[IBCDPE-795] Adds rna_distribution_data GX Suite (#144)

* adds rna_dd gx suite

* pre-commit

config.yaml

@@ -289,6 +289,7 @@ datasets:
       custom_transformations: 1
       provenance: *rna_diff_expr_data_provenance
       destination: *dest
+      gx_enabled: true
 
   - proteomics_distribution_data:
       files:

gx_suite_definitions/rna_distributinon_data.ipynb

@@ -0,0 +1,243 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import synapseclient\n",
+    "\n",
+    "import great_expectations as gx\n",
+    "\n",
+    "context = gx.get_context(project_root_dir='../src/agoradatatools/great_expectations')\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Create Expectation Suite for RNA Distribution Data"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Get Example Data File"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "syn = synapseclient.Synapse()\n",
+    "syn.login()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "rna_distribution_data_file = syn.get(\"syn28094691\").path\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create Validator Object on Data File"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "validator = context.sources.pandas_default.read_json(\n",
+    "    rna_distribution_data_file\n",
+    ")\n",
+    "validator.expectation_suite_name = \"rna_distribution_data\"\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Add Expectations to Validator Object For Each Column"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# model\n",
+    "validator.expect_column_values_to_be_of_type(\"model\", \"str\")\n",
+    "validator.expect_column_values_to_not_be_null(\"model\")\n",
+    "validator.expect_column_values_to_be_in_set(\"model\", [\"AD Diagnosis (males and females)\", \"AD Diagnosis x AOD (males and females)\",\"AD Diagnosis x Sex (females only)\", \"AD Diagnosis x Sex (males only)\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# tissue\n",
+    "validator.expect_column_values_to_be_of_type(\"tissue\", \"str\")\n",
+    "validator.expect_column_values_to_not_be_null(\"tissue\")\n",
+    "validator.expect_column_values_to_be_in_set(\"tissue\", [\"CBE\", \"DLPFC\", \"FP\", \"IFG\", \"PHG\", \"STG\", \"TCX\", \"ACC\", \"PCC\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# min\n",
+    "validator.expect_column_values_to_be_of_type(\"min\", \"float\")\n",
+    "validator.expect_column_values_to_not_be_null(\"min\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# max\n",
+    "validator.expect_column_values_to_be_of_type(\"max\", \"float\")\n",
+    "validator.expect_column_values_to_not_be_null(\"max\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# median\n",
+    "validator.expect_column_values_to_be_of_type(\"median\", \"float\")\n",
+    "validator.expect_column_values_to_not_be_null(\"median\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# first_quartile\n",
+    "validator.expect_column_values_to_be_of_type(\"first_quartile\", \"float\")\n",
+    "validator.expect_column_values_to_not_be_null(\"first_quartile\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# third_quartile\n",
+    "validator.expect_column_values_to_be_of_type(\"third_quartile\", \"float\")\n",
+    "validator.expect_column_values_to_not_be_null(\"third_quartile\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# multi-field\n",
+    "validator.expect_column_pair_values_a_to_be_greater_than_b(\"max\", \"third_quartile\")\n",
+    "validator.expect_column_pair_values_a_to_be_greater_than_b(\"third_quartile\", \"median\")\n",
+    "validator.expect_column_pair_values_a_to_be_greater_than_b(\"median\", \"first_quartile\")\n",
+    "validator.expect_column_pair_values_a_to_be_greater_than_b(\"first_quartile\", \"min\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Save Expectation Suite"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "validator.save_expectation_suite(discard_failed_expectations=False)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create Checkpoint and View Results"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "checkpoint = context.add_or_update_checkpoint(\n",
+    "    name=\"agora-test-checkpoint\",\n",
+    "    validator=validator,\n",
+    ")\n",
+    "checkpoint_result = checkpoint.run()\n",
+    "context.view_validation_result(checkpoint_result)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Build Data Docs - Click on Expectation Suite to View All Expectations"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "context.build_data_docs()\n",
+    "context.open_data_docs()\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}