oda-data 2.1.2__tar.gz → 2.2.2__tar.gz

{oda_data-2.1.2 → oda_data-2.2.2}/PKG-INFO

@@ -1,23 +1,17 @@
 Metadata-Version: 2.3
-Name: oda_data
-Version: 2.1.2
+Name: oda-data
+Version: 2.2.2
 Summary: A python package to work with Official Development Assistance data from the OECD DAC.
+Author: Jorge Rivera, Miguel Haro Ruiz
+Author-email: Jorge Rivera <jorge.rivera@one.org>, Miguel Haro Ruiz <miguel.haroruiz@one.org>
 License: MIT
-Author: Jorge Rivera
-Author-email: jorge.rivera@one.org
-Requires-Python: >=3.10,<4.0
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3.13
-Requires-Dist: cachetools (>=5.5.1,<7.0.0)
-Requires-Dist: oda-reader (>=1.2,<2.0)
-Requires-Dist: pandas (>=2)
-Requires-Dist: pyarrow (>=14,<22)
-Requires-Dist: pydeflate (>=2.0.1)
-Requires-Dist: thefuzz (>=0.22.1)
+Requires-Dist: cachetools>=6.2.0
+Requires-Dist: oda-reader>=1.2.2
+Requires-Dist: pandas[excel,parquet,performance]>=2.3.2
+Requires-Dist: pydeflate>=2.1.3
+Requires-Dist: reader>=3.18
+Requires-Dist: thefuzz>=0.22.1
+Requires-Python: >=3.11
 Project-URL: Documentation, https://github.com/ONEcampaign/oda_data_package
 Project-URL: Homepage, https://github.com/ONEcampaign/oda_data_package
 Project-URL: Repository, https://github.com/ONEcampaign/oda_data_package
@@ -345,4 +339,3 @@ request it via the [issues page](https://github.com/ONEcampaign/oda_data_package
 
 ## Contributing
 Interested in contributing to the package? Please reach out.
-

oda_data-2.2.2/pyproject.toml

@@ -0,0 +1,35 @@
+[project]
+name = "oda_data"
+version = "2.2.2"
+description = "A python package to work with Official Development Assistance data from the OECD DAC."
+requires-python = ">=3.11"
+
+license = {text = "MIT"}
+readme = "README.md"
+authors = [
+    {name = "Jorge Rivera", email = "jorge.rivera@one.org"},
+    {name = "Miguel Haro Ruiz", email = "miguel.haroruiz@one.org"}
+]
+
+dependencies = [
+    "cachetools>=6.2.0",
+    "oda-reader>=1.2.2",
+    "pandas[excel,parquet,performance]>=2.3.2",
+    "pydeflate>=2.1.3",
+    "reader>=3.18",
+    "thefuzz>=0.22.1",
+]
+
+[project.urls]
+Homepage = "https://github.com/ONEcampaign/oda_data_package"
+Repository = "https://github.com/ONEcampaign/oda_data_package"
+Documentation = "https://github.com/ONEcampaign/oda_data_package"
+
+[build-system]
+requires = ["uv_build>=0.8.22,<0.9.0"]
+build-backend = "uv_build"
+
+[dependency-groups]
+dev = [
+    "uv-build>=0.8.22",
+]

{oda_data-2.1.2 → oda_data-2.2.2/src}/oda_data/__init__.py

@@ -1,30 +1,29 @@
-from importlib.metadata import version
+from oda_reader import clear_cache, disable_cache, enable_cache, set_cache_dir
 
-__version__ = version("oda_data")
-
-from oda_data import tools
-from oda_reader import set_cache_dir, disable_cache, enable_cache, clear_cache
 from oda_data.api.oecd import OECDClient
 from oda_data.api.sources import (
+    AidDataData,
+    CRSData,
     DAC1Data,
     DAC2AData,
     MultiSystemData,
-    CRSData,
-    AidDataData,
 )
 from oda_data.indicators.research.policy_markers import bilateral_policy_marker
 from oda_data.tools.compatibility import ODAData
 from oda_data.tools.gni import add_gni_share_column
 from oda_data.tools.groupings import provider_groupings, recipient_groupings
 from oda_data.tools.names.add import add_names_columns
-from oda_data.tools.sector_lists import add_sectors, add_broad_sectors
+from oda_data.tools.sector_lists import add_broad_sectors, add_sectors
+from oda_data.indicators.research import sector_imputations
 
 
 def set_data_path(path):
     from pathlib import Path
-    from oda_data.config import ODAPaths
+
     from pydeflate import set_pydeflate_path
 
