Standardize country codes iso 3166

.example.env

@@ -1,8 +1,8 @@
 # Database Configuration
 DB_URL=postgresql://postgres:postgres@localhost:5432/neso_solar
 
-# country code for fetching data. Other options are "nl", "de"
-COUNTRY="gb" 
+# country code for fetching data. Other options are "nld", "deu", "bel", "ind_rj"
+COUNTRY="gbr_gb" 
 
 # ways to store the data. Other options are "csv", "site-db"
 SAVE_METHOD="db"

README.md

@@ -100,7 +100,7 @@ The package provides three main functionalities:
 ### Environment Variables: (Can be found in the .example.env / .env file)
 
 - `DB_URL=postgresql://postgres:postgres@localhost:5432/neso_solar` : Database Configuration
-- `COUNTRY="gb"` : Country code for fetching data. Currently, other options are ["be", "ind_rajasthan", "nl"] 
+- `COUNTRY="gbr_gb"` : Country code for fetching data. Currently, other options are ["bel", "deu", "ind_rj", "nld"] 
 - `SAVE_METHOD`: Ways to store the data. Options are ["db", "csv", "site-db"].  
   `site-db` is supported for NL, DE, and India (RUVNL).
 - `CSV_DIR=None` : Directory to save CSV files if `SAVE_METHOD="csv"`.

solar_consumer/app.py

@@ -34,7 +34,7 @@ async def app(
     db_url: str,
     save_method: str,
     csv_dir: str = None,
-    country: str = "gb",
+    country: str = "gbr_gb",
     historic_or_forecast: str = "generation",
 ):
     """
@@ -44,22 +44,26 @@ async def app(
         db_url (str): Database connection URL from an environment variable.
         save_method (str): Method to save the forecast data. Options are "db" or "csv".
         csv_dir (str, optional): Directory to save CSV files if save_method is "csv".
-        country (str): Country code for fetching data. Default is "gb".
+        country (str): Country code for fetching data. Default is "gbr_gb".
         historic_or_forecast: (str): Type of data to fetch. Default is "generation".
     """
     logger.info(f"Starting the NESO Solar Forecast pipeline (version: {__version__}).")
 
     # Use the `Neso` class for hardcoded configuration]
-    if country == "gb":
+    if country == "gbr_gb":
         model_tag = "neso-solar-forecast"
-    elif country == "nl":
+    elif country == "nld":
         model_tag = "ned-nl-national"
-    elif country == "de":
+    elif country == "deu":
         model_tag = "entsoe-de"
-    elif country == "be":
+    elif country == "bel":
         model_tag = "elia-be-forecast"
-
-
+    else:
+        supported_countries = ["gbr_gb", "nld", "deu", "bel"]
+        raise ValueError(
+            f"Unsupported country code: {country!r}. "
+            f"Supported country codes are: {', '.join(supported_countries)}."
+        )
     # Step 1: Fetch forecast data (returns as pd.Dataframe)
     logger.info(f"Fetching {historic_or_forecast} data for {country}.")
     data = fetch_data(country=country, historic_or_forecast=historic_or_forecast)
@@ -146,7 +150,7 @@ async def app(
 if __name__ == "__main__":
     # Step 1: Fetch the database URL from the environment variable
     db_url = os.getenv("DB_URL")  # Change from "DATABASE_URL" to "DB_URL"
-    country = os.getenv("COUNTRY", "gb")
+    country = os.getenv("COUNTRY", "gbr_gb")
     save_method = os.getenv("SAVE_METHOD", "db").lower()  # Default to "db"
     csv_dir = os.getenv("CSV_DIR")
     historic_or_forecast = os.getenv("HISTORIC_OR_FORECAST", "generation").lower()

