Add function for retrieving phenotype sample data as dict

1 files changed, 25 insertions, 0 deletions

diff --git a/gn3/db/sample_data.py b/gn3/db/sample_data.py
index 4062705..d8232cb 100644
--- a/gn3/db/sample_data.py
+++ b/gn3/db/sample_data.py
@@ -57,6 +57,31 @@ def __extract_actions(
             )
     return result
 
+def get_trait_sample_data(
+    conn: Any, trait_name: int, phenotype_id: int
+) -> str:
+    """Fetch a trait's sample data and return it as a dict"""
+    with conn.cursor() as cursor:
+        cursor.execute("""
+SELECT st.Name, ifnull(pd.value, 'x'), ifnull(ps.error, 'x'), ifnull(ns.count, 'x')
+FROM PublishFreeze pf JOIN PublishXRef px ON px.InbredSetId = pf.InbredSetId
+     JOIN PublishData pd ON pd.Id = px.DataId JOIN Strain st ON pd.StrainId = st.Id
+     LEFT JOIN PublishSE ps ON ps.DataId = pd.Id AND ps.StrainId = pd.StrainId
+     LEFT JOIN NStrain ns ON ns.DataId = pd.Id AND ns.StrainId = pd.StrainId
+     AND px.Id = %s AND px.PhenotypeId = %s
+ORDER BY st.Name""", (trait_name, phenotype_id))
+
+    sample_data = {}
+    for data in cursor.fetchall():
+        this_data = {}
+        sample, value, error, n_cases = data
+        sample_data[sample] = {
+            'value': value,
+            'error': error,
+            'n_cases:': n_cases
+        }
+
+    return sample_data
 
 def get_trait_csv_sample_data(
     conn: Any, trait_name: int, phenotype_id: int