"""
app.py
HIFFI Artist Intelligence - Executive Dashboard
Clean dark-themed design with aligned dataframes, responsive cards, and scouting dossier.
"""

import io
import os
import pandas as pd
import plotly.express as px
import plotly.graph_objects as go
import streamlit as st

st.set_page_config(
    page_title="HIFFI | Artist Intelligence",
    page_icon="⚡",
    layout="wide",
    initial_sidebar_state="expanded",
)

DATA_PATH = "enriched_artists.csv"

# Global CSS Polish
st.markdown(
    """
    <style>
    /* Global Container Spacing */
    .block-container {
        padding-top: 1.8rem;
        padding-bottom: 2.5rem;
        padding-left: 2.5rem;
        padding-right: 2.5rem;
        max-width: 100% !important;
    }

    /* KPI Cards */
    .kpi-box {
        background: #111827;
        border: 1px solid #1f2937;
        border-radius: 12px;
        padding: 16px 20px;
        margin-bottom: 12px;
    }
    .kpi-title {
        font-size: 0.75rem;
        font-weight: 700;
        color: #9ca3af;
        text-transform: uppercase;
        letter-spacing: 0.05em;
    }
    .kpi-value {
        font-size: 1.9rem;
        font-weight: 800;
        color: #f9fafb;
        margin: 4px 0;
    }
    .kpi-subtitle {
        font-size: 0.75rem;
        color: #6b7280;
    }

    /* Podium Cards */
    .podium-tile {
        background: #111827;
        border-radius: 12px;
        padding: 18px 20px;
        border: 1px solid #1f2937;
        height: 100%;
    }
    .podium-gold { border-top: 4px solid #f59e0b; }
    .podium-silver { border-top: 4px solid #94a3b8; }
    .podium-bronze { border-top: 4px solid #f97316; }

    /* Health Badges */
    .badge {
        display: inline-block;
        padding: 3px 8px;
        border-radius: 6px;
        font-size: 0.70rem;
        font-weight: 700;
        text-transform: uppercase;
    }
    .badge-active { background: rgba(16, 185, 129, 0.15); color: #10b981; }
    .badge-evergreen { background: rgba(56, 189, 248, 0.15); color: #38bdf8; }
    .badge-dormant { background: rgba(239, 68, 68, 0.15); color: #ef4444; }

    /* Clean Section Dividers */
    .custom-divider {
        height: 1px;
        background: #1f2937;
        margin: 24px 0;
    }
    </style>
    """,
    unsafe_allow_html=True,
)


@st.cache_data(ttl=60)
def load_data():
    if not os.path.exists(DATA_PATH):
        return pd.DataFrame()
    df = pd.read_csv(DATA_PATH)
    numeric_cols = [
        "hiffi_score",
        "breakout_velocity_index",
        "subscriber_count",
        "daily_view_velocity",
        "momentum_30d",
        "confidence_score",
        "hiffi_rank",
        "breakout_rank",
    ]
    for col in numeric_cols:
        if col in df.columns:
            df[col] = pd.to_numeric(df[col], errors="coerce")

    # Fallback assignment for subgenre if not yet computed in pipeline
    if "subgenre" not in df.columns:
        def infer_subgenre(r):
            subs = r.get("subscriber_count", 0) or 0
            bvi = r.get("breakout_velocity_index", 0) or 0
            if bvi >= 70:
                return "Breakout / Emerging"
            elif subs >= 15000000:
                return "Legends"
            else:
                return "Trap & Street"
        df["subgenre"] = df.apply(infer_subgenre, axis=1)

    return df


def to_excel_bytes(dataframe: pd.DataFrame) -> bytes:
    """Converts dataframe to downloadable in-memory Excel spreadsheet."""
    output = io.BytesIO()
    with pd.ExcelWriter(output, engine="openpyxl") as writer:
        dataframe.to_excel(writer, index=False, sheet_name="HIFFI_Cohort")
    return output.getvalue()


df = load_data()

