Rehab or remove some of the older notebooks; remove sys.path hack. (#231

)
censusdis · Jan 26, 2024 · 1c2b0b0 · 1c2b0b0
1 parent 6572e52
commit 1c2b0b0
Show file tree

Hide file tree

Showing 29 changed files with 690 additions and 1,408 deletions.
diff --git a/censusdis/geography.py b/censusdis/geography.py
@@ -206,9 +206,9 @@ def _fetch_path_specs(dataset: str, year: int) -> Dict[str, "PathSpec"]:
             f"Census API request to {request.url} failed with status {request.status_code}. {request.text}"
         )
 
-    _PATH_SPECS_BY_DATASET_YEAR: DefaultDict[
-        str, Dict[int, Dict[str, "PathSpec"]]
-    ] = defaultdict(dict)
+    _PATH_SPECS_BY_DATASET_YEAR: DefaultDict[str, Dict[int, Dict[str, "PathSpec"]]] = (
+        defaultdict(dict)
+    )
 
     _PATH_SPEC_SNAKE_MAP: DefaultDict[str, Dict[int, Dict[str, str]]] = defaultdict(
         dict
@@ -221,9 +221,9 @@ def _fetch_path_specs(dataset: str, year: int) -> Dict[str, "PathSpec"]:
     def get_path_specs(dataset: str, vintage: int) -> Dict[str, "PathSpec"]:
         """Fet all the path specifications for the given dataset and vintage."""
         if vintage not in PathSpec._PATH_SPECS_BY_DATASET_YEAR[dataset]:
-            PathSpec._PATH_SPECS_BY_DATASET_YEAR[dataset][
-                vintage
-            ] = PathSpec._fetch_path_specs(dataset, vintage)
+            PathSpec._PATH_SPECS_BY_DATASET_YEAR[dataset][vintage] = (
+                PathSpec._fetch_path_specs(dataset, vintage)
+            )
             PathSpec._PATH_SPEC_SNAKE_MAP[dataset][vintage] = {
                 component.replace(" ", "_")
                 .replace("/", "_")

diff --git a/censusdis/impl/geometry.py b/censusdis/impl/geometry.py
@@ -119,11 +119,11 @@ def drop_slivers_from_geo_series(
         The series with all slivers removed.
     """
     return gs_geo.map(
-        lambda s: drop_slivers_multi_polygon(s, threshold)
-        if isinstance(s, MultiPolygon)
-        else drop_polygon_if_sliver(s, threshold)
-        if isinstance(s, Polygon)
-        else s
+        lambda s: (
+            drop_slivers_multi_polygon(s, threshold)
+            if isinstance(s, MultiPolygon)
+            else drop_polygon_if_sliver(s, threshold) if isinstance(s, Polygon) else s
+        )
     )
 
 

diff --git a/censusdis/impl/us_census_shapefiles.py b/censusdis/impl/us_census_shapefiles.py
@@ -149,9 +149,11 @@
         None,
         "vtd",
         ["STATE", "COUNTY", "VOTING_DISTRICT"],
-        ["STATEFP20", "COUNTYFP20", "VTDST20"]
-        if year >= 2020
-        else ["STATEFP10", "COUNTYFP10", "VTDST10"],
+        (
+            ["STATEFP20", "COUNTYFP20", "VTDST20"]
+            if year >= 2020
+            else ["STATEFP10", "COUNTYFP10", "VTDST10"]
+        ),
     ),
     # This one could be a little dangerous if subminor civil
     # divisions exist in states and are not mapped as subbarios.

diff --git a/censusdis/impl/varcache.py b/censusdis/impl/varcache.py
@@ -31,12 +31,12 @@ def __init__(self, *, variable_source: Optional[VariableSource] = None):
             variable_source = CensusApiVariableSource()
 
         self._variable_source = variable_source
-        self._variable_cache: DefaultDict[
-            str, DefaultDict[int, Dict[str, Any]]
-        ] = defaultdict(lambda: defaultdict(dict))
-        self._group_cache: DefaultDict[
-            str, DefaultDict[int, Dict[str, Any]]
-        ] = defaultdict(lambda: defaultdict(dict))
+        self._variable_cache: DefaultDict[str, DefaultDict[int, Dict[str, Any]]] = (
+            defaultdict(lambda: defaultdict(dict))
+        )
+        self._group_cache: DefaultDict[str, DefaultDict[int, Dict[str, Any]]] = (
+            defaultdict(lambda: defaultdict(dict))
+        )
 
