From f89781d724114c745d59623c5f094504607018bf Mon Sep 17 00:00:00 2001
From: Anh Nguyet Vu <32753274+anngvu@users.noreply.github.com>
Date: Thu, 1 Feb 2024 18:11:58 -0700
Subject: [PATCH] Feat/examples (#84)

* Add first examples to validation

* Ignore GE intermediates

* Update config comment

* Update example
---
 .gitignore                            |  1 +
 config.yml                            |  5 +++--
 tests/validate/config.json            | 18 ++++++++++++++++++
 tests/validate/examples/my_cohort.csv |  3 +++
 4 files changed, 25 insertions(+), 2 deletions(-)
 create mode 100644 tests/validate/config.json
 create mode 100644 tests/validate/examples/my_cohort.csv

diff --git a/.gitignore b/.gitignore
index 31925ec..20f5df8 100644
--- a/.gitignore
+++ b/.gitignore
@@ -8,6 +8,7 @@ schematic_service_account_creds.json
 tests/generate/GF.jsonld
 tests/generate/config.json
 tests/generate/creds.json
+great_expectations
 
 # Tools
 retold
diff --git a/config.yml b/config.yml
index 3181374..e1fb4e8 100644
--- a/config.yml
+++ b/config.yml
@@ -1,4 +1,5 @@
-# Do not change the "definitions" section unless you know what you"re doing
+# This config format is guaranteed to work with schematicpy versions between 23.9.1 and 24.1.1 only.
+# Schematic often changes the config format without notice, check the docs and your installed version.
 # Usage: schematic manifest -c config.yml get -dt ClinicalAssay -t "Test Manifest" --jsonld ./NF.jsonld -s
 asset_store:
   synapse:
@@ -11,7 +12,7 @@ manifest:
   data_type: 
 
   # Clinical Data
-    - "CohortCore"
+    - "CohortCoreTemplate"
     - "CohortCoreRFC"
     - "CohortCorePortal"
 
diff --git a/tests/validate/config.json b/tests/validate/config.json
new file mode 100644
index 0000000..11f06e6
--- /dev/null
+++ b/tests/validate/config.json
@@ -0,0 +1,18 @@
+{ "meta": "Validate example manifests against templates with schematic and data model.",
+  "schematic_reference": { 
+    "version": "23.1.1",
+    "flags" :
+      {
+        "great_expectations" : true
+      }
+  },
+  "tests": [
+    {
+      "manifest": "examples/my_cohort.csv",
+      "template": "CohortCoreTemplate",
+      "expect_pass": true,
+      "expectation": "Should pass",
+      "comment": "Contains mock data for two patients"
+    }
+  ]
+}
\ No newline at end of file
diff --git a/tests/validate/examples/my_cohort.csv b/tests/validate/examples/my_cohort.csv
new file mode 100644
index 0000000..877c2ae
--- /dev/null
+++ b/tests/validate/examples/my_cohort.csv
@@ -0,0 +1,3 @@
+Component,ParticipantID,TimepointLabel,Age,Sex,BMI,Race,Ethnicity,VitalStatus,Height,Weight,Gravidity,Parity,AgeAtMenarche,MenstrualCyclePhase,MenopauseStatus,PrimaryDiagnosis,AgeatDiagnosis,DiagnosisStatusType,ClassBRCA1,ClassBRCA2,TobaccoUse,PackYearsSmoked,AlcoholUse,NumberofDrinksPerWeek,AntibioticUse,SampleCollectionCenter,SampleCollectionYear,ERStatus,PRStatus,HER2Status,Id,entityId
+CohortCoreTemplate,ABC123,,30,female,30.5,white,not hispanic or latino,Alive,Not Reported,Not Reported,0,0,12,Not Reported,Pre,,Not Reported,Not Applicable,Positive,,Former,Unknown- 2yrs,Yes,2,Unknown,MGH,Not Reported,Positive,,,f4fa455b-a495-4ffa-b807-7525947da662,syn53461756
+CohortCoreTemplate,ABC456,,31,female,22.2,white,not hispanic or latino,Alive,Not Reported,Not Reported,1,1,13,Not Reported,Pre,,Not Reported,Not Applicable,Positive,,Never,0.3ppd-unknown,Occasionally,<1,Unknown,MGH,Not Reported,Positive,Negative,Negative,6d049ab5-f089-4c32-9306-f9fb4765ca20,syn53461756