There are a wide variety of studies on player modeling. However, most of these studies target a specific game or genre. In some of these works, the number of in-game actions is used as a feature for modeling a player. However, using this feature leads to a complex model, and the model may miss some high-level relations among actions. In this paper, we propose a generic player modeling method that uses action-trait mapping relations which reveal correlations among actions. Mapping from the action-space to a much smaller trait-space improves interpretability of models. Additionally, to use the differences of impact of actions on player models, we apply feature weighting which uses the inverse of action frequencies. Players are clustered by Expectation Maximization. We demonstrate our method on a casual mobile game, Dusk Racer. We evaluate the feature weighting method using cluster validation with internal criteria. We conclude that using traits and feature weighting improves clustering quality and usability of the player model.