domainiac 0.1.5__tar.gz → 0.2.0__tar.gz

{domainiac-0.1.5 → domainiac-0.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: domainiac
-Version: 0.1.5
+Version: 0.2.0
 Summary: Package for working with Energinet data, but with specialized functions used for Enigma.
 Author: Team Enigma
 Author-email: gridop-enigma@energinet.dk

{domainiac-0.1.5 → domainiac-0.2.0}/domainiac/managers/masterdata_manager.py

@@ -2,6 +2,8 @@ import datamazing.pandas as pdz
 import pandas as pd
 from typeguard import typechecked
 
+from ..wrappers import cache_decorator
+
 
 class MasterdataManager:
     """
@@ -13,27 +15,51 @@ class MasterdataManager:
         db: pdz.Database,
         time_interval: pdz.TimeInterval,
         resolution: pd.Timedelta,
+        cache_masterdata: bool = False,
     ) -> None:
         self.db = db
         self.time_interval = time_interval
         self.resolution = resolution
+        self.cache_masterdata = cache_masterdata
+
+    masterdata_cache = {}
+
+    @typechecked
+    def _get_operational_entities(self, table: str) -> pd.DataFrame:
+        filters = {"standing_entity_state": "InOperation"}
+        df = self.db.query(table, filters=filters)
+        return df
 
     @typechecked
-    def get_operational_entities(self, table: str, filters: dict = {}) -> pd.DataFrame:
+    def get_operational_entities(self, table: str) -> pd.DataFrame:
         """Gets the operational data for a given table."""
 
-        filters["standing_entity_state"] = "InOperation"
-        df = self.db.query(table, filters=filters)
+        if self.cache_masterdata:
+            cached_query = cache_decorator(self.masterdata_cache)(
+                self._get_operational_entities
+            )
+            df = cached_query(table)
+        else:
+            df = self._get_operational_entities(table)
+
         return df
 
     @typechecked
     def get_data(
-        self, table: str, filters: dict = {}, columns: list = []
+        self,
+        table: str,
+        filters: dict = {},
+        columns: list = [],
     ) -> pd.DataFrame:
         """Gets the data for a given table.
         Filters for rows valid at the end of time interval.
         """
-        df = self.get_operational_entities(table, filters)
+        # Get operational entities
+        df = self.get_operational_entities(table)
+
+        # Apply the filters
+        for column, value in filters.items():
+            df = df[df[column] == value].reset_index()
 
         for column in columns:
             if column not in df.columns:

{domainiac-0.1.5 → domainiac-0.2.0}/domainiac/managers/plant_manager.py

@@ -14,10 +14,12 @@ class PlantManager(MasterdataManager):
         db: pdz.Database,
         time_interval: pdz.TimeInterval,
         resolution: pd.Timedelta,
+        cache_masterdata: bool = False,
     ) -> None:
         self.db = db
         self.time_interval = time_interval
         self.resolution = resolution
+        self.cache_masterdata = cache_masterdata
 
     def get_plants(
         self,

domainiac-0.2.0/domainiac/managers/resource_manager.py

@@ -0,0 +1,112 @@
+import datamazing.pandas as pdz
+import pandas as pd
+from typeguard import typechecked
+
+from ..wrappers import cache_decorator
+
+DEFAULT_RESOLUTION = pd.Timedelta("PT5M")
+
+
+class ResourceManager:
+    """
+    Manager which simplifies the process of handling resource schedules.
+    Scheduled resources are delivered in a 5 min resolution. If a higher
+    resolution is chosen,
+    the result will be the most conservative value in the time interval,
+    e.i. max of minimum capacity and min of maximum capacity.
+    If no resolution is given, the default is 5 min.
+    If resolution is less than 5 min, the resulting time series will
+    default to 5 min resolution.
+    """
+
+    def __init__(
+        self,
+        db: pdz.Database,
+        time_interval: pdz.TimeInterval,
+        resolution: pd.Timedelta = DEFAULT_RESOLUTION,
+        cache_reource_schedules: bool = False,
+    ) -> None:
+        self.db = db
+        self.time_interval = time_interval
+        self.resolution = resolution
+        self.cache_reource_schedules = cache_reource_schedules
+
+    resource_schedules_cache = {}
+
+    @typechecked
+    def _query_resource_schedules(self, table: str) -> pd.DataFrame:
+        return self.db.query(
+            table_name=table,
+            time_interval=self.time_interval,
+        )
+
+    @typechecked
+    def query_resource_schedules(self, table: str) -> pd.DataFrame:
+        if self.cache_reource_schedules:
+            cached_query = cache_decorator(self.resource_schedules_cache)(
+                self._query_resource_schedules
+            )
+            df = cached_query(table)
+        else:
+            df = self._query_resource_schedules(table)
+        return df
+
+    @typechecked
+    def get_resource_schedules(self, resource_gsrn: str | list[str]) -> pd.DataFrame:
+        """Gets resource schedules for a given list of resource gsrns."""
+        df_resource_schedules = self.query_resource_schedules(
+            "scheduleResourcePowerPlan"
+        )
+
+        if isinstance(resource_gsrn, str):
+            resource_gsrn = [resource_gsrn]
+        df_resource_schedules = df_resource_schedules[
+            df_resource_schedules["resource_gsrn"].isin(resource_gsrn)
+        ]
+
+        if df_resource_schedules.empty:
+            raise ValueError(f"No resource schedules found for gsrn {resource_gsrn}.")
+
+        if self.resolution != DEFAULT_RESOLUTION:
+            df_resource_schedules = (
+                pdz.group(
+                    df_resource_schedules,
+                    by=[
+                        "market_participant",
+                        "created_time_utc",
+                        "price_area",
+                        "resource_gsrn",
+                    ],
+                )
+                .resample(on="time_utc", resolution=self.resolution)
+                .agg(
+                    {
+                        "schedule_power_MW": "mean",
+                        "schedule_capacity_min_MW": "max",
+                        "schedule_capacity_max_MW": "min",
+                    }
+                )
+                .dropna()
+            )
+        return df_resource_schedules.drop(
+            columns=["masterdata_gsrn", "datahub_gsrn_e18"], errors="ignore"
+        )
+
+    @typechecked
+    def get_latest_resource_schedules(
+        self,
+        resource_gsrn: str | list[str],
+    ) -> pd.DataFrame:
+        """Gets the lastest resource schedules for a given list of resource gsrns."""
+
+        df_resource_schedules = self.get_resource_schedules(resource_gsrn=resource_gsrn)
+
+        df_latest_created_time = pdz.group(
+            df=df_resource_schedules, by=["resource_gsrn", "time_utc"]
+        ).agg({"created_time_utc": "max"})
+
+        df_resource_latest = df_latest_created_time.merge(
+            df_resource_schedules, on=list(df_latest_created_time.columns)
+        )
+
+        return df_resource_latest

