oda-data 2.0.2__tar.gz → 2.0.3__tar.gz

{oda_data-2.0.2 → oda_data-2.0.3}/PKG-INFO

@@ -1,28 +1,26 @@
 Metadata-Version: 2.3
 Name: oda_data
-Version: 2.0.2
+Version: 2.0.3
 Summary: A python package to work with Official Development Assistance data from the OECD DAC.
+License: MIT
 Author: Jorge Rivera
 Author-email: jorge.rivera@one.org
-Requires-Python: >=3.10, <4.0
+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
-Provides-Extra: dev
-Requires-Dist: black (>=24) ; extra == "dev"
-Requires-Dist: cachetools (>=5.5.1,<6.0.0)
-Requires-Dist: oda-reader (>=1.1.3)
+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,<20)
+Requires-Dist: pyarrow (>=14,<22)
 Requires-Dist: pydeflate (>=2.0.1)
-Requires-Dist: pytest (>=8) ; extra == "dev"
-Requires-Dist: pytest-cov (>=4.0.0) ; extra == "dev"
-Requires-Dist: pytest-mock (>=3.10.0) ; extra == "dev"
 Requires-Dist: thefuzz (>=0.22.1)
-Project-URL: Bug_Tracker, https://github.com/ONEcampaign/oda_data_package/issues
+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
 Description-Content-Type: text/markdown
 
 [![pypi](https://img.shields.io/pypi/v/oda_data.svg)](https://pypi.org/project/oda_data/)

{oda_data-2.0.2 → oda_data-2.0.3}/oda_data/__init__.py

@@ -5,7 +5,13 @@ __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 DAC1Data, DAC2AData, MultiSystemData, CRSData
+from oda_data.api.sources import (
+    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
@@ -33,6 +39,7 @@ __all__ = [
     "DAC2AData",
     "MultiSystemData",
     "CRSData",
+    "AidDataData",
     "bilateral_policy_marker",
     "provider_groupings",
     "recipient_groupings",

{oda_data-2.0.2 → oda_data-2.0.3}/oda_data/api/sources.py

@@ -1,4 +1,5 @@
 from abc import abstractmethod
+from pathlib import Path
 from typing import Optional
 
 import pandas as pd
@@ -10,6 +11,7 @@ from oda_reader import (
     download_dac2a,
     bulk_download_multisystem,
     download_multisystem,
+    download_aiddata,
 )
 from oda_reader._cache import memory
 
@@ -18,7 +20,7 @@ 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
+from oda_data.clean_data.schema import ODASchema, AidDataSchema
 from oda_data.clean_data.validation import (
     validate_years_providers_recipients,
     check_integers,
@@ -41,8 +43,8 @@ def _filters_to_query(filters: list[tuple[str, str, list]]) -> str:
     return query
 
 
-class DACSource:
-    """Base class for accessing DAC datasets.
+class Source:
+    """Base class for accessing any dataset.
 
     This class handles validation of parameters and manages the retrieval
     of data in the form of a pandas DataFrame.
@@ -57,6 +59,45 @@ class DACSource:
         self.de_indicators = None
         self.filters = None
         self.de_sectors = None
+        self.schema = None
+
+    def _add_filter(self, column: str, predicate: str, value: str | int | list) -> None:
+        """Adds a filter to the dataset, ensuring no duplicate columns.
+
+        If a filter for the same column already exists, it is replaced with a warning.
+
+        Args:
+            column (str): The name of the column to filter.
+            predicate (str): The condition to apply (e.g., "in").
+            value (str | int | list): The value(s) to filter by.
+        """
+        existing_filter = next((f for f in self.filters if f[0] == column), None)
+
+        if existing_filter:
+            logger.warning(
+                f"A filter for {column} already exists. Replacing with new filter."
+            )
+
+        # Remove existing filter (if any) and add the new one
+        self.filters = [(c, p, v) for c, p, v in self.filters if c != column]
+        self.filters.append((column, predicate, value))
+
+
+class DACSource(Source):
+    """Base class for accessing DAC datasets.
+
+    This class handles validation of parameters and manages the retrieval
+    of data in the form of a pandas DataFrame.
+    """
+
+    memory_cache = TTLCache(maxsize=20, ttl=6000)
+    disk_cache = OnDiskCache(config.ODAPaths.raw_data, ttl_seconds=86400)
+
+    def __init__(self):
+        super().__init__()
+
+        self.schema = ODASchema
+        self._param_hash = None
 
     def _init_filters(
         self,
@@ -80,53 +121,32 @@ class DACSource:
         if self.years is not None:
             self.start = min(self.years)
             self.end = max(self.years)
-            self.add_filter(column=ODASchema.YEAR, predicate="in", value=self.years)
+            self._add_filter(column=self.schema.YEAR, predicate="in", value=self.years)
         else:
             self.start, self.end = None, None
 
         if self.providers is not None:
-            self.add_filter(
-                column=ODASchema.PROVIDER_CODE, predicate="in", value=self.providers
+            self._add_filter(
+                column=self.schema.PROVIDER_CODE, predicate="in", value=self.providers
             )
             self.de_providers = convert_dot_stat_to_data_explorer_codes(
                 codes=self.providers
             )
 
         if self.recipients is not None:
-            self.add_filter(
-                column=ODASchema.RECIPIENT_CODE, predicate="in", value=self.recipients
+            self._add_filter(
+                column=self.schema.RECIPIENT_CODE, predicate="in", value=self.recipients
             )
             self.de_recipients = convert_dot_stat_to_data_explorer_codes(
                 codes=self.recipients
             )
 
         if self.sectors is not None:
-            self.add_filter(
-                column=ODASchema.SECTOR_CODE, predicate="in", value=self.sectors
+            self._add_filter(
+                column=self.schema.SECTOR_CODE, predicate="in", value=self.sectors
             )
             self.de_sectors = check_strings(sectors)
 
-    def add_filter(self, column: str, predicate: str, value: str | int | list) -> None:
-        """Adds a filter to the dataset, ensuring no duplicate columns.
-
-        If a filter for the same column already exists, it is replaced with a warning.
-
-        Args:
-            column (str): The name of the column to filter.
-            predicate (str): The condition to apply (e.g., "in").
-            value (str | int | list): The value(s) to filter by.
-        """
-        existing_filter = next((f for f in self.filters if f[0] == column), None)
-
-        if existing_filter:
-            logger.warning(
-                f"A filter for {column} already exists. Replacing with new filter."
-            )
-
-        # Remove existing filter (if any) and add the new one
-        self.filters = [(c, p, v) for c, p, v in self.filters if c != column]
-        self.filters.append((column, predicate, value))
-
     def _get_filtered_download_filters(self):
         """Generates a dictionary of filters for downloading the dataset.
 
@@ -194,9 +214,16 @@ class DACSource:
 
         return cached_df
 
+    def _bulk_filename(self) -> Path:
+        return self.disk_cache.get_file_path(
+            dataset_name=self.__class__.__name__, param_hash=self._param_hash
+        )
+
     def _cache_dataset(self, param_hash: str, df: pd.DataFrame) -> None:
         """Caches the dataset in memory and on disk."""
-        self.memory_cache[param_hash] = df.copy(deep=True)
+        size = df.memory_usage(deep=True).sum() / (1024 * 1024)  # in MB
+        if size < 50:
+            self.memory_cache[param_hash] = df.copy(deep=True)
         self.disk_cache.save(self.__class__.__name__, param_hash, df)
 
     def _apply_query_and_cache(
@@ -245,6 +272,8 @@ class DACSource:
             else generate_param_hash(filters=filters)
         )
 
+        self._param_hash = param_hash
+
         # If caching is not active, clear the cache
         if not memory().store_backend:
             self.disk_cache.cleanup(hash_str=param_hash, force=True)
@@ -257,10 +286,17 @@ class DACSource:
 
         # If not cached, download the data
         if df is None:
-            df = self.download(bulk=using_bulk_download).pipe(clean_raw_df)
-            df = self._apply_query_and_cache(
-                df=df, query=query, param_hash=param_hash, bulk=using_bulk_download
-            )
+            df = self.download(bulk=using_bulk_download)
+            if df is None:
+                df = self._get_cached_dataset(
+                    param_hash=param_hash, filters=filters, columns=columns
+                )
+            else:
+                df = self._apply_query_and_cache(
+                    df=df, query=query, param_hash=param_hash, bulk=using_bulk_download
+                )
+
+        df = df.pipe(clean_raw_df)
 
         if columns:
             df = df.filter(columns)
@@ -295,8 +331,8 @@ class DAC1Data(DACSource):
         self.indicators = check_integers(indicators) if indicators else None
 
         if self.indicators is not None:
-            self.add_filter(
-                column=ODASchema.AIDTYPE_CODE, predicate="in", value=self.indicators
+            self._add_filter(
+                column=self.schema.AIDTYPE_CODE, predicate="in", value=self.indicators
             )
             self.de_indicators = check_strings(indicators)
 
@@ -322,6 +358,8 @@ class DAC1Data(DACSource):
 
 
 class DAC2AData(DACSource):
+    """Class to handle the DAC2A data."""
+
     def __init__(
         self,
         years: Optional[list[int] | range | int] = None,
@@ -343,8 +381,8 @@ class DAC2AData(DACSource):
         self.indicators = check_integers(indicators) if indicators else None
 
         if self.indicators is not None:
-            self.add_filter(
-                column=ODASchema.AIDTYPE_CODE, predicate="in", value=self.indicators
+            self._add_filter(
+                column=self.schema.AIDTYPE_CODE, predicate="in", value=self.indicators
             )
             self.de_indicators = check_strings(indicators)
 
@@ -389,6 +427,7 @@ class CRSData(DACSource):
         """
         super().__init__()
         self._init_filters(years=years, providers=providers, recipients=recipients)
+        self._param_hash = None
 
     def download(self, bulk: bool = True):
         """Downloads CRS data, either filtered or full dataset.
@@ -403,19 +442,16 @@ class CRSData(DACSource):
                 end_year=self.end,
                 filters=self._get_filtered_download_filters(),
             )
+            logger.info(f"CRS data downloaded successfully.")
+            return clean_raw_df(df)
+
         else:
             logger.info(
                 "The full, detailed CRS is only available as a large file (>1GB). "
                 "The package will now download the data, but it may take a while."
             )
-            df = bulk_download_crs()
-
-        # Clean the DataFrame
-        df = clean_raw_df(df)
-
-        logger.info(f"CRS data downloaded successfully.")
-
-        return df
+            bulk_download_crs(save_to_path=self._bulk_filename())
+            return None
 
 
 class MultiSystemData(DACSource):
@@ -447,8 +483,8 @@ class MultiSystemData(DACSource):
         self.indicators = check_strings(indicators) if indicators else None
 
         if self.indicators is not None:
-            self.add_filter(
-                column=ODASchema.AID_TO_THRU, predicate="in", value=self.indicators
+            self._add_filter(
+                column=self.schema.AID_TO_THRU, predicate="in", value=self.indicators
             )
             self.de_indicators = indicators
 
@@ -465,16 +501,105 @@ class MultiSystemData(DACSource):
                 end_year=self.end,
                 filters=self._get_filtered_download_filters(),
             )
+            logger.info(f"Multisystem data downloaded successfully.")
+            return clean_raw_df(df)
+
         else:
             logger.info(
                 "The full, detailed Multisystem is a large file (>1GB). "
                 "The package will now download the data, but it may take a while."
             )
-            df = bulk_download_multisystem()
+            bulk_download_multisystem(save_to_path=self._bulk_filename())
+            return None
+
+
+class AidDataSource(Source):
+    """Base class for accessing AidData datasets.
+
+    This class handles validation of parameters and manages the retrieval
+    of data in the form of a pandas DataFrame.
+    """
+
+    memory_cache = TTLCache(maxsize=20, ttl=6000)
+    disk_cache = OnDiskCache(config.ODAPaths.raw_data, ttl_seconds=86400)
+
+    def __init__(self):
+        super().__init__()
+
+        self.schema = AidDataSchema
+
+    def _init_filters(
+        self,
+        years: Optional[list[int] | range | int] = None,
+        recipients: Optional[list[str] | str] = None,
+        sectors: Optional[list[int] | int] = None,
+    ):
+        self.years = check_integers(years)
+        self.recipients = check_strings(recipients)
+        self.sectors = check_integers(sectors)
+
+        self.filters = []
+
+        if self.years is not None:
+            self.start = min(self.years)
+            self.end = max(self.years)
+            self._add_filter(
+                column=self.schema.COMMITMENT_YEAR, predicate="in", value=self.years
+            )
+        else:
+            self.start, self.end = None, None
+
+        if self.recipients is not None:
+            self._add_filter(
+                column=self.schema.RECIPIENT_NAME, predicate="in", value=self.recipients
+            )
+
+        if self.sectors is not None:
+            self._add_filter(
+                column=self.schema.SECTOR_CODE, predicate="in", value=self.sectors
+            )
+
+
+class AidDataData(AidDataSource):
+    """Class to handle the AidData data."""
+
+    memory_cache = TTLCache(maxsize=20, ttl=6000)
+    disk_cache = OnDiskCache(config.ODAPaths.raw_data, ttl_seconds=86400)
+
+    def __init__(
+        self,
+        years: Optional[list[int] | range | int] = None,
+        recipients: Optional[list[str] | str] = None,
+        sectors: Optional[list[int] | int] = None,
+    ):
+        """Initializes the AidData data handler.
+
+        Args:
+            years (Optional[list[int] | range | int]): Years to filter based on commitment year.
+            recipients (Optional[list[str] | str]): Recipient names to filter.
+            sectors (Optional[list[int] | int]): Sector codes to filter.
+        """
+        super().__init__()
+
+        self._init_filters(years=years, recipients=recipients, sectors=sectors)
+
+    def download(self, additional_filters: Optional[list[tuple]] = None):
+        """Downloads the full AidData dataset and applies filters.
+
+        Args:
+            additional_filters (Optional[list[tuple]], optional): Additional filters to apply. Defaults to None.
+        """
+
+        df = download_aiddata()
+
+        logger.info(f"Filtering the data")
+
+        self.filters = (
+            self.filters + additional_filters if additional_filters else self.filters
+        )
 
-        # Clean the DataFrame
-        df = clean_raw_df(df)
+        query = _filters_to_query(self.filters)
 
-        logger.info(f"Multisystem data downloaded successfully.")
+        df = df.query(query)
 
         return df

{oda_data-2.0.2 → oda_data-2.0.3}/oda_data/clean_data/schema.py

@@ -277,3 +277,143 @@ CRS_MAPPING: dict[str, str] = {
     "de_regioncode": ODASchema.RECIPIENT_REGION_CODE_DE,
     "incomegroup_name": ODASchema.RECIPIENT_INCOME,
 }
+
+
+@dataclass
+class AidDataSchema:
+    AIDDATA_ID: str = "aiddata_id"
+    RECOMMENDED_FOR_AGGREGATES: str = "recommended_for_aggregates"
+    AIDDATA_PARENT_ID: str = "aiddata_parent_id"
+    UMBRELLA: str = "umbrella"
+    PROVIDER_NAME: str = "donor_name"
+    RECIPIENT_NAME: str = "recipient_name"
+    RECIPIENT_ISO3: str = "recipient_iso3"
+    REGION_NAME: str = "region_name"
+    COMMITMENT_YEAR: str = "commitment_year"
+    IMPLEMENTATION_START_YEAR: str = "start_year"
+    COMPLETION_YEAR: str = "completion_year"
+    PROJECT_TITLE: str = "project_title"
+    LONG_DESCRIPTION: str = "long_description"
+    STAFF_COMMENTS: str = "staff_comments"
+    PROJECT_STATUS: str = "project_status"
+    PROJECT_INTENT: str = "project_intent"
+    FLOW_TYPE: str = "flow_type"
+    FLOW_TYPE_SIMPLIFIED: str = "flow_type_simplified"
+    ODA_CONCESSIONALITY_THRESHOLD: str = "oda_concessionality_threshold"
+    FLOW_CLASS: str = "flow_class"
+    SECTOR_CODE: str = "sector_code"
+    SECTOR_NAME: str = "sector_name"
+    INFRASTRUCTURE: str = "infrastructure"
+    COVID: str = "covid"
+    DONOR_AGENCIES_NAME: str = "donor_agencies_name"
+    DONOR_AGENCIES_TYPE: str = "donor_agencies_type"
+    CO_FINANCED: str = "co_financed"
+    CO_FINANCING_AGENCIES_NAME: str = "co_financing_agencies_name"
+    CO_FINANCING_AGENCIES_TYPE: str = "co_financing_agencies_type"
+    DIRECT_RECIPIENT_AGENCIES_NAME: str = "direct_recipient_agencies_name"
+    DIRECT_RECIPIENT_AGENCIES_TYPE: str = "direct_recipient_agencies_type"
+    INDIRECT_RECIPIENT_AGENCIES_NAME: str = "indirect_recipient_agencies_name"
+    INDIRECT_RECIPIENT_AGENCIES_TYPE: str = "indirect_recipient_agencies_type"
+    ON_LENDING: str = "on_lending"
+    IMPLEMENTING_AGENCIES_NAME: str = "implementing_agencies_name"
+    IMPLEMENTING_AGENCIES_TYPE: str = "implementing_agencies_type"
+    GUARANTEE_PROVIDED: str = "guarantee_provided"
+    GUARANTOR_NAME: str = "guarantor_name"
+    GUARANTOR_TYPE: str = "guarantor_type"
+    INSURANCE_PROVIDED: str = "insurance_provided"
+    INSURANCE_PROVIDER_NAME: str = "insurance_provider_name"
+    INSURANCE_PROVIDER_TYPE: str = "insurance_provider_type"
+    COLLATERALIZED: str = "collateralized"
+    COLLATERAL_PROVIDER_NAME: str = "collateral_provider_name"
+    COLLATERAL_PROVIDER_TYPE: str = "collateral_provider_type"
+    COLLATERAL_AGENT_NAME: str = "collateral_agent_name"
+    COLLATERAL_AGENT_TYPE: str = "collateral_agent_type"
+    COLLATERAL: str = "collateral"
+    VALUE_ORIGINAL_CURRENCY: str = "commitment_original_currency"
+    ORIGINAL_CURRENCY: str = "original_currency"
+    VALUE_ESTIMATED: str = "amount_estimated"
+    VALUE_CONSTANT_USD_2021: str = "usd_commitment_constant"
+    VALUE_CURRENT_USD: str = "usd_commitment"
+    ADJUSTED_VALUE_ORIGINAL_CURRENCY: str = "adjustment_original_currency"
+    ADJUSTED_VALUE_CONSTANT_USD_2021: str = "usd_adjustment_constant"
+    ADJUSTED_VALUE_CURRENT_2021: str = "usd_adjustment"
+    FINANCIAL_DISTRESS: str = "financial_distress"
+    COMMITMENT_DATE: str = "commitment_date"
+    COMMITMENT_DATE_ESTIMATED: str = "commitment_date_estimated"
+    PLANNED_IMPLEMENTATION_DATE: str = "expected_start_date"
+    ACTUAL_IMPLEMENTATION_DATE: str = "actual_start_date"
+    ACTUAL_IMPLEMENTATION_DATE_ESTIMATED: str = "actual_start_date_estimated"
+    DEVIATION_PLANNED_ACTUAL_IMPLEMENTATION_DATE: str = (
+        "deviation_expected_actual_start_date"
+    )
+    PLANNED_COMPLETION_DATE: str = "expected_completion_date"
+    ACTUAL_COMPLETION_DATE: str = "actual_completion_date"
+    ACTUAL_COMPLETION_DATE_ESTIMATED: str = "actual_completion_date_estimated"
+    DEVIATION_PLANNED_ACTUAL_COMPLETION_DATE: str = (
+        "deviation_expected_actual_completion_date"
+    )
+    MATURITY: str = "maturity"
+    INTEREST_RATE: str = "interest_rate"
+    GRACE_PERIOD: str = "grace_period"
+    MANAGEMENT_FEE: str = "management_fee"
+    COMMITMENT_FEE: str = "commitment_fee"
+    INSURANCE_FEE_PERCENT: str = "insurance_fee_percent"
+    INSURANCE_FEE_CURRENT_USD: str = "insurance_fee_usd"
+    DEFAULT_INTEREST_RATE: str = "default_interest_rate"
+    FIRST_LOAN_REPAYMENT_DATE: str = "repaydate1"
+    LAST_LOAN_REPAYMENT_DATE: str = "repaydate2"
+    GRANT_ELEMENT_FLOW: str = "grant_element_flow"
+    GRANT_ELEMENT_GRANT_EQUIVALENT: str = "grant_element_grant_equiv"
+    GRANT_ELEMENT_IMF: str = "grant_element_imf"
+    NUMBER_OF_LENDERS: str = "number_of_lenders"
+    EXPORT_BUYERS_CREDIT: str = "export_buyers_credit"
+    SUPPLIERS_CREDIT_EXPORT_SELLERS_CREDIT: str = (
+        "suppliers_credit_export_sellers_credit"
+    )
+    INTEREST_FREE_LOAN: str = "interest_free_loan"
+    REFINANCING: str = "refinancing"
+    INVESTMENT_PROJECT_LOAN: str = "investment_project_loan"
+    M_A: str = "ma"
+    WORKING_CAPITAL: str = "working_capital"
+    EPCF: str = "epcf"
+    LEASE: str = "lease"
+    FXSL_BOP: str = "fxsl_bop"
+    CC_IRS: str = "cc_irs"
+    RCF: str = "rcf"
+    GCL: str = "gcl"
+    PBC: str = "pbc"
+    PXF_COMMODITY_PREPAYMENT: str = "pxf_commodity_prepayment"
+    INTER_BANK_LOAN: str = "inter_bank_loan"
+    OVERSEAS_PROJECT_CONTRACTING_LOAN: str = "overseas_project_contracting_loan"
+    DPA: str = "dpa"
+    PROJECT_FINANCE: str = "project_finance"
+    INVOLVING_MULTILATERAL: str = "involving_multilateral"
+    NON_CHINESE_FINANCIER: str = "non_chinese_financier"
+    SHORT_TERM: str = "short_term"
+    RESCUE: str = "rescue"
+    PROJECT_JV_SPV_HOST_GOVERNMENT_OWNERSHIP: str = (
+        "project_jv_spv_host_government_ownership"
+    )
+    PROJECT_JV_SPV_CHINESE_GOVERNMENT_OWNERSHIP: str = (
+        "project_jv_spv_chinese_government_ownership"
+    )
+    LEVEL_OF_PUBLIC_LIABILITY: str = "level_of_public_liability"
+    TOTAL_SOURCE_COUNT: str = "total_source_count"
+    OFFICIAL_SOURCE_COUNT: str = "official_source_count"
+    SOURCE_URLS: str = "source_urls"
+    SOURCE_TITLES: str = "source_titles"
+    SOURCE_PUBLISHERS: str = "source_publishers"
+    SOURCE_RESOURCE_TYPES: str = "source_resource_types"
+    CONTACT_NAME: str = "contact_name"
+    CONTACT_POSITION: str = "contact_position"
+    ODA_ELIGIBLE_RECIPIENT: str = "oda_eligible_recipient"
+    INCOME_GROUP_NAME: str = "income_group_name"
+    LOCATION_NARRATIVE: str = "location_narrative"
+    GEOGRAPHIC_PRECISION_LEVEL: str = "geographic_precision_level"
+    ADM1_LEVEL_AVAILABLE: str = "adm1_level_available"
+    ADM2_LEVEL_AVAILABLE: str = "adm2_level_available"
+    GEOSPATIAL_FEATURE_AVAILABLE: str = "geospatial_feature_available"
+    SOURCE_QUALITY: str = "source_quality"
+    DATA_COMPLETENESS: str = "data_completeness"
+    IMPLEMENTATION_DETAIL: str = "implementation_detail"
+    LOAN_DETAIL: str = "loan_detail"

{oda_data-2.0.2 → oda_data-2.0.3}/oda_data/config.py

@@ -9,7 +9,7 @@ class ODAPaths:
     raw_data = scripts / ".raw_data"
     pydeflate = raw_data / ".pydeflate"
     indicators = scripts / "indicators"
-    names = scripts/ "tools"/ "names"
+    names = scripts / "tools" / "names"
     cleaning = scripts / "clean_data"
     settings = scripts / "settings"
     sectors = indicators / "sectors"

{oda_data-2.0.2 → oda_data-2.0.3}/oda_data/indicators/dac1/common.py

@@ -36,5 +36,3 @@ def dac1_aid_name_mapping() -> dict[int, str]:
     file_path = ODAPaths.settings / "dac1_aid_flow_types.json"
     mapping = load_json_file(file_path)
     return {int(k): v["aidtype_name"] for k, v in mapping.items()}
-
-

{oda_data-2.0.2 → oda_data-2.0.3}/oda_data/indicators/dac1/one.py

@@ -76,7 +76,7 @@ def core_oda() -> Indicator:
         code="ONE.10.1010C",
         name="Total Core ODA (ONE Definition)",
         description="Official Development Assistance (ODA) excluding in-donor spending but"
-                    "including administrative costs.",
+        "including administrative costs.",
         sources=["DAC1"],
         filters={
             "DAC1": {

{oda_data-2.0.2 → oda_data-2.0.3}/oda_data/tools/compatibility.py

@@ -49,7 +49,7 @@ class ODAData:
                 currency=self.currency,
                 base_year=self.base_year,
                 use_bulk_download=self.use_bulk_download
-                                  | self._mapping[indicator]["bulk"],
+                | self._mapping[indicator]["bulk"],
             ).get_indicators(indicators=self._mapping[indicator]["indicator"])
 
             self.indicators[indicator] = indicator_data

{oda_data-2.0.2 → oda_data-2.0.3}/oda_data/tools/names/create_mapping.py

@@ -172,4 +172,4 @@ def get_merged_names_mapping():
     # Remove keys with empty dictionaries
     merged_mapping = {k: v for k, v in merged_mapping.items() if v}
 
-    return merged_mapping
+    return merged_mapping

oda_data-2.0.3/pyproject.toml

@@ -0,0 +1,35 @@
+[tool.poetry]
+name = "oda_data"
+version = "2.0.3"
+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-2.0.2/pyproject.toml

@@ -1,31 +0,0 @@
-[project]
-name = "oda_data"
-version = "2.0.2"
-description = "A python package to work with Official Development Assistance data from the OECD DAC."
-readme = "README.md"
-authors = [{ name = "Jorge Rivera", email = "jorge.rivera@one.org" }, { name = "Miguel Haro Ruiz", email = "miguel.haroruiz@one.org" }]
-requires-python = ">=3.10, <4.0"
-dependencies = ["pandas >=2",
-    "thefuzz >=0.22.1",
-    "pyarrow >=14, <20",
-    "oda-reader >=1.1.3",
-    "pydeflate >=2.0.1",
-    "cachetools (>=5.5.1,<6.0.0)"]
-
-[project.optional-dependencies]
-dev = ["black >=24",
-    "pytest >=8",
-    "pytest-cov >=4.0.0",
-    "pytest-mock >=3.10.0"]
-
-[tool.poetry-dynamic-versioning]
-enable = true
-style = "pep440"
-
-[project.urls]
-Homepage = "https://github.com/ONEcampaign/oda_data_package"
-Bug_Tracker = "https://github.com/ONEcampaign/oda_data_package/issues"
-
-[build-system]
-requires = ["poetry-core>=2.0.0,<3.0.0"]
-build-backend = "poetry.core.masonry.api"