This is a data set of Capital Bikeshare users on an hourly basis across Washington D.C. This data was gathered from 2011 - 2012 and it is created by Data Society.
- Link: data.world.
- Or you can download it from the attached file.
Predict the total users that depends on time.
This data has 17,379 rows, 14 columns.
| Num | Command | Description |
|---|---|---|
| 1 | Date | The date of the day |
| 2 | Season | Seasons of the year -> 1=Spring 2=Summer 3=Fall 4=Winter |
| 3 | Hour | Hour (0 to 23) |
| 4 | Holiday | Is this Day is holiday or not |
| 5 | Day of the Week | Day of the week (0 to 6) |
| 6 | Working Day | Does the day is working day or not |
| 7 | Weather Type | Weather Type -> 1=Sunny 2=Cloudy 3=Windy 4=Rainy |
| 8 | Temperature F | Normalized temperature in fehrenhite |
| 9 | Temperature Feels F | Normalized feeling temperature in fehrenhite |
| 10 | Humidity | Normalized humidity |
| 11 | Wind Speed | Normalized wind speed |
| 12 | Casual Users | Count of casual users |
| 13 | Registered Users | Count of registered users |
| 14 | Total Users | Count of total rental bikes including both casual and registered |
- Jupyter notebook
- Libraries(Pandas,Numpy,matplotlib,seaborn,plotly)
- Git Bash
- Zoom
- What are the most crowded days and what time was it?
- What is the difference between registered and casual users?
- How does the season affect the number of users?
- Did the low temperature in winter affect the registered users and casual users?
- Time Series Data
The MVP goal is to answer at least three of the mentioned questions.