cehrgpt 0.1.2__py3-none-any.whl → 0.1.3__py3-none-any.whl

{cehrgpt-0.1.2.dist-info → cehrgpt-0.1.3.dist-info}/RECORD

@@ -1,8 +1,9 @@
 __init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 cehrgpt/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 cehrgpt/cehrgpt_args.py,sha256=zPLp9Qjlq5PapWx3R15BNnyaX8zV3dxr4PuWj71r0Lg,3516
-cehrgpt/gpt_utils.py,sha256=IA5qw-hxcKkGO07AB47lDNRU6mlb9jblpKO7KeLLN78,11342
+cehrgpt/gpt_utils.py,sha256=gMPqHpOS7_6N81r7t_p6bGJ0FFVK5AgtEIMYLYKb9iA,13746
 cehrgpt/analysis/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+cehrgpt/analysis/htn_treatment_pathway.py,sha256=KMjSEdIFNr2bSAyw1W6_bh59aV067-ZhT-AymiKCyr8,21961
 cehrgpt/analysis/irregularity.py,sha256=Rfl_daMvSh9cZ68vUwfmuH-JYCFXdAph2ITHHffYC0Y,1047
 cehrgpt/analysis/privacy/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 cehrgpt/analysis/privacy/attribute_inference.py,sha256=0ANVW0I5uvOl6IxQ15-vMVQd0mugOgSGReBUQQESImg,9368
@@ -11,29 +12,38 @@ cehrgpt/analysis/privacy/member_inference.py,sha256=a_-4rkYYffYl0ucnjK6uYy8jesup
 cehrgpt/analysis/privacy/nearest_neighbor_inference.py,sha256=qoJgWW7VsUMzjMGpTaK84iY_QLOuF3HCYXAEKLZOZsU,6391
 cehrgpt/analysis/privacy/reid_inference.py,sha256=Pypd3QJXQNY8VljpnIEa5zeAbTZHMjQOazaL-9VsBGw,13955
 cehrgpt/analysis/privacy/utils.py,sha256=CRA4H9mPLBjMQGKzZ_x_3ro3tMap-NjsMDVqSOjHSVQ,8226
+cehrgpt/analysis/treatment_pathway/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+cehrgpt/analysis/treatment_pathway/depression_treatment_pathway.py,sha256=7mrzaMBv09Gn6I5OM86f7gNfPvncVVKg2C3jZo0bmsU,3024
+cehrgpt/analysis/treatment_pathway/diabetes_treatment_pathway.py,sha256=qwAtJ3KVesvqvR22Tbk19k35sDL-sGlRZo2sjJNo3yQ,2962
+cehrgpt/analysis/treatment_pathway/htn_treatment_pathway.py,sha256=0bsEE1VFIxzU33bSipM30p2fnHsWjGWWcu59y_38K3c,2870
+cehrgpt/analysis/treatment_pathway/treatment_pathway.py,sha256=SCWphYH9ARa4ZKB9fgBYM9RC2Hc8PDwtoHHCX7th16Q,25496
 cehrgpt/data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-cehrgpt/data/hf_cehrgpt_dataset.py,sha256=hwJlGW7XiJIr6cXtmwvReQf9yLZJPD-dvJGvRg5ERqU,3755
-cehrgpt/data/hf_cehrgpt_dataset_collator.py,sha256=juM5HeZScgj8w15Bl1qC83Swld4gY6avh0QkSWLqITA,45465
-cehrgpt/data/hf_cehrgpt_dataset_mapping.py,sha256=_QDX9NXfmQ_S3kOf3yndb3AhoEeFiSzAOv836uYW0AY,26230
+cehrgpt/data/cehrgpt_data_processor.py,sha256=0Y6GPWu6fRBLemXJu5IxuOPbF2wmSrX-18uyofTeUzk,23096
+cehrgpt/data/hf_cehrgpt_dataset.py,sha256=uz05TG5QCl3_Ybn9zZyWRg0pEbiAvL1yPWXK3BGsj0Q,3815
+cehrgpt/data/hf_cehrgpt_dataset_collator.py,sha256=2UcYB241dWhvS-mV0ZTbCJdjlgPrVjZOAh3V8EWFfCg,27930
+cehrgpt/data/hf_cehrgpt_dataset_mapping.py,sha256=-Igd-P-yvYlJXGZSGlYHRnez464NCkZIko3boQDYS1E,27638
 cehrgpt/data/sample_packing_sampler.py,sha256=vovGMtmhG70DRkSCeiaDEJ_rjKZ38y-YLaI1kkhFEkI,6747
 cehrgpt/generation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-cehrgpt/generation/cehrgpt_conditional_generation.py,sha256=AM76yaPyw1B-bcdei24HO0uspGZWHGKWpYpHywotTIQ,11972
