Car Crash Subset Dataset

This dataset is a subset of the “Motor Vehicle Collisions – Vehicles” dataset available from NYC OpenData.

To create this subset, I filtered the full dataset (approximately 4.42 million rows) to include only sedans involved in crashes. I selected only the first 500 entries, as there were many entries.

While the original dataset contains many more columns, the following are included in this subset:

• UNIQUE_ID – A unique identifier generated by the NYC record system (sequential ordinal attribute)
• CRASH_DATE – The date of the crash (temporal attribute)
• VEHICLE_MAKE – The manufacturer of the car involved (categorical attribute)
• VEHICLE_MODEL – The model of the car involved (categorical attribute)
• VEHICLE_DAMAGE – Location on the vehicle where most of the damage occurred (categorical attribute)
• DRIVER_SEX – The gender of the driver (categorical attribute)
• CONTRIBUTING_FACTOR_1 – A primary factor contributing to the crash (categorical attribute)
• CONTRIBUTING_FACTOR_2 – A secondary factor contributing to the crash (categorical attribute)