"""Join actual CPI observations with sector returns relative to SPY, then compare descriptive relationships across the sample.

Research example. Live observations can change.
"""

from datetime import UTC, datetime
from decimal import Decimal
from textwrap import fill

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd

AS_OF = datetime.now(UTC).date()
NAVY, BLUE, PINK = "#132244", "#8fb9ff", "#e7a2cc"


def fetch(qj):
    return {
        "cpi": qj.fred.get_fred_data_series_by_id(
            search_id="CPIAUCSL", start="2020-01-01", end="2025-12-31", frequency="m"
        ),
        "prices": qj.eod.get_historical_prices(
            symbols=["SPY", "XLE", "XLK", "XLF", "XLU", "XLP", "XLY"],
            start_date="2020-01-01",
            end_date="2025-12-31",
            frequency="1d",
        ),
    }


def analyze(raw):
    cpi = macro(raw["cpi"], "CPIAUCSL").resample(pd.offsets.MonthEnd()).last()
    inflation = (100 * (cpi / cpi.shift(12) - 1)).rename("CPI YoY %")
    returns = {}
    for symbol in ["SPY", "XLE", "XLK", "XLF", "XLU", "XLP", "XLY"]:
        monthly = history(raw["prices"], symbol)["price"].resample(pd.offsets.MonthEnd()).last()
        returns[symbol] = change(monthly)
    joined = pd.DataFrame(returns).join(inflation, how="inner").dropna()
    if len(joined) < 24:
        raise ValueError("Need at least 24 common macro and return observations")
    rows = []
    for symbol in ["XLE", "XLK", "XLF", "XLU", "XLP", "XLY"]:
        relative = joined[symbol] - joined["SPY"]
        correlation = relative.corr(joined["CPI YoY %"])
        rows.append({"Sector ETF": symbol, "Correlation": correlation, "Months": len(joined)})
    result = pd.DataFrame(rows).sort_values("Correlation")
    fig, (ax,) = canvas("Inflation · sector-relative relationships", "Sector ETF")
    ax.barh(result["Sector ETF"], result["Correlation"], color=[PINK if v < 0 else BLUE for v in result["Correlation"]])
    ax.axvline(0, color="#afc1dc", lw=0.8)
    ax.set_xlabel("Correlation with CPI YoY · sector return minus SPY return")
    return result, fig


def payload(response):
    if hasattr(response, "to_dict"):
        response = response.to_dict()
    while isinstance(response, dict):
        if response.get("error") or response.get("error_code") or response.get("success") is False:
            raise ValueError("Provider request failed")
        if "data" in response:
            response = response["data"]
        elif "value" in response:
            response = response["value"]
        else:
            break
    return response


def frame(response, date="date"):
    rows = payload(response)
    if not isinstance(rows, list) or not rows:
        raise ValueError("No provider observations returned")
    result = pd.DataFrame(rows)
    if date:
        result[date] = pd.to_datetime(result[date], utc=True)
        result = result.sort_values(date)
    return result


def decimal(value):
    if pd.isna(value):
        raise ValueError("Required monetary value or quantity is missing")
    return Decimal(str(value))


def ratio(numerator, denominator):
    denominator = decimal(denominator)
    if denominator == 0:
        raise ValueError("Required denominator is zero")
    return float(decimal(numerator) / denominator)


def change(values, periods=1):
    previous = values.shift(periods)
    return pd.Series(
        [ratio(x, y) - 1 if pd.notna(x) and pd.notna(y) else np.nan for x, y in zip(values, previous, strict=True)],
        index=values.index,
    )


def history(response, symbol, adjusted=True):
    values = payload(response)
    if not isinstance(values, dict) or symbol not in values:
        raise ValueError(f"No price coverage for {symbol}")
    result = frame(values[symbol]).set_index("date")
    field = "adjusted_close" if adjusted else "close"
    result["price"] = result[field].map(decimal)
    result["volume"] = result["volume"].map(decimal)
    if result.index.has_duplicates:
        raise ValueError("Duplicate trading dates")
    return result


def macro(response, column):
    values = frame(response).set_index("date")[column]
    values = pd.to_numeric(values, errors="coerce").dropna()
    if values.empty:
        raise ValueError(f"No numeric observations for {column}")
    return values


def canvas(title, ylabel, panels=1):
    plt.rcParams.update(
        {
            "figure.facecolor": NAVY,
            "axes.facecolor": NAVY,
            "savefig.facecolor": NAVY,
            "text.color": "#e9eef8",
            "axes.labelcolor": "#afc1dc",
            "xtick.color": "#afc1dc",
            "ytick.color": "#afc1dc",
            "axes.edgecolor": "#34486b",
            "grid.color": "#34486b",
            "font.size": 10,
            "axes.prop_cycle": plt.cycler(color=[BLUE, PINK, "#ba9dea"]),
        }
    )
    fig, axes = plt.subplots(panels, 1, figsize=(9, 6.1), squeeze=False, layout="constrained")
    fig.suptitle(fill(title, width=58), fontsize=17, x=0.04, ha="left", weight="medium")
    for ax in axes.flat:
        ax.grid(axis="y", alpha=0.45)
        ax.set_axisbelow(True)
        ax.spines[["top", "right"]].set_visible(False)
    axes.flat[0].set_ylabel(ylabel)
    return fig, list(axes.flat)


def run():
    from quantjourney.sdk import QuantJourneyAPI

    qj = QuantJourneyAPI.from_env()
    raw = fetch(qj)
    table, fig = analyze(raw)
    print(table.to_string(index=False))
    fig.savefig(OUTPUT, dpi=180)
    plt.show()


OUTPUT = "sdk_inflation.png"

if __name__ == "__main__":
    run()