+cehrgpt/generation/cehrgpt_conditional_generation.py,sha256=6I4tI-cCQ6QdFxhDAkhu0ZNo57DINjD-NncxMbyUwgg,12032
 cehrgpt/generation/chatgpt_generation.py,sha256=SrnLwHLdNtnAOEg36gNjqfoT9yd12iyPgpZffL2AFJo,4428
-cehrgpt/generation/generate_batch_hf_gpt_sequence.py,sha256=P8al4-zqymqEkCHCCu2sqz_45akcKF2o_AtQIjJdVmQ,11919
-cehrgpt/generation/omop_converter_batch.py,sha256=LUmCD-t_6ZP1YfNDZCqYewl-XIIaIgRZ_dAxuR_VdCQ,26275
+cehrgpt/generation/generate_batch_hf_gpt_sequence.py,sha256=lpKEvJ2hhB8bwS06c5jEAksFUrGKCUv6t7hXrsMj-Ns,12284
+cehrgpt/generation/omop_converter_batch.py,sha256=h4dg9fc23w6i82KMrOQFM-KxD6iuLnJfrv7YISc0dMw,26620
 cehrgpt/generation/omop_entity.py,sha256=Q5Sr0AlyuPAm1FRPfnJO13q-u1fqRgYVHXruZ9g4xNE,19400
 cehrgpt/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-cehrgpt/models/config.py,sha256=nOAKgH5420HLCcy7n1hE7MbqR861Iq4DTutKoAd25tg,11090
-cehrgpt/models/hf_cehrgpt.py,sha256=3P7bOLDr7NMSedGszhmlJJN4Mhpd_65-x6uzwvSjigE,92837
+cehrgpt/models/activations.py,sha256=crVPS-cZpUGrvLD7xhNjGmGr9S4e4LEfNmgIEsiuQ88,981
+cehrgpt/models/config.py,sha256=SwsHVXzsgDmFSfrzv90lZBePenoHv-fIGGSLdxAIiu8,11193
+cehrgpt/models/gpt2.py,sha256=4H9sFzf_qFGY-Bk0mfztxlKJXxvA0kTKwKiWFbqJLrQ,22079
+cehrgpt/models/hf_cehrgpt.py,sha256=YTZtY1p-M-utQa6iJvDXFOjgc1SDdL3ZcWuy_-ZN41g,81167
 cehrgpt/models/hf_modeling_outputs.py,sha256=5X4WEYKqT37phv_e5ZAv3A_N0wqdAUJLJRm6TxS6dDQ,10356
 cehrgpt/models/pretrained_embeddings.py,sha256=vLLVs17TLpXRqCVEWQxGGwPHkUJUO7laNTeBuyBK_yk,3238
 cehrgpt/models/special_tokens.py,sha256=lrw45B4tea4Dsajn09Cz6w5D2TfHmYXikZkgwnstu_o,521
-cehrgpt/models/tokenization_hf_cehrgpt.py,sha256=cAxHTctpVBxfWfC3XcwDQavN1zwWN9Nid_Fajd5zQWQ,53159
+cehrgpt/models/tokenization_hf_cehrgpt.py,sha256=yHuNXvLznaSjwxVJsq7r9bZLi4msM8n4LVrzHINqsgY,66225
 cehrgpt/omop/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 cehrgpt/omop/condition_era.py,sha256=hPZALz2XaWnro_1bwIYNkI48foOJjueyg3CZ1BliCno,626
 cehrgpt/omop/observation_period.py,sha256=TRMgv5Ya2RaS2im7oQ6BLC_5JL9EJYNYR62ApxIuHvg,1211
 cehrgpt/omop/omop_argparse.py,sha256=WI_-vZGfPdZ8atIeB-CrpaPdkv07kDBabyEpaRZfl64,998
 cehrgpt/omop/omop_table_builder.py,sha256=6K_YYKyayDUBwxUdwaliI5tufpfIQqByDY5HeBbjHok,2742
+cehrgpt/omop/ontology.py,sha256=LZIp0X3gY_VDZqIl6gTwGq7ZwV1nb0raPLTQAbJm6nM,5683
 cehrgpt/omop/sample_omop_tables.py,sha256=2JZ8BNSvssceinwFanvuCRh-YlKrKn25U9w1pL79kQ0,2300
 cehrgpt/omop/queries/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 cehrgpt/omop/queries/condition_era.py,sha256=LFB6vBAvshHJxtYIRkl7cfrF0kf7ay0piBKpmHBwrpE,2578
@@ -41,11 +51,11 @@ cehrgpt/omop/queries/observation_period.py,sha256=fpzr5DMNw-QLoSwp2Iatfch88E3hyh
 cehrgpt/runners/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 cehrgpt/runners/data_utils.py,sha256=i-krtBx_6rvPYtdLdDoWwOTtJcaovd0wH8gBYmgN2l4,16013
 cehrgpt/runners/gpt_runner_util.py,sha256=YJQSRW9Mo4TjXSOUOTf6BUFcs1MGFiXU5T4ztKZcYhU,3485