+    from oda_data.config import ODAPaths
+
     """Set the path to the data folder."""
     global ODAPaths
 
@@ -56,4 +55,5 @@ __all__ = [
     "disable_cache",
     "enable_cache",
     "clear_cache",
+    "sector_imputations",
 ]

{oda_data-2.1.2 → oda_data-2.2.2/src}/oda_data/api/oecd.py

@@ -7,14 +7,14 @@ import pandas as pd
 
 from oda_data import config
 from oda_data.api.constants import (
-    MEASURES,
-    Measure,
+    _EXCLUDE,
     CURRENCIES,
+    MEASURES,
     PRICES,
-    _EXCLUDE,
+    Measure,
 )
 from oda_data.api.representations import _ODADict, _ODAList
-from oda_data.api.sources import DAC1Data, DAC2AData, CRSData, MultiSystemData
+from oda_data.api.sources import CRSData, DAC1Data, DAC2AData, MultiSystemData
 from oda_data.clean_data import common as clean
 from oda_data.clean_data.validation import validate_currency, validate_measure
 from oda_data.indicators.crs import crs_functions

{oda_data-2.1.2 → oda_data-2.2.2/src}/oda_data/api/sources.py

@@ -1,18 +1,18 @@
+import threading
 from abc import abstractmethod
 from pathlib import Path
 from typing import Optional
-import threading
 
 import pandas as pd
 from cachetools import TTLCache
 from oda_reader import (
-    download_crs,
     bulk_download_crs,
+    bulk_download_multisystem,
+    download_aiddata,
+    download_crs,
     download_dac1,
     download_dac2a,
-    bulk_download_multisystem,
     download_multisystem,
-    download_aiddata,
 )
 from oda_reader._cache import memory
 
@@ -20,17 +20,33 @@ from oda_data.clean_data.common import (
     clean_raw_df,
     convert_dot_stat_to_data_explorer_codes,
 )
-from oda_data.clean_data.schema import ODASchema, AidDataSchema
+from oda_data.clean_data.schema import (
+    CORE_CRS_MAPPING,
+    AidDataSchema,
+    ODASchema,
+)
 from oda_data.clean_data.validation import (
-    validate_years_providers_recipients,
     check_integers,
     check_strings,
+    validate_years_providers_recipients,
 )
 from oda_data.config import ODAPaths
 from oda_data.logger import logger
 from oda_data.tools.cache import OnDiskCache, generate_param_hash
 
 
+def translate_cols_and_filters_to_raw(columns, filters) -> tuple[list, list]:
+    crs_mapping = {v: k for k, v in CORE_CRS_MAPPING.items()}
+    cols = [crs_mapping.get(col, col) for col in columns] if columns else columns
+    filters = (
+        [(crs_mapping.get(col, col), op, val) for col, op, val in filters]
+        if filters
+        else None
+    )
+
+    return cols, filters
+
+
 def _filters_to_query(filters: list[tuple[str, str, list]]) -> str:
     """Transform a list of filters into a query string."""
     query = ""
@@ -79,9 +95,7 @@ class Source:
         with Source._shared_disk_cache_lock:
             dc = Source._shared_disk_cache
             if dc is None or dc.base_dir != current_raw:
-                Source._shared_disk_cache = OnDiskCache(
-                    current_raw, ttl_seconds=86400
-                )
+                Source._shared_disk_cache = OnDiskCache(current_raw, ttl_seconds=86400)
             return Source._shared_disk_cache
 
     def _add_filter(self, column: str, predicate: str, value: str | int | list) -> None:
@@ -124,7 +138,6 @@ class Source:
     def _get_cached_dataset(
         self, param_hash: str, filters: list[tuple], columns: list[str]
     ) -> pd.DataFrame | None:
-
         cached_df = self.memory_cache.get(param_hash)
 
         if cached_df is None:
@@ -156,7 +169,6 @@ class DACSource(Source):
         recipients: Optional[list[int] | int] = None,
         sectors: Optional[list[int] | int] = None,
     ):
-
         self.years, self.providers, self.recipients = (
             validate_years_providers_recipients(
                 years=years, providers=providers, recipients=recipients
@@ -317,10 +329,13 @@ class DACSource(Source):
                     df=df, query=query, param_hash=param_hash, bulk=using_bulk_download
                 )
 
