import os
import pandas as pd

DATA_DIR = "data"
INPUT_PATH = os.path.join(DATA_DIR, "master_artists_intelligence_17k_final.csv")
OUTPUT_PATH = os.path.join(DATA_DIR, "master_artists_intelligence_17k_final.csv")


def run_empirical_catalog_ranking():
    if not os.path.exists(INPUT_PATH):
        print(f"ERROR: Dataset not found at {INPUT_PATH}")
        return

    print(f"Loading master verified catalog: {INPUT_PATH}")
    df = pd.read_csv(INPUT_PATH)

    # 1. Define Strict Registry Tier Hierarchy
    tier_priority = {
        "TIER_1_GLOBAL_SUPERSTAR_CSPC": 1,
        "TIER_2A_MAJOR_COMMERCIAL_CORE": 2,
        "TIER_2B_CERTIFIED_CATALOG": 3,
        "TIER_3A_VERIFIED_DIGITAL_CATALOG": 4,
        "TIER_3B_ACTIVE_MONTHLY_STREAMERS": 5,
        "TIER_3_LASTFM_VERIFIED_ENTITY": 6,
        "TIER_3_UNAUDITED_DIGITAL_CATALOG": 7
    }

    df["tier_order"] = df["catalog_intelligence_tier"].map(tier_priority).fillna(99)

    # 2. Extract Primary Audited Metric per Tier (No conversions, pure integers)
    def extract_tier_metric(row):
        order = row["tier_order"]
        if order in [1, 2, 3]:
            # CSPC EAS / RIAA Certified Units
            val = row.get("audited_sales_units")
            return float(val) if pd.notna(val) else 0.0
        elif order == 4:
            # Kworb Spotify Total Discography Streams
            val = row.get("spotify_total_streams")
            return float(val) if pd.notna(val) else 0.0
        elif order == 5:
            # Kworb Spotify Peak Monthly Listeners
            val = row.get("spotify_monthly_listeners")
            return float(val) if pd.notna(val) else 0.0
        elif order == 6:
            # Last.fm Global Verified Listeners
            val = row.get("lastfm_listeners")
            return float(val) if pd.notna(val) else 0.0
        return 0.0

    df["primary_empirical_metric"] = df.apply(extract_tier_metric, axis=1)

    # 3. Sort strictly by Tier Order (1 -> 6), then by Primary Metric (Highest -> Lowest)
    df.sort_values(
        by=["tier_order", "primary_empirical_metric"],
        ascending=[True, False],
        inplace=True
    )
    df.reset_index(drop=True, inplace=True)

    # 4. Generate Global Catalog Rank (Only for verified tiers 1 through 6)
    verified_mask = df["tier_order"] <= 6
    df["catalog_rank"] = None
    df.loc[verified_mask, "catalog_rank"] = range(1, int(verified_mask.sum()) + 1)

    # 5. Generate Peer Tier Rank
    df["tier_rank"] = None
    for tier_name in df["catalog_intelligence_tier"].unique():
        if tier_name != "TIER_3_UNAUDITED_DIGITAL_CATALOG":
            t_mask = df["catalog_intelligence_tier"] == tier_name
            df.loc[t_mask, "tier_rank"] = range(1, int(t_mask.sum()) + 1)

    # Clean up temporary helper columns
    df.drop(columns=["tier_order", "primary_empirical_metric"], inplace=True)

    # Save finalized ranked dataset
    df.to_csv(OUTPUT_PATH, index=False)
    print(f"\nEmpirical ranking complete! Saved to {OUTPUT_PATH}")

    # Display Top 15 Overall
    preview_cols = [
        col for col in ["catalog_rank", "tier_rank", "artist_name", "catalog_intelligence_tier", "audited_sales_units", "lastfm_listeners"]
        if col in df.columns
    ]
    print("\n--- TOP 15 CATALOG ARTISTS ---")
    print(df[preview_cols].head(15).to_string(index=False))

    # Display Top 5 in Tier 3 Last.fm Verified Entities
    lastfm_sample = df[df["catalog_intelligence_tier"] == "TIER_3_LASTFM_VERIFIED_ENTITY"]
    if not lastfm_sample.empty:
        print("\n--- TOP 5 TIER 3 (LAST.FM VERIFIED) ARTISTS ---")
        lfm_cols = ["catalog_rank", "tier_rank", "artist_name", "lastfm_listeners", "lastfm_playcount"]
        print(lastfm_sample[lfm_cols].head(5).to_string(index=False))


if __name__ == "__main__":
    run_empirical_catalog_ranking()