Update app.py

app.py

@@ -1,687 +1,13 @@
-import os
-import json
-import time
-import traceback
-from pathlib import Path
-from typing import Dict, Any, List, Tuple
-
-import pandas as pd
 import gradio as gr
-import papermill as pm
-import plotly.graph_objects as go
-
-# Optional LLM (kept for compatibility with template)
-try:
-    from huggingface_hub import InferenceClient
-except Exception:
-    InferenceClient = None
-
-
-# =========================================================
-# CONFIG
-# =========================================================
-
-BASE_DIR = Path(__file__).resolve().parent
-
-NB1 = os.environ.get("NB1", "datacreation.ipynb").strip()
-NB2 = os.environ.get("NB2", "pythonanalysis.ipynb").strip()
-
-RUNS_DIR = BASE_DIR / "runs"
-ART_DIR = BASE_DIR / "artifacts"
-PY_FIG_DIR = ART_DIR / "py" / "figures"
-PY_TAB_DIR = ART_DIR / "py" / "tables"
-
-PAPERMILL_TIMEOUT = int(os.environ.get("PAPERMILL_TIMEOUT", "1800"))
-MAX_PREVIEW_ROWS = int(os.environ.get("MAX_FILE_PREVIEW_ROWS", "50"))
-MAX_LOG_CHARS = int(os.environ.get("MAX_LOG_CHARS", "8000"))
-
-HF_API_KEY = os.environ.get("HF_API_KEY", "").strip()
-MODEL_NAME = os.environ.get("MODEL_NAME", "deepseek-ai/DeepSeek-R1").strip()
-HF_PROVIDER = os.environ.get("HF_PROVIDER", "novita").strip()
-N8N_WEBHOOK_URL = os.environ.get("N8N_WEBHOOK_URL", "").strip()
-
-LLM_ENABLED = False
-llm_client = None
-
-
-# =========================================================
-# HELPERS
-# =========================================================
-
-def ensure_dirs():
-    for p in [RUNS_DIR, ART_DIR, PY_FIG_DIR, PY_TAB_DIR]:
-        p.mkdir(parents=True, exist_ok=True)
-
-
-def stamp():
-    return time.strftime("%Y%m%d-%H%M%S")
-
-
-def tail(text: str, n: int = MAX_LOG_CHARS) -> str:
-    return (text or "")[-n:]
-
-
-def _ls(dir_path: Path, exts: Tuple[str, ...]) -> List[str]:
-    if not dir_path.is_dir():
-        return []
-    return sorted(
-        p.name for p in dir_path.iterdir()
-        if p.is_file() and p.suffix.lower() in exts
-    )
-
-
-def _read_csv(path: Path) -> pd.DataFrame:
-    return pd.read_csv(path, nrows=MAX_PREVIEW_ROWS)
-
-
-def _read_json(path: Path):
-    with path.open(encoding="utf-8") as f:
-        return json.load(f)
-
-
-def artifacts_index() -> Dict[str, Any]:
-    return {
-        "python": {
-            "figures": _ls(PY_FIG_DIR, (".png", ".jpg", ".jpeg")),
-            "tables": _ls(PY_TAB_DIR, (".csv", ".json")),
-        },
-    }
-
-
-def load_css() -> str:
-    css_path = BASE_DIR / "style.css"
-    return css_path.read_text(encoding="utf-8") if css_path.exists() else ""
-
-
-# =========================================================
-# DATA LOADING
-# =========================================================
-
-def make_demo_dashboard_df() -> pd.DataFrame:
-    data = [
-        ["Paris", "E-Scooter", 4.6, 4.1, 0.12, 0.06],
-        ["Paris", "E-Bike", 4.3, 4.2, 0.14, 0.05],
-        ["Berlin", "E-Scooter", 4.9, 3.8, 0.05, 0.08],
-        ["Berlin", "E-Bike", 4.5, 4.0, 0.09, 0.06],
-        ["Madrid", "E-Scooter", 4.2, 4.3, 0.17, 0.05],
-        ["Madrid", "Bus-Connect", 3.9, 4.1, 0.16, 0.04],
-        ["Warsaw", "E-Scooter", 4.4, 3.9, 0.08, 0.07],
-        ["Warsaw", "Shared-EV", 5.0, 4.0, 0.07, 0.05],
-        ["Turin", "E-Bike", 4.1, 4.2, 0.10, 0.04],
-        ["Turin", "Shared-EV", 4.8, 4.1, 0.09, 0.05],
-    ]
-    return pd.DataFrame(
-        data,
-        columns=[
-            "city",
-            "vehicle_type",
-            "avg_final_price_eur",
-            "avg_rating",
-            "avg_sentiment",
-            "cancellation_rate",
-        ],
-    )
-
-
-def load_dashboard_df() -> pd.DataFrame:
-    candidates = [
-        BASE_DIR / "merged_summary.csv",
-        BASE_DIR / "dashboard_data.csv",
-        PY_TAB_DIR / "merged_summary.csv",
-        PY_TAB_DIR / "dashboard_data.csv",
-    ]
-
-    for path in candidates:
-        if path.exists():
-            try:
-                df = pd.read_csv(path)
-                df.columns = [str(c).strip() for c in df.columns]