solar_consumer/data/locations.csv

@@ -1,18 +1,18 @@
 name,latitude,longitude,region_id,region,country_code
-nl_national,52.13,5.29,0,,nl
-nl_groningen,53.22,6.74,1,,nl
-nl_region_2_friesland,53.11,5.85,2,,nl
-nl_region_3_drenthe,52.86,6.62,3,,nl
-nl_region_4_overijssel,52.45,6.45,4,,nl
-nl_region_5_flevoland,52.53,5.60,5,,nl
-nl_region_6_gelderland,52.06,5.95,6,,nl
-nl_region_7_utrecht,52.08,5.17,7,,nl
-nl_region_8_noord_holland,52.58,4.87,8,,nl
-nl_region_9_zuid_holland,51.94,4.47,9,,nl
-nl_region_10_zeeland,51.45,3.84,10,,nl
-nl_region_11_noord_brabant,51.56,5.20,11,,nl
-nl_region_12_limburg,51.21,5.94,12,,nl
-be_belgium,50.85,4.35,,Belgium,be
-be_flanders,51.00,4.46,,Flanders,be
-be_wallonia,50.50,4.70,,Wallonia,be
-be_brussels,50.85,4.35,,Brussels,be
+nl_national,52.13,5.29,0,,nld
+nl_groningen,53.22,6.74,1,,nld
+nl_region_2_friesland,53.11,5.85,2,,nld
+nl_region_3_drenthe,52.86,6.62,3,,nld
+nl_region_4_overijssel,52.45,6.45,4,,nld
+nl_region_5_flevoland,52.53,5.60,5,,nld
+nl_region_6_gelderland,52.06,5.95,6,,nld
+nl_region_7_utrecht,52.08,5.17,7,,nld
+nl_region_8_noord_holland,52.58,4.87,8,,nld
+nl_region_9_zuid_holland,51.94,4.47,9,,nld
+nl_region_10_zeeland,51.45,3.84,10,,nld
+nl_region_11_noord_brabant,51.56,5.20,11,,nld
+nl_region_12_limburg,51.21,5.94,12,,nld
+be_belgium,50.85,4.35,,Belgium,bel
+be_flanders,51.00,4.46,,Flanders,bel
+be_wallonia,50.50,4.70,,Wallonia,bel
+be_brussels,50.85,4.35,,Brussels,bel

solar_consumer/fetch_data.py

@@ -16,23 +16,25 @@
 from solar_consumer.data.fetch_ind_rajasthan_data import fetch_ind_rajasthan_data
 
 
-def fetch_data(country: str = "gb", historic_or_forecast: str = "forecast") -> pd.DataFrame:
+def fetch_data(country: str = "gbr_gb", historic_or_forecast: str = "forecast") -> pd.DataFrame:
     """
     Get data from different countries
 
-    :param country: "gb", "nl", "de", "ind_rajasthan", or "be"
-    :param historic_or_forecast: "generation" or "forecast"
+    :param country: "gbr_gb", "nld", "deu", "ind_rj", or "bel"
+    :param historic_or_forecast: Indicator passed through to the country-specific fetcher, e.g. "forecast",
+        "generation", or "historic". The exact accepted values are backend-specific; see the corresponding
+        fetch_<country>_data function for details.
     :return: Pandas dataframe with the following columns:
         target_datetime_utc: Combined date and time in UTC.
         solar_generation_kw: Solar generation in kW. Can be a forecast, or historic values
     """
 
     country_data_functions = {
-        "gb": fetch_gb_data,
-        "nl": fetch_nl_data,
-        "de": fetch_de_data,
-        "ind_rajasthan": fetch_ind_rajasthan_data,
-        "be": fetch_be_data
+        "gbr_gb": fetch_gb_data,
+        "nld": fetch_nl_data,
+        "deu": fetch_de_data,
+        "ind_rj": fetch_ind_rajasthan_data,
+        "bel": fetch_be_data
     }
 
     if country in country_data_functions:
@@ -48,7 +50,7 @@ def fetch_data(country: str = "gb", historic_or_forecast: str = "forecast") -> p
             raise Exception(f"An error occurred while fetching data for {country}: {e}") from e
 
     else:
-        print("Only UK (gb), Netherlands (nl), Germany (de), Belgium (be), and Rajasthan India (ind_rajasthan) data can be fetched at the moment")
+        print("Only UK (gbr_gb), Netherlands (nld), Germany (deu), Belgium (bel), and Rajasthan India (ind_rj) data can be fetched at the moment")
 
     return pd.DataFrame()  # Always return a DataFrame (never None)
 