# ----------------- Sidebar Controls -----------------
with st.sidebar:
    st.markdown("### ⚡ HIFFI Intelligence")
    st.caption("Hip-Hop Market Scoring & Breakout Detection")
    st.markdown("<div class='custom-divider'></div>", unsafe_allow_html=True)

    if df.empty:
        st.error(f"'{DATA_PATH}' not found. Please run 'python main.py' first!")
        st.stop()

    view_mode = st.radio(
        "Leaderboard Perspective:",
        ["🏆 Overall HIFFI Rank", "🚀 Breakout Velocity (BVI)", "🔍 Master Audit Grid"],
        index=0,
    )

    st.markdown("<div class='custom-divider'></div>", unsafe_allow_html=True)
    st.markdown("##### 🛡️ Filters")

    # Subgenre / Vertical Filter
    all_verticals = sorted(df["subgenre"].dropna().unique().tolist())
    target_presets = ["Legends", "Trap & Street", "UK Drill", "Lyricists", "Breakout / Emerging"]
    vertical_choices = [v for v in target_presets if v in all_verticals] + [v for v in all_verticals if v not in target_presets]
    
    selected_verticals = st.multiselect(
        "Hip-Hop Vertical",
        options=vertical_choices,
        default=vertical_choices,
    )

    available_statuses = df["health_status"].dropna().unique().tolist()
    selected_statuses = st.multiselect(
        "Channel Status",
        options=available_statuses,
        default=available_statuses,
    )

    min_conf = st.slider(
        "Min Confidence",
        min_value=0.0,
        max_value=1.0,
        value=0.50,
        step=0.05,
    )

# Filter logic
filtered_df = df[
    (df["health_status"].isin(selected_statuses))
    & (df["subgenre"].isin(selected_verticals))
    & (df["confidence_score"] >= min_conf)
].copy()

# Sidebar Data Export Buttons (Filters applied)
with st.sidebar:
    st.markdown("<div class='custom-divider'></div>", unsafe_allow_html=True)
    st.markdown("##### 💾 Export Filtered Cohort")
    
    col_csv, col_xlsx = st.columns(2)
    
    csv_payload = filtered_df.to_csv(index=False).encode("utf-8")
    col_csv.download_button(
        label="📥 CSV",
        data=csv_payload,
        file_name="hiffi_filtered_cohort.csv",
        mime="text/csv",
        use_container_width=True,
    )

    excel_payload = to_excel_bytes(filtered_df)
    col_xlsx.download_button(
        label="📊 Excel",
        data=excel_payload,
        file_name="hiffi_filtered_cohort.xlsx",
        mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
        use_container_width=True,
    )

    st.markdown("<div class='custom-divider'></div>", unsafe_allow_html=True)
    st.caption("Momentum (35%) • Velocity (30%) • Reach (20%) • Cadence (15%)")

# ----------------- Main Header -----------------
head_col1, head_col2 = st.columns([3, 1])
with head_col1:
    st.markdown("<h2 style='margin-bottom: 2px;'>HIFFI Artist Intelligence Hub</h2>", unsafe_allow_html=True)
    st.markdown("<p style='color: #9ca3af; font-size: 0.92rem; margin-top: 0;'>Cross-platform tracking of catalog sustainability and audience breakout velocity.</p>", unsafe_allow_html=True)
with head_col2:
    st.markdown(
        f"<div style='text-align: right; color: #6b7280; font-size: 0.8rem; padding-top: 10px;'>Active Cohort: <b>{len(filtered_df)} / {len(df)}</b> artists</div>",
        unsafe_allow_html=True,
    )

# ----------------- KPI Cards Row -----------------
k1, k2, k3, k4 = st.columns(4)

with k1:
    st.markdown(
        f"""
        <div class="kpi-box">
            <div class="kpi-title">Tracked Artists</div>
            <div class="kpi-value">{len(df)}</div>
            <div class="kpi-subtitle">Monitored pipeline size</div>
        </div>
        """,
        unsafe_allow_html=True,
    )

with k2:
    active_count = len(df[df["health_status"] == "ACTIVE_HEALTHY"])
    st.markdown(
        f"""
        <div class="kpi-box">
            <div class="kpi-title" style="color: #10b981;">Active Healthy</div>
            <div class="kpi-value" style="color: #10b981;">{active_count}</div>
            <div class="kpi-subtitle">Recent uploads & steady traction</div>
        </div>
        """,
        unsafe_allow_html=True,
    )

