Source code for kaxanuk.attribution_analysis.modules.table_conversion

"""
Conversion utilities for bridging PyArrow tables to pandas DataFrames.

Provides functions to convert PyArrow tables produced by the market data
and portfolio pipelines into pandas DataFrames with proper datetime indexing,
as well as a standalone returns computation function.
"""

import pandas as pd
import pyarrow as pa




def pyarrow_table_to_pandas(
    table: pa.Table,
    date_column: str,
) -> pd.DataFrame:
    df = table.to_pandas()
    df[date_column] = pd.to_datetime(df[date_column])
    df = df.set_index(date_column)
    df.index.name = None

    # Convert decimal.Decimal columns (from PyArrow decimal256) to float64
    # so downstream pandas arithmetic (*, +, etc.) works with native floats
    numeric_cols = df.columns
    df[numeric_cols] = df[numeric_cols].astype(float)

    return df





def portfolio_table_to_pandas(table: pa.Table) -> pd.DataFrame:
    df = table.to_pandas()
    df = df.set_index("Ticker").T
    try:
        df.index = pd.to_datetime(df.index, format='%Y-%m-%d')
    except (ValueError, TypeError):
        df.index = pd.to_datetime(df.index, format="%d/%m/%Y")

    df.index.name = None
    return df.astype(float)





def compute_returns_from_prices(price_df: pd.DataFrame) -> pd.DataFrame:
    returns = price_df.pct_change(fill_method=None)
    return returns.dropna(axis='columns', how='all')