Fix metadata collectors

data/src/config/config.py

@@ -3,7 +3,7 @@
 from contextlib import contextmanager
 from pathlib import Path
 
-FORCE_RELOAD = True
+FORCE_RELOAD = False
 """ During the data load, whether to query the various GIS API services for the data to load. If True, will query the
 API services and report on data differences.  If false will read the cached data."""
 

data/src/data_utils/access_process.py

@@ -3,11 +3,13 @@
 import geopandas as gpd
 import pandas as pd
 
+from src.metadata.metadata_utils import current_metadata, provide_metadata
 from src.validation.access_process import AccessProcessOutputValidator
 from src.validation.base import ValidationResult, validate_output
 
 
 @validate_output(AccessProcessOutputValidator)
+@provide_metadata(current_metadata=current_metadata)
 def access_process(
     dataset: gpd.GeoDataFrame,
 ) -> Tuple[gpd.GeoDataFrame, ValidationResult]:
@@ -30,7 +32,7 @@ def access_process(
         access_process (str): The access process for each property based on city ownership and market value.
         Will be NA for non-vacant properties.
 
-    Primary Feature Layer Columns Referenced:
+    Columns referenced:
         city_owner_agency, market_value, vacant
 
     Side Effects:

data/src/data_utils/city_owned_properties.py

@@ -3,10 +3,11 @@
 
 import geopandas as gpd
 
+from src.metadata.metadata_utils import current_metadata, provide_metadata
 from src.validation.base import ValidationResult, validate_output
 from src.validation.city_owned_properties import (
-    CityOwnedPropertiesOutputValidator,
     CityOwnedPropertiesInputValidator,
+    CityOwnedPropertiesOutputValidator,
 )
 
 from ..classes.loaders import EsriLoader
@@ -17,27 +18,28 @@
 
 
 @validate_output(CityOwnedPropertiesOutputValidator)
+@provide_metadata(current_metadata=current_metadata)
 def city_owned_properties(
     input_gdf: gpd.GeoDataFrame,
 ) -> Tuple[gpd.GeoDataFrame, ValidationResult]:
     """
-    Processes city-owned property data by joining it with the primary feature layer,
+    Processes city-owned property data by joining it with the input dataframe,
     renaming columns, and updating access information for properties based on ownership.
     All instances where the "city_owner_agency" is "PLB" are changed to "Land Bank (PHDC)".
 
     Args:
-        primary_featurelayer (FeatureLayer): The primary feature layer to which city-owned
+        input_gdf (GeoDataFrame): The GeoDataFrame to which city-owned
                                              property data will be joined.
 
     Returns:
-        FeatureLayer: The updated primary feature layer with processed city ownership
+        GeoDataFrame: The updated GeoDataFrame with processed city ownership
                       information.
 
     Columns added:
         city_owner_agency (str): The agency that owns the city property.
         side_yard_eligible (bool): Indicates if the property is eligible for the side yard program.
 
-    Primary Feature Layer Columns Referenced:
+    Columns referenced:
         opa_id, owner_1, owner2
 
     Tagline:

data/src/data_utils/community_gardens.py

@@ -3,6 +3,7 @@
 import geopandas as gpd
 
 from src.constants.city_limits import PHL_GEOMETRY
+from src.metadata.metadata_utils import current_metadata, provide_metadata
 from src.validation.base import ValidationResult, validate_output
 from src.validation.community_gardens import (
     CommunityGardensInputValidator,
@@ -15,19 +16,20 @@
 
 
 @validate_output(CommunityGardensOutputValidator)
+@provide_metadata(current_metadata=current_metadata)
 def community_gardens(
     input_gdf: gpd.GeoDataFrame,
 ) -> Tuple[gpd.GeoDataFrame, ValidationResult]:
     """
-    Updates the 'vacant' column in the primary feature layer to ensure community gardens
+    Updates the 'vacant' column in the input dataframe to ensure community gardens
     are marked as not vacant. This protects known community gardens from being categorized
     as vacant, preventing potential predatory development.
 
     Args:
-        primary_featurelayer (FeatureLayer): The feature layer containing property data.
+        input_gdf (GeoDataFrame): The input GeoDataFrame containing property data.
 
     Returns:
-        FeatureLayer: The input feature layer with the 'vacant' column updated to False
+        GeoDataFrame: The input GeoDataFrame with the 'vacant' column updated to False
         for parcels containing community gardens.
 
     Tagline:
@@ -36,7 +38,7 @@ def community_gardens(
     Columns updated:
         vacant: Updated to False for parcels containing community gardens.
 
