import gradio as gr
import pandas as pd
import plotly.graph_objects as go

# ── load data ──────────────────────────────────────────────
df = pd.read_csv("restaurant_master_scored.csv")

CUISINES = ["All"] + sorted(df["cuisine_type"].unique().tolist())
PRICES = ["All"] + ["€", "€€", "€€€", "€€€€"]
ARRONDS = ["All"] + sorted(df["arrondissement"].unique().tolist())

LABEL_COLOR = {"Worth It": "#1A6B3C", "Maybe": "#7D5A00", "Skip It": "#8B1A1A"}
LABEL_BG = {"Worth It": "#EAF3DE", "Maybe": "#FAEEDA", "Skip It": "#FCEBEB"}


# ── charts ──────────────────────────────────────────────
def make_chart(row, filtered_df):
    # First chart: score component chart for top result
    components = {
        "Sentiment adj": round(row["sentiment_adj_norm"] * 0.35 * 100, 1),
        "Price fairness": round(row["price_fairness"] * 0.25 * 100, 1),
        "Consistency": round(row["consistency_index"] * 0.20 * 100, 1),
        "Trust": round(row["trust_score"] * 0.10 * 100, 1),
        "Divergence −": round(-row["star_sentiment_divergence"] * 0.10 * 100, 1),
    }

    colors = ["#3D2B8E", "#7B6FCA", "#1A6B3C", "#7D5A00", "#8B1A1A"]

    fig_bar = go.Figure(
        go.Bar(
            x=list(components.values()),
            y=list(components.keys()),
            orientation="h",
            marker_color=colors,
            text=[f"{v:+.1f}" for v in components.values()],
            textposition="outside",
        )
    )

    fig_bar.update_layout(
        margin=dict(l=10, r=60, t=10, b=10),
        height=220,
        xaxis=dict(
            showgrid=False,
            zeroline=True,
            zerolinecolor="#cccccc",
            title="Points",
        ),
        yaxis=dict(showgrid=False),
        paper_bgcolor="rgba(0,0,0,0)",
        plot_bgcolor="rgba(0,0,0,0)",
        font=dict(size=12),
    )

    # Second chart: scatter plot of all filtered restaurants
    fig_scatter = go.Figure()

    for label in ["Worth It", "Maybe", "Skip It"]:
        subset = filtered_df[filtered_df["worth_it_label"] == label]
        if not subset.empty:
            fig_scatter.add_trace(
                go.Scatter(
                    x=subset["star_rating"],
                    y=subset["true_score"],
                    mode="markers",
                    name=label,
                    marker=dict(
                        size=10,
                        color=LABEL_COLOR.get(label, "#666666"),
                        line=dict(width=1, color="white"),
                    ),
                    text=subset["restaurant_name"],
                    hovertemplate=(
                        "<b>%{text}</b><br>"
                        "Stars: %{x:.1f}<br>"
                        "True Score: %{y:.1f}<br>"
                        "Verdict: " + label +
                        "<extra></extra>"
                    ),
                )
            )

    fig_scatter.update_layout(
        margin=dict(l=10, r=10, t=40, b=10),
        height=320,
        xaxis=dict(title="Star rating", showgrid=True, gridcolor="#eeeeee"),
        yaxis=dict(title="True score", showgrid=True, gridcolor="#eeeeee"),
        paper_bgcolor="rgba(0,0,0,0)",
        plot_bgcolor="rgba(0,0,0,0)",
        font=dict(size=12),
        legend=dict(orientation="h", y=1.12, x=0),
    )

    return fig_bar, fig_scatter


# ── AI explanation (rule-based, no API key needed) ─────────
import requests

def explain(row):
    payload = {
        "restaurant_name": row["restaurant_name"],
        "true_score": float(row["true_score"]),
        "worth_it_label": row["worth_it_label"],
        "sentiment_score": float(row["sentiment_score"]),
        "star_rating": float(row["star_rating"]),
        "price_category": row["price_category"],
    }

    try:
        r = requests.post(
            "https://scohen3012.app.n8n.cloud/webhook/explain",
            json=payload,
            timeout=8
        )
        return r.json().get("explanation", "No explanation returned.")
    except Exception as e:
        return f"Explanation service unavailable: {e}"
    


# ── main function ──────────────────────────────────────────
def search(cuisine, price, arrond, top_n):
    filtered = df.copy()

    if cuisine != "All":
        filtered = filtered[filtered["cuisine_type"] == cuisine]
    if price != "All":
        filtered = filtered[filtered["price_category"] == price]
    if arrond != "All":
        filtered = filtered[filtered["arrondissement"] == arrond]

    if filtered.empty:
        empty_fig = go.Figure()
        return "No restaurants match your filters.", empty_fig, empty_fig, ""

    top = filtered.nlargest(int(top_n), "true_score").reset_index(drop=True)
    best = top.iloc[0]

    # Results table
    display = top[
        [
            "restaurant_name",
            "cuisine_type",
            "arrondissement",
            "price_category",
            "star_rating",
            "true_score",
            "worth_it_label",
        ]
    ].rename(
        columns={
            "restaurant_name": "Name",
            "cuisine_type": "Cuisine",
            "arrondissement": "Area",
            "price_category": "Price",
            "star_rating": "Stars",
            "true_score": "True Score",
            "worth_it_label": "Verdict",
        }
    )

    score_chart, scatter_chart = make_chart(best, top)
    explanation = explain(best)

    return display, score_chart, scatter_chart, explanation


# ── interface ──────────────────────────────────────────────
with gr.Blocks(title="Restaurant Worth-It Score — Paris") as demo:
    gr.Markdown(
        "## Restaurant Worth-It Score — Paris\n"
        "AI-powered ratings that go beyond the stars. "
        "Select your filters to find restaurants that truly deliver."
    )

    with gr.Row():
        cuisine_dd = gr.Dropdown(CUISINES, value="All", label="Cuisine type")
        price_dd = gr.Dropdown(PRICES, value="All", label="Price tier")
        arrond_dd = gr.Dropdown(ARRONDS, value="All", label="Arrondissement")
        top_n_sl = gr.Slider(3, 20, value=10, step=1, label="Results to show")

    search_btn = gr.Button("Find restaurants", variant="primary")

    gr.Markdown("### Top results")
    results_table = gr.Dataframe(label="Ranked restaurants", interactive=False)

    with gr.Row():
        with gr.Column(scale=1):
            gr.Markdown("#### Score breakdown — top result")
            score_chart = gr.Plot(label="")

        with gr.Column(scale=1):
            gr.Markdown("#### All filtered restaurants")
            scatter_chart = gr.Plot(label="")

    gr.Markdown("#### AI explanation — top result")
    explanation_box = gr.Markdown()

    search_btn.click(
        fn=search,
        inputs=[cuisine_dd, price_dd, arrond_dd, top_n_sl],
        outputs=[results_table, score_chart, scatter_chart, explanation_box],
    )

demo.launch()