/mta_safety_index

Primary LanguageJupyter Notebook

MTA Safety Index

Abstract

The goal of this project was to use MTA subway data and Arrest reports to assist tourists and non-locals in avoiding crime and navigating around the MTA network safely.

Design

  • Created ingest pipeline for MTA data for preperation into database
  • Classifying Arrest Data into "Primary" categories

Data

Algorithms

  • md5 hashing to create unique ID for entries (observations) to avoid conflict with future incoming data
  • Identifying selectable number of top stations for given dataframe
  • Correcting Arrest Data latitude and longitude contained within the space between two points

Tools

  • Tableau
  • Seaborn
  • Excel
  • Matplotlib
  • VSCode