In this challenge I extracted from bigquery-public-data.nhtsa_traffic_fatalities
database the table of accidents for 2015. This data is public and comes from Bigquery by using GoogleCloud CLI.
My steps:
- Extracting the data from database using SQL language.
- Transform the query to pandas dataframe.
- Separate the 10 total of fatalities in each state and in which hour (or month) the incident occurs.
- Creating a new query for extrancting the ratio of accidents and drunken driver percentage and select the 10 biggest percentages.
Next steps
- None
Acknowledgements
I thank to Dr. Dario Lopez for the great discussion about the project.