Conda environment in Google Colab

clinicalml · Jun 17, 2023 · dd07655 · dd07655
1 parent 50461e3
commit dd07655
Showing 1 changed file with 40 additions and 7 deletions.
diff --git a/examples/eol/sard_eol.ipynb b/examples/eol/sard_eol.ipynb
@@ -16,7 +16,7 @@
     "id": "n3ieKAgvPfsZ"
    },
    "source": [
-    "# Run End of Life prediction task on Synthetic Patient Data in OMOP"
+    "# End of Life prediction task on Synthetic Patient Data in OMOP"
    ]
   },
   {
@@ -30,13 +30,48 @@
     "Data is sourced from the publicly available Medicare Claims Synthetic Public Use Files (SynPUF), released by the Centers for Medicare and Medicaid Services (CMS) and available in [Google BigQuery](https://console.cloud.google.com/marketplace/product/hhs/synpuf). The synthetic set contains 2008-2010 Medicare insurance claims for development and demonstration purposes and was coverted to the Medical Outcomes Partnership (OMOP) Common Data Model from its original CSV form."
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Install conda environment "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "If using this notebook in Google Colaboratory, the following cells must be run to create and activate the conda environment needed to run `omop-learn`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install -q condacolab\n",
+    "!git clone https://github.com/clinicalml/omop-learn.git\n",
+    "!conda env create -f omop-learn/environment.yml"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%bash\n",
+    "source activate omop-learn"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {
     "id": "YaHCADZXPfsd"
    },
    "source": [
-    "## Imports and GPU setup"
+    "## Imports"
    ]
   },
   {
@@ -92,9 +127,7 @@
    "source": [
     "## Cohort, Outcome and Feature Collection\n",
     "\n",
-    "### 1. Set up a connection to the OMOP CDM database\n",
-    "\n",
-    "Parameters for connection to be specified in ./config.py"
+    "### 1. Set up a connection to the OMOP CDM database"
    ]
   },
   {
@@ -154,7 +187,7 @@
     "id": "Oa7ULCSRPfsh"
    },
    "source": [
-    "### 4. Process the collected data and calculate indices needed for the deep model"
+    "### 2. Process the collected data and calculate indices needed for the deep model"
    ]
   },
   {
@@ -278,7 +311,7 @@
     "# train the regression model over several choices of regularization parameter\n",
     "reg_lambdas = [2, 0.2, 0.02]\n",
     "lr_val_aucs = []\n",
-    "model = OMOPLogisticRegression(\"eol_new_50\", windowed_dataset)\n",
+    "model = OMOPLogisticRegression(\"synpuf_eol\", windowed_dataset)\n",
     "\n",
     "for reg_lambda in reg_lambdas:\n",
     "    # Gen and fit\n",