A toolkit for simulating UK crime data.
Crime data simulating toolkit
This package was built over the course of an internship at Leeds Institute of Data Analytics to simulate realistic crime data (predominantly for West Yorkshire) to generate as an input into an agent-based model.
The toolkit exists in three main strategies for data simualtion:
- a simple poisson sampler based on past data
- a decision tree using a wide range of predictor variables
- a microsimulation using transition probabilities
The data_manipulation folder contains notebooks highlighting how some data sources have been constructed.
This package is now available via PyPi.
pip install crime_sim_toolkit
For examples of useage checkout this example notebook.
Notes on datafiles
the census_2011_population_hh.csv file is derived from ONS data. Taking data from sheet LSOA and using row 12 as the header row and keeping only rows below with data.
The expected input data for this package is from Police data UK. If it can't find data there it will default to test data.
import crime_sim_toolkit.poisson_sim as Poisson_sim sim_week = Poisson_sim.Poisson_sim( # specify the local authorities to look at (all five for West Yorkshire here) LA_names=['Kirklees','Calderdale','Leeds','Bradford','Wakefield'], # specify the path to the top level directory containing PoliceUK data directory='/root/crime_sim_toolkit/sample_data', # this can either be Day or Week timeframe='Day', # do you want to aggregate data to Police Force aggregate=True) # view the head of the generated pandas dataframe sim_week.data.head() datetime Crime_type LSOA_code Counts 0 2017-01-01 Anti-social behaviour West Yorkshire 147 1 2017-01-01 Bicycle theft West Yorkshire 7 2 2017-01-01 Burglary West Yorkshire 65
This will create an object that contains the PoliceUK data formated into counts by crime type, by LSOA (or Police force) by timeframe. Forecasts can be generated using this transformed past data as shown in the example notebooks.
- Build method for using Police data API
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
|Filename, size||File type||Python version||Upload date||Hashes|
|Filename, size crime_sim_toolkit-1.4.1-py3-none-any.whl (6.5 MB)||File type Wheel||Python version py3||Upload date||Hashes View hashes|
|Filename, size crime_sim_toolkit-1.4.1.tar.gz (6.4 MB)||File type Source||Python version None||Upload date||Hashes View hashes|
Hashes for crime_sim_toolkit-1.4.1-py3-none-any.whl