solar_consumer/save/save_data_platform.py

@@ -24,27 +24,27 @@
 def _get_country_config(country: str) -> dict:
     """Get country-specific configuration for data platform operations."""
     configs = {
-        "nl": {
+        "nld": {
             "id_key": "region_id",
             "location_type": dp.LocationType.NATION,
             "metadata_type": "number",  
             "observer_name": "nednl",
         },
-        "be": {
+        "bel": {
             "id_key": "region",
             "location_type": dp.LocationType.NATION,
             "metadata_type": "string",  
             "observer_name": "elia_be",
         },
-        "gb": {
+        "gbr_gb": {
             "required_observers": {"pvlive_in_day", "pvlive_day_after"},
             "id_key": "gsp_id",
             "location_type": [dp.LocationType.GSP, dp.LocationType.NATION],
             "metadata_type": "number", 
             "observer_name": None, 
         },
     }
-    return configs.get(country, configs["gb"])
+    return configs.get(country, configs["gbr_gb"])
 
 
 def _extract_metadata_value(metadata: dict, key: str, metadata_type: str) -> any:
@@ -156,25 +156,25 @@ async def _create_locations_from_csv(
 
 
 async def save_generation_to_data_platform(
-    data_df: pd.DataFrame, client: dp.DataPlatformDataServiceStub, country: str = "gb"
+    data_df: pd.DataFrame, client: dp.DataPlatformDataServiceStub, country: str = "gbr_gb"
 ) -> None:
     """
     Saves model data via the data platform.
 
     Incoming data is enriched with location information from the data platform. Anything with zero
     capacity, or without a corresponding entry in the data platform, is ignored.
 
-    For GB: Data is joined via the gsp_id, which is a column in the incoming data, and has to be
+    For GBR_GB: Data is joined via the gsp_id, which is a column in the incoming data, and has to be
     extracted from the metadata field in the data platform location data.
 
-    For NL: Data is joined via the region_id.
+    For NLD: Data is joined via the region_id.
 
-    For BE: Data is joined via the region (string-based matching).
+    For BEL: Data is joined via the region (string-based matching).
 
     Args:
         data_df: DataFrame containing the generation data
         client: Data platform client stub
-        country: Country identifier ('gb', 'nl', or 'be')
+        country: Country identifier ('gbr_gb', 'nld', or 'bel')
     """
     tasks: list[asyncio.Task] = []
     config = _get_country_config(country)
@@ -212,7 +212,7 @@ async def save_generation_to_data_platform(
         await _execute_async_tasks(tasks)
 
     # 1. Get locations and join to the incoming data.
-    if country in ["nl", "be"]:
+    if country in ["nld", "bel"]:
         # NL and BE support CSV-based location creation
         locations_data = await _list_locations(client, config["location_type"])
 
@@ -231,7 +231,7 @@ async def save_generation_to_data_platform(
     data_df = data_df.copy()
 
     # Extract metadata and create join key based on country
-    if country == "be":
+    if country == "bel":
         # BE uses string matching with normalization
         data_df["join_key"] = data_df[id_key]
 
@@ -339,7 +339,7 @@ async def save_generation_to_data_platform(
     if len(tasks) > 0:
         logging.info("updating %d %s location capacities", len(tasks), country.upper())
         # NL was previously ignoring these exceptions
-        await _execute_async_tasks(tasks, ignore_exceptions=(country == "nl"))
+        await _execute_async_tasks(tasks, ignore_exceptions=(country == "nld"))
 
     # 3. Generate the CreateObservationRequest objects from the DataFrame.
     observations_by_loc: dict[str, list[dp.CreateObservationsRequestValue]] = defaultdict(list)

solar_consumer/save/save_site_database.py

@@ -72,7 +72,7 @@ def get_or_create_pvsite(
     Parameters:
         session (Session): CurrentSQLAlchemy session
         pvsite (PVSite): Pydantic model with site metadata
-        country (str): Country code ('nl' or 'de')
+        country (str): Country code ('nld', 'deu', or 'ind_rj')
         capacity_override_kw (Optional[int]): Force a specific capacity on creation
 
     Returns:
@@ -88,14 +88,14 @@ def get_or_create_pvsite(
     except Exception:
         logger.info(f"Creating site {pvsite.client_site_name} in the database.")
 
