Prepare data

– How the data is collected

The data was given by the Cyclistic in this URL: https://divvy-tripdata.s3.amazonaws.com/index.html, and would be understandable that the data would be Reliable, Original, Comprehensive, Current, and Cited (ROCCC). However, after revising the data it is easy to see that there are a few issues.

There is not much information on how the data is collected, it is mentioned that the bikes are geo-tracked, but no mention of an app. I can’t know how the data related to the time of the trip or membership status was acquired.

– Identify data (formats and types)

The data is divided into 12 CSV, one for each month, though there were 19 CSV compiled over 1 year and 8 months of data. These were the files that I originally used until the Analysis phase.

Each CSV contain 13 columns:

1. ride_id-(string data type)

2. rideable_type-(string data type), (classic_bike, electric_bike and docked_bike)

3. started_at-(string data type), year-month-day hour:minute:second

4. ended_at-(string data type), year-month-day hour:minute:second

5. start_station_name-(string data type)

6. start_station_id-(string data type) except for the month of November (integer data type)

7. end_station_name-(string data type)

8. end_station_id-(string data type) except for the month of November(integer data type)

9. start_lat-(float point data type)

10. start_lng-(float point data type)

11. end_lat-(float point data type)

12. end_lng-(float point data type)

13. member_casual-(string data type), (member, casual)

– Verify data credibility