update typing information

offsets_db_data/credits.py

@@ -14,7 +14,9 @@
 
 
 @pf.register_dataframe_method
-def filter_and_merge_transactions(df, arb_data, project_id_column: str = 'project_id'):
+def filter_and_merge_transactions(
+    df: pd.DataFrame, arb_data: pd.DataFrame, project_id_column: str = 'project_id'
+) -> pd.DataFrame:
     if intersection_values := list(
         set(df[project_id_column]).intersection(set(arb_data[project_id_column]))
     ):
@@ -26,7 +28,7 @@ def filter_and_merge_transactions(df, arb_data, project_id_column: str = 'projec
 
 
 @pf.register_dataframe_method
-def aggregate_issuance_transactions(df):
+def aggregate_issuance_transactions(df: pd.DataFrame) -> pd.DataFrame:
     # Check if 'transaction_type' exists in DataFrame columns
     if 'transaction_type' not in df.columns:
         raise KeyError("The column 'transaction_type' is missing.")
@@ -53,13 +55,13 @@ def aggregate_issuance_transactions(df):
 
 
 @pf.register_dataframe_method
-def handle_non_issuance_transactions(df):
+def handle_non_issuance_transactions(df: pd.DataFrame) -> pd.DataFrame:
     df = df.copy()
     df_non_issuance = df[df['transaction_type'] != 'issuance']
     return df_non_issuance
 
 
-def calculate_verra_issuances(*, df):
+def calculate_verra_issuances(*, df: pd.DataFrame) -> pd.DataFrame:
     """Logic to calculate verra transactions from prepocessed transaction data
 
     Verra allows rolling/partial issuances. This requires inferring vintage issuance from `Total Vintage Quantity`
@@ -78,14 +80,14 @@ def calculate_verra_issuances(*, df):
     return df_issuance
 
 
-def calculate_verra_retirements(*, df):
+def calculate_verra_retirements(*, df: pd.DataFrame) -> pd.DataFrame:
     """retirements + cancelations, but data doesnt allow us to distinguish the two"""
     retirements = df[df['transaction_type'] != 'issuance']
     retirements = retirements.rename(columns={'Quantity Issued': 'quantity'})
     return retirements
 
 
-def preprocess_verra_transactions(*, df):
+def preprocess_verra_transactions(*, df: pd.DataFrame) -> pd.DataFrame:
     """Preprocess Verra transactions data"""
 
     df = df.copy()
@@ -112,7 +114,7 @@ def preprocess_verra_transactions(*, df):
     return df
 
 
-def preprocess_gold_standard_transactions(*, df, download_type):
+def preprocess_gold_standard_transactions(*, df: pd.DataFrame, download_type: str) -> pd.DataFrame:
     """Preprocess Gold Standard transactions data"""
     df = df.copy()
     df['project'] = df['project'].apply(lambda x: x if isinstance(x, dict) else ast.literal_eval(x))
@@ -137,7 +139,7 @@ def add_gcc_project_id(*, transactions, projects):
     return transactions
 
 
-def preprocess_gcc_transactions(*, df, download_type):
+def preprocess_gcc_transactions(*, df: pd.DataFrame, download_type: str) -> pd.DataFrame:
     """Preprocess GCC transactions data"""
     df = df.copy()
 
@@ -166,7 +168,9 @@ def preprocess_gcc_transactions(*, df, download_type):
     return df
 
 
-def preprocess_apx_transactions(*, df, download_type, registry_name):
+def preprocess_apx_transactions(
+    *, df: pd.DataFrame, download_type: str, registry_name: str
+) -> pd.DataFrame:
     transaction_type_mapping = {
         'issuances': 'issuance',
         'retirements': 'retirement',

offsets_db_data/projects.py

@@ -1,3 +1,4 @@
+import contextlib
 import json
 from collections import defaultdict
 
@@ -138,7 +139,7 @@ def add_category(df, protocol_mapping) -> pd.DataFrame:
 
 
 @pf.register_dataframe_method
-def add_is_compliance_flag(df) -> pd.DataFrame:
+def add_is_compliance_flag(df: pd.DataFrame) -> pd.DataFrame:
     """Add is_arb flag"""
     print('Adding is_compliance flag...')
     df['is_compliance'] = df.apply(
@@ -150,7 +151,9 @@ def add_is_compliance_flag(df) -> pd.DataFrame:
 
 @pf.register_dataframe_method
 def map_protocol(
-    df, inverted_protocol_mapping, original_protocol_column: str = 'original_protocol'
+    df: pd.DataFrame,
+    inverted_protocol_mapping: dict,
+    original_protocol_column: str = 'original_protocol',
 ) -> pd.DataFrame:
     """Map protocol based on known string"""
     print('Mapping protocol based on known string...')
@@ -166,13 +169,13 @@ def map_protocol(
 
 
 @pf.register_dataframe_method
-def harmonize_status_codes(df, status_column: str = 'status') -> pd.DataFrame:
+def harmonize_status_codes(df: pd.DataFrame, status_column: str = 'status') -> pd.DataFrame:
     """Harmonize project status codes across registries
 
     Excludes ACR, as it requires special treatment across two columns
     """
     print('Harmonizing status codes')
-    try:
+    with contextlib.suppress(KeyError):
         GCC_STATES = {
             'VERIFICATION': 'listed',
             'RFR CC INCOMPLETE': 'unknown',
@@ -210,8 +213,6 @@ def harmonize_status_codes(df, status_column: str = 'status') -> pd.DataFrame:
 
         state_dict = GCC_STATES | CAR_STATES | VERRA_STATES | GS_STATES
         df[status_column] = df[status_column].apply(lambda x: state_dict.get(x, 'unknown'))
-    except KeyError:  # status not in raw data
-        pass
     return df
 
 
@@ -254,7 +255,7 @@ def _get_category(protocol_str, protocol_mapping):
     return [_get_category(protocol_str, protocol_mapping) for protocol_str in protocol_strs]
 
 
-def harmonize_acr_status(row):
+def harmonize_acr_status(row: pd.Series) -> str:
     """Derive single project status for CAR and ACR projects
 
     Raw CAR and ACR data has two status columns -- one for compliance status, one for voluntary.
@@ -299,7 +300,7 @@ def load_protocol_mapping(path: upath.UPath = PROTOCOL_MAPPING_UPATH) -> dict:
     return json.loads(path.read_text())
 
 
-def load_inverted_protocol_mapping():
+def load_inverted_protocol_mapping() -> dict:
     protocol_mapping = load_protocol_mapping()
     store = defaultdict(list)
     for protocol_str, metadata in protocol_mapping.items():