hydroserverpy 1.4.0b3__tar.gz → 1.5.1__tar.gz

hydroserverpy-1.5.1/PKG-INFO

@@ -0,0 +1,66 @@
+Metadata-Version: 2.4
+Name: hydroserverpy
+Version: 1.5.1
+Summary: A Python client for managing HydroServer data
+Requires-Python: <4,>=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: requests>=2
+Requires-Dist: pydantic>=2.6
+Requires-Dist: pydantic[email]>=2.6
+Requires-Dist: pandas>=2.1
+Requires-Dist: numpy>=1.22.4
+Requires-Dist: pyyaml>=5
+Requires-Dist: simplejson>=3
+Requires-Dist: crontab>=1
+Requires-Dist: python-dateutil>=2.8.2
+Requires-Dist: croniter>=2.0.1
+Requires-Dist: jmespath>=1.0.1
+Provides-Extra: docs
+Requires-Dist: sphinx_autodoc_typehints; extra == "docs"
+Dynamic: license-file
+
+# HydroServer Python Client
+
+The hydroserverpy Python package provides an interface for managing HydroServer data and metadata, loading observations, and performing data quality control. This guide will go over how to install the package and connect to a HydroServer instance. Full hydroserverpy documentation and examples can be found [here](https://hydroserver2.github.io/hydroserver/how-to/hydroserverpy/hydroserverpy-examples.html).
+
+## Installation
+
+You can install the package via pip:
+
+```bash
+pip install hydroserverpy
+```
+
+## Connecting to HydroServer
+
+To connect to HydroServer, you need to initialize the client with the instance of HydroServer you're using and your user credentials if you want to access and modify your own data. If you don't provide authentication credentials you can read public data, but you will not be able to create or modify any data.
+
+### Example: Anonymous User
+
+```python
+from hydroserverpy import HydroServer
+
+# Initialize HydroServer connection.
+hs_api = HydroServer(
+    host='https://playground.hydroserver.org'
+)
+```
+
+### Example: Basic Authentication
+
+```python
+from hydroserverpy import HydroServer
+
+# Initialize HydroServer connection with credentials.
+hs_api = HydroServer(
+    host='https://playground.hydroserver.org',
+    email='user@example.com',
+    password='******'
+)
+```
+
+## Funding and Acknowledgements
+
+Funding for this project was provided by the National Oceanic & Atmospheric Administration (NOAA), awarded to the Cooperative Institute for Research to Operations in Hydrology (CIROH) through the NOAA Cooperative Agreement with The University of Alabama (NA22NWS4320003). Utah State University is a founding member of CIROH and receives funding under subaward from the University of Alabama. Additional funding and support have been provided by the State of Utah Division of Water Rights, the World Meteorological Organization, and the Utah Water Research laboratory at Utah State University.
+

{hydroserverpy-1.4.0b3 → hydroserverpy-1.5.1}/README.md

@@ -1,6 +1,6 @@
 # HydroServer Python Client
 
-The hydroserverpy Python package provides an interface for managing HydroServer data and metadata, loading observations, and performing data quality control. This guide will go over how to install the package and connect to a HydroServer instance. Full hydroserverpy documentation can be found [here](https://hydroserver2.github.io/hydroserverpy).
+The hydroserverpy Python package provides an interface for managing HydroServer data and metadata, loading observations, and performing data quality control. This guide will go over how to install the package and connect to a HydroServer instance. Full hydroserverpy documentation and examples can be found [here](https://hydroserver2.github.io/hydroserver/how-to/hydroserverpy/hydroserverpy-examples.html).
 
