pandahub 0.3.14__zip → 0.3.16__zip

{pandahub-0.3.14 → pandahub-0.3.16}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pandahub
-Version: 0.3.14
+Version: 0.3.16
 Summary: Data hub for pandapower and pandapipes networks based on MongoDB
 Author-email: Jan Ulffers <jan.ulffers@iee.fraunhofer.de>, Leon Thurner <leon.thurner@retoflow.de>, Jannis Kupka <jannis.kupka@retoflow.de>, Mike Vogt <mike.vogt@iee.fraunhofer.de>, Joschka Thurner <joschka.thurner@retoflow.de>, Alexander Scheidler <alexander.scheidler@iee.fraunhofer.de>
 License: Copyright (c) 2022 by University of Kassel, Fraunhofer Institute for Energy Economics

{pandahub-0.3.14 → pandahub-0.3.16}/pandahub/lib/PandaHub.py

@@ -38,6 +38,7 @@ from pandahub.lib.database_toolbox import (
     get_dtypes,
     decompress_timeseries_data,
     convert_geojsons,
+    get_metadata_for_timeseries_collections
 )
 from pandahub.lib.mongodb_indexes import MONGODB_INDEXES
 
@@ -2053,20 +2054,21 @@ class PandaHub:
             self.check_permission("write")
             db = self._get_project_database()
         if self.collection_is_timeseries(collection_name, project_id, global_database):
-            metadata = kwargs
-            if data_type is not None:
-                metadata["data_type"] = data_type
-            net_id = metadata.get('net_id', None)
-            if net_id is None:
-                net_ids = db["_networks"].distinct("_id")
-                if len(net_ids) == 1:
-                    net_id = net_ids[0]
-                else:
-                    raise ValueError(
-                        "No net_id was provided and multiple networks exist in the database. "
-                        "Please provide a net_id."
-                    )
-            metadata["_id"] = f"{net_id}_{metadata.get('element_type', None)}_{metadata.get('element_index', None)}_{data_type}"
+            # get metadata dictionary based on the input arguments
+            metadata = get_metadata_for_timeseries_collections(db, data_type=data_type, **kwargs)
+            _id =  metadata["_id"]
+
+            # delete overlapping timeseries already in the database
+            filter = {
+                "metadata._id": _id,
+                "timestamp": {
+                    "$gte": timeseries.index.min(),
+                    "$lte":  timeseries.index.max()
+                }
+            }
+            db.timeseries.delete_many(filter)
+
+            # create new timeseries documents
             if isinstance(timeseries, pd.Series):
                 documents = [
                     {"metadata": metadata, "timestamp": idx, "value": value}
@@ -2078,9 +2080,11 @@ class PandaHub:
                     for idx, row in timeseries.iterrows()
                 ]
             db[collection_name].insert_many(documents)
+
             if kwargs.get("return_id"):
-                return metadata["_id"]
+                return _id
             return None
+
         document = create_timeseries_document(
             timeseries=timeseries,
             data_type=data_type,
@@ -2345,11 +2349,9 @@ class PandaHub:
             self.check_permission("read")
             db = self._get_project_database()
         if self.collection_is_timeseries(collection_name, project_id, global_database):
-            meta_filter = {
-                "metadata." + key: value for key, value in filter_document.items()
-            }
+            metadata = get_metadata_for_timeseries_collections(db, **kwargs)
             pipeline = []
-            pipeline.append({"$match": meta_filter})
+            pipeline.append({"$match": {"metadata._id": metadata["_id"]}})
             pipeline.append({"$project": {"_id": 0, "metadata": 0}})
             timeseries = db[collection_name].aggregate_pandas_all(pipeline)
             if len(timeseries) == 0:
@@ -2995,15 +2997,8 @@ class PandaHub:
         self.check_permission("write")
         db = self._get_project_database()
         if self.collection_is_timeseries(collection_name):
-            meta_filter = {
-                "metadata.element_type": element_type,
-                "metadata.data_type": data_type,
-            }
-            if netname is not None:
-                meta_filter["metadata.netname"] = netname
-            if element_index is not None:
-                meta_filter["metadata.element_index"] = element_index
-            return db[collection_name].delete_many(meta_filter)
+            metadata = get_metadata_for_timeseries_collections(db, data_type, **kwargs)
+            return db[collection_name].delete_many({"metadata._id": metadata["_id"]})
         filter_document = {"element_type": element_type, "data_type": data_type}
         if netname is not None:
             filter_document["netname"] = netname
@@ -3062,8 +3057,11 @@ class PandaHub:
         del_res = db[collection_name].delete_many(match_filter)
         return del_res
 
-    def create_timeseries_collection(self, collection_name, overwrite=False):
-        db = self._get_project_database()
+    def create_timeseries_collection(self, collection_name, overwrite=False, project_id=None):
+        if project_id is None:
+            db = self._get_project_database()
+        else:
+            db = self.mongo_client[str(project_id)]
         collection_exists = collection_name in db.list_collection_names()
         if collection_exists:
             if overwrite:
@@ -3196,6 +3194,7 @@ class PandaHub:
         return self.get_net_collections(db, with_areas)
 
 
+
 if __name__ == "__main__":
     self = PandaHub()
     project_name = "test_project"

{pandahub-0.3.14 → pandahub-0.3.16}/pandahub/lib/database_toolbox.py

@@ -478,3 +478,22 @@ def mongo_client(database: str | None = None, collection: str | None = None, con
         client.close()
 
 
+def get_metadata_for_timeseries_collections(db, data_type=None, net_id=None, element_type=None, element_index=None, **kwargs):
+        if element_type is None:
+            raise ValueError("element_type needs to be defined for timeseries collections")
+        if element_index is None:
+            raise ValueError("element_index needs to be defined for timeseries collections")
+        if data_type is None:
+            raise ValueError("data_type needs to be defined for timeseries collections")
+        if net_id is None:
+            net_ids = db["_networks"].distinct("_id")
+            if len(net_ids) == 1:
+                net_id = net_ids[0]
+            else:
+                raise ValueError(
+                    "No net_id was provided and multiple networks exist in the database. "
+                    "Please provide a net_id."
+                )
+        metadata = {"data_type": data_type, "net_id": net_id, "element_type": element_type, "element_index": element_index, **kwargs}
+        metadata["_id"] = f"{net_id}_{element_type}_{element_index}_{data_type}"
+        return metadata

{pandahub-0.3.14 → pandahub-0.3.16}/pandahub.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pandahub
-Version: 0.3.14
+Version: 0.3.16
 Summary: Data hub for pandapower and pandapipes networks based on MongoDB
 Author-email: Jan Ulffers <jan.ulffers@iee.fraunhofer.de>, Leon Thurner <leon.thurner@retoflow.de>, Jannis Kupka <jannis.kupka@retoflow.de>, Mike Vogt <mike.vogt@iee.fraunhofer.de>, Joschka Thurner <joschka.thurner@retoflow.de>, Alexander Scheidler <alexander.scheidler@iee.fraunhofer.de>
 License: Copyright (c) 2022 by University of Kassel, Fraunhofer Institute for Energy Economics

{pandahub-0.3.14 → pandahub-0.3.16}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "pandahub"
-version = "0.3.14"  # File format version '__format_version__' is tracked in __init__.py
+version = "0.3.16"  # File format version '__format_version__' is tracked in __init__.py
 authors=[
     { name = "Jan Ulffers", email = "jan.ulffers@iee.fraunhofer.de" },
     { name = "Leon Thurner", email = "leon.thurner@retoflow.de" },