with k3:
    evergreen_count = len(df[df["health_status"] == "CATALOG_EVERGREEN"])
    st.markdown(
        f"""
        <div class="kpi-box">
            <div class="kpi-title" style="color: #38bdf8;">Catalog Evergreen</div>
            <div class="kpi-value" style="color: #38bdf8;">{evergreen_count}</div>
            <div class="kpi-subtitle">Strong passive catalog streams</div>
        </div>
        """,
        unsafe_allow_html=True,
    )

with k4:
    zombies = len(df[df["health_status"] == "DORMANT_CATALOG"])
    st.markdown(
        f"""
        <div class="kpi-box">
            <div class="kpi-title" style="color: #ef4444;">Dormant / Excluded</div>
            <div class="kpi-value" style="color: #ef4444;">{zombies}</div>
            <div class="kpi-subtitle">Disqualified (&lt;NA&gt; Rank)</div>
        </div>
        """,
        unsafe_allow_html=True,
    )

st.markdown("<div class='custom-divider'></div>", unsafe_allow_html=True)

# ----------------- Top 3 Leaders Podium -----------------
top3 = (
    filtered_df[filtered_df["is_rank_eligible"] == True]
    .sort_values(by="hiffi_rank", ascending=True)
    .head(3)
)

if len(top3) >= 3:
    st.markdown("#### 👑 Market Leaders")
    p1, p2, p3 = st.columns(3)

    podium_data = [
        (p1, top3.iloc[0], "🥇 RANK #1", "podium-gold", "#f59e0b"),
        (p2, top3.iloc[1], "🥈 RANK #2", "podium-silver", "#94a3b8"),
        (p3, top3.iloc[2], "🥉 RANK #3", "podium-bronze", "#f97316"),
    ]

    for col, row_data, rank_label, css_class, accent_color in podium_data:
        badge_cls = (
            "badge-active"
            if row_data["health_status"] == "ACTIVE_HEALTHY"
            else "badge-evergreen"
        )
        bvi_str = f"{row_data['breakout_velocity_index']:.1f}" if pd.notna(row_data.get("breakout_velocity_index")) else "N/A"
        vel_str = f"{int(row_data['daily_view_velocity']):,}" if pd.notna(row_data.get("daily_view_velocity")) else "N/A"

        with col:
            st.markdown(
                f"""
                <div class="podium-tile {css_class}">
                    <div style="display: flex; justify-content: space-between; align-items: center; margin-bottom: 6px;">
                        <span style="font-weight: 800; color: {accent_color}; font-size: 0.85rem;">{rank_label}</span>
                        <span class="badge {badge_cls}">{row_data['health_status'].replace('_', ' ')}</span>
                    </div>
                    <div style="font-size: 1.35rem; font-weight: 800; color: #ffffff; margin-bottom: 2px;">{row_data['name']}</div>
                    <div style="font-size: 0.8rem; color: #6b7280; margin-bottom: 12px;">{row_data.get('channel_title', '')}</div>
                    <div style="display: flex; justify-content: space-between; background: #0b0f17; padding: 10px 14px; border-radius: 8px;">
                        <div>
                            <div style="font-size: 0.68rem; color: #9ca3af; text-transform: uppercase;">HIFFI Score</div>
                            <div style="font-size: 1.25rem; font-weight: 800; color: {accent_color};">{row_data['hiffi_score']:.1f}</div>
                        </div>
                        <div>
                            <div style="font-size: 0.68rem; color: #9ca3af; text-transform: uppercase;">Breakout Index</div>
                            <div style="font-size: 1.25rem; font-weight: 800; color: #a855f7;">{bvi_str}</div>
                        </div>
                        <div>
                            <div style="font-size: 0.68rem; color: #9ca3af; text-transform: uppercase;">Daily Views</div>
                            <div style="font-size: 1.05rem; font-weight: 700; color: #e5e7eb;">{vel_str}</div>
                        </div>
                    </div>
                </div>
                """,
                unsafe_allow_html=True,
            )

    st.markdown("<div class='custom-divider'></div>", unsafe_allow_html=True)

