Communicate Data Findings
Code Quality
Criteria | Meet Specification |
---|---|
Does the code work? |
All code is functional (i.e. no errors are thrown by the code). Warnings are okay, as long as they are not a result of poor coding practices. |
Does the project follow good coding practices? |
The project uses functions and loops where possible to reduce repetitive code. Comments and docstrings are used as needed to document code functionality. |
Exploratory Data Analysis
Criteria | Meet Specification |
---|---|
Is the data explored systematically? |
The project appropriately uses univariate, bivariate, and multivariate plots to explore many relationships in the data set. Reasoning is used to justify the flow of the exploration. |
Are questions and observations documented in the report? |
Questions and observations are placed regularly throughout the report, after each plot or set of related plots. |
Is the data visualized using appropriate plot types, encodings, and parameter choices? |
Visualizations made in the project depict the data in an appropriate manner that allows plots to be readily interpreted. This includes choice of appropriate plot type, data encodings, transformations, and labels as needed. |
Explanatory Data Analysis
Criteria | Meet Specification |
---|---|
Have the main findings from the exploration been documented? |
A section in the submitted materials includes a summary of main findings that reflects on the steps taken during the data exploration. The section also describes the key insights that are conveyed by the explanatory presentation. |
Does the presentation clearly convey key insights? |
A slideshow is provided, with at least three visualizations used in the presentation to convey key insights. These key insights match those documented in the summary. Each visualization is associated with comments that accurately depict their purpose. |
Are the plots polished? |
All plots in the presentation have an appropriate title with labeled axes and legends. Labels include units as needed. Plot type, encodings, and transformations are all appropriate. |
Tips to make your project standout:
- During the exploration, use a variety of plot types to explore different relationships in the dataset. Be willing to investigate unexpected relationships and don’t be afraid of finding a dead-end in your exploration.
- As part of your exploration, document your thought processes to justify the steps you take.
- When you select key insights for your explanatory presentation, focus on one or two paths that tell a compelling story.
- When planning your explanation’s flow, document design decisions that make your visualizations information-rich but still easy to read.
- Gather feedback from others to get a different perspective on your explanatory presentation. Document that feedback and note any changes in your designs based on that feedback.