After git cloning the repository, download the NYC 311 request data:

$ mkdir data/
$ curl https://data.cityofnewyork.us/api/views/erm2-nwe9/rows.csv?accessType=DOWNLOAD \
--output 311_Service_Requests_from_2010_to_Present.csv

Create a conda environment and install dependencies:

conda env create -f environment.yml
conda activate nyc311

The data preparation process is explained in data_cleaning.ipynb. It exports a clean dataset nyc311_clean.csv in the data folder.

analysis.ipynb walks through the analysis to answer three questions:

1. What are the number of complaints per agency for each zip code?
2. For each zip code, find which other zip code they are most and least similar to
3. What are the anomalous zip codes for each agency?

The results are saved in the results folder.