{domainiac-0.1.5 → domainiac-0.2.0}/domainiac/managers/unit_manager.py

@@ -14,10 +14,12 @@ class UnitManager(MasterdataManager):
         db: pdz.Database,
         time_interval: pdz.TimeInterval,
         resolution: pd.Timedelta,
+        cache_masterdata: bool = False,
     ) -> None:
         self.db = db
         self.time_interval = time_interval
         self.resolution = resolution
+        self.cache_masterdata = cache_masterdata
 
     def get_units(
         self,

domainiac-0.2.0/domainiac/wrappers/__init__.py

@@ -0,0 +1 @@
+from .cache_wrapper import cache_decorator

domainiac-0.2.0/domainiac/wrappers/cache_wrapper.py

@@ -0,0 +1,16 @@
+from functools import wraps
+
+
+def cache_decorator(cache):
+    def decorator(func):
+        @wraps(func)
+        def wrapper(*args, **kwargs):
+            if args in cache:
+                return cache[args]
+            result = func(*args, **kwargs)
+            cache[args] = result
+            return result
+
+        return wrapper
+
+    return decorator

{domainiac-0.1.5 → domainiac-0.2.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "domainiac"
-version = "0.1.5"
+version = "0.2.0"
 description = "Package for working with Energinet data, but with specialized functions used for Enigma."
 authors = ["Team Enigma <gridop-enigma@energinet.dk>"]
 packages = [

domainiac-0.1.5/domainiac/managers/resource_manager.py

@@ -1,79 +0,0 @@
-import datamazing.pandas as pdz
-import pandas as pd
-from typeguard import typechecked
-
-
-class ResourceManager:
-    """
-    Manager which simplifies the process of handling resource schedules.
-    Scheduled resources are delivered in a 5 min resolution. If a higher
-    resolution is chosen,
-    the result will be the most conservative value in the time interval,
-    e.i. max of minimum capacity and min of maximum capacity.
-    If no resolution is given, the default is 5 min.
-    If resolution is less than 5 min, the resulting time series will
-    default to 5 min resolution.
-    """
-
-    def __init__(
-        self,
-        db: pdz.Database,
-        time_interval: pdz.TimeInterval,
-        resolution: pd.Timedelta = pd.Timedelta("PT5M"),
-    ) -> None:
-        self.db = db
-        self.time_interval = time_interval
-        self.resolution = resolution
-
-    @typechecked
-    def get_resource_schedules(self, resource_gsrn: str | list[str]) -> pd.DataFrame:
-        """Gets resource schedules for a given list of resource gsrns."""
-        df_resource_schedules = self.db.query(
-            table_name="scheduleResourcePowerPlan",
-            time_interval=self.time_interval,
-            filters={"resource_gsrn": resource_gsrn},
-        )
-
-        if df_resource_schedules.empty:
-            raise ValueError(f"No resource schedules found for gsrn {resource_gsrn}.")
-
-        df_resource_resampled = (
-            pdz.group(
-                df_resource_schedules,
-                by=[
-                    "market_participant",
-                    "created_time_utc",
-                    "price_area",
-                    "resource_gsrn",
-                ],
-            )
-            .resample(on="time_utc", resolution=self.resolution)
-            .agg(
-                {
-                    "schedule_power_MW": "mean",
-                    "schedule_capacity_min_MW": "max",
-                    "schedule_capacity_max_MW": "min",
-                }
-            )
-            .dropna()
-        )
-        return df_resource_resampled
-
-    @typechecked
-    def get_latest_resource_schedules(
-        self,
-        resource_gsrn: str | list[str],
-    ) -> pd.DataFrame:
-        """Gets the lastest resource schedules for a given list of resource gsrns."""
-
-        df_resource_schedules = self.get_resource_schedules(resource_gsrn=resource_gsrn)
-
-        df_latest_created_time = pdz.group(
-            df=df_resource_schedules, by=["resource_gsrn", "time_utc"]
-        ).agg({"created_time_utc": "max"})
-
-        df_resource_latest = df_latest_created_time.merge(
-            df_resource_schedules, on=list(df_latest_created_time.columns)
-        )
-
-        return df_resource_latest