[IBCDPE-712] Implement Great Expectations for the genes_biodomains Datset

config.yaml

@@ -62,6 +62,7 @@ datasets:
         ensembl_id: ensembl_gene_id
         goterm_name: go_terms
       destination: *dest
+      gx_folder: syn53127958
 
   - neuropath_corr:
       files:

gx_suite_definitions/genes_biodomains.ipynb

@@ -0,0 +1,187 @@
+{
+ "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",
+    "\n",
+    "from expectations.expect_column_values_to_have_list_length import ExpectColumnValuesToHaveListLength\n",
+    "from expectations.expect_column_values_to_have_list_length_in_range import ExpectColumnValuesToHaveListLengthInRange\n",
+    "from expectations.expect_column_values_to_have_list_members import ExpectColumnValuesToHaveListMembers\n",
+    "from expectations.expect_column_values_to_have_list_members_of_type import ExpectColumnValuesToHaveListMembersOfType\n",
+    "from expectations.expect_column_values_to_have_list_of_dict_with_expected_values import ExpectColumnValuesToHaveListOfDictWithExpectedValues\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Create Expectation Suite for Genes Biodomains 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": [
+    "genes_biodomains_data_file = syn.get(\"syn51062085\").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",
+    "    genes_biodomains_data_file\n",
+    ")\n",
+    "validator.expectation_suite_name = \"genes_biodomains\"\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Add Expectations to Validator Object For Each Column"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# ensembl_gene_id\n",
+    "validator.expect_column_values_to_be_of_type(\"ensembl_gene_id\", \"str\")\n",
+    "validator.expect_column_values_to_not_be_null(\"ensembl_gene_id\")\n",
+    "validator.expect_column_value_lengths_to_equal(\"ensembl_gene_id\", 15)\n",
+    "# checks format and allowed chatacters\n",
+    "validator.expect_column_values_to_match_regex(\"ensembl_gene_id\", \"^ENSG\\d{11}$\")\n",
+    "validator.expect_column_values_to_be_unique(\"ensembl_gene_id\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# gene_biodomains\n",
+    "validator.expect_column_values_to_be_of_type(\"gene_biodomains\", \"list\")\n",
+    "validator.expect_column_values_to_not_be_null(\"gene_biodomains\")\n",
+    "validator.expect_column_values_to_have_list_length_in_range(column=\"gene_biodomains\", list_length_range=[1, 19])\n",
+    "validator.expect_column_values_to_have_list_members_of_type(column=\"gene_biodomains\", member_type=\"dict\")\n",
+    "biodomain_list = ['Apoptosis', 'Vasculature', 'Lipid Metabolism', 'Proteostasis', 'Immune Response', 'Autophagy', 'Mitochondrial Metabolism', 'Structural Stabilization', 'Synapse', 'Endolysosome', 'Metal Binding and Homeostasis', 'Oxidative Stress', 'Epigenetic', 'APP Metabolism', 'Cell Cycle', 'DNA Repair', 'RNA Spliceosome', 'Tau Homeostasis', 'Myelination']\n",
+    "validator.expect_column_values_to_have_list_of_dict_with_expected_values(column=\"gene_biodomains\", list_dict_values={\"key\": \"biodomain\", \"values\": biodomain_list})\n"
+   ]
+  },
+  {
+   "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
+}

src/agoradatatools/great_expectations/gx/checkpoints/genes_biodomains.yml

@@ -0,0 +1,30 @@
+name: genes_biodomains
+config_version: 1.0
+template_name:
+module_name: great_expectations.checkpoint
+class_name: Checkpoint
+run_name_template:
+expectation_suite_name:
+batch_request: {}
+action_list:
+  - name: store_validation_result
+    action:
+      class_name: StoreValidationResultAction
+  - name: store_evaluation_params
+    action:
+      class_name: StoreEvaluationParametersAction
+  - name: update_data_docs
+    action:
+      class_name: UpdateDataDocsAction
+evaluation_parameters: {}
+runtime_configuration: {}
+validations:
+  - batch_request:
+      datasource_name: default_pandas_datasource
+      data_asset_name: '#ephemeral_pandas_asset'
+      options: {}
+      batch_slice:
+    expectation_suite_name: genes_biodomains
+profilers: []
+ge_cloud_id:
+expectation_suite_ge_cloud_id:

src/agoradatatools/great_expectations/gx/expectations/genes_biodomains.json

@@ -0,0 +1,113 @@
+{
+  "data_asset_type": null,
+  "expectation_suite_name": "genes_biodomains",
+  "expectations": [
+    {
+      "expectation_type": "expect_column_values_to_be_of_type",
+      "kwargs": {
+        "column": "ensembl_gene_id",
+        "type_": "str"
+      },
+      "meta": {}
+    },
+    {
+      "expectation_type": "expect_column_values_to_not_be_null",
+      "kwargs": {
+        "column": "ensembl_gene_id"
+      },
+      "meta": {}
+    },
+    {
+      "expectation_type": "expect_column_value_lengths_to_equal",
+      "kwargs": {
+        "column": "ensembl_gene_id",
+        "value": 15
+      },
+      "meta": {}
+    },
+    {
+      "expectation_type": "expect_column_values_to_match_regex",
+      "kwargs": {
+        "column": "ensembl_gene_id",
+        "regex": "^ENSG\\d{11}$"
+      },
+      "meta": {}
+    },
+    {
+      "expectation_type": "expect_column_values_to_be_unique",
+      "kwargs": {
+        "column": "ensembl_gene_id"
+      },
+      "meta": {}
+    },
+    {
+      "expectation_type": "expect_column_values_to_be_of_type",
+      "kwargs": {
+        "column": "gene_biodomains",
+        "type_": "list"
+      },
+      "meta": {}
+    },
+    {
+      "expectation_type": "expect_column_values_to_not_be_null",
+      "kwargs": {
+        "column": "gene_biodomains"
+      },
+      "meta": {}
+    },
+    {
+      "expectation_type": "expect_column_values_to_have_list_length_in_range",
+      "kwargs": {
+        "column": "gene_biodomains",
+        "list_length_range": [
+          1,
+          19
+        ]
+      },
+      "meta": {}
+    },
+    {
+      "expectation_type": "expect_column_values_to_have_list_members_of_type",
+      "kwargs": {
+        "column": "gene_biodomains",
+        "member_type": "dict"
+      },
+      "meta": {}
+    },
+    {
+      "expectation_type": "expect_column_values_to_have_list_of_dict_with_expected_values",
+      "kwargs": {
+        "column": "gene_biodomains",
+        "list_dict_values": {
+          "key": "biodomain",
+          "values": [
+            "Apoptosis",
+            "Vasculature",
+            "Lipid Metabolism",
+            "Proteostasis",
+            "Immune Response",
+            "Autophagy",
+            "Mitochondrial Metabolism",
+            "Structural Stabilization",
+            "Synapse",
+            "Endolysosome",
+            "Metal Binding and Homeostasis",
+            "Oxidative Stress",
+            "Epigenetic",
+            "APP Metabolism",
+            "Cell Cycle",
+            "DNA Repair",
+            "RNA Spliceosome",
+            "Tau Homeostasis",
+            "Myelination"
+          ]
+        }
+      },
+      "meta": {}
+    }
+  ],
+  "ge_cloud_id": null,
+  "meta": {
+    "great_expectations_version": "0.18.1"
+  }
+}