aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--gn3/db/traits.py28
-rw-r--r--tests/unit/db/test_traits.py144
2 files changed, 170 insertions, 2 deletions
diff --git a/gn3/db/traits.py b/gn3/db/traits.py
index 5013844..3827c34 100644
--- a/gn3/db/traits.py
+++ b/gn3/db/traits.py
@@ -99,12 +99,36 @@ def get_trait_csv_sample_data(conn: Any,
"cxref.StrainId = st.Id) "
"LEFT JOIN CaseAttribute ca ON ca.Id = cxref.CaseAttributeId"
"WHERE px.Id = %s AND px.PhenotypeId = %s ORDER BY st.Name")
+ case_attr_columns = set()
+ csv_data = {}
with conn.cursor() as cursor:
cursor.execute(__query, (trait_name, phenotype_id))
- return ("Strain Name,Value,SE,Count\n" +
- "\n".join(map(lambda x:x[0], cursor.fetchall())))
+ for data in cursor.fetchall():
+ if data[1] == "x":
+ csv_data[data[0]] = None
+ else:
+ sample, case_attr, value = data[0], data[1], data[2]
+ if not csv_data.get(sample):
+ csv_data[sample] = {}
+ csv_data[sample][case_attr] = None if value == "x" else value
+ case_attr_columns.add(case_attr)
+ if not case_attr_columns:
+ return ("Strain Name,Value,SE,Count\n" +
+ "\n".join(csv_data.keys()))
+ else:
+ columns = sorted(case_attr_columns)
+ csv = ("Strain Name,Value,SE,Count," +
+ ",".join(columns) + "\n")
+ for key, value in csv_data.items():
+ if not value:
+ csv += (key + (len(case_attr_columns) * ",x") + "\n")
+ else:
+ vals = [str(value.get(column, "x")) for column in columns]
+ csv += (key + "," + ",".join(vals) + "\n")
+ return csv
return "No Sample Data Found"
+
def update_sample_data(conn: Any, #pylint: disable=[R0913]
trait_name: str,
strain_name: str,
diff --git a/tests/unit/db/test_traits.py b/tests/unit/db/test_traits.py
index de65348..a1c1136 100644
--- a/tests/unit/db/test_traits.py
+++ b/tests/unit/db/test_traits.py
@@ -5,6 +5,7 @@ from gn3.db.traits import (
build_trait_name,
export_trait_data,
export_informative,
+ get_trait_csv_sample_data,
set_haveinfo_field,
update_sample_data,
retrieve_trait_info,
@@ -431,3 +432,146 @@ class TestTraitsDBFunctions(TestCase):
with self.subTest(trait_data=trait_data):
self.assertEqual(
export_informative(trait_data, inc_var), expected)
+
+
+class TestRetrieveCsvData(TestCase):
+ "Test cases for retrieving csv data"
+ def test_get_trait_csv_sample_data_with_case_attributes(self):
+ """Test that correct csv is returned when all samples have case attribute
+values"""
+ mock_conn = mock.MagicMock()
+ with mock_conn.cursor() as cursor:
+ cursor.fetchall.return_value = [
+ ['H1044,25.900000,x,1', 'Strain', 'BXD29'],
+ ['H1044,25.900000,x,1', 'Condition', 'CD'],
+ ['H1044,25.900000,x,1', 'EarTag', 1044],
+ ['H1044,25.900000,x,1', 'Age', 724],
+ ['H1096,23.700001,x,1', 'EarTag', 1096],
+ ['H1096,23.700001,x,1', 'Age', 732],
+ ['H1096,23.700001,x,1', 'Strain', 'BXD90'],
+ ['H1096,23.700001,x,1', 'Condition', 'CD'],
+ ['H1163,95.000000,x,1', 'Strain', 'D2B6F1'],
+ ['H1163,95.000000,x,1', 'Condition', 'HF'],
+ ['H1163,95.000000,x,1', 'EarTag', 1163],
+ ['H1163,95.000000,x,1', 'Age', 1114],
+ ['H1230,88.099998,x,1', 'EarTag', 1230],
+ ['H1230,88.099998,x,1', 'Age', 726],
+ ['H1230,88.099998,x,1', 'Strain', 'B6D2F1'],
+ ['H1230,88.099998,x,1', 'Condition', 'HF'],
+ ['H1251,24.100000,x,1', 'EarTag', 1251],
+ ['H1251,24.100000,x,1', 'Age', 711],
+ ['H1251,24.100000,x,1', 'Strain', 'C57BL/6J'],
+ ['H1251,24.100000,x,1', 'Condition', 'CD'],
+ ['H1292,24.900000,x,1', 'Strain', 'C57BL/6J'],
+ ['H1292,24.900000,x,1', 'Condition', 'CD'],
+ ['H1292,24.900000,x,1', 'EarTag', 1292],
+ ['H1292,24.900000,x,1', 'Age', 705],
+ ]
+ csv = get_trait_csv_sample_data(conn=mock_conn,
+ trait_name=10006,
+ phenotype_id=28409)
+ self.assertEqual(csv, """Strain Name,Value,SE,Count,Age,Condition,EarTag,Strain
+H1044,25.900000,x,1,724,CD,1044,BXD29
+H1096,23.700001,x,1,732,CD,1096,BXD90
+H1163,95.000000,x,1,1114,HF,1163,D2B6F1
+H1230,88.099998,x,1,726,HF,1230,B6D2F1