-        df = df.pipe(clean_raw_df)
-
         if columns:
-            df = df.filter(columns)
+            try:
+                df = df[columns]
+            except Exception as e:
+                df = df.pipe(clean_raw_df)[columns]
+
+        df = df.pipe(clean_raw_df)
 
         return df
 

{oda_data-2.1.2 → oda_data-2.2.2/src}/oda_data/clean_data/common.py

@@ -4,7 +4,7 @@ from functools import partial
 from typing import Optional
 
 import pandas as pd
-from pydeflate import set_pydeflate_path, oecd_dac_deflate, oecd_dac_exchange
+from pydeflate import oecd_dac_deflate, oecd_dac_exchange, set_pydeflate_path
 
 from oda_data.clean_data.dtypes import set_default_types
 from oda_data.clean_data.schema import CRS_MAPPING, ODASchema

{oda_data-2.1.2 → oda_data-2.2.2/src}/oda_data/clean_data/schema.py

@@ -134,9 +134,154 @@ class ODASchema:
     AID_TO_THRU: str = "aid_to_or_thru"
     AMOUNT_TYPE_CODE: str = "amounttype_code"
     MEASURE: str = "measure"
+    INITIAL_REPORT: str = "initial_report"
+    DE_INCOMEGROUPCODE: str = "de_incomegroupcode"
+    CHANNEL_REPORTED_NAME: str = "channel_reported_name"
+    GEOGRAPHY: str = "geography"
+    KEYWORDS: str = "keywords"
+    BUDGET_IDENTIFIER: str = "budget_ident"
+    PSI_GRANT_EQ_USD: str = "usd_psi_gr_eq_memo"
 