-cehrgpt/runners/hf_cehrgpt_finetune_runner.py,sha256=1OgxLm4T7iHv5pKi2QaSdaz9ogWo2n3sSUGp6cHDF9s,28309
-cehrgpt/runners/hf_cehrgpt_pretrain_runner.py,sha256=ERSnvB38fPYVghtKQeNTZ8VfeXnoRcCHB0cWISWaZ84,26523
-cehrgpt/runners/hf_gpt_runner_argument_dataclass.py,sha256=fJR4RHPqal1YI6_KUH-WlkoQLSZuBT5bKUGfPHDFrWI,9350
-cehrgpt/runners/hyperparameter_search_util.py,sha256=YWdFQ1igQs-G_wqWUrUzYraGiz8OSpSYyvid-I5nhWA,9262
-cehrgpt/runners/sample_packing_trainer.py,sha256=Zb7Aqwnk8-VqrjEKUVeg5XzZWmHxXOU2sDn1YURS-FU,7960
+cehrgpt/runners/hf_cehrgpt_finetune_runner.py,sha256=AY9QxH4WupfWpLm9rjeSMOzedmw_03kTWuhncVRuhqs,26032
+cehrgpt/runners/hf_cehrgpt_pretrain_runner.py,sha256=I_fuuKNzWx6yZiDcAAZdQtyxUEgNKLygQyS-SyQpptY,26840
+cehrgpt/runners/hf_gpt_runner_argument_dataclass.py,sha256=8qHVUp-hx7xKozaE_EaEJphrs1QfRSXx0P6YMByK9Ww,9981
+cehrgpt/runners/hyperparameter_search_util.py,sha256=SD02j1D8IBtIOG41dh7VgmVT2SWCF-VPZ7zVHlEIN70,12801
+cehrgpt/runners/sample_packing_trainer.py,sha256=HfxHCIGBXb1RbN7nbU6jmSy_Zzwx_joj-UoYqbKl5-0,8375
 cehrgpt/simulations/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 cehrgpt/simulations/generate_plots.py,sha256=BTZ71r8Kah0PMorkiO3vw55_p_9U1Z8KiD3GsPfaV0s,2520
 cehrgpt/simulations/run_simulation.sh,sha256=DcJ6B19jIteUO0pZ0Tc21876lB9XxQHFAxlre7MtAzk,795
@@ -63,13 +73,13 @@ cehrgpt/tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 cehrgpt/tools/ehrshot_benchmark.py,sha256=E-m_5srlYEw7Y7i9twIJWDvrkwNlop-6yZB-80FZid0,2667
 cehrgpt/tools/generate_causal_patient_split_by_age.py,sha256=dmHiPAL_kR1WrhRteIiHH9dwMtMi3PVl8jXm2O06_gI,4177
 cehrgpt/tools/generate_pretrained_embeddings.py,sha256=lhFSacGv8bMld6qigKZN8Op8eXpFi0DsJuQbWKOWXqI,4160
-cehrgpt/tools/merge_synthetic_real_dataasets.py,sha256=O1dbQ32Le0t15fwymwAh9mfNVLEWuFwW53DNvESrWbY,7589
+cehrgpt/tools/merge_synthetic_real_datasets.py,sha256=O1dbQ32Le0t15fwymwAh9mfNVLEWuFwW53DNvESrWbY,7589
 cehrgpt/tools/upload_omop_tables.py,sha256=vdBAbkeAsGPA4NsyhNjelPVj3gS8yzmS1sKNM1Qk96g,3791
 cehrgpt/tools/linear_prob/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-cehrgpt/tools/linear_prob/compute_cehrgpt_features.py,sha256=Hpx7WvAWm2WwPHFfimCADXh019I7bwdzJ4_5_YCxQzU,19817
+cehrgpt/tools/linear_prob/compute_cehrgpt_features.py,sha256=0i34zAwePG0hZK2HSDaUlO-Fzyb5K4LqRuhrCVWivxA,19906
 cehrgpt/tools/linear_prob/train_with_cehrgpt_features.py,sha256=w0UvzMKYGenN_KDVnbzutmy8IPLUxW5hPvpKKxDSL5U,5820
-cehrgpt-0.1.2.dist-info/licenses/LICENSE,sha256=LOfC32zkfUIdGm8e_098jPbt8OHKtNWymDzxn2pA9Zk,1093
-cehrgpt-0.1.2.dist-info/METADATA,sha256=D7gGKrQThiLivViFeNm711NCP8J-wXfkueMGb6RKqV0,8481
-cehrgpt-0.1.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-cehrgpt-0.1.2.dist-info/top_level.txt,sha256=akNCJBbMSLV8nkOzdVzdy13hMJ5CIQURnAS_YYEDVwA,17
-cehrgpt-0.1.2.dist-info/RECORD,,
+cehrgpt-0.1.3.dist-info/licenses/LICENSE,sha256=LOfC32zkfUIdGm8e_098jPbt8OHKtNWymDzxn2pA9Zk,1093