# ----------------- Leaderboard Grid -----------------
st.markdown(f"#### 📋 {view_mode}")

if view_mode == "🏆 Overall HIFFI Rank":
    table_df = (
        filtered_df[filtered_df["is_rank_eligible"] == True]
        .sort_values(by="hiffi_rank", ascending=True)
        .copy()
    )
    cols = [
        "hiffi_rank",
        "name",
        "subgenre",
        "hiffi_score",
        "breakout_rank",
        "breakout_velocity_index",
        "daily_view_velocity",
        "momentum_30d",
        "health_status",
    ]
elif view_mode == "🚀 Breakout Velocity (BVI)":
    table_df = (
        filtered_df[
            (filtered_df["is_rank_eligible"] == True)
            & (filtered_df["breakout_rank"].notna())
        ]
        .sort_values(by="breakout_rank", ascending=True)
        .copy()
    )
    cols = [
        "breakout_rank",
        "name",
        "subgenre",
        "breakout_velocity_index",
        "hiffi_rank",
        "hiffi_score",
        "daily_view_velocity",
        "subscriber_count",
        "health_status",
    ]
else:
    table_df = filtered_df.sort_values(by=["is_rank_eligible", "hiffi_score"], ascending=[False, False]).copy()
    cols = [
        "name",
        "subgenre",
        "hiffi_score",
        "breakout_velocity_index",
        "daily_view_velocity",
        "subscriber_count",
        "health_status",
        "confidence_score",
        "is_rank_eligible",
    ]

# Keep only columns that exist in DataFrame to prevent KeyError
render_cols = [c for c in cols if c in table_df.columns]

st.dataframe(
    table_df[render_cols].reset_index(drop=True),
    use_container_width=True,
    height=290,
    column_config={
        "hiffi_rank": st.column_config.NumberColumn("Rank", format="%d", width="small"),
        "breakout_rank": st.column_config.NumberColumn("BVI Rank", format="%d", width="small"),
        "name": st.column_config.TextColumn("Artist", width="medium"),
        "subgenre": st.column_config.TextColumn("Vertical", width="medium"),
        "hiffi_score": st.column_config.ProgressColumn(
            "HIFFI Score",
            format="%.1f",
            min_value=0,
            max_value=100,
            width="medium",
        ),
        "breakout_velocity_index": st.column_config.ProgressColumn(
            "Breakout (BVI)",
            format="%.1f",
            min_value=0,
            max_value=100,
            width="medium",
        ),
        "daily_view_velocity": st.column_config.NumberColumn(
            "Daily Views / Day",
            format="%,d",
            width="medium",
        ),
        "momentum_30d": st.column_config.NumberColumn(
            "30d Momentum",
            format="%.1f%%",
            width="small",
        ),
        "subscriber_count": st.column_config.NumberColumn(
            "Subscribers",
            format="%,d",
            width="medium",
        ),
        "health_status": st.column_config.TextColumn("Status", width="medium"),
        "confidence_score": st.column_config.NumberColumn("Confidence", format="%.2f", width="small"),
        "is_rank_eligible": st.column_config.CheckboxColumn("Eligible", width="small"),
    },
)

st.markdown("<div class='custom-divider'></div>", unsafe_allow_html=True)

# ----------------- Visual Insights Charts -----------------
st.markdown("#### 📊 Market Landscape Visualizer")

c_left, c_right = st.columns(2)

with c_left:
    scatter_df = filtered_df[filtered_df["is_rank_eligible"] == True].copy()
    fig_scatter = px.scatter(
        scatter_df,
        x="daily_view_velocity",
        y="momentum_30d",
        size="subscriber_count",
        color="health_status",
        color_discrete_map={
            "ACTIVE_HEALTHY": "#10b981",
            "CATALOG_EVERGREEN": "#38bdf8",
            "DORMANT_CATALOG": "#ef4444",
        },
        hover_name="name",
        hover_data={"daily_view_velocity": ":,d", "momentum_30d": ":.1f%"},
        log_x=True,
        title="View Velocity vs. 30-Day Momentum",
        labels={
            "daily_view_velocity": "Daily Views / Day (Log Scale)",
            "momentum_30d": "30-Day Growth (%)",
            "health_status": "Vitality",
        },
        template="plotly_dark",
    )
    fig_scatter.update_layout(
        paper_bgcolor="#111827",
        plot_bgcolor="#111827",
        font=dict(color="#9ca3af"),
        margin=dict(l=20, r=20, t=40, b=20),
        height=320,
    )
    st.plotly_chart(fig_scatter, use_container_width=True)