 
-CRS_MAPPING: dict[str, str] = {
+CORE_CRS_MAPPING: dict[str, str] = {
+    "year": ODASchema.YEAR,
+    "donor_code": ODASchema.PROVIDER_CODE,
+    "donor_name": ODASchema.PROVIDER_NAME,
+    "agency_code": ODASchema.AGENCY_CODE,
+    "agency_name": ODASchema.AGENCY_NAME,
+    "crs_id": ODASchema.CRS_ID,
+    "initial_report": ODASchema.INITIAL_REPORT,
+    "project_number": ODASchema.PROJECT_ID,
+    "recipient_code": ODASchema.RECIPIENT_CODE,
+    "recipient_name": ODASchema.RECIPIENT_NAME,
+    "region_name": ODASchema.RECIPIENT_REGION,
+    "region_code": ODASchema.RECIPIENT_REGION_CODE,
+    "incomegoup_name": ODASchema.RECIPIENT_INCOME,
+    "incomegroup_code": ODASchema.RECIPIENT_INCOME_CODE,
+    "de_incomegroupcode": ODASchema.DE_INCOMEGROUPCODE,
+    "recipient_income_group_oecd_classification": ODASchema.RECIPIENT_INCOME,
+    "aid_t": ODASchema.FLOW_MODALITY,
+    "financial_instrument": ODASchema.FINANCIAL_INSTRUMENT,
+    "type_of_finance": ODASchema.FINANCE_TYPE,
+    "finance_t": ODASchema.FINANCE_TYPE,
+    "channel_of_delivery": ODASchema.CHANNEL_NAME_DELIVERY,
+    "channel_of_delivery_code": ODASchema.CHANNEL_CODE_DELIVERY,
+    "channel_code": ODASchema.CHANNEL_CODE,
+    "channel_name": ODASchema.CHANNEL_NAME,
+    "purpose_code": ODASchema.PURPOSE_CODE,
+    "sector_code": ODASchema.SECTOR_CODE,
+    "purpose_name": ODASchema.PURPOSE_NAME,
+    "sector_name": ODASchema.SECTOR_NAME,
+    "project_title": ODASchema.PROJECT_TITLE,
+    "long_description": ODASchema.PROJECT_DESCRIPTION,
+    "short_description": ODASchema.PROJECT_DESCRIPTION_SHORT,
+    "flow_code": ODASchema.FLOW_CODE,
+    "flow_name": ODASchema.FLOW_NAME,
+    "bi_multi": ODASchema.BI_MULTI,
+    "gender": ODASchema.GENDER,
+    "category": ODASchema.CATEGORY,
+    "usd_commitment": ODASchema.USD_COMMITMENT,
+    "usd_disbursement": ODASchema.USD_DISBURSEMENT,
+    "usd_received": ODASchema.USD_RECEIVED,
+    "usd_grant_equiv": ODASchema.USD_GRANT_EQUIV,
+    "usd_net_disbursement": ODASchema.USD_NET_DISBURSEMENT,
+    "usd_commitment_defl": ODASchema.USD_COMMITMENT_DEFL,
+    "usd_disbursement_defl": ODASchema.USD_DISBURSEMENT_DEFL,
+    "usd_received_defl": ODASchema.USD_RECEIVED_DEFL,
+    "usd_adjustment": ODASchema.USD_ADJUSTMENT,
+    "usd_adjustment_defl": ODASchema.USD_ADJUSTMENT_DEFL,
+    "usd_amount_untied": ODASchema.USD_AMOUNT_UNTIED,
+    "usd_amount_untied_defl": ODASchema.USD_AMOUNT_UNTIED_DEFL,
+    "usd_amount_tied": ODASchema.USD_AMOUNT_TIED,
+    "usd_amount_tied_defl": ODASchema.USD_AMOUNT_TIED_DEFL,
+    "usd_amount_partial_tied": ODASchema.USD_AMOUNT_PARTIAL_TIED,
+    "usd_amount_partial_tied_defl": ODASchema.USD_AMOUNT_PARTIAL_TIED_DEFL,
+    "usd_irtc_code": ODASchema.USD_IRTC_CODE,
+    "usd_expert_commitment": ODASchema.USD_EXPERT_COMMITMENT,
+    "usd_expert_extended": ODASchema.USD_EXPERT_EXTENDED,
+    "usd_export_credit": ODASchema.USD_EXPORT_CREDIT,
+    "commitment_national": ODASchema.COMMITMENT_NATIONAL,
+    "disbursement_national": ODASchema.DISBURSEMENT_NATIONAL,
+    "grant_equiv": ODASchema.GRANT_EQUIV_NATIONAL,
+    "parent_channel_code": ODASchema.PARENT_CHANNEL_CODE,
+    "ld_cflag": ODASchema.LDC_FLAG_CODE,
+    "ldcflag": ODASchema.LDC_FLAG_CODE,
+    "ld_cflag_name": ODASchema.LDC_FLAG,
+    "ldcflag_name": ODASchema.LDC_FLAG,
+    "sdg_focus": ODASchema.SDG_FOCUS,
+    "sdgfocus": ODASchema.SDG_FOCUS,
+    "sd_gfocus": ODASchema.SDG_FOCUS,
+    "expected_start_date": ODASchema.EXPECTED_START_DATE,
+    "completion_date": ODASchema.COMPLETION_DATE,
+    "environment": ODASchema.ENVIRONMENT,
+    "dig_code": ODASchema.DIG_CODE,
+    "dig": ODASchema.DIG_CODE,
+    "trade": ODASchema.TRADE,
+    "rmnch": ODASchema.RMNCH_CODE,
+    "drr": ODASchema.DRR_CODE,
+    "rmnch_code": ODASchema.RMNCH_CODE,
+    "drr_code": ODASchema.DRR_CODE,
+    "nutrition": ODASchema.NUTRITION,
+    "disability": ODASchema.DISABILITY,
+    "ftc": ODASchema.FTC_CODE,
+    "ftc_code": ODASchema.FTC_CODE,
+    "pba": ODASchema.PBA_CODE,
+    "pba_code": ODASchema.PBA_CODE,
+    "investment_project": ODASchema.INVESTMENT_PROJECT,
+    "assoc_finance": ODASchema.ASSOC_FINANCE,
+    "biodiversity": ODASchema.BIODIVERSITY,
+    "desertification": ODASchema.DESERTIFICATION,
+    "commitment_date": ODASchema.COMMITMENT_DATE,
