Give dates a usable structure.
The AI-assisted Python notebook combines year, month, and day into a date field, then groups observations by month. This creates a consistent basis for comparison.
10 / Seattle Temperature Study
Daily data.
Seasonal patterns.
Turn Seattle temperature observations into a readable month-by-month and annual view.
- My contribution
- AI-assisted Python analysis. Prompt refinement, data preparation, and visualization.
- Team context
- Individual UW coursework.
- Stage
- Completed notebook
- Delivered
- Twelve monthly charts and one annual temperature summary.
Notebook workflow / reconstructed
- PrepareRead daily Seattle weather data.
- OrganizeCreate dates and month groups.
- ComparePlot each month’s temperatures.
- SummarizeVisualize the full year.
The notebook analyzes 2024 observations; trend lines are descriptive.
Key decisions.
Show two scales.
Twelve monthly plots show daily variation alongside linear trends. An annual scatter plot with a polynomial fit provides a broader view of seasonal change.
Make the charts readable.
Prompt refinement focused on month names, Fahrenheit labels, legends, and clear axes. The notebook uses pandas for preparation and Matplotlib and Seaborn for visualization.
Outcome & next step.
A notebook with saved chart outputs connecting daily observations to monthly and annual patterns.