with c_right:
    bvi_df = (
        filtered_df[filtered_df["breakout_velocity_index"].notna()]
        .sort_values(by="breakout_velocity_index", ascending=True)
    )
    fig_bar = px.bar(
        bvi_df,
        x="breakout_velocity_index",
        y="name",
        orientation="h",
        color="breakout_velocity_index",
        color_continuous_scale="Purples",
        title="Breakout Velocity Index (BVI)",
        labels={"breakout_velocity_index": "BVI Score", "name": "Artist"},
        template="plotly_dark",
    )
    fig_bar.update_layout(
        paper_bgcolor="#111827",
        plot_bgcolor="#111827",
        font=dict(color="#9ca3af"),
        coloraxis_showscale=False,
        margin=dict(l=20, r=20, t=40, b=20),
        height=320,
    )
    st.plotly_chart(fig_bar, use_container_width=True)

st.markdown("<div class='custom-divider'></div>", unsafe_allow_html=True)

# ----------------- Deep Dive Scouting Dossier -----------------
st.markdown("#### 🔎 Artist Dossier")

selected_name = st.selectbox("Inspect Artist Details:", df["name"].unique(), label_visibility="collapsed")
row = df[df["name"] == selected_name].iloc[0]

# Resolve YouTube channel direct link
yt_url = str(row.get("youtube_url", "")).strip()
yt_id = str(row.get("channel_id", row.get("youtube_channel_id", ""))).strip()

if (not yt_url or yt_url == "nan") and yt_id and yt_id != "nan":
    if yt_id.startswith("UC"):
        yt_url = f"https://www.youtube.com/channel/{yt_id}"
    elif yt_id.startswith("@"):
        yt_url = f"https://www.youtube.com/{yt_id}"
    else:
        yt_url = f"https://www.youtube.com/@{yt_id}"

d1, d2, d3, d4 = st.columns(4)

with d1:
    h_val = row.get("hiffi_score")
    st.metric("HIFFI Score", f"{h_val:.1f}" if pd.notna(h_val) else "N/A")
with d2:
    b_val = row.get("breakout_velocity_index")
    st.metric("Breakout Index (BVI)", f"{b_val:.1f}" if pd.notna(b_val) else "N/A")
with d3:
    s_val = row.get("subscriber_count")
    st.metric("Subscribers", f"{int(s_val):,}" if pd.notna(s_val) else "N/A")
with d4:
    conf = row.get("confidence_score", 0.0)
    tier = row.get("confidence_tier", "Standard")
    st.metric("Entity Confidence", f"{conf * 100:.0f}%", delta=tier, delta_color="normal")

badge_cls = (
    "badge-active"
    if row.get("health_status") == "ACTIVE_HEALTHY"
    else "badge-evergreen"
    if row.get("health_status") == "CATALOG_EVERGREEN"
    else "badge-dormant"
)

# Dossier info box with integrated Official YouTube Button
st.markdown(
    f"""
    <div style="background: #111827; padding: 14px 18px; border-radius: 8px; border: 1px solid #1f2937; margin-top: 10px; display: flex; justify-content: space-between; align-items: center; font-size: 0.85rem;">
        <div style="display: flex; gap: 24px; align-items: center;">
            <div><b>Artist:</b> {row['name']}</div>
            <div><b>Vertical:</b> <span style="color: #a855f7;">{row.get('subgenre', 'N/A')}</span></div>
            <div><b>Channel:</b> {row.get('channel_title', 'Unknown')}</div>
            <div><b>Status:</b> <span class="badge {badge_cls}">{row.get('health_status', 'UNKNOWN')}</span></div>
            <div><b>Zombie Flag:</b> {'⚠️ Yes' if row.get('is_zombie') else '✅ Clean'}</div>
            <div><b>Eligible for Rank:</b> {'✅ Yes' if row.get('is_rank_eligible') else '❌ Disqualified'}</div>
        </div>
    </div>
    """,
    unsafe_allow_html=True,
)

st.write("")
if yt_url and yt_url != "nan":
    st.link_button("▶ Open Official YouTube Channel", yt_url, use_container_width=False)
else:
    st.caption("⚠️ No verified YouTube channel link available for this artist.")