+    "type_repayment": ODASchema.TYPE_REPAYMENT,
+    "number_repayment": ODASchema.NUMBER_REPAYMENT,
+    "interest1": ODASchema.INTEREST1,
+    "interest2": ODASchema.INTEREST2,
+    "repaydate1": ODASchema.REPAYDATE1,
+    "repaydate2": ODASchema.REPAYDATE2,
+    "usd_interest": ODASchema.USD_INTEREST,
+    "usd_outstanding": ODASchema.USD_OUTSTANDING,
+    "usd_arrears_principal": ODASchema.USD_ARREARS_PRINCIPAL,
+    "usd_arrears_interest": ODASchema.USD_ARREARS_INTEREST,
+    "capital_expend": ODASchema.CAPITAL_EXPEND,
+    "ps_iflag": ODASchema.PSI_FLAG,
+    "psiflag": ODASchema.PSI_FLAG,
+    "psi_flag": ODASchema.PSI_FLAG,
+    "ps_iadd_type": ODASchema.PSI_ADD_TYPE,
+    "psiadd_type": ODASchema.PSI_ADD_TYPE,
+    "psi_add_type": ODASchema.PSI_ADD_TYPE,
+    "ps_iadd_assess": ODASchema.PSI_ADD_ASSESS,
+    "psiadd_assess": ODASchema.PSI_ADD_ASSESS,
+    "psi_add_assess": ODASchema.PSI_ADD_ASSESS,
+    "ps_iadd_dev_obj": ODASchema.PSI_ADD_DEV_OBJECTIVE,
+    "psiadd_dev_obj": ODASchema.PSI_ADD_DEV_OBJECTIVE,
+    "psi_add_dev_obj": ODASchema.PSI_ADD_DEV_OBJECTIVE,
+    "oecd_climate_total": ODASchema.CLIMATE_UNSPECIFIED,
+    "reporting_type": ODASchema.REPORTING_METHOD,
+    "type": ODASchema.MULTILATERAL_TYPE,
+    "converged_reporting": ODASchema.CONVERGED_REPORTING,
+    "coal_related_financing": ODASchema.COAL_FINANCING,
+    "flow_type": ODASchema.FLOW_TYPE,
+    "type_of_flow": ODASchema.FLOW_TYPE,
+    "aidtype_code": ODASchema.AIDTYPE_CODE,
+    "aid_type": ODASchema.AIDTYPE_NAME,
+    "flows_code": ODASchema.FLOWS_CODE,
+    "fund_flows": ODASchema.FUND_FLOWS,
+    "amounttype_code": ODASchema.AMOUNT_TYPE_CODE,
+    "de_donorcode": ODASchema.PROVIDER_CODE_DE,
+    "de_recipientcode": ODASchema.RECIPIENT_CODE_DE,
+    "de_regioncode": ODASchema.RECIPIENT_REGION_CODE_DE,
+    "incomegroup_name": ODASchema.RECIPIENT_INCOME,
+    "channel_reported_name": ODASchema.CHANNEL_REPORTED_NAME,
+    "geography": ODASchema.GEOGRAPHY,
+    "keywords": ODASchema.KEYWORDS,
+    "climate_adaptation": ODASchema.ADAPTATION,
+    "climate_mitigation": ODASchema.MITIGATION,
+    "budget_ident": ODASchema.BUDGET_IDENTIFIER,
+    "usd_psi_gr_eq_memo": ODASchema.PSI_GRANT_EQ_USD,
+}
+
+CRS_MAPPING: dict[str, str] = CORE_CRS_MAPPING | {
+    "year": ODASchema.YEAR,
     "donor_code": ODASchema.PROVIDER_CODE,
     "donor_name": ODASchema.PROVIDER_NAME,
     "provider": ODASchema.PROVIDER_NAME,
@@ -146,7 +291,9 @@ CRS_MAPPING: dict[str, str] = {
     "agency_code": ODASchema.AGENCY_CODE,
     "agency_name": ODASchema.AGENCY_NAME,
     "extending_agency": ODASchema.AGENCY_NAME,
+    "crs_id": ODASchema.CRS_ID,
     "crs_identification_n": ODASchema.CRS_ID,
+    "initial_report": ODASchema.INITIAL_REPORT,
     "donor_project_n": ODASchema.PROJECT_ID,
     "project_number": ODASchema.PROJECT_ID,
     "recipient_code": ODASchema.RECIPIENT_CODE,
@@ -155,6 +302,7 @@ CRS_MAPPING: dict[str, str] = {
     "region_code": ODASchema.RECIPIENT_REGION_CODE,
     "incomegoup_name": ODASchema.RECIPIENT_INCOME,
     "incomegroup_code": ODASchema.RECIPIENT_INCOME_CODE,
+    "de_incomegroupcode": ODASchema.DE_INCOMEGROUPCODE,
     "recipient_income_group_oecd_classification": ODASchema.RECIPIENT_INCOME,
     "development_cooperation_modality": ODASchema.FLOW_MODALITY,
     "aid_t": ODASchema.FLOW_MODALITY,
@@ -177,6 +325,8 @@ CRS_MAPPING: dict[str, str] = {
     "sub_sector": ODASchema.PURPOSE_NAME,
     "purpose_code": ODASchema.PURPOSE_CODE,
     "sector_code": ODASchema.SECTOR_CODE,
+    "purpose_name": ODASchema.PURPOSE_NAME,
+    "sector_name": ODASchema.SECTOR_NAME,
     "project_title": ODASchema.PROJECT_TITLE,
     "long_description": ODASchema.PROJECT_DESCRIPTION,
     "short_description": ODASchema.PROJECT_DESCRIPTION_SHORT,
@@ -276,6 +426,13 @@ CRS_MAPPING: dict[str, str] = {
     "de_recipientcode": ODASchema.RECIPIENT_CODE_DE,
     "de_regioncode": ODASchema.RECIPIENT_REGION_CODE_DE,
     "incomegroup_name": ODASchema.RECIPIENT_INCOME,
+    "channel_reported_name": ODASchema.CHANNEL_REPORTED_NAME,
+    "geography": ODASchema.GEOGRAPHY,
+    "keywords": ODASchema.KEYWORDS,
+    "climate_adaptation": ODASchema.ADAPTATION,
+    "climate_mitigation": ODASchema.MITIGATION,
+    "budget_ident": ODASchema.BUDGET_IDENTIFIER,
+    "usd_psi_gr_eq_memo": ODASchema.PSI_GRANT_EQ_USD,
 }
 
