Crimes data with `flexmix`

Count data is everywhere, ranging from the products bought by the customers in a shop to the number of interactions a group of users have on Twitter. Being able to extract valuable information as subpopulation with similar behavior is essential to several applications. Poisson mixture models (PMM) are a convenient tool to cluster count data.

The objectives of this lesson are (1) to explore the dataset, (2) to apply PMM using a statistical criterion to select the number of clusters, (3) to analyze the parameters of the model and (4) to illustrate how the communities are grouped depending on the level of crimes

Check the dimensions of crimes.
Check the data with glimpse().
Create a matrix called matrix_crimes which is formed by crimes data frame without the column community.
Show the first six values of this matrix.

Exercise

Crimes data with `flexmix`

Instructions 1/4