 ## Installation
 
@@ -40,5 +40,5 @@ hs_api = HydroServer(
 
 ## Funding and Acknowledgements
 
-Funding for this project was provided by the National Oceanic & Atmospheric Administration (NOAA), awarded to the Cooperative Institute for Research to Operations in Hydrology (CIROH) through the NOAA Cooperative Agreement with The University of Alabama (NA22NWS4320003). Utah State University is a founding member of CIROH and receives funding under subaward from the University of Alabama. Additional funding and support have been provided by the State of Utah Division of Water Rights, the World Meorological Organization, and the Utah Water Research laboratory at Utah State University.
+Funding for this project was provided by the National Oceanic & Atmospheric Administration (NOAA), awarded to the Cooperative Institute for Research to Operations in Hydrology (CIROH) through the NOAA Cooperative Agreement with The University of Alabama (NA22NWS4320003). Utah State University is a founding member of CIROH and receives funding under subaward from the University of Alabama. Additional funding and support have been provided by the State of Utah Division of Water Rights, the World Meteorological Organization, and the Utah Water Research laboratory at Utah State University.
 

{hydroserverpy-1.4.0b3 → hydroserverpy-1.5.1}/setup.cfg

@@ -1,6 +1,9 @@
 [metadata]
 name = hydroserverpy
-version = 1.4.0b3
+version = 1.5.1
+description = A Python client for managing HydroServer data
+long_description_content_type = text/markdown
+long_description = file: README.md
 
 [options]
 package_dir = 
@@ -12,8 +15,8 @@ install_requires =
 	requests >= 2
 	pydantic >= 2.6
 	pydantic[email] >= 2.6
-	pandas >= 2.2
-	numpy >= 2.0
+	pandas >= 2.1
+	numpy >= 1.22.4
 	pyyaml >= 5
 	simplejson >= 3
 	crontab >= 1

{hydroserverpy-1.4.0b3 → hydroserverpy-1.5.1}/src/hydroserverpy/api/models/etl/etl_configuration.py

@@ -74,7 +74,7 @@ class Timestamp(BaseModel):
     timezone: Optional[Union[FixedOffsetTimezone, str]] = Field(None, alias="timezone")
 
     class Config:
-        allow_population_by_field_name = True
+        populate_by_name = True
 
     @field_validator("timezone")
     def check_timezone(cls, timezone_value, info):
@@ -96,7 +96,7 @@ class RunTimePlaceholder(BaseModel):
     timestamp: Timestamp
 
     class Config:
-        allow_population_by_field_name = True
+        populate_by_name = True
 
 
 PlaceholderVariable = Annotated[
@@ -114,7 +114,7 @@ class BaseExtractor(BaseModel):
     )
 
     class Config:
-        allow_population_by_field_name = True
+        populate_by_name = True
 
 
 class HTTPExtractor(BaseExtractor):
@@ -140,7 +140,7 @@ class JSONTransformer(BaseTransformer):
     jmespath: str = Field(..., alias="JMESPath")
 
     class Config:
-        allow_population_by_field_name = True
+        populate_by_name = True
 
 
 class CSVTransformer(BaseTransformer):
@@ -151,7 +151,7 @@ class CSVTransformer(BaseTransformer):
     identifier_type: IdentifierType = Field(..., alias="identifierType")
 
     class Config:
-        allow_population_by_field_name = True
+        populate_by_name = True
 
 
 TransformerConfig = Union[JSONTransformer, CSVTransformer]
@@ -173,7 +173,7 @@ class ExpressionDataTransformation(BaseModel):
     expression: str
 
     class Config:
-        allow_population_by_field_name = True
+        populate_by_name = True
 
 
 class LookupTableDataTransformation(BaseModel):
@@ -181,7 +181,7 @@ class LookupTableDataTransformation(BaseModel):
     lookup_table_id: str = Field(..., alias="lookupTableId")
 
     class Config:
-        allow_population_by_field_name = True
+        populate_by_name = True
 
 
 DataTransformation = Union[ExpressionDataTransformation, LookupTableDataTransformation]
@@ -194,7 +194,7 @@ class MappingPath(BaseModel):
     )
 
     class Config:
-        allow_population_by_field_name = True
+        populate_by_name = True
 
 
 class SourceTargetMapping(BaseModel):
@@ -202,7 +202,7 @@ class SourceTargetMapping(BaseModel):
     paths: List[MappingPath] = Field(default_factory=list)
 
     class Config:
-        allow_population_by_field_name = True
+        populate_by_name = True
 
 
 class Payload(BaseModel):
@@ -213,7 +213,7 @@ class Payload(BaseModel):
     )
 
     class Config:
-        allow_population_by_field_name = True
+        populate_by_name = True
 
 
 class EtlConfiguration(BaseModel):

