ODSC-39738: allow for attaching customized scorepy in prepare (#133)

Author: mingkang111

ads/model/generic_model.py

@@ -789,6 +789,7 @@ def prepare(
         ignore_pending_changes: bool = True,
         max_col_num: int = DATA_SCHEMA_MAX_COL_NUM,
         ignore_conda_error: bool = False,
+        score_py_uri: str = None,
         **kwargs: Dict,
     ) -> "GenericModel":
         """Prepare and save the score.py, serialized model and runtime.yaml file.
@@ -841,6 +842,10 @@ def prepare(
             number of features(columns).
         ignore_conda_error: (bool, optional). Defaults to False.
             Parameter to ignore error when collecting conda information.
+        score_py_uri: (str, optional). Defaults to None.
+            The uri of the customized score.py, which can be local path or OCI object storage URI.
+            When provide with this attibute, the `score.py` will not be auto generated, and the
+            provided `score.py` will be added into artifact_dir.
         kwargs:
             impute_values: (dict, optional).
                 The dictionary where the key is the column index(or names is accepted
@@ -1001,13 +1006,22 @@ def prepare(
                 jinja_template_filename = (
                     "score-pkl" if self._serialize else "score_generic"
                 )
-        self.model_artifact.prepare_score_py(
-            jinja_template_filename=jinja_template_filename,
-            model_file_name=self.model_file_name,
-            data_deserializer=self.model_input_serializer.name,
-            model_serializer=self.model_save_serializer.name,
-            **{**kwargs, **self._score_args},
-        )
+
+        if score_py_uri:
+            utils.copy_file(
+                uri_src=score_py_uri,
+                uri_dst=os.path.join(self.artifact_dir, "score.py"),
+                force_overwrite=force_overwrite,
+                auth=self.auth
+            )
+        else:
+            self.model_artifact.prepare_score_py(
+                jinja_template_filename=jinja_template_filename,
+                model_file_name=self.model_file_name,
+                data_deserializer=self.model_input_serializer.name,
+                model_serializer=self.model_save_serializer.name,
+                **{**kwargs, **self._score_args},
+            )
 
         self._summary_status.update_status(
             detail="Generated score.py", status=ModelState.DONE.value

docs/source/user_guide/model_registration/model_artifact.rst

@@ -30,6 +30,7 @@ Auto generation of ``score.py`` with framework specific code for loading models
 
 To accomodate for other frameworks that are unknown to ADS, a template code for ``score.py`` is generated in the provided artificat directory location.
 
+
 Prepare the Model Artifact
 --------------------------
 
@@ -98,8 +99,25 @@ ADS automatically captures:
 *  ``UseCaseType`` in ``metadata_taxonomy`` cannot be automatically populated. One way to populate the use case is to pass ``use_case_type`` to the ``prepare`` method.
 *  Model introspection is automatically triggered.
 
-.. include:: _template/score.rst
+Prepare with custom ``score.py``
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+.. versionadded:: 2.8.4
 
+You could provide the location of your own ``score.py`` by ``score_py_uri`` in :py:meth:`~ads.model.GenericModel.prepare`.
+The provided ``score.py`` will be added into model artifact.
+
+.. code-block:: python3
+
+    tf_model.prepare(
+        inference_conda_env="generalml_p38_cpu_v1",
+        use_case_type=UseCaseType.MULTINOMIAL_CLASSIFICATION,
+        X_sample=trainx,
+        y_sample=trainy,
+        score_py_uri="/path/to/score.py"
+    )
+
+.. include:: _template/score.rst
 
 Model Introspection
 -------------------

tests/unitary/with_extras/model/test_files/custom_score.py

@@ -0,0 +1,11 @@
+# THIS IS A CUSTOM SCORE.PY
+
+model_name = "model.pkl"
+
+
+def load_model(model_file_name=model_name):
+    return model_file_name
+
+
+def predict(data, model=load_model()):
+    return {"prediction": "This is a custom score.py."}

tests/unitary/with_extras/model/test_generic_model.py

@@ -168,14 +168,16 @@
     "training_script": None,
 }
 
+INFERENCE_CONDA_ENV = "oci://bucket@namespace/<path_to_service_pack>"
+TRAINING_CONDA_ENV = "oci://bucket@namespace/<path_to_service_pack>"
+
 
 class TestEstimator:
     def predict(self, x):
         return x**2
 
 
 class TestGenericModel:
-
     iris = load_iris()
     X, y = iris.data, iris.target
     X_train, X_test, y_train, y_test = train_test_split(X, y)
@@ -297,6 +299,19 @@ def test_prepare_both_conda_env(self, mock_signer):
             == "3.7"
         )
 
+    @patch("ads.common.auth.default_signer")
+    def test_prepare_with_custom_scorepy(self, mock_signer):
+        """Test prepare a trained model with custom score.py."""
+        self.generic_model.prepare(
+            INFERENCE_CONDA_ENV,
+            model_file_name="fake_model_name",
+            score_py_uri=f"{os.path.dirname(os.path.abspath(__file__))}/test_files/custom_score.py",
+        )
+        assert os.path.exists(os.path.join("fake_folder", "score.py"))
+
+        prediction = self.generic_model.verify(data="test")["prediction"]
+        assert prediction == "This is a custom score.py."
+
     @patch("ads.common.auth.default_signer")
     def test_verify_without_reload(self, mock_signer):
         """Test verify input data without reload artifacts."""
@@ -795,7 +810,6 @@ def test_predict_success__serialize_input(self, mock_client, mock_signer):
             with patch.object(
                 GenericModel, "get_data_serializer"
             ) as mock_get_data_serializer:
-
                 mock_get_data_serializer.return_value.data = df.to_json()
                 mock_state.return_value = ModelDeploymentState.ACTIVE
                 with patch.object(ModelDeployment, "predict") as mock_predict:
@@ -1782,7 +1796,6 @@ def test_upload_artifact_fail(self):
     def test_upload_artifact_success(self):
         """Tests uploading model artifacts to the provided `uri`."""
         with tempfile.TemporaryDirectory() as tmp_dir:
-
             # copy test artifacts to the temp folder
             shutil.copytree(
                 os.path.join(self.curr_dir, "test_files/valid_model_artifacts"),