v1.2.0

• added new calculation_method for surv_shap() called "treeshap" that uses the treeshap package (#75)
• enable to calculate SurvSHAP(t) explanations based on subsample of the explainer's data
• changed default kernel width in SurvLIME from sqrt(p * 0.75) to sqrt(p) * 0.75
• fixed error in SurvLIME when non-factor categorical_variables were provided