{hydroserverpy-1.4.0b3 → hydroserverpy-1.5.1}/src/hydroserverpy/api/models/etl/extractors/http_extractor.py

@@ -17,11 +17,8 @@ class HTTPExtractor(Extractor):
         url = self.resolve_placeholder_variables(payload, loader)
         logging.info(f"Requesting data from → {url}")
 
-        try:
-            response = requests.get(url)
-        except Exception as e:
-            logging.error(f"Failed to fetch {url}: {e}")
-            raise
+        response = requests.get(url)
+        response.raise_for_status()
 
         data = BytesIO()
         for chunk in response.iter_content(chunk_size=8192):

{hydroserverpy-1.4.0b3 → hydroserverpy-1.5.1}/src/hydroserverpy/api/models/etl/extractors/local_file_extractor.py

@@ -7,7 +7,7 @@ class LocalFileExtractor(Extractor):
     def __init__(self, extractor_config: ExtractorConfig):
         super().__init__(extractor_config)
 
-    def extract(self):
+    def extract(self, *args, **kwargs):
         """
         Opens the file and returns a file-like object.
         """

{hydroserverpy-1.4.0b3 → hydroserverpy-1.5.1}/src/hydroserverpy/api/models/etl/loaders/hydroserver_loader.py

@@ -36,8 +36,6 @@ class HydroServerLoader(Loader):
             if df.empty:
                 logging.warning(f"No new data for {col}, skipping.")
                 continue
-            logging.info(f"loading dataframe {df}")
-            logging.info(f"dtypes: {df.dtypes}")
 
             df = df.rename(columns={"timestamp": "phenomenon_time", "value": "result"})
 

{hydroserverpy-1.4.0b3 → hydroserverpy-1.5.1}/src/hydroserverpy/api/models/etl/schedule.py

@@ -1,6 +1,6 @@
 from datetime import datetime
 from typing import Literal, Optional
-from pydantic import BaseModel, Field, EmailStr
+from pydantic import BaseModel, Field
 
 
 class Schedule(BaseModel):
@@ -13,4 +13,4 @@ class Schedule(BaseModel):
     end_time: Optional[datetime] = Field(None, alias="endTime")
 
     class Config:
-        allow_population_by_field_name = True
+        populate_by_name = True

{hydroserverpy-1.4.0b3 → hydroserverpy-1.5.1}/src/hydroserverpy/api/models/etl/status.py

@@ -11,4 +11,4 @@ class Status(BaseModel):
     next_run: Optional[datetime] = Field(None, alias="nextRun")
 
     class Config:
-        allow_population_by_field_name = True
+        populate_by_name = True

{hydroserverpy-1.4.0b3 → hydroserverpy-1.5.1}/src/hydroserverpy/api/models/etl/timestamp_parser.py

@@ -73,11 +73,14 @@ class TimestampParser:
         return localized.dt.tz_convert(timezone.utc)
 
     def parse_series(self, raw_series: pd.Series) -> pd.Series:
-        s = raw_series.str.strip()
+        if pd.api.types.is_datetime64_any_dtype(raw_series):
+            s = raw_series  # already datetimes
+        else:
+            s = raw_series.astype("string", copy=False).str.strip()
         parsed = self._convert_series_to_UTC(s)
 
         if parsed.isna().any():
-            bad_rows = s[parsed.isna()].head(5).tolist()
+            bad_rows = s[parsed.isna()].head(2).tolist()
             logging.warning(
                 f"{parsed.isna().sum()} timestamps failed to parse. "
                 f"Sample bad values: {bad_rows}"

{hydroserverpy-1.4.0b3 → hydroserverpy-1.5.1}/src/hydroserverpy/api/models/etl/transformers/base.py