+cehrgpt-0.1.3.dist-info/METADATA,sha256=MTgv1L9ru4evziAW2yTLsd3m9d1Ept8xy85u2CpBNTM,10167
+cehrgpt-0.1.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+cehrgpt-0.1.3.dist-info/top_level.txt,sha256=akNCJBbMSLV8nkOzdVzdy13hMJ5CIQURnAS_YYEDVwA,17
+cehrgpt-0.1.3.dist-info/RECORD,,

cehrgpt-0.1.2.dist-info/METADATA

@@ -1,209 +0,0 @@
-Metadata-Version: 2.4
-Name: cehrgpt
-Version: 0.1.2
-Summary: CEHR-GPT: Generating Electronic Health Records with Chronological Patient Timelines
-Author-email: Chao Pang <chaopang229@gmail.com>, Xinzhuo Jiang <xj2193@cumc.columbia.edu>, Krishna Kalluri <kk3326@cumc.columbia.edu>, Elise Minto <em3697@cumc.columbia.edu>, Jason Patterson <jp3477@cumc.columbia.edu>, Nishanth Parameshwar Pavinkurve <np2689@cumc.columbia.edu>, Karthik Natarajan <kn2174@cumc.columbia.edu>
-License: MIT License
-Classifier: Development Status :: 5 - Production/Stable
-Classifier: Intended Audience :: Developers
-Classifier: Intended Audience :: Science/Research
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Programming Language :: Python :: 3
-Requires-Python: >=3.10.0
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: cehrbert==1.4.5
-Requires-Dist: cehrbert_data==0.0.11
-Requires-Dist: openai==1.54.3
-Requires-Dist: optuna==4.0.0
-Requires-Dist: transformers==4.44.1
-Requires-Dist: tokenizers==0.19.0
-Requires-Dist: peft==0.10.0
-Requires-Dist: lightgbm
-Requires-Dist: polars
-Provides-Extra: dev
-Requires-Dist: pre-commit; extra == "dev"
-Requires-Dist: pytest; extra == "dev"
-Requires-Dist: pytest-cov; extra == "dev"
-Requires-Dist: pytest-subtests; extra == "dev"
-Requires-Dist: rootutils; extra == "dev"
-Requires-Dist: hypothesis; extra == "dev"
-Requires-Dist: black; extra == "dev"
-Provides-Extra: flash-attn
-Requires-Dist: flash_attn; extra == "flash-attn"
-Dynamic: license-file
-
-# CEHRGPT
-
-[![PyPI - Version](https://img.shields.io/pypi/v/cehrgpt)](https://pypi.org/project/cehrgpt/)
-![Python](https://img.shields.io/badge/-Python_3.11-blue?logo=python&logoColor=white)
-[![tests](https://github.com/knatarajan-lab/cehrgpt/actions/workflows/tests.yaml/badge.svg)](https://github.com/knatarajan-lab/cehrgpt/actions/workflows/tests.yaml)
-[![license](https://img.shields.io/badge/License-MIT-green.svg?labelColor=gray)](https://github.com/knatarajan-lab/cehrgpt/blob/main/LICENSE)
-[![contributors](https://img.shields.io/github/contributors/knatarajan-lab/cehrgpt.svg)](https://github.com/knatarajan-lab/cehrgpt/graphs/contributors)
-
-## Description
-CEHRGPT is a synthetic data generation model developed to handle structured electronic health records (EHR) with enhanced privacy and reliability. It leverages state-of-the-art natural language processing techniques to create realistic, anonymized patient data that can be used for research and development without compromising patient privacy.