-    Primary Feature Layer Columns Referenced:
+    Columns referenced:
         opa_id, vacant
 
     Source:

data/src/data_utils/conservatorship.py

@@ -5,6 +5,7 @@
 import pytz
 from dateutil.parser import parse
 
+from src.metadata.metadata_utils import current_metadata, provide_metadata
 from src.validation.base import ValidationResult, validate_output
 from src.validation.conservatorship import ConservatorshipOutputValidator
 
@@ -15,26 +16,27 @@
 
 
 @validate_output(ConservatorshipOutputValidator)
+@provide_metadata(current_metadata=current_metadata)
 def conservatorship(
     input_gdf: gpd.GeoDataFrame,
 ) -> Tuple[gpd.GeoDataFrame, ValidationResult]:
     """
-    Determines conservatorship eligibility for properties in a feature layer.
+    Determines conservatorship eligibility for properties in a GeoDataFrame.
 
     Args:
-        primary_featurelayer (FeatureLayer): A feature layer containing property data in a GeoDataFrame (`gdf`).
+        input_gdf (GeoDataFrame): A GeoDataFrame containing property data in a GeoDataFrame (`gdf`).
 
     Columns Added:
         conservatorship (bool): Indicates whether each property qualifies for conservatorship (True or False).
 
-    Primary Feature Layer Columns Referenced:
+    Columns referenced:
         city_owner_agency, sheriff_sale, market_value, all_violations_past_year, sale_date
 
     Tagline:
         Identify conservatorship-eligible properties
 
     Returns:
-        FeatureLayer: The input feature layer with an added "conservatorship" column indicating
+        GeoDataFrame: The input GeoDataFrame with an added "conservatorship" column indicating
         whether each property qualifies for conservatorship (True or False).
     """
     conservatorships = []

data/src/data_utils/contig_neighbors.py

@@ -6,24 +6,26 @@
 import numpy as np
 from libpysal.weights import Queen
 
+from src.metadata.metadata_utils import current_metadata, provide_metadata
 from src.validation.base import ValidationResult, validate_output
 from src.validation.contig_neighbors import ContigNeighborsOutputValidator
 
 from ..utilities import opa_join
 
 
 @validate_output(ContigNeighborsOutputValidator)
+@provide_metadata(current_metadata=current_metadata)
 def contig_neighbors(
     input_gdf: gpd.GeoDataFrame,
 ) -> Tuple[gpd.GeoDataFrame, ValidationResult]:
     """
-    Calculates the number of contiguous vacant neighbors for each property in a feature layer.
+    Calculates the number of contiguous vacant neighbors for each property in a GeoDataFrame.
 
     Args:
-        primary_featurelayer (FeatureLayer): A feature layer containing property data in a GeoDataFrame (`gdf`).
+        input_gdf: A input GeoDataFrame containing property data in a GeoDataFrame (`gdf`).
 
     Returns:
-        FeatureLayer: The input feature layer with an added "n_contiguous" column indicating
+        GeoDataFrame: The input GeoDataFrame with an added "n_contiguous" column indicating
         the number of contiguous vacant neighbors for each property.
 
     Tagline:
@@ -32,7 +34,7 @@ def contig_neighbors(
     Columns Added:
         n_contiguous (int): The number of contiguous vacant neighbors for each property.
 
-    Primary Feature Layer Columns Referenced:
+    Columns referenced:
         opa_id, vacant
     """
     print(f"[DEBUG] contig_neighbors: Starting with {len(input_gdf)} properties")
@@ -192,7 +194,7 @@ def contig_neighbors(
         f"[DEBUG] contig_neighbors: vacant_parcels opa_ids in input_gdf: {len(matching_opa_ids)} / {len(vacant_opa_ids)}"
     )
 
-    # Merge the results back to the primary feature layer
+    # Merge the results back to the input GeoDataFrame
     input_gdf = opa_join(input_gdf, vacant_parcels[["opa_id", "n_contiguous"]])
 
     # Debug: Check what's in input_gdf after join

data/src/data_utils/council_dists.py

@@ -3,6 +3,7 @@
 import geopandas as gpd
 import pandas as pd
 
+from src.metadata.metadata_utils import current_metadata, provide_metadata
 from src.validation.base import ValidationResult, validate_output
 from src.validation.council_dists import (
     CouncilDistrictsInputValidator,
@@ -17,18 +18,19 @@
 
 
 @validate_output(CouncilDistrictsOutputValidator)
+@provide_metadata(current_metadata=current_metadata)
 def council_dists(
     input_gdf: gpd.GeoDataFrame,
 ) -> Tuple[gpd.GeoDataFrame, ValidationResult]:
     """
-    Associates properties in the primary feature layer with council districts
+    Associates properties in the input GeoDataFrame with council districts
     using a spatial join.
 
     Args:
-        primary_featurelayer (FeatureLayer): The feature layer containing property data.
+        input_gdf (GeoDataFrame): The GeoDataFrame containing property data.
 
     Returns:
-        FeatureLayer: The input feature layer with properties spatially joined
+        GeoDataFrame: The input GeoDataFrame with properties spatially joined
         to council districts, ensuring no duplicate entries.
 
     Tagline:
@@ -37,7 +39,7 @@ def council_dists(
     Columns added:
         district (str): The council district associated with the property.
 
