/Cancer-Mutation-Classification

Random Forest and XGboosted classification task for predicting cancer mutation classes using natural language data

Primary LanguageJupyter Notebook

Multiclass prediction using random forest and XGboost models

Dataset taken from Kaggle's 2017 competition on Personalized Medicine: Redefining Cancer Treatment: redict the effect of Genetic Variants to enable Personalized Medicine

Citation : @misc{msk-redefining-cancer-treatment, author = {Iker Huerga, Wendy Kan}, title = {Personalized Medicine: Redefining Cancer Treatment}, publisher = {Kaggle}, year = {2017}, url = {https://kaggle.com/competitions/msk-redefining-cancer-treatment} }

  • Project demonstrates:

  • Foundational understanding of ML models and how to evaluate performance

  • Natural Lang/ processing

  • Parameter Tuning

  • Feature Engineering