         self._all_data_sets_cache: Optional[pd.DataFrame] = None
         self._data_sets_by_year_cache: Dict[int, pd.DataFrame] = {}
@@ -385,9 +385,11 @@ def _datasets_from_source_dict(datasets) -> pd.DataFrame:
                     "DATASET": "/".join(dataset["c_dataset"]),
                     "TITLE": dataset.get("title", None),
                     "DESCRIPTION": dataset.get("description", None),
-                    "API BASE URL": dataset["distribution"][0].get("accessURL", None)
-                    if dataset.get("distribution")
-                    else None,
+                    "API BASE URL": (
+                        dataset["distribution"][0].get("accessURL", None)
+                        if dataset.get("distribution")
+                        else None
+                    ),
                 }
                 for dataset in datasets
             ]

diff --git a/censusdis/maps.py b/censusdis/maps.py
@@ -1145,12 +1145,12 @@ def sjoin_mostly_contains(
 
     # Keep the original geos around in EPSG 3857 so
     # we can check intersection areas.
-    gdf_large_geos[
-        f"_original_large_geos_{area_epsg}"
-    ] = gdf_large_geos.geometry.to_crs(epsg=area_epsg)
-    gdf_small_geos[
-        f"_original_small_geos_{area_epsg}"
-    ] = gdf_small_geos.geometry.to_crs(epsg=area_epsg)
+    gdf_large_geos[f"_original_large_geos_{area_epsg}"] = (
+        gdf_large_geos.geometry.to_crs(epsg=area_epsg)
+    )
+    gdf_small_geos[f"_original_small_geos_{area_epsg}"] = (
+        gdf_small_geos.geometry.to_crs(epsg=area_epsg)
+    )
 
     # Do an intersection join.
     gdf_intersection = gdf_small_geos.sjoin(

diff --git a/docs/conf.py b/docs/conf.py
@@ -1,4 +1,5 @@
 """Configure sphinx."""
+
 # Configuration file for the Sphinx documentation builder.
 #
 # For the full list of built-in configuration values, see the documentation:

diff --git a/notebooks/ACS Comparison Profile.ipynb b/notebooks/ACS Comparison Profile.ipynb
diff --git a/notebooks/ACS Data Profile.ipynb b/notebooks/ACS Data Profile.ipynb
diff --git a/notebooks/ACS Subject Table.ipynb b/notebooks/ACS Subject Table.ipynb
diff --git a/notebooks/Block Groups in CBSAs.ipynb b/notebooks/Block Groups in CBSAs.ipynb
@@ -18,24 +18,6 @@
     "some additional [GeoPandas](https://geopandas.org) spatial operations."
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "66fded3e-f576-4848-a8ab-7eff3f10f6a6",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "# So we can run from within the censusdis project and find the packages we need.\n",
-    "import os\n",
-    "import sys\n",
-    "\n",
-    "sys.path.append(\n",
-    "    os.path.join(os.path.abspath(os.path.join(os.path.curdir, os.path.pardir)))\n",
-    ")"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "0be695ac-3484-474d-bc85-8aa3d0ea4be1",
@@ -48,7 +30,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "id": "9a0fdca1-d022-4224-878e-a2da5ecd969a",
    "metadata": {},
    "outputs": [],
@@ -64,7 +46,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "id": "1673a2a4-cc6e-4e9c-9721-b599d97e9e19",
    "metadata": {},
    "outputs": [],
@@ -75,7 +57,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "id": "fe2f4bcd-beaf-4823-bc4d-ad27702a9acd",
    "metadata": {},
    "outputs": [],
@@ -87,7 +69,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "id": "e38abd6d-d69b-4a8d-b09a-f1f7755ea123",
    "metadata": {},
    "outputs": [],
@@ -112,7 +94,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 5,
    "id": "405395e5-dbf6-4a24-8c68-44ef4a040f84",
    "metadata": {},
    "outputs": [],
@@ -138,7 +120,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 6,
    "id": "c2a9e355-89cd-4bf5-8346-fbd913ac3f7c",
    "metadata": {},
    "outputs": [],
@@ -168,7 +150,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 7,
    "id": "709d396e-a2aa-4aad-b334-541fa8d76b8a",
    "metadata": {},
    "outputs": [],
@@ -199,7 +181,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 8,
    "id": "d2182ec6-e1e8-4d2b-a620-bdaa8ad1389a",
    "metadata": {},
    "outputs": [],
@@ -215,7 +197,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 9,
    "id": "587aec27-e0df-4a3b-aa45-0da6c598dc0a",
    "metadata": {},
    "outputs": [