upload_folder function for managed folders (#186)

* upload_folder function for managed folders

* Add import from managed folder for mlflow

* Improve doc mlflow

* Improve doc mlflow

* Add possibility to load mlflow version from managed_folder object

* Improve upload_folder utils function

* Rename smartFolderId into folderRef

* Remove useless argument check

* Update documentation

Co-authored-by: Adrien Lavoillotte <adrien.lavoillotte@dataiku.com>

* Add inline comment

Co-authored-by: Adrien Lavoillotte <adrien.lavoillotte@dataiku.com>

Co-authored-by: Adrien Lavoillotte <adrien.lavoillotte@dataiku.com>

Author: Valentin Thorey

dataikuapi/dss/managedfolder.py

@@ -2,6 +2,7 @@
 from ..utils import DataikuUTF8CSVReader
 from ..utils import DataikuStreamedHttpUTF8CSVReader
 import json
+import os
 from requests import utils
 from .metrics import ComputedMetrics
 from .future import DSSFuture
@@ -99,7 +100,7 @@ def delete_file(self, path):
     def put_file(self, path, f):
         """
         Upload the file to the managed folder
-        
+
         Args:
             f: the file contents, as a stream
             path: the path of the file
@@ -108,6 +109,21 @@ def put_file(self, path, f):
                 "POST", "/projects/%s/managedfolders/%s/contents/%s" % (self.project_key, self.odb_id, utils.quote(path)),
                 "", f)
 
+    def upload_folder(self, path, folder):
+        """
+        Upload folder and its content as path in the managed folder.
+
+        :param str path: the destination path of the folder in the managed folder
+        :param str folder: path  (absolute or relative) of the source folder to upload
+        """
+        real_root = os.path.realpath(folder)
+        for root, _, files in os.walk(real_root):
+            for file in files:
+                filename = os.path.join(root, file)
+                relpath = os.path.relpath(filename, real_root)
+                with open(filename, "rb") as f:
+                    self.put_file(os.path.join(path, relpath), f)
+
     ########################################################
     # Managed folder actions
     ########################################################

dataikuapi/dss/savedmodel.py

@@ -4,6 +4,7 @@
 from .ml import DSSMLTask
 from .ml import DSSTrainedClusteringModelDetails
 from .ml import DSSTrainedPredictionModelDetails
+from .managedfolder import DSSManagedFolder
 
 from ..utils import _make_zipfile
 
@@ -135,7 +136,6 @@ def import_mlflow_version_from_path(self, version_id, path, code_env_name="INHER
         :return a :class:MLFlowVersionHandler in order to interact with the new MLFlow model version
         """
         # TODO: Add a check that it's indeed a MLFlow model folder
-        # TODO: cleanup the archive
         import shutil
         import os
 
@@ -150,6 +150,36 @@ def import_mlflow_version_from_path(self, version_id, path, code_env_name="INHER
         finally:
             shutil.rmtree(archive_temp_dir)
 
+    def import_mlflow_version_from_managed_folder(self, version_id, managed_folder, path, code_env_name="INHERIT"):
+        """
+        Create a new version for this saved model from a path containing a MLFlow model in a managed folder.
+
+        Requires the saved model to have been created using :meth:`dataikuapi.dss.project.DSSProject.create_mlflow_pyfunc_model`.
+
+        :param str version_id: Identifier of the version to create
+        :param str managed_folder: Identifier of the managed folder or `dataikuapi.dss.managedfolder.DSSManagedFolder`
+        :param str path: Path of the MLflow folder in the managed folder
+        :param str code_env_name: Name of the code env to use for this model version. The code env must contain at least
+                                  mlflow and the package(s) corresponding to the used MLFlow-compatible frameworks.
+                                  If value is "INHERIT", the default active code env of the project will be used
+        :return a :class:MLFlowVersionHandler in order to interact with the new MLFlow model version
+        """
+        # TODO: Add a check that it's indeed a MLFlow model folder
+        folder_ref = None
+        if type(managed_folder) is DSSManagedFolder:
+            folder_ref = "{}.{}".format(managed_folder.project_key, managed_folder.id)
+        else:
+            folder_ref = managed_folder
+
+        self.client._perform_empty(
+            "POST", "/projects/{project_id}/savedmodels/{saved_model_id}/versions/{version_id}?codeEnvName={codeEnvName}".format(
+                project_id=self.project_key, saved_model_id=self.sm_id, version_id=version_id, codeEnvName=code_env_name
+            ),
+            params={"folderRef": folder_ref, "path": path},
+            files={"file": (None, None)}  # required for backend-mandated multipart request
+        )
+        return self.get_mlflow_version_handler(version_id)
+
     def get_mlflow_version_handler(self, version_id):
         """
         Returns a :class:MLFlowVersionHandler to interact with a MLFlow model version