"""
reconcile_all_500.py
Fills 100% of the HIFFI 500 cohort with verified sales or mathematically derived SEA.
Uses YouTube lifetime catalog views (1 Album Unit = 3,750 views) for uncertified acts.
"""

from pathlib import Path
import math
import pandas as pd
import numpy as np

DATA_PATH = Path("data/hiffi_multiplatform_500.csv")


def clean_num(val) -> float:
    if pd.isna(val) or val is None:
        return 0.0
    try:
        f = float(val)
        return 0.0 if math.isnan(f) else f
    except (ValueError, TypeError):
        return 0.0


def reconcile_entire_cohort():
    if not DATA_PATH.exists():
        print(f"File not found: {DATA_PATH}")
        return

    df = pd.read_csv(DATA_PATH)
    print(f"Processing all {len(df)} artists in master catalog...")

    for idx, row in df.iterrows():
        status = str(row.get("sales_data_status", "")).strip()
        eas_val = clean_num(row.get("total_eas_cspc"))
        album_u = clean_num(row.get("riaa_certified_album_units"))
        singles_u = clean_num(row.get("riaa_certified_singles_units"))
        sp_listeners = clean_num(row.get("spotify_monthly_listeners"))
        yt_views = clean_num(row.get("lifetime_views"))

        # Case 1: ChartMasters Verified (Do not modify)
        if status == "VERIFIED_CSPC":
            continue

        # Case 2: RIAA Verified (Keep RIAA status and ensure EAS reflects awards)
        elif status == "VERIFIED_RIAA" or (album_u > 0 or singles_u > 0):
            df.at[idx, "sales_data_status"] = "VERIFIED_RIAA"
            if eas_val == 0.0:
                if album_u > 0:
                    df.at[idx, "total_eas_cspc"] = album_u
                    df.at[idx, "pure_album_sales"] = album_u
                else:
                    df.at[idx, "total_eas_cspc"] = singles_u / 10.0
                    df.at[idx, "digital_singles_sales"] = singles_u

        # Case 3: Spotify Stream Conversion
        elif sp_listeners > 0.0:
            sea_units = float(round((sp_listeners * 36.0) / 1500.0))
            df.at[idx, "streaming_eas"] = sea_units
            df.at[idx, "total_eas_cspc"] = sea_units
            df.at[idx, "sales_data_status"] = "ESTIMATED_SEA"

        # Case 4: YouTube Lifetime Views Conversion (Billboard/Luminate Video Formula)
        elif yt_views > 0.0:
            # 3,750 on-demand ad-supported streams = 1 Album Unit
            sea_units = float(round(yt_views / 3750.0))
            # Floor safety to prevent 0
            sea_units = max(sea_units, 1000.0)
            df.at[idx, "streaming_eas"] = sea_units
            df.at[idx, "total_eas_cspc"] = sea_units
            df.at[idx, "sales_data_status"] = "ESTIMATED_SEA"

        # Case 5: Developing Floor Anchor
        else:
            subs = clean_num(row.get("subscriber_count"))
            sea_units = float(round(max(subs * 0.5, 500.0)))
            df.at[idx, "streaming_eas"] = sea_units
            df.at[idx, "total_eas_cspc"] = sea_units
            df.at[idx, "sales_data_status"] = "ESTIMATED_SEA"

    # Ensure total_eas_cspc has no NaNs
    df["total_eas_cspc"] = df["total_eas_cspc"].fillna(0.0)

    # Re-calculate Cohort Sales Rank across all 500 artists
    df["cohort_sales_rank"] = df["total_eas_cspc"].rank(ascending=False, method="min").astype(int)

    df.to_csv(DATA_PATH, index=False)

    print("\n==========================================")
    print("ALL 500 ARTISTS SUCCESSFULLY CATALOGED!")
    print(f"VERIFIED_CSPC: {(df['sales_data_status'] == 'VERIFIED_CSPC').sum()}")
    print(f"VERIFIED_RIAA: {(df['sales_data_status'] == 'VERIFIED_RIAA').sum()}")
    print(f"ESTIMATED_SEA: {(df['sales_data_status'] == 'ESTIMATED_SEA').sum()}")
    print(f"Unresolved / Pending: {((df['sales_data_status'] != 'VERIFIED_CSPC') & (df['sales_data_status'] != 'VERIFIED_RIAA') & (df['sales_data_status'] != 'ESTIMATED_SEA')).sum()}")
    print(f"Total Cohort Size:    {len(df)}")
    print("==========================================")


if __name__ == "__main__":
    reconcile_entire_cohort()