-
-## Features
-- **Synthetic Patient Data Generation**: Generates comprehensive patient profiles including demographics, medical history, treatment courses, and outcomes.
-- **Privacy-Preserving**: Implements techniques to ensure the generated data does not reveal identifiable information.
-- **Compatibility with OMOP**: Fully compatible with the OMOP common data model, allowing seamless integration with existing healthcare data systems.
-- **Extensible**: Designed to be adaptable to new datasets and different EHR systems.
-
-## Installation
-To install CEHRGPT, clone this repository and install the required dependencies.
-
-```bash
-git clone https://github.com/knatarajan-lab/cehrgpt.git
-cd cehrgpt
-pip install .
-```
-
-## Pretrain
-Pretrain cehrgpt using the Hugging Face trainer, the parameters can be found in the sample configuration yaml
-```bash
-mkdir test_results
-# This is NOT required when streaming is set to true
-mkdir test_dataset_prepared
-python -u -m cehrgpt.runners.hf_cehrgpt_pretrain_runner sample_configs/cehrgpt_pretrain_sample_config.yaml
-```
-
-## Generate synthetic sequences
-Generate synthetic sequences using the trained model
-```bash
-export TRANSFORMERS_VERBOSITY=info
-export CUDA_VISIBLE_DEVICES="0"
-python -u -m cehrgpt.generation.generate_batch_hf_gpt_sequence \
-  --model_folder test_results \
-  --tokenizer_folder test_results \
-  --output_folder test_results \
-  --num_of_patients 128 \
-  --batch_size 32 \
-  --buffer_size 128 \
-  --context_window 1024 \
-  --sampling_strategy TopPStrategy \
-  --top_p 1.0 --temperature 1.0 --repetition_penalty 1.0 \
-  --epsilon_cutoff 0.00 \
-  --demographic_data_path sample_data/pretrain
-```
-
-## Convert synthetic sequences to OMOP
-```bash
-# omop converter requires the OHDSI vocabulary
-export OMOP_VOCAB_DIR = ""
-# the omop derived tables need to be built using pyspark
-export SPARK_WORKER_INSTANCES="1"
-export SPARK_WORKER_CORES="8"
-export SPARK_EXECUTOR_CORES="2"
-export SPARK_DRIVER_MEMORY="2g"
-export SPARK_EXECUTOR_MEMORY="2g"
-
-# Convert the sequences, create the omop derived tables
-sh scripts/omop_pipeline.sh \
-  test_results/top_p10000/generated_sequences/ \
-  test_results/top_p10000/restored_omop/ \
-  $OMOP_VOCAB_DIR
-```
-
-# MEDS Support
-
-This section demonstrates how to pretrain CEHR-GPT using MIMIC-IV data in the MEDS (Medical Event Data Standard) format.
