Source: https://github.com/aipoch/medical-research-skills

XGBoost Modeling And Feature Importance Ranking

Use this skill to train an XGBoost model from a tabular dataset and export both feature importance ranking tables and feature importance plots.

Use This Skill When

• You need a command-line XGBoost workflow in R for tabular data.
• You need a reproducible train-test split, model training, and evaluation.
• You need feature importance ranking outputs as both a table and a figure.
• You need automatic one-hot encoding for categorical predictors.
• Your data may contain a first unnamed sample ID column such as V1 that should not enter the model.

Do Not Use This Skill When

• Your classification target has more than 2 classes.
• Your input is not tabular CSV, TXT, or TSV data.
• You need causal interpretation, mechanism claims, or policy, business, or clinical conclusions.
• You only need narrative interpretation or triage of an existing result rather than model training.

Primary Command

Rscript scripts/main.R \
  --data_file <input_file> \
  --target_var <target_column> \
  --task_type <auto|classification|regression> \
  --output_dir <output_dir>

Prerequisites

• Rscript is available in the shell.
• Required R packages: optparse, data.table, Matrix, xgboost.
• Install missing packages with Rscript -e 'install.packages(c("optparse", "data.table", "Matrix", "xgboost"), repos="https://cloud.r-project.org")'.

Core Arguments