 

{oda_data-2.1.2 → oda_data-2.2.2/src}/oda_data/config.py

@@ -4,7 +4,7 @@ from pathlib import Path
 class ODAPaths:
     """Class to store the paths to the data and output folders."""
 
-    project = Path(__file__).resolve().parent.parent
+    project = Path(__file__).resolve().parent.parent.parent
     scripts = project / "oda_data"
     raw_data = (Path.cwd() / ".raw_data").resolve()
     pydeflate = raw_data / ".pydeflate"

{oda_data-2.1.2 → oda_data-2.2.2/src}/oda_data/indicators/crs/common.py

@@ -1,5 +1,5 @@
 import json
-from typing import Callable, Dict, Any
+from typing import Any, Callable, Dict
 
 import pandas as pd
 

{oda_data-2.1.2 → oda_data-2.2.2/src}/oda_data/indicators/crs/crs_functions.py

@@ -1,6 +1,6 @@
 import pandas as pd
 
-from oda_data.clean_data.channels import add_multi_channel_codes, add_channel_names
+from oda_data.clean_data.channels import add_channel_names, add_multi_channel_codes
 from oda_data.clean_data.schema import ODASchema
 from oda_data.indicators.crs.common import crs_value_cols
 

{oda_data-2.1.2 → oda_data-2.2.2/src}/oda_data/indicators/crs/oecd.py

@@ -11,12 +11,12 @@ from oda_data import CRSData
 from oda_data.config import ODAPaths
 from oda_data.indicators.common import update_mapping_file
 from oda_data.indicators.crs.common import (
-    read_crs_type_of_flow,
-    read_crs_type_of_finance_mapping,
     read_crs_modality_mapping,
     read_crs_purpose_mapping,
+    read_crs_type_of_finance_mapping,
+    read_crs_type_of_flow,
 )
-from oda_data.indicators.indicator import Indicator, SEPARATOR
+from oda_data.indicators.indicator import SEPARATOR, Indicator
 
 
 def generate_totals(crs_indicators: pd.DataFrame) -> pd.DataFrame:
@@ -34,7 +34,6 @@ def generate_totals(crs_indicators: pd.DataFrame) -> pd.DataFrame:
 
     # Iteratively group and aggregate data to generate totals
     for idx, column in enumerate(crs_indicators.columns):
-
         # Create a grouping Total
         if idx >= 2:
             columns_g.append(column)