@@ -68,12 +68,19 @@ class Transformer(ABC):
     def standardize_dataframe(
         self, df: pd.DataFrame, mappings: List[SourceTargetMapping]
     ):
+        if not df.empty:
+            logging.info(f"Read payload into dataframe: {df.iloc[0].to_dict()}")
+        else:
+            logging.info("Read payload into dataframe: [empty dataframe]")
+
         # 1) Normalize timestamp column
         df.rename(columns={self.timestamp.key: "timestamp"}, inplace=True)
         if "timestamp" not in df.columns:
             msg = f"Timestamp column '{self.timestamp.key}' not found in data."
             logging.error(msg)
             raise ValueError(msg)
+        logging.info(f"Renamed timestamp column to 'timestamp'")
+
         df["timestamp"] = self.timestamp_parser.parse_series(df["timestamp"])
         df = df.drop_duplicates(subset=["timestamp"], keep="last")
 

{hydroserverpy-1.4.0b3 → hydroserverpy-1.5.1}/src/hydroserverpy/api/models/etl/transformers/csv_transformer.py

@@ -50,7 +50,7 @@ class CSVTransformer(Transformer):
             df = pd.read_csv(
                 clean_file,
                 sep=self.delimiter,
-                header=self.header_row,
+                header=0,
                 skiprows=self._build_skiprows(),
                 usecols=usecols,
                 dtype={self.timestamp.key: "string"},

{hydroserverpy-1.4.0b3 → hydroserverpy-1.5.1}/src/hydroserverpy/api/models/etl/transformers/json_transformer.py

@@ -24,6 +24,11 @@ class JSONTransformer(Transformer):
         Returns:
             pd.DataFrame: pandas DataFrames in the format pd.Timestamp, datastream_id_1, datastream_id_2, ...
         """
+        if data_file is None:
+            raise TypeError(
+                "JSONTransformer received None; expected file-like, bytes, or str"
+            )
+
         json_data = json.load(data_file)
         data_points = self.extract_data_points(json_data)
         if not data_points:

{hydroserverpy-1.4.0b3 → hydroserverpy-1.5.1}/src/hydroserverpy/api/models/iam/workspace.py

@@ -1,7 +1,7 @@
 from typing import List, Union, Optional, ClassVar, TYPE_CHECKING
 from uuid import UUID
 from datetime import datetime
-from pydantic import Field, EmailStr
+from pydantic import Field, EmailStr, AliasPath
 from ..base import HydroServerBaseModel
 
 if TYPE_CHECKING:
@@ -28,7 +28,9 @@ class Workspace(HydroServerBaseModel):
     name: str = Field(..., max_length=255)
     is_private: bool
     owner: "Account"
-    collaborator_role: Optional["Role"] = None
+    collaborator_role_id: Optional[Union[UUID, str]] = Field(
+        None, validation_alias=AliasPath("collaboratorRole", "id")
+    )
     pending_transfer_to: Optional["Account"] = None
 
     _editable_fields: ClassVar[set[str]] = {"name", "is_private"}
@@ -38,6 +40,7 @@ class Workspace(HydroServerBaseModel):
 
         self._roles = None
         self._collaborators = None
+        self._collaborator_role = None
         self._apikeys = None
         self._things = None
         self._observedproperties = None
@@ -72,6 +75,15 @@ class Workspace(HydroServerBaseModel):
 
         return self._collaborators
 
+    @property
+    def collaborator_role(self) -> Optional["Role"]:
+        """The user's collaborator role on this workspace."""
+
+        if self._collaborator_role is None and self.collaborator_role_id is not None:
+            self._collaborator_role = self.client.roles.get(uid=self.collaborator_role_id)
+
+        return self._collaborator_role
+
     @property
     def apikeys(self) -> List["APIKey"]:
         """The API keys associated with this workspace."""

