a-glance/statewide/time-serie
Beef production data: https://quickstats.nass.usda.gov
wheat production data:https://quickstats.nass.usda.gov
CA county data: https://www.nass.usda.gov/Statistics_by_State/California/Publications/County_Estimates/2022/CATCNTYE2022.pdf
Our initial plan was to look at monthly statistics of rainfall and average temperature as our potential indications of climate change. First we decided to limit the scope to just California instead of the entire US. We began to pull the data from the USDA site and found that beef production statistics could only be found at the annual level so we switched from monthly to annual comparison.
For the California county data and charts, after consulting with Matt we found that displaying our county data on a map required coding skills that we haven’t learned yet and was a bit too much for our first project. We decided instead to find the county seat for each county in California and then map the data to the city.
As mentioned previously, one problem we encountered was the inability to find monthly statistics on beef production. We switched to annual, which means fewer points on our graphs making them cleaner, however we had some concerns that an annual average temp, for example, might not provide enough granular detail for a significant analysis.
We also chose to alter the analysis to limit to only aspects that had the potential to affect beef production, removing milk production from the scale. In addition to comparing rainfall and temperature, we also added statistics on wheat production. Our reasoning is that climate change effects on wheat, as representative of the cattles’ food source, could reduce the amount of food available for the cattle, resulting in smaller weight gains and therefore less beef to sell.
Our goal was to explore potential relationships between climate change and beef production. The data we compared show little correlation between the effect of climate change as represented by rainfall and temperature on the beef and wheat production in California. One reason we may not have found the anticipated connection is that the data was too concentrated, meaning an average temperature in California, for example, may be the wrong metric for a state of over 160,00 miles in area. Weather in northern towns like Crescent City, Grenada, and Redding will be very different from that in LA, San Diego, and Palm Springs. Further study should include more granular analysis, such as limiting the data to a single county or region, to reduce the effects of averaging the extreme temperatures within the state.
Another area of exploration would be to look at other potential factors that could affect beef production beyond rainfall, temperature, and available food source that we looked at here.
Presentation Link: https://docs.google.com/presentation/d/19_LynnP9FKALFdarFGL5-iwkWalxgH6-/edit?usp=sharing&ouid=111575204932088164314&rtpof=true&sd=true
Notes
● All code used is included in the jupyter notebook in the group project repository.
● Analysis can be found in the powerpoint presentation and also within the code.
● CA map requires BokehJS installed on computer to run. Copy of map is added to output file.