Rename vceregen to vcerare

docs/conf.py

@@ -162,7 +162,7 @@ def data_sources_metadata_to_rst(app):
         "epacems",
         "phmsagas",
         "gridpathratoolkit",
-        "vceregen",
+        "vcerare",
     ]
     package = PUDL_PACKAGE
     extra_etl_groups = {"eia860": ["entity_eia"], "ferc1": ["glue"]}

docs/data_sources/index.rst

@@ -18,7 +18,7 @@ The following data sources serve as the foundation for our data pipeline.
    ferc714
    phmsagas
    gridpathratoolkit
-   vceregen
+   vcerare
    other_data
 
 .. toctree::

docs/templates/vceregen_child.rst.jinja → docs/templates/vcerare_child.rst.jinja

@@ -1,8 +1,9 @@
 {% extends "data_source_parent.rst.jinja" %}
 {% block background %}
-The data in this table were produced by Vibrant Clean Energy based on outputs from the
-NOA HRRR model and are licensed to the public under the Creative Commons Attribution
-4.0 International license (CC-BY-4.0).
+The data in the Resource Adequacy Renewble Energy (RARE) Power Dataset was produced by
+Vibrant Clean Energy based on outputs from the NOA HRRR model and are licensed
+to the public under the Creative Commons Attribution 4.0 International license
+(CC-BY-4.0).
 
 See the Zenodo archive README for more detailed information.
 
@@ -44,10 +45,12 @@ the cities but kept the lakes in the data. Note that lakes bordering multiple st
 will appear more than once in the data. VCE used a nearest neighbor technique to assign
 the state waters to the counties (this pertains to coastal areas as well).
 
-Abnormally large capacity factors
----------------------------------
-There are also a couple of capacity factor values for the solar pv data that exceed
-the maximum value of 1 for capacity factor. This is due to cooler panel temperatures.
+Capacity factors > 1
+--------------------
+There are a couple of capacity factor values for the solar pv data that exceed
+the maximum value of 1 for capacity factor. This is due to power production performance
+being correlated with panel temperatures. During cold sunny periods, some solar capacity
+factor values are greater than 1 (but less that 1.1).
 
 8760-hour years
 ---------------

src/pudl/etl/__init__.py

@@ -82,7 +82,7 @@
     "core_ferc714": [pudl.transform.ferc714],
     "core_gridpathratoolkit": [pudl.transform.gridpathratoolkit],
     "core_nrelatb": [pudl.transform.nrelatb],
-    "core_vceregen": [pudl.transform.vceregen],
+    "core_vcerare": [pudl.transform.vcerare],
 }
 
 out_module_groups = {

src/pudl/metadata/classes.py

@@ -1284,7 +1284,7 @@ class Resource(PudlMeta):
             "ppe",
             "pudl",
             "nrelatb",
-            "vceregen",
+            "vcerare",
         ]
         | None
     ) = None
@@ -1312,7 +1312,7 @@ class Resource(PudlMeta):
             "static_pudl",
             "service_territories",
             "nrelatb",
-            "vceregen",
+            "vcerare",
         ]
         | None
     ) = None

src/pudl/metadata/resources/vceregen.py → src/pudl/metadata/resources/vcerare.py

@@ -3,7 +3,7 @@
 from typing import Any
 
 RESOURCE_METADATA: dict[str, dict[str, Any]] = {
-    "out_vceregen__hourly_available_capacity_factor": {
+    "out_vcerare__hourly_available_capacity_factor": {
         "description": (
             "The data in this table were produced by Vibrant Clean Energy, and are "
             "licensed to the public under the Creative Commons Attribution 4.0 International "
@@ -54,9 +54,9 @@
             ],
             "primary_key": ["datetime_utc", "state", "county_or_lake_name"],
         },
-        "sources": ["vceregen"],
-        "field_namespace": "vceregen",
-        "etl_group": "vceregen",
+        "sources": ["vcerare"],
+        "field_namespace": "vcerare",
+        "etl_group": "vcerare",
         "create_database_schema": False,
     },
 }

src/pudl/transform/__init__.py

@@ -77,5 +77,5 @@
     gridpathratoolkit,
     nrelatb,
     params,
-    vceregen,
+    vcerare,
 )

src/pudl/transform/vceregen.py → src/pudl/transform/vcerare.py

@@ -235,11 +235,11 @@ def _combine_city_county_records(df: pd.DataFrame) -> pd.DataFrame:
     compute_kind="pandas",
     op_tags={"memory-use": "high"},
 )
-def out_vceregen__hourly_available_capacity_factor(
+def out_vcerare__hourly_available_capacity_factor(
     raw_vcegen__lat_lon_fips: pd.DataFrame,
-    raw_vceregen__fixed_solar_pv_lat_upv: pd.DataFrame,
-    raw_vceregen__offshore_wind_power_140m: pd.DataFrame,
-    raw_vceregen__onshore_wind_power_100m: pd.DataFrame,
+    raw_vcerare__fixed_solar_pv_lat_upv: pd.DataFrame,
+    raw_vcerare__offshore_wind_power_140m: pd.DataFrame,
+    raw_vcerare__onshore_wind_power_100m: pd.DataFrame,
 ) -> pd.DataFrame:
     """Transform raw Vibrant Clean Energy renewable generation profiles.
 
@@ -253,9 +253,9 @@ def out_vceregen__hourly_available_capacity_factor(
     # than doing it to a concatinated table but less memory intensive because
     # it doesn't need to process the ginormous table all at once.
     raw_dict = {
-        "solar_pv": raw_vceregen__fixed_solar_pv_lat_upv,
-        "offshore_wind": raw_vceregen__offshore_wind_power_140m,
-        "onshore_wind": raw_vceregen__onshore_wind_power_100m,
+        "solar_pv": raw_vcerare__fixed_solar_pv_lat_upv,
+        "offshore_wind": raw_vcerare__offshore_wind_power_140m,
+        "onshore_wind": raw_vcerare__onshore_wind_power_100m,
     }
     clean_dict = {
         df_name: _check_for_valid_counties(df, fips_df, df_name)
@@ -273,7 +273,7 @@ def out_vceregen__hourly_available_capacity_factor(
 
 
 @asset_check(
-    asset=out_vceregen__hourly_available_capacity_factor,
+    asset=out_vcerare__hourly_available_capacity_factor,
     blocking=True,
     description="Check that output table is as expected.",
 )