{hydroserverpy-1.4.0b3 → hydroserverpy-1.5.1}/src/hydroserverpy/api/models/sta/datastream.py

@@ -194,6 +194,7 @@ class Datastream(HydroServerBaseModel):
         order_by: List[str] = ...,
         phenomenon_time_max: datetime = ...,
         phenomenon_time_min: datetime = ...,
+        result_qualifier_code: str = ...,
         fetch_all: bool = False,
     ) -> pd.DataFrame:
         """Retrieve the observations for this datastream."""
@@ -205,18 +206,21 @@ class Datastream(HydroServerBaseModel):
             order_by=order_by,
             phenomenon_time_max=phenomenon_time_max,
             phenomenon_time_min=phenomenon_time_min,
+            result_qualifier_code=result_qualifier_code,
             fetch_all=fetch_all
         )
 
     def load_observations(
         self,
         observations: pd.DataFrame,
+        mode: str = "insert"
     ) -> None:
         """Load a DataFrame of observations to the datastream."""
 
         return self.client.datastreams.load_observations(
             uid=self.uid,
             observations=observations,
+            mode=mode
         )
 
     def delete_observations(

{hydroserverpy-1.4.0b3 → hydroserverpy-1.5.1}/src/hydroserverpy/api/models/sta/observation.py

@@ -38,7 +38,9 @@ class ObservationCollection:
             data = response.json()
             self.dataframe = pd.DataFrame({to_snake(k): v for k, v in data.items()})
             if "phenomenon_time" in self.dataframe.columns:
-                self.dataframe["phenomenon_time"] = pd.to_datetime(self.dataframe["phenomenon_time"], utc=True)
+                self.dataframe["phenomenon_time"] = pd.to_datetime(
+                    self.dataframe["phenomenon_time"], utc=True, format="ISO8601"
+                )
         else:
             self.dataframe = pd.DataFrame()
 

{hydroserverpy-1.4.0b3 → hydroserverpy-1.5.1}/src/hydroserverpy/api/services/sta/datastream.py

@@ -220,6 +220,7 @@ class DatastreamService(HydroServerBaseService):
         order_by: List[str] = ...,
         phenomenon_time_max: datetime = ...,
         phenomenon_time_min: datetime = ...,
+        result_qualifier_code: str = ...,
         fetch_all: bool = False,
     ) -> ObservationCollection:
         """Retrieve observations of a datastream."""
@@ -230,6 +231,7 @@ class DatastreamService(HydroServerBaseService):
             "order_by": ",".join(order_by) if order_by is not ... else order_by,
             "phenomenon_time_max": phenomenon_time_max,
             "phenomenon_time_min": phenomenon_time_min,
+            "result_qualifier_code": result_qualifier_code,
             "format": "column"
         }
         params = {
@@ -256,12 +258,13 @@ class DatastreamService(HydroServerBaseService):
         self,
         uid: Union[UUID, str],
         observations: pd.DataFrame,
+        mode: str = "insert"
     ) -> None:
         """Load observations to a datastream."""
 
         path = f"/{self.client.base_route}/{self.model.get_route()}/{str(uid)}/observations/bulk-create"
         headers = {"Content-type": "application/json"}
-        params = {"mode": "insert"}
+        params = {"mode": mode}
         body = {
             "fields": [to_camel(col) for col in observations.columns.tolist()],
             "data": observations.values.tolist()