-        # Choose capacity based on country; per-TSO for de; nl only has 20GW hard‑coded
+        # Choose capacity based on country; per-TSO for deu; nld only has 20GW hard‑coded
         if capacity_override_kw is not None:
             capacity = capacity_override_kw
-        elif country == "de":
+        elif country == "deu":
             capacity = DE_TSO_CAPACITY[pvsite.client_site_name]
-        elif country == "nl":
+        elif country == "nld":
             capacity = 20_000_000
-        else: #in
+        else: #ind_rj
             capacity = capacity_override_kw or 0
 
         site, _ = create_site(
@@ -137,7 +137,7 @@ def update_capacity(
 
 
 def save_generation_to_site_db(
-    generation_data: pd.DataFrame, session: Session, country: str = "nl"
+    generation_data: pd.DataFrame, session: Session, country: str = "nld"
 ):
     """Save generation data to the database.
 
@@ -147,9 +147,9 @@ def save_generation_to_site_db(
             - solar_generation_kw
             - target_datetime_utc
             - capacity_kw (optional, used when present)
-            - tso_zone (only when country="de")
+            - tso_zone (only when country="deu")
         session (Session): SQLAlchemy session for database access.
-        country: (str): Country code for the generation data ('nl', 'de', 'ind_rajasthan')
+        country: (str): Country code for the generation data ('nld', 'deu', 'ind_rj')
 
 
     Return:
@@ -162,27 +162,27 @@ def save_generation_to_site_db(
         return
 
     # Determine country
-    if country == "nl":
+    if country == "nld":
         country_sites = NL_NATIONAL_AND_REGIONS
-    elif country == "de":
+    elif country == "deu":
         country_sites = DE_TSO_SITES
-    elif country == "ind_rajasthan":
+    elif country == "ind_rj":
         country_sites = IND_RAJASTHAN_SITES
     else:
         raise Exception( 
             "Only generation data from the following countries is supported "
-            "when saving: 'nl', 'de', 'ind_rajasthan'"
+            "when saving: 'nld', 'deu', 'ind_rj'"
         )
 
     # Loop per site
     for key, pvsite in country_sites.items():
 
         # Filter by TSO for Germany, or use all data for NL
-        if country == "de":
+        if country == "deu":
             generation_data_tso_df = generation_data[generation_data["tso_zone"] == key].copy()
-        elif country == "nl":
+        elif country == "nld":
             generation_data_tso_df = generation_data[generation_data["region_id"] == int(key)].copy()
-        elif country == "ind_rajasthan":
+        elif country == "ind_rj":
             generation_data_tso_df = generation_data[generation_data["energy_type"] == key].copy()
         else:
             generation_data_tso_df = generation_data.copy()
@@ -207,7 +207,7 @@ def save_generation_to_site_db(
         )
 
         generation_data_tso_df = generation_data_tso_df.copy()
-        if country == "ind_rajasthan":
+        if country == "ind_rj":
             generation_data_tso_df["energy_type"] = key
         else:
             generation_data_tso_df["energy_type"] = "solar"
@@ -242,7 +242,7 @@ def save_forecasts_to_site_db(
     session: Session,
     model_tag: str,
     model_version: str,
-    country: str = "nl",
+    country: str = "nld",
 ):
     """Save generation data to the database.
 
@@ -252,14 +252,14 @@ def save_forecasts_to_site_db(
         session (Session): SQLAlchemy session for database access.
         model_tag (str): Model tag to fetch model metadata.
         model_version (str): Model version to fetch model metadata.
-        country: (str): Country code for the generation data. Currently only 'nl' is supported.
+        country: (str): Country code for the generation data. Currently only 'nld' is supported.
 
     Return:
         None
     """
 
-    if country != "nl":
-        raise Exception("Only NL forecast data is supported when saving (atm).")
+    if country != "nld":
+        raise Exception("Only NLD forecast data is supported when saving (atm).")
 
     site = get_or_create_pvsite(session, nl_national, country)