{oda_data-2.1.2 → oda_data-2.2.2/src}/oda_data/indicators/dac1/dac1_functions.py

@@ -17,8 +17,7 @@ def official_oda(data: pd.DataFrame) -> pd.DataFrame:
         A filtered pandas DataFrame with only official ODA rows.
     """
     oda_query = (
-        "(year < 2018 & aidtype_code == 1010) | "
-        "(year >= 2018 & aidtype_code == 11010)"
+        "(year < 2018 & aidtype_code == 1010) | (year >= 2018 & aidtype_code == 11010)"
     )
     return data.query(oda_query)
 

{oda_data-2.1.2 → oda_data-2.2.2/src}/oda_data/indicators/dac1/oecd.py

@@ -1,11 +1,11 @@
 from oda_data.config import ODAPaths
+from oda_data.indicators.common import update_mapping_file
 from oda_data.indicators.dac1.common import (
     dac1_aid_flow_type_mapping,
     dac1_aid_name_mapping,
     flow_types,
 )
-from oda_data.indicators.common import update_mapping_file
-from oda_data.indicators.indicator import Indicator, SEPARATOR
+from oda_data.indicators.indicator import SEPARATOR, Indicator
 
 
 def dac1_oecd_indicators():

{oda_data-2.1.2 → oda_data-2.2.2/src}/oda_data/indicators/dac2a/oecd.py

@@ -1,7 +1,7 @@
 from oda_data.config import ODAPaths
 from oda_data.indicators.common import update_mapping_file
 from oda_data.indicators.dac2a.common import aid_type
-from oda_data.indicators.indicator import Indicator, SEPARATOR
+from oda_data.indicators.indicator import SEPARATOR, Indicator
 
 
 def dac2a_oecd_indicators():

{oda_data-2.1.2 → oda_data-2.2.2/src}/oda_data/indicators/indicator.py

@@ -1,4 +1,4 @@
-from dataclasses import dataclass, field, asdict
+from dataclasses import asdict, dataclass, field
 from typing import Literal, Optional
 
 SEPARATOR = "."

{oda_data-2.1.2 → oda_data-2.2.2/src}/oda_data/indicators/research/eu.py

@@ -3,7 +3,7 @@
 import pandas as pd
 
 from oda_data.api.constants import Measure
-from oda_data.api.oecd import get_measure_filter, OECDClient
+from oda_data.api.oecd import OECDClient, get_measure_filter
 from oda_data.api.sources import DAC1Data
 from oda_data.clean_data.schema import ODASchema
 

{oda_data-2.1.2 → oda_data-2.2.2/src}/oda_data/indicators/research/policy_markers.py

@@ -1,13 +1,15 @@
 import pandas as pd
+from pyarrow import ArrowInvalid
 
 from oda_data.api.constants import (
-    Measure,
-    PolicyMarker,
-    MEASURES,
     EXTENDED_PROVIDER_PURPOSE_GROUPER,
+    MEASURES,
     MarkerScore,
+    Measure,
+    PolicyMarker,
 )
-from oda_data.clean_data.common import convert_units
+from oda_data.api.sources import translate_cols_and_filters_to_raw
+from oda_data.clean_data.common import clean_raw_df, convert_units
 from oda_data.clean_data.schema import ODASchema
 
 
@@ -23,7 +25,7 @@ def _marker_score_map(marker: PolicyMarker | str) -> list:
 def _marker_modality_filter() -> list:
     return [
         (
-            "modality",
+            ODASchema.FLOW_MODALITY,
             "in",
             [
                 "A02",
@@ -94,17 +96,34 @@ def bilateral_policy_marker(
         filters.append((marker, "in", marker_filter))
 
     if oda_only:
-        filters.append(("category", "in", [10, 60]))
+        filters.append(
+            (
+                ODASchema.FLOW_CODE,
+                "in",
+                [11, 13, 19, 60],
+            )
+        )
 
     # Set up the CRS data object
     crs = CRSData(providers=providers, years=years, recipients=recipients)
 
     # Read the data and group by provider and purpose
-    data = crs.read(
-        columns=grouper + [measure],
-        additional_filters=filters,
-        using_bulk_download=True,
-    )
+
+    cols = grouper + [measure]
+
+    try:
+        data = crs.read(
+            columns=cols,
+            additional_filters=filters,
+            using_bulk_download=True,
+        )
+    except ArrowInvalid as e:
+        c, f = translate_cols_and_filters_to_raw(cols, filters)
+        data = crs.read(
+            columns=c,
+            additional_filters=f,
+            using_bulk_download=True,
+        )
 
