Merge pull request sunlabuiuc#1 from zzachw/main

Reorganize file structure

Author: zzachw

.gitignore

@@ -0,0 +1,109 @@
+.idea
+examples/data/raw/*
+examples/data/processed/*
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+.pytest_cache
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# 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
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/

README.md

@@ -1,4 +1,32 @@
-# PyHealth OMOP Development PLAN
+# PyHealth
+
+## Environment
+- pytorch: 1.12.0
+- pytorch-lightning: 1.6.4
+
+## Dataset
+- MIMIC-III
+- MIMIC-IV
+- eICU
+- OMOP CDM
+
+## Input
+- Condition code
+- Drug code
+- Procedure code
+
+## Output
+- Mortality prediction
+- Length-of-stay estimation
+- Drug recommendation
+- Phenotyping
+
+## Model
+
+
+
+
+
 
 ### datasets.py
 - provide process for MIMIC-III, eICU and MIMIC-IV

Example.ipynb examples/Example.ipynbExample.ipynb renamed to examples/Example.ipynb

@@ -10,15 +10,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 4,
    "id": "e424d935",
    "metadata": {},
    "outputs": [
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n"
+     "ename": "ModuleNotFoundError",
+     "evalue": "No module named 'pandas'",
+     "output_type": "error",
+     "traceback": [
+      "\u001B[0;31m---------------------------------------------------------------------------\u001B[0m",
+      "\u001B[0;31mModuleNotFoundError\u001B[0m                       Traceback (most recent call last)",
+      "\u001B[0;32m<ipython-input-4-65ab904da1ab>\u001B[0m in \u001B[0;36m<module>\u001B[0;34m\u001B[0m\n\u001B[1;32m      1\u001B[0m \u001B[0;32mimport\u001B[0m \u001B[0mnumpy\u001B[0m \u001B[0;32mas\u001B[0m \u001B[0mnp\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m----> 2\u001B[0;31m \u001B[0;32mimport\u001B[0m \u001B[0mpandas\u001B[0m \u001B[0;32mas\u001B[0m \u001B[0mpd\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m      3\u001B[0m \u001B[0;32mfrom\u001B[0m \u001B[0mpytorch_lightning\u001B[0m \u001B[0;32mimport\u001B[0m \u001B[0mLightningModule\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mTrainer\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m      4\u001B[0m \u001B[0;32mfrom\u001B[0m \u001B[0mpytorch_lightning\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mcallbacks\u001B[0m \u001B[0;32mimport\u001B[0m \u001B[0mModelCheckpoint\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m      5\u001B[0m \u001B[0;32mfrom\u001B[0m \u001B[0mMedCode\u001B[0m \u001B[0;32mimport\u001B[0m \u001B[0mCodeMapping\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;31mModuleNotFoundError\u001B[0m: No module named 'pandas'"
      ]
     }
    ],
@@ -29,15 +33,16 @@
     "from pytorch_lightning.callbacks import ModelCheckpoint\n",
     "from MedCode import CodeMapping\n",
     "\n",
-    "import datasets\n",
-    "import models\n",
-    "import utils\n",
+    "import pyhealth.datasets as datasets\n",
+    "import pyhealth.models as models\n",
+    "import pyhealth.utils as utils\n",
     "from importlib import reload\n",
     "reload(datasets)\n",
     "reload(models)\n",
     "reload(utils)\n",
     "\n",
-    "print ()\n"
+    "import torch\n",
+    "print(torch.cuda.is_available())\n"
    ]
   },
   {
@@ -519,4 +524,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 5
-}
+}

examples/data/README.md

@@ -0,0 +1,3 @@
+# Data
+
+Put raw data under `./data`.

model_cpt/epoch=19-step=1140.ckpt …amples/model_cpt/epoch=19-step=1140.ckptmodel_cpt/epoch=19-step=1140.ckpt renamed to examples/model_cpt/epoch=19-step=1140.ckpt model_cpt/epoch=19-step=1140.ckpt renamed to examples/model_cpt/epoch=19-step=1140.ckpt

@@ -10,7 +10,7 @@
 from collections import defaultdict
 
 def collate_func_RETAIN(cur_patient, voc_size):
-    """ data is a list of sample from the dataset """
+    """ datasets is a list of sample from the dataset """
     max_len = max([len(visit[0]) + len(visit[1]) for visit in cur_patient])
     X = []
     y = torch.zeros((len(cur_patient), voc_size[2]))
@@ -86,7 +86,7 @@ def encodes(self, code_list):
 
 class MIMIC_III:
     """
-    MIMIC-III data object
+    MIMIC-III datasets object
         - the original MIMIC-III medication is encoded by RxNorm (the column name uses "NDC")
         - when initialize, input the target_code and the according code_map
     For example, 
@@ -211,12 +211,12 @@ def get_atc3(x):
 
     def get_dataloader(self, MODEL):
         """
-        get the dataloaders for MODEL, since different models has different data loader (input formats are different)
-            - data <list>: each element is a patient record
-                - data[0] <list>: each element is a visit
-                    - data[0][0] <list>: diag encoded list for this visit
-                    - data[0][1] <list>: prod encoded list for this visit
-                    - data[0][2] <list>: med encoded list for this visit
+        get the dataloaders for MODEL, since different models has different datasets loader (input formats are different)
+            - datasets <list>: each element is a patient record
+                - datasets[0] <list>: each element is a visit
+                    - datasets[0][0] <list>: diag encoded list for this visit
+                    - datasets[0][1] <list>: prod encoded list for this visit
+                    - datasets[0][2] <list>: med encoded list for this visit
         """
         data = []
         for _, visit_ls in self.pat_to_visit.items():
@@ -233,7 +233,7 @@ def get_dataloader(self, MODEL):
             if len(cur_pat) <= 1: continue
             data.append(cur_pat)
 
-        # data split
+        # datasets split
         split_point = int(len(data) * 2 / 3)
         data_train = data[:split_point]
         eval_len = int(len(data[split_point:]) / 2)

pyhealth/__init__.py

@@ -3,7 +3,7 @@
 import torch.nn as nn
 import torch.nn.functional as F
 import numpy as np
-from utils import multi_label_metric
+from pyhealth.utils import multi_label_metric
 
 class RETAIN(LightningModule):
     def __init__(self, voc_size, emb_size=64):