✅ Add sample test

tests/data/sample_registration/data/sample_manifest.csv

@@ -0,0 +1,13 @@
+sample_id,aliquot_id,participant,tissue_type,composition,age_at_collection,analyte,parent_sample
+s001,a001,p01,tumor,tissue,32,DNA,na
+s001,a002,p01,tumor,tissue,32,DNA,na
+s001,a003,p01,tumor,tissue,32,DNA,na
+s001,a004,p01,tumor,tissue,32,RNA,na
+s002,a005,p01,normal,blood,42,DNA,na
+s002,a006,p01,normal,blood,42,DNA,na
+s003,a007,p01,tumor,tissue,32,RNA,s001
+s003,a008,p01,tumor,tissue,32,DNA,s001
+s004,na,p01,tumor,tissue,32,na,s003
+s005,a009,p02,tumor,bone,56,DNA,na
+s006,a010,p02,normal,blood,58,DNA,na
+s007,na,p03,tumor,tissue,61,NA,na

tests/data/sample_registration/extract_configs/sample.py

@@ -0,0 +1,53 @@
+"""
+Auto-generated extract config module.
+
+See documentation at
+https://kids-first.github.io/kf-lib-data-ingest/tutorial/extract.html for
+information on writing extract config files.
+"""
+
+from kf_lib_data_ingest.common import constants
+from kf_lib_data_ingest.etl.extract.operations import keep_map, value_map
+from kf_lib_data_ingest.common.concept_schema import CONCEPT
+
+# TODO - Replace this with a URL to your own data file
+source_data_url = "file://../data/sample_manifest.csv"
+
+# TODO - Replace this with operations that make sense for your own data file
+operations = [
+    keep_map(in_col="participant", out_col=CONCEPT.PARTICIPANT.ID),
+    keep_map(in_col="sample_id", out_col=CONCEPT.SAMPLE.ID),
+    value_map(
+        in_col="aliquot_id",
+        m=lambda x: None if x == "na" else x,
+        out_col=CONCEPT.BIOSPECIMEN.ID,
+    ),
+    value_map(
+        in_col="tissue_type",
+        m={
+            "tumor": constants.SPECIMEN.TISSUE_TYPE.TUMOR,
+            "normal": constants.SPECIMEN.TISSUE_TYPE.NORMAL,
+        },
+        out_col=CONCEPT.SAMPLE.TISSUE_TYPE,
+    ),
+    value_map(
+        in_col="composition",
+        m={
+            "tissue": constants.SPECIMEN.COMPOSITION.TISSUE,
+            "blood": constants.SPECIMEN.COMPOSITION.BLOOD,
+            "bone": constants.SPECIMEN.COMPOSITION.BONE,
+        },
+        out_col=CONCEPT.SAMPLE.COMPOSITION,
+    ),
+    keep_map(in_col="age_at_collection", out_col=CONCEPT.SAMPLE.EVENT_AGE_DAYS),
+    value_map(
+        in_col="analyte",
+        m={
+            "DNA": constants.SEQUENCING.ANALYTE.DNA,
+            "RNA": constants.SEQUENCING.ANALYTE.RNA,
+            "NA": None,
+            "na": None,
+        },
+        out_col=CONCEPT.BIOSPECIMEN.ANALYTE,
+    ),
+]

tests/data/sample_registration/extract_configs/sample_relationship.py

@@ -0,0 +1,25 @@
+"""
+Auto-generated extract config module.
+
+See documentation at
+https://kids-first.github.io/kf-lib-data-ingest/tutorial/extract.html for
+information on writing extract config files.
+"""
+
+from kf_lib_data_ingest.common import constants
+from kf_lib_data_ingest.etl.extract.operations import keep_map, value_map
+from kf_lib_data_ingest.common.concept_schema import CONCEPT
+
+# TODO - Replace this with a URL to your own data file
+source_data_url = "file://../data/sample_manifest.csv"
+
+# TODO - Replace this with operations that make sense for your own data file
+operations = [
+    keep_map(in_col="participant", out_col=CONCEPT.PARTICIPANT.ID),
+    keep_map(in_col="sample_id", out_col=CONCEPT.SAMPLE.ID),
+    value_map(
+        in_col="parent_sample",
+        m=lambda x: None if x == "na" else x,
+        out_col=CONCEPT.BIOSPECIMEN.ID,
+    ),
+]

tests/data/sample_registration/ingest_package_config.py

@@ -0,0 +1,11 @@
+""" Ingest Package Config """
+
+# The list of entities that will be loaded into the target service
+target_service_entities = ["sample" "biospecimen", "sample_relationship"]
+
+# All paths are relative to the directory this file is in
+extract_config_dir = "extract_configs"
+
+transform_function_path = "transform_module.py"
+
+study = "SD_ME0WME0W"

tests/data/sample_registration/transform_module.py

@@ -0,0 +1,23 @@
+"""
+Auto-generated transform module
+
+Replace the contents of transform_function with your own code
+
+See documentation at
+https://kids-first.github.io/kf-lib-data-ingest/ for information on
+implementing transform_function.
+"""
+
+import os
+
+# Use these merge funcs, not pandas.merge
+from kf_lib_data_ingest.common.pandas_utils import outer_merge
+from kf_lib_data_ingest.common.concept_schema import CONCEPT
+from kf_lib_data_ingest.config import DEFAULT_KEY
+
+
+def transform_function(mapped_df_dict):
+    sr = mapped_df_dict["sample_relationship.py"]
+    sr = sr.dropna()
+
+    return {DEFAULT_KEY: mapped_df_dict["sample.py"], "sample_relationship": sr}