brajiang/octopus

CMUHacks 2017 Project

octopus

CMUHacks 2017 Project

The main function in this repository is collect_data. It uses final_tentacle.csv (modified version of data from https://data.cityofchicago.org/Public-Safety/Crimes-2001-to-present/ijzp-q8t2) as the training input. The function prompts the user for his/her location, after which the app does a quick computation to place the user into one of many proximity districts in Chicago. See map_numbers.py for more on how this computation is done. Then, based on the time of day and date in the year, Octopus calculates the most probable crime in the area. See danger_level.py for a heuristic of how dangerous an area is (we didn't have time to add this tto the main function collect_data). modify_data.py and timeCalc.py were helper functions used to turn the raw crime data into the format final_tentacle uses. Finally, the website (written in HTML) is in the website folder. Finally, we use the package pickle to save our model as a .pickl file, which means we don't have to train it every time we run the program.