added get samples, get subsamples

docs/changelog.md

@@ -6,7 +6,7 @@ This project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.htm
 - Fixed forking schema
 - Improved forking efficiency [#129](https://github.com/pepkit/pepdbagent/issues/129)
 - Added uploading project from dict 
-- Added get_config method to project module [#128](https://github.com/pepkit/pepdbagent/issues/128)
+- Added get_config, get_smaples, get_subsamples methods to project module [#128](https://github.com/pepkit/pepdbagent/issues/128)
 - Fixed error handling in views API [#130](https://github.com/pepkit/pepdbagent/issues/130)
 - Added no_fail to views API 
 

pepdbagent/modules/project.py

@@ -8,6 +8,7 @@
 from sqlalchemy.exc import IntegrityError, NoResultFound
 from sqlalchemy.orm import Session
 from sqlalchemy import Select
+import numpy as np
 
 from peppy.const import (
     SAMPLE_RAW_DICT_KEY,
@@ -256,6 +257,9 @@ def create(
         elif isinstance(project, dict):
             # verify if the dictionary has all necessary elements.
             # samples should be always presented as list of dicts (orient="records"))
+            _LOGGER.warning(
+                f"Project f{namespace}/{name}:{tag} is provided as dictionary. Project won't be validated."
+            )
             proj_dict = ProjectDict(**project).model_dump(by_alias=True)
         else:
             raise PEPDatabaseAgentError(
@@ -909,3 +913,56 @@ def get_config(self, namespace: str, name: str, tag: str) -> Union[dict, None]:
         if result:
             return result[0]
         return None
+
+    def get_subsamples(self, namespace: str, name: str, tag: str) -> Union[list, None]:
+        """
+        Get project subsamples by providing namespace, name, and tag
+
+        :param namespace: project namespace
+        :param name: project name
+        :param tag: project tag
+        :return: list with project subsamples
+        """
+        statement = self._create_select_statement(name, namespace, tag)
+
+        with Session(self._sa_engine) as session:
+
+            found_prj = session.scalar(statement)
+
+            if found_prj:
+                _LOGGER.info(f"Project has been found: {found_prj.namespace}, {found_prj.name}")
+                subsample_dict = {}
+                if found_prj.subsamples_mapping:
+                    for subsample in found_prj.subsamples_mapping:
+                        if subsample.subsample_number not in subsample_dict.keys():
+                            subsample_dict[subsample.subsample_number] = []
+                        subsample_dict[subsample.subsample_number].append(subsample.subsample)
+                    return list(subsample_dict.values())
+                else:
+                    return []
+            else:
+                raise ProjectNotFoundError(
+                    f"No project found for supplied input: '{namespace}/{name}:{tag}'. "
+                    f"Did you supply a valid namespace and project?"
+                )
+
+    def get_samples(self, namespace: str, name: str, tag: str, raw: bool = True) -> list:
+        """
+        Get project samples by providing namespace, name, and tag
+
+        :param namespace: project namespace
+        :param name: project name
+        :param tag: project tag
+        :param raw: if True, retrieve unprocessed (raw) PEP dict. [Default: True]
+
+        :return: list with project samples
+        """
+        if raw:
+            return self.get(namespace=namespace, name=name, tag=tag, raw=True).get(
+                SAMPLE_RAW_DICT_KEY
+            )
+        return (
+            self.get(namespace=namespace, name=name, tag=tag, raw=False)
+            .sample_table.replace({np.nan: None})
+            .to_dict(orient="records")
+        )

requirements/requirements-all.txt

@@ -6,3 +6,4 @@ coloredlogs>=15.0.1
 pytest-mock
 pydantic>=2.0
 psycopg>=3.1.15
+numpy>=1.26.4

tests/test_pepagent.py

@@ -5,6 +5,7 @@
 import peppy
 import pytest
 from sqlalchemy.exc import OperationalError
+import numpy as np
 
 import pepdbagent
 from pepdbagent.exceptions import (
@@ -105,6 +106,60 @@ def test_get_config(self, initiate_pepdb_con, namespace, name):
         ff.name = name
         assert kk == ff.config
 
+    @pytest.mark.parametrize(
+        "namespace, name",
+        [
+            ["namespace3", "subtables"],
+        ],
+    )
+    def test_get_subsamples(self, initiate_pepdb_con, namespace, name):
+        prj_subtables = initiate_pepdb_con.project.get_subsamples(
+            namespace=namespace,
+            name=name,
+            tag="default",
+        )
+        orgiginal_prj = peppy.Project(get_path_to_example_file(namespace, name))
+
+        assert (
+            prj_subtables
+            == orgiginal_prj.to_dict(extended=True, orient="records")["_subsample_list"]
+        )
+
+    @pytest.mark.parametrize(
+        "namespace, name",
+        [
+            ["namespace3", "subtables"],
+        ],
+    )
+    def test_get_samples_raw(self, initiate_pepdb_con, namespace, name):
+        prj_samples = initiate_pepdb_con.project.get_samples(
+            namespace=namespace, name=name, tag="default", raw=True
+        )
+        orgiginal_prj = peppy.Project(get_path_to_example_file(namespace, name))
+
+        assert (
+            prj_samples == orgiginal_prj.to_dict(extended=True, orient="records")["_sample_dict"]
+        )
+
+    @pytest.mark.parametrize(
+        "namespace, name",
+        [
+            ["namespace3", "subtables"],
+        ],
+    )
+    def test_get_samples_processed(self, initiate_pepdb_con, namespace, name):
+        prj_samples = initiate_pepdb_con.project.get_samples(
+            namespace=namespace,
+            name=name,
+            tag="default",
+            raw=False,
+        )
+        orgiginal_prj = peppy.Project(get_path_to_example_file(namespace, name))
+
+        assert prj_samples == orgiginal_prj.sample_table.replace({np.nan: None}).to_dict(
+            orient="records"
+        )
+
     @pytest.mark.parametrize(
         "namespace, name,tag",
         [