+H1251,24.100000,x,1,711,CD,1251,C57BL/6J
+H1292,24.900000,x,1,705,CD,1292,C57BL/6J
+""")
+
+ def test_get_trait_csv_sample_data_with_missing_case_attributes(self):
+ """Test that the correct csv is returned when some case attributes are not
+present from some samples"""
+ mock_conn = mock.MagicMock()
+ with mock_conn.cursor() as cursor:
+ cursor.fetchall.return_value = [
+ ['H1044,25.900000,x,1', 'Strain', 'BXD29'],
+ ['H1044,25.900000,x,1', 'Condition', 'CD'],
+ ['H1044,25.900000,x,1', 'Age', 724],
+ ['H1096,23.700001,x,1', 'Age', 732],
+ ['H1096,23.700001,x,1', 'Strain', 'BXD90'],
+ ['H1096,23.700001,x,1', 'Condition', 'CD'],
+ ['H1163,95.000000,x,1', 'Condition', 'HF'],
+ ['H1163,95.000000,x,1', 'EarTag', 1163],
+ ['H1163,95.000000,x,1', 'Age', 1114],
+ ['H1230,88.099998,x,1', 'EarTag', 1230],
+ ['H1230,88.099998,x,1', 'Age', 726],
+ ['H1230,88.099998,x,1', 'Strain', 'B6D2F1'],
+ ['H1230,88.099998,x,1', 'Condition', 'HF'],
+ ['H1251,24.100000,x,1', 'EarTag', 1251],
+ ['H1251,24.100000,x,1', 'Age', 711],
+ ['H1251,24.100000,x,1', 'Strain', 'C57BL/6J'],
+ ['H1251,24.100000,x,1', 'Condition', 'CD'],
+ ['H1292,24.900000,x,1', 'Strain', 'C57BL/6J'],
+ ['H1292,24.900000,x,1', 'Condition', 'CD'],
+ ['H1292,24.900000,x,1', 'EarTag', 1292],
+ ]
+ csv = get_trait_csv_sample_data(conn=mock_conn,
+ trait_name=10006,
+ phenotype_id=28409)
+ self.assertEqual(csv, """Strain Name,Value,SE,Count,Age,Condition,EarTag,Strain
+H1044,25.900000,x,1,724,CD,x,BXD29
+H1096,23.700001,x,1,732,CD,x,BXD90
+H1163,95.000000,x,1,1114,HF,1163,x
+H1230,88.099998,x,1,726,HF,1230,B6D2F1
+H1251,24.100000,x,1,711,CD,1251,C57BL/6J
+H1292,24.900000,x,1,x,CD,1292,C57BL/6J
+""")
+
+ def test_get_trait_csv_sample_data_with_varying_case_attributes(self):
+ """Test that the correct csv is returned when case attributes are entirely
+missing from same samples, and only one sample has a case attribute that is
+not present in all other samples"""
+ mock_conn = mock.MagicMock()
+ with mock_conn.cursor() as cursor:
+ cursor.fetchall.return_value = [
+ ['H1044,25.900000,x,1', 'x', 'x'],
+ ['H1096,23.700001,x,1', 'x', 'x'],
+ ['H1163,95.000000,x,1', 'x', 'x'],
+ ['H1230,88.099998,x,1', 'x', 'x'],
+ ['H1251,24.100000,x,1', 'x', 'x'],
+ ['H1292,24.900000,x,1', 'x', 'x'],
+ ]
+ csv = get_trait_csv_sample_data(conn=mock_conn,
+ trait_name=10006,
+ phenotype_id=28409)
+ self.assertEqual(csv, """Strain Name,Value,SE,Count
+H1044,25.900000,x,1
+H1096,23.700001,x,1
+H1163,95.000000,x,1
+H1230,88.099998,x,1
+H1251,24.100000,x,1
+H1292,24.900000,x,1""")
+
+ def test_get_trait_csv_sample_data_with_empty_case_attributes(self):
+ mock_conn = mock.MagicMock()
+ with mock_conn.cursor() as cursor:
+ cursor.fetchall.return_value = [
+ ['H1044,25.900000,x,1', 'x', 'x'],
+ ['H1096,23.700001,x,1', 'Age', 732],
+ ['H1096,23.700001,x,1', 'Sex', "M"],
+ ['H1096,23.700001,x,1', 'Strain', 'BXD90'],
+ ['H1096,23.700001,x,1', 'Condition', 'CD'],
+ ['H1163,95.000000,x,1', 'Condition', 'HF'],
+ ['H1163,95.000000,x,1', 'EarTag', 1163],
+ ['H1163,95.000000,x,1', 'Age', 1114],
+ ['H1230,88.099998,x,1', 'EarTag', 1230],
+ ['H1230,88.099998,x,1', 'Age', 726],
+ ['H1230,88.099998,x,1', 'Strain', 'B6D2F1'],
+ ['H1230,88.099998,x,1', 'Condition', 'HF'],
+ ['H1251,24.100000,x,1', 'x', 'x'],
+ ['H1292,24.900000,x,1', 'Strain', 'C57BL/6J'],
+ ['H1292,24.900000,x,1', 'Condition', 'CD'],
+ ['H1292,24.900000,x,1', 'EarTag', 1292],
+ ]
+ csv = get_trait_csv_sample_data(conn=mock_conn,
+ trait_name=10006,
+ phenotype_id=28409)
+ self.assertEqual(csv, """Strain Name,Value,SE,Count,Age,Condition,EarTag,Sex,Strain
+H1044,25.900000,x,1,x,x,x,x,x
+H1096,23.700001,x,1,732,CD,x,M,BXD90
+H1163,95.000000,x,1,1114,HF,1163,x,x
+H1230,88.099998,x,1,726,HF,1230,x,B6D2F1
+H1251,24.100000,x,1,x,x,x,x,x
+H1292,24.900000,x,1,x,CD,1292,x,C57BL/6J
+""")
generated by cgit v1.2.3 (git 2.44.0) at 2024-11-22 06:31:57 +0000