hydroserverpy-1.5.1/src/hydroserverpy.egg-info/PKG-INFO

@@ -0,0 +1,66 @@
+Metadata-Version: 2.4
+Name: hydroserverpy
+Version: 1.5.1
+Summary: A Python client for managing HydroServer data
+Requires-Python: <4,>=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: requests>=2
+Requires-Dist: pydantic>=2.6
+Requires-Dist: pydantic[email]>=2.6
+Requires-Dist: pandas>=2.1
+Requires-Dist: numpy>=1.22.4
+Requires-Dist: pyyaml>=5
+Requires-Dist: simplejson>=3
+Requires-Dist: crontab>=1
+Requires-Dist: python-dateutil>=2.8.2
+Requires-Dist: croniter>=2.0.1
+Requires-Dist: jmespath>=1.0.1
+Provides-Extra: docs
+Requires-Dist: sphinx_autodoc_typehints; extra == "docs"
+Dynamic: license-file
+
+# HydroServer Python Client
+
+The hydroserverpy Python package provides an interface for managing HydroServer data and metadata, loading observations, and performing data quality control. This guide will go over how to install the package and connect to a HydroServer instance. Full hydroserverpy documentation and examples can be found [here](https://hydroserver2.github.io/hydroserver/how-to/hydroserverpy/hydroserverpy-examples.html).
+
+## Installation
+
+You can install the package via pip:
+
+```bash
+pip install hydroserverpy
+```
+
+## Connecting to HydroServer
+
+To connect to HydroServer, you need to initialize the client with the instance of HydroServer you're using and your user credentials if you want to access and modify your own data. If you don't provide authentication credentials you can read public data, but you will not be able to create or modify any data.
+
+### Example: Anonymous User
+
+```python
+from hydroserverpy import HydroServer
+
+# Initialize HydroServer connection.
+hs_api = HydroServer(
+    host='https://playground.hydroserver.org'
+)
+```
+
+### Example: Basic Authentication
+
+```python
+from hydroserverpy import HydroServer
+
+# Initialize HydroServer connection with credentials.
+hs_api = HydroServer(
+    host='https://playground.hydroserver.org',
+    email='user@example.com',
+    password='******'
+)
+```
+
+## Funding and Acknowledgements
+
+Funding for this project was provided by the National Oceanic & Atmospheric Administration (NOAA), awarded to the Cooperative Institute for Research to Operations in Hydrology (CIROH) through the NOAA Cooperative Agreement with The University of Alabama (NA22NWS4320003). Utah State University is a founding member of CIROH and receives funding under subaward from the University of Alabama. Additional funding and support have been provided by the State of Utah Division of Water Rights, the World Meteorological Organization, and the Utah Water Research laboratory at Utah State University.
+

{hydroserverpy-1.4.0b3 → hydroserverpy-1.5.1}/src/hydroserverpy.egg-info/requires.txt

@@ -1,8 +1,8 @@
 requests>=2
 pydantic>=2.6
 pydantic[email]>=2.6
-pandas>=2.2
-numpy>=2.0
+pandas>=2.1
+numpy>=1.22.4
 pyyaml>=5
 simplejson>=3
 crontab>=1

hydroserverpy-1.4.0b3/PKG-INFO

@@ -1,19 +0,0 @@
-Metadata-Version: 2.4
-Name: hydroserverpy
-Version: 1.4.0b3
-Requires-Python: <4,>=3.9
-License-File: LICENSE
-Requires-Dist: requests>=2
-Requires-Dist: pydantic>=2.6
-Requires-Dist: pydantic[email]>=2.6
-Requires-Dist: pandas>=2.2
-Requires-Dist: numpy>=2.0
-Requires-Dist: pyyaml>=5
-Requires-Dist: simplejson>=3
-Requires-Dist: crontab>=1
-Requires-Dist: python-dateutil>=2.8.2
-Requires-Dist: croniter>=2.0.1
-Requires-Dist: jmespath>=1.0.1
-Provides-Extra: docs
-Requires-Dist: sphinx_autodoc_typehints; extra == "docs"
-Dynamic: license-file

hydroserverpy-1.4.0b3/src/hydroserverpy.egg-info/PKG-INFO

@@ -1,19 +0,0 @@
-Metadata-Version: 2.4
-Name: hydroserverpy
-Version: 1.4.0b3
-Requires-Python: <4,>=3.9
-License-File: LICENSE
-Requires-Dist: requests>=2
-Requires-Dist: pydantic>=2.6
-Requires-Dist: pydantic[email]>=2.6
-Requires-Dist: pandas>=2.2
-Requires-Dist: numpy>=2.0
-Requires-Dist: pyyaml>=5
-Requires-Dist: simplejson>=3
-Requires-Dist: crontab>=1
-Requires-Dist: python-dateutil>=2.8.2
-Requires-Dist: croniter>=2.0.1
-Requires-Dist: jmespath>=1.0.1
-Provides-Extra: docs
-Requires-Dist: sphinx_autodoc_typehints; extra == "docs"
-Dynamic: license-file