-
-## Prerequisites
-
-Set up the required environment variables before beginning:
-
-```bash
-export CEHR_GPT_MODEL_DIR=""    # Path to CEHR-GPT model directory
-export MEDS_DIR=""              # Path to MEDS data directory
-export MEDS_READER_DIR=""       # Path to MEDS reader output directory
-```
-
-## Step 1: Create MIMIC MEDS Data
-
-Transform your MIMIC files into MEDS format by following the instructions in the [MEDS_transforms](https://github.com/mmcdermott/MEDS_transforms/) repository.
-
-## Step 2: Create the MEDS Reader
-
-Convert the MEDS data for use with CEHR-GPT:
-
-```bash
-meds_reader_convert $MEDS_DIR $MEDS_READER_DIR --num_threads 10
-```
-
-## Step 3: Pretrain CEHR-GPT
-
-Run the pretraining process using the prepared MEDS data:
-
-```bash
-python -u -m cehrgpt.runners.hf_cehrgpt_pretrain_runner \
-  --model_name_or_path $CEHR_GPT_MODEL_DIR \
-  --tokenizer_name_or_path $CEHR_GPT_MODEL_DIR \
-  --output_dir $CEHR_GPT_MODEL_DIR \
-  --data_folder $MEDS_READER_DIR \
-  --dataset_prepared_path "$CEHR_GPT_MODEL_DIR/dataset_prepared" \
-  --do_train true --seed 42 \
-  --dataloader_num_workers 16 --dataloader_prefetch_factor 8 \
-  --hidden_size 768 --num_hidden_layers 14 --max_position_embeddings 8192 \
-  --evaluation_strategy epoch --save_strategy epoch \
-  --sample_packing --max_tokens_per_batch 16384 \
-  --warmup_steps 500 --weight_decay 0.01 \
-  --num_train_epochs 50 --learning_rate 0.0002 \
-  --use_early_stopping --early_stopping_threshold 0.001 \
-  --is_data_in_meds --inpatient_att_function_type day \
-  --att_function_type day --include_inpatient_hour_token \
-  --include_auxiliary_token --include_demographic_prompt \
-  --meds_to_cehrbert_conversion_type "MedsToBertMimic4"
-```
-
-## Step 4: Generate MEDS Trajectories
-
-### Environment Setup for Trajectory Generation
-
-Configure additional environment variables for trajectory generation with task labels (`subject_id`, `prediction_time`, `boolean_value` [optional]):
-
-```bash
-# MEDS_LABEL_COHORT_DIR must contain a set of parquet files
-export MEDS_LABEL_COHORT_DIR=""     # Path to cohort labels directory
-export MEDS_TRAJECTORY_DIR=""       # Path for trajectory output
-```
-
-### Generate Trajectories
-
-Create synthetic patient trajectories using the trained model:
-
-> **Important:** The total sequence length (`generation_input_length` + `generation_max_new_tokens`) cannot exceed the `max_position_embeddings` value (8192) defined during pretraining.
-
-```bash
-python -u -m cehrgpt.generation.cehrgpt_conditional_generation \
-  --cohort_folder $MEDS_LABEL_COHORT_DIR \
-  --data_folder $MEDS_READER_DIR \
-  --dataset_prepared_path "$CEHR_GPT_MODEL_DIR/dataset_prepared" \
-  --model_name_or_path $CEHR_GPT_MODEL_DIR \
-  --tokenizer_name_or_path $CEHR_GPT_MODEL_DIR \
-  --output_dir $MEDS_TRAJECTORY_DIR \
-  --per_device_eval_batch_size 16 \
-  --num_of_trajectories_per_sample 2 \
-  --generation_input_length 4096 \
-  --generation_max_new_tokens 4096 \
-  --is_data_in_meds \
-  --att_function_type day --inpatient_att_function_type day \
-  --meds_to_cehrbert_conversion_type MedsToBertMimic4 \
-  --include_auxiliary_token --include_demographic_prompt \
-  --include_inpatient_hour_token
-```
-
-### Parameters Explanation
-
-- `generation_input_length`: Controls the length of input context for generation
-- `generation_max_new_tokens`: Maximum number of new tokens to generate
-- `num_of_trajectories_per_sample`: Number of trajectories to generate per patient sample
-
-## Citation
-```
-@article{cehrgpt2024,
-  title={CEHRGPT: Synthetic Data Generation for Electronic Health Records},
-  author={Natarajan, K and others},
-  journal={arXiv preprint arXiv:2402.04400},
-  year={2024}
-}