As far in the blog, I talked about the analysis of the correlations between variables in the data and the shooting happened in the states depends upon the factors and the age group of the people.

Later I worked on the Monte Carlo approximation technique as we can analyse the data to the approximate numerical results through random sampling.

Currently I am working on the clustering technique so that I can unveil the covered information in the data set. I applied Elbow method in my clustering technique so that I can get the optimal number clusters in the analysis. Using this method, the inertia—the total of squared distances between each point and the cluster centre—is calculated for a range of cluster sizes and plotted. The ideal number of clusters is indicated by the “elbow,” or the point at which inertia begins to diminish more slowly.

Moreover, I distinguished the variables on the basis of Race and Gender as per the shootings happened by the cops. While doing the analysis, I can relate that the most encounters has been done to the White people and after that the Black people were in the second number in the shootings. The Unknown and the Hispanic killings are quite same in numbers whereas the shootings to the asian, Native American, and Others are also bit equal in numbers. As I previously defined in my blog that the shootings on the basis of gender is varying a lot as encounters for male is much higher as compared to the female. Refer the plot below so that one can understand the picture of shootings happened for the two variables i.e Race and Gender.

Further, I will explore more in the technique of clustering and try to apply K-Means clustering technique in the analysis.