init

Author: huiwenn

.gitignore

@@ -0,0 +1,108 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+notebooks/aim_2_figs/*
+*.py[cod]
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# DotEnv configuration
+.env
+
+# Database
+*.db
+*.rdb
+
+# Pycharm
+.idea
+
+# VS Code
+.vscode/
+
+# Spyder
+.spyproject/
+
+# Jupyter NB Checkpoints
+.ipynb_checkpoints/
+
+# Mac OS-specific storage files
+.DS_Store
+
+# vim
+*.swp
+*.swo
+
+# Mypy cache
+.mypy_cache/
+
+
+# Data
+data/trends/*
+*.npy
+.tmp*
+
+*Icon
+
+log/
+models/
+
+/tmp*
+/data/
+/results/
+/kube/build/
+/wandb/*
+
+/logger_plotting_logs/
+*results
+output.yaml

README.md

@@ -0,0 +1,29 @@
+# Data-Driven Simulator for Mechanical Circulatory Support with Domain Adversarial Neural Process
+
+This repository contains code for the Domain Adversarial Neural Process (DANP) and various baselines reported in the paper, *Data-Driven Simulator for Mechanical Circulatory Support with Domain Adversarial Neural Process*. The data used in this project cannot be shared publicly due to privacy and confidentiality agreements. However, we provide the necessary scripts and instructions to run the model with your own data.
+
+
+## | Installation
+
+Clone the repository and install the required dependencies:
+
+```bash
+pip install -r requirements.txt
+```
+
+Setup [wandb](https://wandb.ai/site/) for model evaluation and dashboard. 
+
+## | Usage 
+
+### Preparing Your Data
+
+Since the original data used in the paper cannot be shared, you will need to prepare your own dataset. Ensure your data is in the appropriate format as described in the `data_preparation.md` file.
+
+
+### Running the Model
+
+Execute the training script with your dataset.
+
+```bash
+python src/model/DANP.py -cohort cohort_name -seq_steps 90 -cuda cuda_number -nepochs 150 -lr 0.001 -bc 64
+```

data_preparation.md

@@ -0,0 +1,11 @@
+# Data preparation
+
+All our data are preprocessed into 0.1Hz signals of length of 180 time steps.
+
+The DANP model in `src/model/DANP.py` takes in three pytorch tensors as input: `train_real.pt`, `test_real.pt`, and `sim_data.pt`. Each of the three tensors should be of dimension `[N, 180, 7]`, where `N` is the number of rows, depending on source data. The 7 columns are features in the following order:
+
+```
+[MAP, motor_speed, pump_flow, LVP, heart_rate, tau_lv, contractiity]
+```
+
+Please see the paper for more details on preprocessing.

requirements.txt

@@ -0,0 +1,7 @@
+matplotlib==3.9.0
+numpy==1.21.2
+scipy==1.7.3
+seaborn==0.13.2
+torch==1.10.0
+tqdm==4.62.3
+wandb==0.17.0