Lint and format

.pre-commit-config.yaml

@@ -18,6 +18,7 @@ repos:
       - id: mypy
         additional_dependencies:
           - "types-requests"
+          - "types-python-dateutil"
 
   # Notebooks
   # - repo: https://github.com/nbQA-dev/nbQA

award_pynder/sources/base.py

@@ -1,7 +1,6 @@
 """Data sources module for the award_pynder package."""
 
 from abc import ABC, abstractmethod
-from datetime import datetime
 from typing import TYPE_CHECKING, Literal
 
 from dateutil.parser import parse as dateutil_parse
@@ -13,9 +12,10 @@
 
 ###############################################################################
 
+
 class DatasetFields:
     institution = "institution"
-    pi= "pi"
+    pi = "pi"
     year = "year"
     start = "start"
     end = "end"
@@ -27,13 +27,16 @@ class DatasetFields:
     query = "query"
     source = "source"
 
+
 ALL_DATASET_FIELDS = [
-    field_value for field_name, field_value in vars(DatasetFields).items()
+    field_value
+    for field_name, field_value in vars(DatasetFields).items()
     if not field_name.startswith("_")
 ]
 
 ###############################################################################
 
+
 class DataSource(ABC):
     """Abstract base class for data sources."""
 
@@ -43,7 +46,7 @@ def _parse_datetime(dt: str | datetime) -> datetime:
             return dateutil_parse(dt)
 
         return dt
-    
+
     @staticmethod
     def _format_date_for_pynder_standard(
         dt: str,
@@ -53,7 +56,7 @@ def _format_date_for_pynder_standard(
             return str(dateutil_parse(dt).year)
 
         return dateutil_parse(dt).date().isoformat()
-    
+
     @staticmethod
     @abstractmethod
     def _format_dataframe(data: "pd.DataFrame") -> "pd.DataFrame":
@@ -64,4 +67,4 @@ def _format_dataframe(data: "pd.DataFrame") -> "pd.DataFrame":
     @abstractmethod
     def get_data() -> "pd.DataFrame":
         """Get data from the source."""
-        raise NotImplementedError()
+        raise NotImplementedError()

award_pynder/sources/nsf.py

@@ -1,15 +1,15 @@
 #!/usr/bin/env python
 
 from __future__ import annotations
-from datetime import datetime
 
-from .base import DataSource, DatasetFields, ALL_DATASET_FIELDS
+import logging
+from datetime import datetime
 
-import requests
 import pandas as pd
+import requests
 from tqdm import tqdm
 
-import logging
+from .base import ALL_DATASET_FIELDS, DatasetFields, DataSource
 
 ###############################################################################
 
@@ -46,6 +46,7 @@
 ###############################################################################
 # LUTs
 
+
 class NSFPrograms:
     Biological_Sciences = "BIO"
     Computer_and_Information_Science_and_Engineering = "CISE"
@@ -58,6 +59,7 @@ class NSFPrograms:
     Social_Behavioral_and_Economic_Sciences = "SBE"
     Technology_Innovation_and_Partnerships = "TIP"
 
+
 CFDA_NUMBER_TO_NSF_PROGRAM_NAME_LUT = {
     "47.041": NSFPrograms.Engineering,
     "47.049": NSFPrograms.Mathematical_and_Physical_Sciences,
@@ -77,14 +79,15 @@ class NSFPrograms:
 
 ###############################################################################
 
+
 class NSF(DataSource):
-    """Data source for the National Science Foundation."""    
+    """Data source for the National Science Foundation."""
 
     @staticmethod
     def _format_datetime(dt: str | datetime) -> str:
         """Parse datetime string or datetime and return NSF support datetime string."""
         return DataSource._parse_datetime(dt).strftime("%m/%d/%Y")
-    
+
     @staticmethod
     def _format_query(
         query: str | None,
@@ -118,7 +121,7 @@ def _format_query(
             api_str += f"&keyword={query}"
 
         return api_str
-    
+
     @staticmethod
     def _format_dataframe(
         data: pd.DataFrame,
@@ -161,7 +164,7 @@ def _format_dataframe(
 
         # Create new dataframe with only the columns we want
         return data[ALL_DATASET_FIELDS]
-        
+
     @staticmethod
     def _get_chunk(
         query: str | None = None,
@@ -206,7 +209,7 @@ def _get_chunk(
                 f"Error while fetching NSF data: {e}; "
                 f"'raise_on_error' is False, ignoring..."
             )
-        
+
         # Default return but make this strict
         return None
 
@@ -215,11 +218,10 @@ def get_data(
         query: str | None = None,
         from_datetime: str | datetime | None = None,
         to_datetime: str | datetime | None = None,
-        cfda_number: str | int | None = None,
+        cfda_number: str | None = None,
         project_outcomes_required: bool = False,
         raise_on_error: bool = True,
         tqdm_kwargs: dict | None = None,
-        **kwargs,
     ) -> pd.DataFrame:
         """Get data from the National Science Foundation."""
         # Continuously get chunks of data
@@ -252,4 +254,4 @@ def get_data(
             pd.concat(chunks, ignore_index=True)
             .drop_duplicates(subset="id")
             .reset_index(drop=True)
-        )
+        )

award_pynder/tests/__init__.py

@@ -1 +1 @@
-"""Tests package for award_pynder."""
+"""Tests package for award_pynder."""

award_pynder/tests/sources/__init__.py

@@ -1 +1 @@
-"""Sources sub-moduble for the tests package for award_pynder."""
+"""Sources sub-moduble for the tests package for award_pynder."""

award_pynder/tests/sources/test_nsf.py

@@ -1,11 +1,12 @@
 #!/usr/bin/env python
 
-from ..utils import assert_dataset_basics
+from award_pynder.sources.nsf import NSF, NSF_PROGRAM_TO_CFDA_NUMBER_LUT, NSFPrograms
 
-from award_pynder.sources.nsf import NSF, NSFPrograms, NSF_PROGRAM_TO_CFDA_NUMBER_LUT
+from ..utils import assert_dataset_basics
 
 ###############################################################################
 
+
 def test_nsf() -> None:
     # Get data
     data = NSF.get_data(
@@ -16,4 +17,4 @@ def test_nsf() -> None:
     )
 
     # Run tests
-    assert_dataset_basics(data)
+    assert_dataset_basics(data)

award_pynder/tests/utils.py

@@ -1,6 +1,7 @@
 #!/usr/bin/env python
 
 from __future__ import annotations
+
 from typing import TYPE_CHECKING
 
 from award_pynder.sources.base import ALL_DATASET_FIELDS
@@ -10,6 +11,7 @@
 
 ###############################################################################
 
+
 def assert_dataset_basics(df: pd.DataFrame) -> None:
     # Assert that not only are all required fields present,
     # but that no extraneous fields are present as well
@@ -22,4 +24,4 @@ def assert_dataset_basics(df: pd.DataFrame) -> None:
     assert df.id.nunique() == len(df)
 
     # Assert that there is at least some data
-    assert len(df) > 0
+    assert len(df) > 0