     # if marker is not_screened, we need to filter out the screened data
     if marker == "not_screened":

{oda_data-2.1.2 → oda_data-2.2.2/src}/oda_data/tools/compatibility.py

@@ -4,7 +4,7 @@ from dataclasses import dataclass, field
 
 import pandas as pd
 
-from oda_data import config, OECDClient
+from oda_data import OECDClient, config
 
 
 @dataclass

{oda_data-2.1.2 → oda_data-2.2.2/src}/oda_data/tools/gni.py

@@ -1,11 +1,12 @@
 """Compute GNI share indicators, including EU Institutions if applicable."""
 
 from copy import copy
+
 import pandas as pd
 
 from oda_data import OECDClient
-from oda_data.tools.groupings import provider_groupings
 from oda_data.clean_data.schema import ODASchema
+from oda_data.tools.groupings import provider_groupings
 
 
 def _get_eu27_gni_as_eu_institutions(gni_obj: OECDClient) -> pd.DataFrame:

{oda_data-2.1.2 → oda_data-2.2.2/src}/oda_data/tools/names/add.py

@@ -1,6 +1,7 @@
 """Adds human-readable name columns to a DataFrame based on code columns."""
 
 import pandas as pd
+
 from oda_data.tools.names.create_mapping import get_merged_names_mapping
 
 

oda_data-2.1.2/LICENSE

@@ -1,21 +0,0 @@
-MIT License
-
-Copyright (c) 2022 ONE Campaign
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.

oda_data-2.1.2/pyproject.toml

@@ -1,35 +0,0 @@
-[tool.poetry]
-name = "oda_data"
-version = "2.1.2"
-description = "A python package to work with Official Development Assistance data from the OECD DAC."
-readme = "README.md"
-authors = [
-    "Jorge Rivera <jorge.rivera@one.org>",
-    "Miguel Haro Ruiz <miguel.haroruiz@one.org>"
-]
-license = "MIT"
-homepage = "https://github.com/ONEcampaign/oda_data_package"
-repository = "https://github.com/ONEcampaign/oda_data_package"
-documentation = "https://github.com/ONEcampaign/oda_data_package"
-
-[tool.poetry.dependencies]
-python = ">=3.10,<4.0"
-pandas = ">=2"
-thefuzz = ">=0.22.1"
-pyarrow = ">=14,<22"
-pydeflate = ">=2.0.1"
-cachetools = ">=5.5.1,<7.0.0"
-oda-reader = "^1.2"
-
-[tool.poetry.group.dev.dependencies]
-black = ">=25"
-pytest = ">=8"
-
-
-[tool.poetry-dynamic-versioning]
-enable = true
-style = "pep440"
-
-[build-system]
-requires = ["poetry-core>=2.0.0,<3.0.0"]
-build-backend = "poetry.core.masonry.api"

{oda_data-2.1.2 → oda_data-2.2.2/src}/oda_data/indicators/research/sector_imputations.py

@@ -2,10 +2,10 @@ import pandas as pd
 
 from oda_data import provider_groupings
 from oda_data.api.constants import (
-    Measure,
+    CHANNEL_PURPOSE_SHARE_GROUPER,
     MEASURES,
     PROVIDER_PURPOSE_GROUPER,
-    CHANNEL_PURPOSE_SHARE_GROUPER,
+    Measure,
 )
 from oda_data.clean_data.channels import add_multi_channel_codes
 from oda_data.clean_data.common import convert_units

{oda_data-2.1.2 → oda_data-2.2.2/src}/oda_data/tools/names/create_mapping.py

@@ -39,6 +39,7 @@ def snake_to_pascal(name: str, *, keep_single_letter: bool = False) -> str:
             out.append(part.capitalize())
     return "".join(out)
 
+
 def _code_name(df: pd.DataFrame, code_col: str, name_col: str) -> dict:
     """Return a dictionary mapping code to name."""
     return (
@@ -187,7 +188,6 @@ def crs_codes_names():
 
 
 def get_merged_names_mapping():
-
     files = ["dac1_names.json", "dac2a_names.json", "crs_names.json"]
 
     merged_mapping = {}