The analysis of Crime patterns in India was performed on a dataset with the demographic information of crimes. This is looking into the aspect of a system that works on clustering which is based on the type of crimes committed and finding out sister cities that would be similar in these aspects.
- The dataset contains the datasets used. The following are the files: a. 01_District_wise_crimes_committed_IPC_2001_2012 - The main dataset used for the project b. 2013.csv - Contains the data for the calculation of accuracy of the ARIMA model.
- The code contains the following files: a. visualization.R conatins the code for the visualization. b. states_pred.R contains the code for the ARIMA model and prediction for Indian States. c. india_pred.R contains the code for the ARIMA model and prediction for India. d. sister_cities contains the code for the clustering algorithm.