.gitignore
.pre-commit-config.yaml
LICENSE
README.md
constraints.txt
data_generation.md
feature_representation.md
pyproject.toml
spark_setup.md
synthetic_data_generation.md
zero_shot_prediction.md
.github/workflows/build-python.yaml
.github/workflows/tests.yaml
sample_configs/cehrgpt_pretrain_sample_config.yaml
sample_configs/credential_file_sample.ini
sample_data/omop_vocab/concept/concept.parquet
sample_data/pretrain/patient_sequence.parquet
sample_data/pretrained_embeddings/pretrained_embedding_concepts.pkl
sample_data/pretrained_embeddings/pretrained_embedding_vectors.npy
scripts/create_cehrgpt_pretraining_data.sh
scripts/extract_features_gpt.sh
scripts/level_three_evaluation.sh
scripts/omop_pipeline.sh
scripts/pool_generated_sequences.sh
scripts/run_linear_prob.sh
src/__init__.py
src/cehrgpt/__init__.py
src/cehrgpt/cehrgpt_args.py
src/cehrgpt/gpt_utils.py
src/cehrgpt.egg-info/PKG-INFO
src/cehrgpt.egg-info/SOURCES.txt
src/cehrgpt.egg-info/dependency_links.txt
src/cehrgpt.egg-info/requires.txt
src/cehrgpt.egg-info/top_level.txt
src/cehrgpt/analysis/__init__.py
src/cehrgpt/analysis/htn_treatment_pathway.py
src/cehrgpt/analysis/irregularity.py
src/cehrgpt/analysis/privacy/__init__.py
src/cehrgpt/analysis/privacy/attribute_inference.py
src/cehrgpt/analysis/privacy/attribute_inference_config.yml
src/cehrgpt/analysis/privacy/member_inference.py
src/cehrgpt/analysis/privacy/nearest_neighbor_inference.py
src/cehrgpt/analysis/privacy/reid_inference.py
src/cehrgpt/analysis/privacy/utils.py
src/cehrgpt/analysis/treatment_pathway/__init__.py
src/cehrgpt/analysis/treatment_pathway/depression_treatment_pathway.py
src/cehrgpt/analysis/treatment_pathway/diabetes_treatment_pathway.py
src/cehrgpt/analysis/treatment_pathway/htn_treatment_pathway.py
src/cehrgpt/analysis/treatment_pathway/treatment_pathway.py
src/cehrgpt/data/__init__.py
src/cehrgpt/data/cehrgpt_data_processor.py
src/cehrgpt/data/hf_cehrgpt_dataset.py
src/cehrgpt/data/hf_cehrgpt_dataset_collator.py
src/cehrgpt/data/hf_cehrgpt_dataset_mapping.py
src/cehrgpt/data/sample_packing_sampler.py
src/cehrgpt/generation/__init__.py
src/cehrgpt/generation/cehrgpt_conditional_generation.py
src/cehrgpt/generation/chatgpt_generation.py
src/cehrgpt/generation/generate_batch_hf_gpt_sequence.py
src/cehrgpt/generation/omop_converter_batch.py
src/cehrgpt/generation/omop_entity.py
src/cehrgpt/models/__init__.py
src/cehrgpt/models/activations.py
src/cehrgpt/models/config.py
src/cehrgpt/models/gpt2.py
src/cehrgpt/models/hf_cehrgpt.py
src/cehrgpt/models/hf_modeling_outputs.py
src/cehrgpt/models/pretrained_embeddings.py
src/cehrgpt/models/special_tokens.py
src/cehrgpt/models/tokenization_hf_cehrgpt.py
src/cehrgpt/omop/__init__.py
src/cehrgpt/omop/condition_era.py
src/cehrgpt/omop/observation_period.py
src/cehrgpt/omop/omop_argparse.py
src/cehrgpt/omop/omop_table_builder.py
src/cehrgpt/omop/ontology.py
src/cehrgpt/omop/sample_omop_tables.py
src/cehrgpt/omop/queries/__init__.py
src/cehrgpt/omop/queries/condition_era.py
src/cehrgpt/omop/queries/observation_period.py
src/cehrgpt/runners/__init__.py
src/cehrgpt/runners/data_utils.py
src/cehrgpt/runners/gpt_runner_util.py
src/cehrgpt/runners/hf_cehrgpt_finetune_runner.py
src/cehrgpt/runners/hf_cehrgpt_pretrain_runner.py
src/cehrgpt/runners/hf_gpt_runner_argument_dataclass.py
src/cehrgpt/runners/hyperparameter_search_util.py
src/cehrgpt/runners/sample_packing_trainer.py
src/cehrgpt/simulations/__init__.py
src/cehrgpt/simulations/generate_plots.py
src/cehrgpt/simulations/run_simulation.sh
src/cehrgpt/simulations/time_embedding_simulation.py
src/cehrgpt/simulations/time_token_simulation.py
src/cehrgpt/time_to_event/__init__.py
src/cehrgpt/time_to_event/time_to_event_model.py
src/cehrgpt/time_to_event/time_to_event_prediction.py
src/cehrgpt/time_to_event/time_to_event_utils.py
src/cehrgpt/time_to_event/config/1_year_cabg.yaml
src/cehrgpt/time_to_event/config/30_day_readmission.yaml
src/cehrgpt/time_to_event/config/next_visit_type_prediction.yaml
src/cehrgpt/time_to_event/config/t2dm_hf.yaml
src/cehrgpt/tools/__init__.py
src/cehrgpt/tools/ehrshot_benchmark.py
src/cehrgpt/tools/generate_causal_patient_split_by_age.py
src/cehrgpt/tools/generate_pretrained_embeddings.py
src/cehrgpt/tools/merge_synthetic_real_datasets.py
src/cehrgpt/tools/upload_omop_tables.py
src/cehrgpt/tools/linear_prob/__init__.py
src/cehrgpt/tools/linear_prob/compute_cehrgpt_features.py
src/cehrgpt/tools/linear_prob/train_with_cehrgpt_features.py
tests/__init__.py
tests/integration_tests/__init__.py
tests/integration_tests/runners/__init__.py
tests/integration_tests/runners/hf_cehrgpt_pretrain_runner_test.py
tests/integration_tests/runners/hf_cehrgpt_pretrain_sample_packing_runner_test.py
tests/integration_tests/runners/hf_cehrgpt_pretrain_sfm_runner_test.py
tests/unit_tests/__init__.py
tests/unit_tests/gpt_utils_test.py
tests/unit_tests/numeric_concept_statistics_test.py
tests/unit_tests/tokenization_test.py
tests/unit_tests/models/__init__.py
tests/unit_tests/models/model_utils_test.py
tests/unit_tests/models/rotary_embedding_test.py
tests/unit_tests/models/tokenization/__init__.py
tests/unit_tests/models/tokenization/create_bins_with_spline_test.py
tests/unit_tests/models/tokenization/create_sample_from_bins_test.py
tests/unit_tests/runners/__init__.py
tests/unit_tests/runners/hf_cehrgpt_finetune_runner_test.py
tests/unit_tests/tools/__init__.py
tests/unit_tests/tools/upload_omop_tables_test.py