-    Primary Feature Layer Columns Referenced:
+    Columns referenced:
         opa_id, geometry
     """
 
@@ -74,7 +76,7 @@ def council_dists(
 
     merged_gdf = spatial_join(input_gdf, council_dists, predicate="within")
 
-    # Drop duplicates in the primary feature layer
+    # Drop duplicates in the input GeoDataFrame
     merged_gdf.drop_duplicates(inplace=True)
 
     # Debug: Check for duplicate OPA IDs and show what's causing them

data/src/data_utils/delinquencies.py

@@ -3,6 +3,7 @@
 import geopandas as gpd
 import pandas as pd
 
+from src.metadata.metadata_utils import current_metadata, provide_metadata
 from src.validation.base import ValidationResult, validate_output
 from src.validation.delinquencies import DelinquenciesOutputValidator
 
@@ -12,18 +13,19 @@
 
 
 @validate_output(DelinquenciesOutputValidator)
+@provide_metadata(current_metadata=current_metadata)
 def delinquencies(
     input_gdf: gpd.GeoDataFrame,
 ) -> Tuple[gpd.GeoDataFrame, ValidationResult]:
     """
-    Adds property tax delinquency information to the primary feature layer by
+    Adds property tax delinquency information to the input GeoDataFrame by
     joining with a tax delinquencies dataset.
 
     Args:
-        primary_featurelayer (FeatureLayer): The feature layer containing property data.
+        input_gdf (GeoDataFrame): The GeoDataFrame containing property data.
 
     Returns:
-        FeatureLayer: The input feature layer with added columns for tax delinquency
+        GeoDataFrame: The input GeoDataFrame with added columns for tax delinquency
         information, including total due, actionable status, payment agreements, and more.
 
     Tagline:
@@ -41,7 +43,7 @@ def delinquencies(
         sheriff_sale (bool): Indicates if the property is at risk of sheriff sale.
         total_assessment (float): Total property assessment.
 
-    Primary Feature Layer Columns Referenced:
+    Columns referenced:
         opa_id
     """
 

data/src/data_utils/dev_probability.py

@@ -6,6 +6,7 @@
 import requests
 
 from src.config.config import USE_CRS
+from src.metadata.metadata_utils import current_metadata, provide_metadata
 from src.validation.base import ValidationResult, validate_output
 from src.validation.dev_probability import DevProbabilityOutputValidator
 
@@ -15,19 +16,20 @@
 
 
 @validate_output(DevProbabilityOutputValidator)
+@provide_metadata(current_metadata=current_metadata)
 def dev_probability(
     input_gdf: gpd.GeoDataFrame,
 ) -> Tuple[gpd.GeoDataFrame, ValidationResult]:
     """
     Calculates development probability based on permit counts and assigns
     development ranks to census block groups. The results are joined to the
-    primary feature layer.
+    input GeoDataFrame.
 
     Args:
-        primary_featurelayer (FeatureLayer): The feature layer containing property data.
+        input_gdf (GeoDataFrame): The GeoDataFrame containing property data.
 
     Returns:
-        FeatureLayer: The input feature layer with added spatial join data for
+        GeoDataFrame: The input GeoDataFrame with added spatial join data for
         development probability and ranks.
 
     Tagline:
@@ -37,7 +39,7 @@ def dev_probability(
         permit_count (int): The number of permits issued in the census block group.
         dev_rank (str): The development rank of the census block group.
 
-    Primary Feature Layer Columns Referenced:
+    Columns referenced:
         opa_id, geometry
 
     Source:

data/src/data_utils/drug_crimes.py

@@ -3,24 +3,26 @@
 import geopandas as gpd
 
 from src.data_utils.kde import apply_kde_to_input
+from src.metadata.metadata_utils import current_metadata, provide_metadata
 from src.validation.base import ValidationResult, validate_output
 from src.validation.drug_crimes import DrugCrimesOutputValidator
 
 from ..constants.services import DRUGCRIME_SQL_QUERY
 
 
 @validate_output(DrugCrimesOutputValidator)
+@provide_metadata(current_metadata=current_metadata)
 def drug_crimes(
     input_gdf: gpd.GeoDataFrame,
 ) -> Tuple[gpd.GeoDataFrame, ValidationResult]:
     """
-    Applies kernel density estimation (KDE) analysis for drug crimes to the primary feature layer.
+    Applies kernel density estimation (KDE) analysis for drug crimes to the input GeoDataFrame.
 
     Args:
-        primary_featurelayer (FeatureLayer): The feature layer containing property data.
+        input_gdf (GeoDataFrame): The GeoDataFrame containing property data.
 
     Returns:
-        FeatureLayer: The input feature layer with KDE analysis results for drug crimes.
+        GeoDataFrame: The input GeoDataFrame with KDE analysis results for drug crimes.
 
     Tagline:
         Density analysis for drug crimes
@@ -31,7 +33,7 @@ def drug_crimes(
         drug_crimes_density_label (str): Categorized density level.
         drug_crimes_density_percentile (float): Percentile rank of density.
 
-    Primary Feature Layer Columns Referenced:
+    Columns referenced:
         geometry
 
     Source: