pydeflate 2.0.1__tar.gz → 2.1.0__tar.gz

{pydeflate-2.0.1 → pydeflate-2.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pydeflate
-Version: 2.0.1
+Version: 2.1.0
 Summary: Package to convert current prices figures to constant prices and vice versa
 License: MIT
 Author: Jorge Rivera

{pydeflate-2.0.1 → pydeflate-2.1.0}/pydeflate/__init__.py

@@ -1,5 +1,5 @@
 __author__ = """Jorge Rivera"""
-__version__ = "2.0.1"
+__version__ = "2.1.0"
 
 from pydeflate.deflate.deflators import (
     oecd_dac_deflate,
@@ -12,7 +12,12 @@ from pydeflate.deflate.deflators import (
 )
 
 from pydeflate.deflate.legacy_deflate import deflate
-from pydeflate.exchange.exchangers import oecd_dac_exchange, wb_exchange, imf_exchange
+from pydeflate.exchange.exchangers import (
+    oecd_dac_exchange,
+    wb_exchange,
+    wb_exchange_ppp,
+    imf_exchange,
+)
 from pydeflate.pydeflate_config import setup_logger
 
 

{pydeflate-2.0.1 → pydeflate-2.1.0}/pydeflate/core/api.py

@@ -77,7 +77,9 @@ def _base_operation(
     )
 
     # Flag missing data
-    flag_missing_pydeflate_data(base_obj._unmatched_data)
+    flag_missing_pydeflate_data(
+        base_obj._unmatched_data, entity_column=entity_column, year_column=year_column
+    )
     x = base_obj._merged_data[value_column]
     y = base_obj._merged_data[
         "pydeflate_EXCHANGE" if exchange else "pydeflate_deflator"

{pydeflate-2.0.1 → pydeflate-2.1.0}/pydeflate/core/exchange.py

@@ -37,8 +37,6 @@ class Exchange:
             self.exchange_data = self.exchange_rate(
                 self.source_currency, self.target_currency
             )
-            if self.source_currency == "USA":
-                self.exchange_data["pydeflate_EXCHANGE_D"] = 1
 
     def _get_exchange_rate(self, currency):
         """Helper function to fetch exchange rates for a given currency."""

{pydeflate-2.0.1 → pydeflate-2.1.0}/pydeflate/core/source.py

@@ -5,7 +5,7 @@ import pandas as pd
 from pydeflate.sources.common import AvailableDeflators
 from pydeflate.sources.dac import read_dac
 from pydeflate.sources.imf import read_weo
-from pydeflate.sources.world_bank import read_wb
+from pydeflate.sources.world_bank import read_wb, read_wb_lcu_ppp, read_wb_usd_ppp
 
 
 @dataclass
@@ -49,6 +49,15 @@ class WorldBank(Source):
         super().__init__(name="World Bank", reader=read_wb, update=update)
 
 
+class WorldBankPPP(Source):
+    def __init__(self, update: bool = False, *, from_lcu: bool = True):
+        super().__init__(
+            name="World Bank PPP",
+            reader=read_wb_lcu_ppp if from_lcu else read_wb_usd_ppp,
+            update=update,
+        )
+
+
 class DAC(Source):
     def __init__(self, update: bool = False):
         super().__init__(name="DAC", reader=read_dac, update=update)

{pydeflate-2.0.1 → pydeflate-2.1.0}/pydeflate/exchange/exchangers.py

@@ -1,9 +1,10 @@
 from functools import wraps
 
 import pandas as pd
+from frictionless.console.common import source
 
 from pydeflate.core.api import BaseExchange
-from pydeflate.core.source import DAC, WorldBank, IMF
+from pydeflate.core.source import DAC, WorldBank, IMF, WorldBankPPP
 
 
 def _generate_docstring(source_name: str) -> str:
@@ -28,26 +29,33 @@ def _generate_docstring(source_name: str) -> str:
     )
 
 
-def _exchange(exchange_source_cls):
+def _exchange(exchange_source_cls, **fixed_params):
     """Decorator to create exchange wrappers with specific source"""
 
     def decorator(func):
         @wraps(func)
-        def wrapper(
-            data: pd.DataFrame,
-            *,
-            source_currency: str = "USA",
-            target_currency: str = "USA",
-            id_column: str = "iso_code",
-            year_column: str = "year",
-            use_source_codes: bool = False,
-            value_column: str = "value",
-            target_value_column: str = "value",
-            reversed_: bool = False,
-            year_format: str | None = None,
-            update_rates: bool = False,
-        ):
+        def wrapper(data: pd.DataFrame, **kwargs):
             # Validate input parameters
+            for param in fixed_params:
+                if param in kwargs:
+                    raise ValueError(
+                        f"The parameter '{param}' cannot be passed to this function."
+                    )
+            # set fixed parameters
+            kwargs.update(fixed_params)
+
+            # Unpack the parameters
+            source_currency = kwargs.get("source_currency", "USA")
+            target_currency = kwargs.get("target_currency", "USA")
+            id_column = kwargs.get("id_column", "iso_code")
+            year_column = kwargs.get("year_column", "year")
+            use_source_codes = kwargs.get("use_source_codes", False)
+            value_column = kwargs.get("value_column", "value")
+            target_value_column = kwargs.get("target_value_column", "value")
+            reversed_ = kwargs.get("reversed_", False)
+            year_format = kwargs.get("year_format", None)
+            update_rates = kwargs.get("update_rates", False)
+
             if not isinstance(data, pd.DataFrame):
                 raise ValueError("The 'data' parameter must be a pandas DataFrame.")
 
@@ -68,7 +76,14 @@ def _exchange(exchange_source_cls):
             to_exchange = data.copy()
 
             # Initialize the deflator source
-            source = exchange_source_cls(update=update_rates)
+            if exchange_source_cls.__name__ == "WorldBankPPP":
+                source = exchange_source_cls(
+                    update=update_rates,
+                    from_lcu=False if source_currency == "USA" else True,
+                )
+                source_currency = "LCU" if source_currency == "USA" else source_currency
+            else:
+                source = exchange_source_cls(update=update_rates)
 
             # Create a deflator object
             exchange = BaseExchange(
@@ -130,6 +145,22 @@ def wb_exchange(
 ) -> pd.DataFrame: ...
 
 
+@_exchange(WorldBankPPP, target_currency="PPP")
+def wb_exchange_ppp(
+    data: pd.DataFrame,
+    *,
+    source_currency: str = "USA",
+    id_column: str = "iso_code",
+    year_column: str = "year",
+    use_source_codes: bool = False,
+    value_column: str = "value",
+    target_value_column: str = "value",
+    reversed_: bool = False,
+    year_format: str | None = None,
+    update_rates: bool = False,
+) -> pd.DataFrame: ...
+
+
 @_exchange(IMF)
 def imf_exchange(
     data: pd.DataFrame,

{pydeflate-2.0.1 → pydeflate-2.1.0}/pydeflate/sources/common.py

@@ -21,7 +21,7 @@ def check_file_age(file: Path) -> int:
     """
     current_date = datetime.today()
     # Extract date from the filename (format: weo_YYYY-MM-DD.parquet)
-    file_date = datetime.strptime(file.stem.split("_")[1], "%Y-%m-%d")
+    file_date = datetime.strptime(file.stem.split("_")[-1], "%Y-%m-%d")
 
     # Return the difference in days between today and the file's date
     return (current_date - file_date).days

{pydeflate-2.0.1 → pydeflate-2.1.0}/pydeflate/sources/world_bank.py

@@ -21,6 +21,18 @@ _INDICATORS: dict = {
     "PA.NUS.FCRF": "EXCHANGE",  # Official Exchange Rate
 }
 
+_INDICATORS_LCU_PPP: dict = {
+    "NY.GDP.DEFL.ZS": "NGDP_D",  # GDP Deflator (Index)
+    "NY.GDP.DEFL.ZS.AD": "NGDP_DL",  # GDP Deflator linked series
+    "PA.NUS.PPP": "EXCHANGE",  # PPP conversion factor
+}
+
+_INDICATORS_USD_PPP: dict = {
+    "NY.GDP.DEFL.ZS": "NGDP_D",  # GDP Deflator (Index)
+    "NY.GDP.DEFL.ZS.AD": "NGDP_DL",  # GDP Deflator linked series
+    "PA.NUS.PPPC.RF": "EXCHANGE",  # PPP conversion factor to market exchange rate
+}
+
 
 def get_wb_indicator(series: str, value_name: str | None = None) -> pd.DataFrame:
     """Fetch a World Bank indicator and transform it into a cleaned DataFrame.
@@ -126,7 +138,28 @@ def _parallel_download_indicators(indicators: dict) -> list[pd.DataFrame]:
     return dfs
 
 
-def download_wb() -> None:
+def _add_ppp_ppp_exchange(df: pd.DataFrame) -> pd.DataFrame:
+    """
+    Add the PPP exchange rate to the DataFrame.
+
+    Args:
+        df: pd.DataFrame: The DataFrame containing the World Bank data.
+
+    Returns:
+        pd.DataFrame: The DataFrame with the PPP exchange rates
+
+    """
+    ppp = df.loc[lambda d: d["entity_code"] == "USA"].copy()
+    ppp[["entity_code", "entity", "pydeflate_iso3"]] = "PPP"
+
+    df = pd.concat([df, ppp], ignore_index=True)
+
+    return df
+
+
+def _download_wb(
+    indicators: dict, prefix: str = "wb", add_ppp_exchange: bool = False
+) -> None:
     """Download multiple World Bank indicators in parallel and save as a parquet file.
 
     This function fetches all indicators defined in _INDICATORS in parallel, concatenates
@@ -134,7 +167,7 @@ def download_wb() -> None:
     """
     logger.info("Downloading the latest World Bank data...")
 
-    indicators_data = _parallel_download_indicators(indicators=_INDICATORS)
+    indicators_data = _parallel_download_indicators(indicators=indicators)
 
     # Concatenate all DataFrames horizontally (by columns)
     df = pd.concat(indicators_data, axis=1).reset_index()
@@ -145,7 +178,13 @@ def download_wb() -> None:
         .pipe(compute_exchange_deflator, base_year_measure="NGDP_D")
         .assign(pydeflate_iso3=lambda d: d.entity_code)
         .sort_values(by=["year", "entity_code"])
-        .pipe(prefix_pydeflate_to_columns)
+    )
+
+    if add_ppp_exchange:
+        df = df.pipe(_add_ppp_ppp_exchange)
+
+    df = (
+        df.pipe(prefix_pydeflate_to_columns)
         .pipe(enforce_pyarrow_types)
         .reset_index(drop=True)
     )
@@ -154,10 +193,29 @@ def download_wb() -> None:
     suffix = today()
 
     # Save the DataFrame as a parquet file
-    output_path = PYDEFLATE_PATHS.data / f"wb_{suffix}.parquet"
+    output_path = PYDEFLATE_PATHS.data / f"{prefix}_{suffix}.parquet"
     df.to_parquet(output_path)
 
-    logger.info(f"Saved World Bank data to wb_{suffix}.parquet")
+    logger.info(f"Saved World Bank data to {prefix}_{suffix}.parquet")
+
+
+def download_wb() -> None:
+    """Download the latest World Bank data."""
+    _download_wb(indicators=_INDICATORS, prefix="wb")
+
+
+def download_wb_lcu_ppp() -> None:
+    """Download the latest World Bank data (PPP)."""
+    _download_wb(
+        indicators=_INDICATORS_LCU_PPP, prefix="wb_lcu_ppp", add_ppp_exchange=True
+    )
+
+
+def download_wb_usd_ppp() -> None:
+    """Download the latest World Bank data (PPP)."""
+    _download_wb(
+        indicators=_INDICATORS_USD_PPP, prefix="wb_usd_ppp", add_ppp_exchange=True
+    )
 
 
 def _find_wb_files_in_path(path: Path) -> list:
@@ -169,7 +227,31 @@ def _find_wb_files_in_path(path: Path) -> list:
     Returns:
         list: List of WB parquet files found in the directory.
     """
-    return list(path.glob("wb_*.parquet"))
+    return list(path.glob(f"wb_*.parquet"))
+
+
+def _find_wb_lcu_ppp_files_in_path(path: Path) -> list:
+    """Find all WB PPP parquet files in the specified directory.
+
+    Args:
+        path (Path): The directory path to search for WB parquet files.
+
+    Returns:
+        list: List of WB parquet files found in the directory.
+    """
+    return list(path.glob(f"wb_lcu_ppp_*.parquet"))
+
+
+def _find_wb_usd_ppp_files_in_path(path: Path) -> list:
+    """Find all WB PPP parquet files in the specified directory.
+
+    Args:
+        path (Path): The directory path to search for WB parquet files.
+
+    Returns:
+        list: List of WB parquet files found in the directory.
+    """
+    return list(path.glob(f"wb_usd_ppp_*.parquet"))
 
 
 def read_wb(update: bool = False) -> pd.DataFrame:
@@ -182,5 +264,27 @@ def read_wb(update: bool = False) -> pd.DataFrame:
     )
 
 
+def read_wb_lcu_ppp(update: bool = False) -> pd.DataFrame:
+    """Read the latest World Bank data from parquet files or download fresh data."""
+    return read_data(
+        file_finder_func=_find_wb_lcu_ppp_files_in_path,
+        download_func=download_wb_lcu_ppp,
+        data_name="World Bank",
+        update=update,
+    )
+
+
+def read_wb_usd_ppp(update: bool = False) -> pd.DataFrame:
+    """Read the latest World Bank data from parquet files or download fresh data."""
+    return read_data(
+        file_finder_func=_find_wb_usd_ppp_files_in_path,
+        download_func=download_wb_usd_ppp,
+        data_name="World Bank",
+        update=update,
+    )
+
+
 if __name__ == "__main__":
-    df = read_wb(True)
+    df_wb = read_wb(False)
+    df_usd = read_wb_usd_ppp(False)
+    df_lcu = read_wb_lcu_ppp(False)

{pydeflate-2.0.1 → pydeflate-2.1.0}/pydeflate/utils.py

@@ -35,6 +35,7 @@ def clean_number(number):
 
     return float(number)
 
+
 def create_pydeflate_year(
     data: pd.DataFrame, year_column: str, year_format: str | None = None
 ) -> pd.DataFrame:
@@ -84,17 +85,21 @@ def get_matched_pydeflate_data(
     )
 
 
-def flag_missing_pydeflate_data(unmatched_data: pd.DataFrame):
+def flag_missing_pydeflate_data(
+    unmatched_data: pd.DataFrame, entity_column: str, year_column: str
+):
     """Flag data which is present in the input data but missing in pydeflate's data."""
     if unmatched_data.empty:
         return
-
     missing = (
-        unmatched_data.drop_duplicates()
-        .dropna(axis=1)
-        .drop(columns="_merge")
-        .to_string(index=False)
+        unmatched_data.filter([entity_column, year_column])
+        .drop_duplicates()
+        .groupby(entity_column)[year_column]
+        .apply(lambda x: ", ".join(map(str, sorted(x))))
+        .to_dict()
     )
 
+    missing_str = "\n".join(f"{entity}: {years}" for entity, years in missing.items())
+
     # log all missing data
-    logger.info(f"Missing exchange data for:\n {missing}")
+    logger.info(f"Missing exchange data for:\n{missing_str}")

{pydeflate-2.0.1 → pydeflate-2.1.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "pydeflate"
-version = "2.0.1"
+version = "2.1.0"
 description = "Package to convert current prices figures to constant prices and vice versa"
 authors = ["Jorge Rivera <jorge.rivera@one.org>"]
 license = "MIT"