feat(FilterView): switched standardized_address for street_address. switched some data types in schema that were off.

Author: gabecano4308

data/src/data_utils/city_owned_properties.py

@@ -54,9 +54,6 @@ def city_owned_properties(
     )
 
     city_owned_properties, input_validation = loader.load_or_fetch()
-    print("City-Owned Properties Input:")
-    print(city_owned_properties.columns)
-    print(city_owned_properties.head())
 
     merged_gdf = opa_join(input_gdf, city_owned_properties)
 
@@ -159,8 +156,4 @@ def city_owned_properties(
         "Land Bank (PHDC)"
     )
 
-    print("City-Owned Properties Output:")
-    print(merged_gdf.columns)
-    print(merged_gdf.head())
-
     return merged_gdf, input_validation

data/src/data_utils/council_dists.py

@@ -49,9 +49,6 @@ def council_dists(
     )
 
     council_dists, input_validation = loader.load_or_fetch()
-    print("Council Districts Input:")
-    print(council_dists.columns)
-    print(council_dists.head())
 
     # Check that the required columns exist in the DataFrame
     required_columns = ["district", "geometry"]
@@ -72,7 +69,4 @@ def council_dists(
     # Drop duplicates in the primary feature layer
     merged_gdf.drop_duplicates(inplace=True)
 
-    print("Council Districts Output:")
-    print(merged_gdf.columns)
-    print(merged_gdf.head())
     return merged_gdf, input_validation

data/src/validation/base.py

@@ -197,7 +197,7 @@ def validate(self, gdf: gpd.GeoDataFrame) -> ValidationResult:
             try:
                 self.schema.validate(gdf, lazy=True)
             except pa.errors.SchemaErrors as err:
-                self.errors.append(err.failure_case)
+                self.errors.append(err.failure_cases)
         schema_time = time.time() - schema_start
 
         # Custom validation

data/src/validation/city_owned_properties.py

@@ -1,5 +1,6 @@
 import geopandas as gpd
 import pandera.pandas as pa
+import pandas as pd
 from .base import BaseValidator
 
 # Expecting ~7,796 records returned (within ±20% tolerance).
@@ -10,8 +11,8 @@
 
 CityOwnedPropertiesInputSchema = pa.DataFrameSchema(
     columns={
-        "opa_id": pa.Column(int, checks=pa.Check(lambda s: s.dropna() != "")),
-        "agency": pa.Column(str, nullable=True),
+        "opa_id": pa.Column(pa.Int, checks=pa.Check(lambda s: s.dropna() != "")),
+        "agency": pa.Column(pa.String, nullable=True),
         "sideyardeligible": pa.Column(
             pa.Category, nullable=True, checks=pa.Check.isin(["Yes", "No"])
         ),
@@ -23,23 +24,23 @@
 
 CityOwnedPropertiesOutputSchema = pa.DataFrameSchema(
     columns={
-        "opa_id": pa.Column(int, checks=pa.Check(lambda s: s.dropna() != "")),
-        "market_value": pa.Column(int, nullable=True),
-        "sale_date": pa.Column(pa.DateTime, nullable=True),
-        "sale_price": pa.Column(int, nullable=True),
-        "owner_1": pa.Column(str, nullable=True),
-        "owner_2": pa.Column(str, nullable=True),
-        "building_code_description": pa.Column(str, nullable=True),
-        "zip_code": pa.Column(str, nullable=True),
-        "zoning": pa.Column(str, nullable=True),
-        "parcel_type": pa.Column(str, nullable=True),
-        "standardized_address": pa.Column(str, nullable=True),
+        "opa_id": pa.Column(pa.Int, checks=pa.Check(lambda s: s.dropna() != "")),
+        "market_value": pa.Column(pa.Int, nullable=True),
+        "sale_date": pa.Column(pd.DatetimeTZDtype(tz="UTC"), nullable=True),
+        "sale_price": pa.Column(pa.Float, nullable=True),
+        "owner_1": pa.Column(pa.String, nullable=True),
+        "owner_2": pa.Column(pa.String, nullable=True),
+        "building_code_description": pa.Column(pa.String, nullable=True),
+        "zip_code": pa.Column(pa.String, nullable=True),
+        "zoning": pa.Column(pa.String, nullable=True),
+        "parcel_type": pa.Column(pa.String, nullable=True),
+        "standardized_address": pa.Column(pa.String, nullable=True),
         "vacant": pa.Column(pa.Bool, nullable=True),
-        "district": pa.Column(str, nullable=True),
-        "neighborhood": pa.Column(str, nullable=True),
-        "rco_info": pa.Column(str, nullable=True),
-        "rco_names": pa.Column(str, nullable=True),
-        "city_owner_agency": pa.Column(str, nullable=True),
+        "district": pa.Column(pa.String, nullable=True),
+        "neighborhood": pa.Column(pa.String, nullable=True),
+        "rco_info": pa.Column(pa.String, nullable=True),
+        "rco_names": pa.Column(pa.String, nullable=True),
+        "city_owner_agency": pa.Column(pa.String, nullable=True),
         "side_yard_eligible": pa.Column(
             pa.Category, nullable=True, checks=pa.Check.isin(["Yes", "No"])
         ),

data/src/validation/council_dists.py

@@ -1,5 +1,6 @@
 import geopandas as gpd
 import pandera.pandas as pa
+import pandas as pd
 from .base import BaseValidator
 
 CouncilDistrictsInputSchema = pa.DataFrameSchema(
@@ -21,16 +22,16 @@
 CouncilDistrictsOutputSchema = pa.DataFrameSchema(
     columns={
         "opa_id": pa.Column(pa.String),
+        "street_address": pa.Column(pa.String, nullable=True),
         "market_value": pa.Column(pa.Int, nullable=True),
-        "sale_date": pa.Column(pa.DateTime, nullable=True),
-        "sale_price": pa.Column(pa.Int, nullable=True),
+        "sale_date": pa.Column(pd.DatetimeTZDtype(tz="UTC"), nullable=True),
+        "sale_price": pa.Column(pa.Float, nullable=True),
         "owner_1": pa.Column(pa.String, nullable=True),
         "owner_2": pa.Column(pa.String, nullable=True),
         "building_code_description": pa.Column(pa.String, nullable=True),
         "zip_code": pa.Column(pa.String, nullable=True),
         "zoning": pa.Column(pa.String, nullable=True),
         "parcel_type": pa.Column(pa.String, nullable=True),
-        "standardized_address": pa.Column(pa.String, nullable=True),
         "vacant": pa.Column(pa.Bool, nullable=True),
         "district": pa.Column(
             str, nullable=True, checks=pa.Check.isin([str(i) for i in range(1, 11)])