Merge pull request #678 from CodeForPhilly/lebovits/issu31-add-neighb…

…oring-properties-count

Lebovits/issu31 add neighboring properties count

data/src/Pipfile

@@ -26,6 +26,8 @@ data-diff = {extras = ["postgresql"], version = "*"}
 future = "*"
 slack-sdk = "*"
 pytest = "*"
+networkx = "*"
+libpysal = "*"
 jenkspy = "*"
 
 [dev-packages]

data/src/classes/featurelayer.py

@@ -5,35 +5,34 @@
 import geopandas as gpd
 import pandas as pd
 import requests
-from config.config import FORCE_RELOAD, USE_CRS
 from config.psql import conn
 from esridump.dumper import EsriDumper
 from google.cloud import storage
 from google.cloud.storage.bucket import Bucket
 from shapely import Point, wkb
 
+from config.config import FORCE_RELOAD, USE_CRS
+
 
-# Configure Google
 def google_cloud_bucket() -> Bucket:
     """Build the google cloud bucket with name configured in your environ or default of cleanandgreenphl
 
     Returns:
         Bucket: the gcp bucket
     """
-    credentials_path = os.path.expanduser("/app/service-account-key.json")
+    credentials_path = os.path.expanduser("/app/account-service-key.json")
+
+    if not os.path.exists(credentials_path):
+        raise FileNotFoundError(f"Credentials file not found at {credentials_path}")
+
     os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = credentials_path
-    bucket_name = (
-        os.environ["GOOGLE_CLOUD_BUCKET_NAME"]
-        if os.environ["GOOGLE_CLOUD_BUCKET_NAME"] is not None
-        else "cleanandgreenphl"
-    )
+    bucket_name = os.getenv("GOOGLE_CLOUD_BUCKET_NAME", "cleanandgreenphl")
+
     storage_client = storage.Client(project="clean-and-green-philly")
     return storage_client.bucket(bucket_name)
 
-
 bucket = google_cloud_bucket()
 
-
 class FeatureLayer:
     """
     FeatureLayer is a class to represent a GIS dataset. It can be initialized with a URL to an Esri Feature Service, a SQL query to Carto, or a GeoDataFrame.

data/src/data_utils/contig_neighbors.py

@@ -0,0 +1,25 @@
+import warnings
+
+import geopandas as gpd
+import networkx as nx
+from libpysal.weights import Queen
+
+
+def contig_neighbors(primary_featurelayer):
+
+    parcels = primary_featurelayer.gdf
+
+    with warnings.catch_warnings():
+        warnings.filterwarnings("ignore", category=FutureWarning)
+        warnings.filterwarnings("ignore", category=UserWarning, message="The weights matrix is not fully connected")
+
+        w = Queen.from_dataframe(parcels)
+
+    g = w.to_networkx()
+
+    # Calculate the number of contiguous neighbors for each feature in parcels
+    n_contiguous = [len(nx.node_connected_component(g, i)) for i in range(len(parcels))]
+
+    primary_featurelayer.gdf['n_contiguous'] = n_contiguous
+
+    return primary_featurelayer

data/src/script.py

@@ -7,6 +7,7 @@
 from data_utils.city_owned_properties import city_owned_properties
 from data_utils.community_gardens import community_gardens
 from data_utils.conservatorship import conservatorship
+from data_utils.contig_neighbors import contig_neighbors
 from data_utils.deliquencies import deliquencies
 from data_utils.dev_probability import dev_probability
 from data_utils.drug_crimes import drug_crimes
@@ -52,6 +53,7 @@
     community_gardens,
     park_priority,
     ppr_properties,
+    contig_neighbors,
     dev_probability,
 ]