🍱 Add test data (#1)

laminlabs · May 8, 2024 · 40c1432 · 40c1432
1 parent 019f976
commit 40c1432
Show file tree

Hide file tree

Showing 8 changed files with 160 additions and 75 deletions.
diff --git a/.gitignore b/.gitignore
@@ -1,3 +1,7 @@
+docs/mimic-iv-demo-data-in-the-omop-common-data-model-0.9
+docs/mimic-iv-demo-data-in-the-omop-common-data-model-0.9.zip
+docs/test-omop/
+
 # macOS
 .DS_Store
 .AppleDouble

diff --git a/docs/guide/index.md → docs/guide.md b/docs/guide/index.md → docs/guide.md
diff --git a/docs/guide/quickstart.ipynb b/docs/guide/quickstart.ipynb
diff --git a/docs/index.md b/docs/index.md
@@ -7,7 +7,7 @@
 :maxdepth: 1
 :hidden:
 
-guide/index
+guide
 reference
 changelog
 ```
diff --git a/docs/quickstart.ipynb b/docs/quickstart.ipynb
@@ -0,0 +1,102 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Quickstart"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
+   "outputs": [],
+   "source": [
+    "!wget https://physionet.org/static/published-projects/mimic-iv-demo-omop/mimic-iv-demo-data-in-the-omop-common-data-model-0.9.zip\n",
+    "!unzip mimic-iv-demo-data-in-the-omop-common-data-model-0.9.zip"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!lamin init --storage ./test-omop --schema omop"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import lamindb as ln\n",
+    "import omop as oo\n",
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv(\"./mimic-iv-demo-data-in-the-omop-common-data-model-0.9/1_omop_data_csv/2b_concept.csv\")\n",
+    "df.columns = df.columns.str.lower()\n",
+    "df.rename(columns={\"concept_class_id\": \"concept_class\"}, inplace=True)\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "concepts = [oo.Concept(**row.to_dict()) for _, row in df.iterrows()]\n",
+    "for concept in concepts:\n",
+    "    concept.save()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "oo.Concept.df()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "py310",
+   "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": "3.10.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/omop/__init__.py b/omop/__init__.py
@@ -15,7 +15,6 @@
    CohortDefinition
    Concept
    ConceptAncestor
-   ConceptClass
    ConceptRelationship
    ConceptSynonym
    ConditionEra
@@ -74,7 +73,6 @@ def __getattr__(name):
         CohortDefinition,
         Concept,
         ConceptAncestor,
-        ConceptClass,
         ConceptRelationship,
         ConceptSynonym,
         ConditionEra,

diff --git a/omop/migrations/0002_alter_concept_concept_class_remove_concept_domain_and_more.py b/omop/migrations/0002_alter_concept_concept_class_remove_concept_domain_and_more.py
@@ -0,0 +1,40 @@
+# Generated by Django 5.0.4 on 2024-05-08 10:00
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("omop", "0001_initial"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="concept",
+            name="concept_class",
+            field=models.CharField(max_length=255),
+        ),
+        migrations.RemoveField(
+            model_name="concept",
+            name="domain",
+        ),
+        migrations.RemoveField(
+            model_name="concept",
+            name="vocabulary",
+        ),
+        migrations.AddField(
+            model_name="concept",
+            name="domain_id",
+            field=models.CharField(default="0", max_length=255),
+            preserve_default=False,
+        ),
+        migrations.AddField(
+            model_name="concept",
+            name="vocabulary_id",
+            field=models.CharField(default="0", max_length=255),
+            preserve_default=False,
+        ),
+        migrations.DeleteModel(
+            name="ConceptClass",
+        ),
+    ]
diff --git a/omop/models.py b/omop/models.py
@@ -100,9 +100,9 @@ class Concept(Registry):
 
     concept_id = models.IntegerField(primary_key=True)
     concept_name = models.CharField(max_length=255)
-    domain = models.ForeignKey("Domain", models.DO_NOTHING)
-    vocabulary = models.ForeignKey("Vocabulary", models.DO_NOTHING)
-    concept_class = models.ForeignKey("ConceptClass", models.DO_NOTHING)
+    domain_id = models.CharField(max_length=255)
+    vocabulary_id = models.CharField(max_length=255)
+    concept_class = models.CharField(max_length=255)
     standard_concept = models.CharField(max_length=1, blank=True, null=True)
     concept_code = models.CharField(max_length=50)
     valid_start_date = models.DateField()
@@ -136,19 +136,19 @@ class Meta:
         db_table = "concept_ancestor"
 
 
-class ConceptClass(Registry):
-    """The CONCEPT_CLASS table is a reference table, which includes a list of the classifications used to differentiate Concepts within a given Vocabulary.
+# class ConceptClass(Registry):
+#     """The CONCEPT_CLASS table is a reference table, which includes a list of the classifications used to differentiate Concepts within a given Vocabulary.
 
-    This reference table is populated with a single record for each Concept Class.
-    """
+#     This reference table is populated with a single record for each Concept Class.
+#     """
 
-    concept_class_id = models.CharField(primary_key=True, max_length=20)
-    concept_class_name = models.CharField(max_length=255)
-    concept_class_concept = models.ForeignKey(Concept, models.DO_NOTHING)
+#     concept_class_id = models.CharField(primary_key=True, max_length=20)
+#     concept_class_name = models.CharField(max_length=255)
+#     concept_class_concept = models.ForeignKey(Concept, models.DO_NOTHING)  # introduce a loop
 
-    class Meta:
-        managed = True
-        db_table = "concept_class"
+#     class Meta:
+#         managed = True
+#         db_table = "concept_class"
 
 
 class ConceptRelationship(Registry):