This week

• [x] Find the 2013 dataset
• [x] Read the dataset with python to create a pandas dataframe
• [x] Explore the dataset columns and the number of data
• [x] Search for missing values

The 2013 dataset

This dataset is no more publicly available on the NYC taxi and limousine commission, this is because in 2013 the dataset provided two other columns:

1. Medallion
2. Hack License

These two columns represent the hashed taxi’s unique id number and the hashed taxi driver license unique number.

Why has it been removed?

The unique taxi id number is very short, and hash of this value is easy to revert with a rainbow table, so all the taxi numbers and the hack licenses have been deanonymised!

More on this at:

On Taxis and Rainbows

New York taxi details can be extracted from anonymised data, researchers say

Where to find this dataset?

The dataset is now provided just by a GitHub user https://github.com/andresmh

and downloadable at this location:

http://www.andresmh.com/nyctaxitrips/

The data are split in two datasets:

1. trip_data