-                return df
-            except Exception:
-                pass
-
-    return make_demo_dashboard_df()
-
-
-def normalize_dashboard_df(df: pd.DataFrame) -> pd.DataFrame:
-    df = df.copy()
-    cols = {c.lower().strip(): c for c in df.columns}
-
-    rename_map = {}
-    if "city" not in cols and "City" in df.columns:
-        rename_map["City"] = "city"
-    if "vehicle_type" not in cols:
-        for candidate in ["ride_type", "vehicle", "VehicleType", "vehicle"]:
-            if candidate in df.columns:
-                rename_map[candidate] = "vehicle_type"
-                break
-    if "avg_final_price_eur" not in cols:
-        for candidate in ["final_price_eur", "avg_price", "avg_final_price", "price"]:
-            if candidate in df.columns:
-                rename_map[candidate] = "avg_final_price_eur"
-                break
-    if "avg_rating" not in cols:
-        for candidate in ["rating", "avg_star_rating", "star_rating"]:
-            if candidate in df.columns:
-                rename_map[candidate] = "avg_rating"
-                break
-    if "avg_sentiment" not in cols:
-        for candidate in ["sentiment", "compound", "vader_compound", "avg_compound_score"]:
-            if candidate in df.columns:
-                rename_map[candidate] = "avg_sentiment"
-                break
-    if "cancellation_rate" not in cols:
-        for candidate in ["cancel_rate", "avg_cancellation_rate"]:
-            if candidate in df.columns:
-                rename_map[candidate] = "cancellation_rate"
-                break
-
-    if rename_map:
-        df = df.rename(columns=rename_map)
-
-    for needed in [
-        "city",
-        "vehicle_type",
-        "avg_final_price_eur",
-        "avg_rating",
-        "avg_sentiment",
-        "cancellation_rate",
-    ]:
-        if needed not in df.columns:
-            if needed in ["city", "vehicle_type"]:
-                df[needed] = "Unknown"
-            else:
-                df[needed] = 0.0
-
-    return df
-
-
-def filter_dashboard_df(df: pd.DataFrame, city: str, vehicle: str) -> pd.DataFrame:
-    out = df.copy()
-    if city != "All":
-        out = out[out["city"] == city]
-    if vehicle != "All":
-        out = out[out["vehicle_type"] == vehicle]
-    return out
-
-
-# =========================================================
-# PIPELINE RUNNERS
-# =========================================================
-
-def run_notebook(nb_name: str) -> str:
-    ensure_dirs()
-    nb_in = BASE_DIR / nb_name
-    if not nb_in.exists():
-        return f"ERROR: {nb_name} not found."
-    nb_out = RUNS_DIR / f"run_{stamp()}_{nb_name}"
-    pm.execute_notebook(
-        input_path=str(nb_in),
-        output_path=str(nb_out),
-        cwd=str(BASE_DIR),
-        log_output=True,
-        progress_bar=False,
-        request_save_on_cell_execute=True,
-        execution_timeout=PAPERMILL_TIMEOUT,
-    )
-    return f"Executed {nb_name}"
-
-
-def run_datacreation() -> str:
-    try:
-        log = run_notebook(NB1)
-        csvs = [f.name for f in BASE_DIR.glob("*.csv")]
-        return f"OK  {log}\n\nCSVs now in /app:\n" + "\n".join(
-            f"  - {c}" for c in sorted(csvs)
-        )
-    except Exception as e:
-        return f"FAILED  {e}\n\n{traceback.format_exc()[-2000:]}"
-
-
-def run_pythonanalysis() -> str:
-    try:
-        log = run_notebook(NB2)
-        idx = artifacts_index()
-        figs = idx["python"]["figures"]
-        tabs = idx["python"]["tables"]
-        return (
-            f"OK  {log}\n\n"
-            f"Figures: {', '.join(figs) or '(none)'}\n"
-            f"Tables:  {', '.join(tabs) or '(none)'}"
-        )
-    except Exception as e:
-        return f"FAILED  {e}\n\n{traceback.format_exc()[-2000:]}"
-
-
-def run_full_pipeline() -> str:
-    logs = []
-    logs.append("=" * 50)
-    logs.append("STEP 1/2: Data Creation")
-    logs.append("=" * 50)
-    logs.append(run_datacreation())
-    logs.append("")
-    logs.append("=" * 50)
-    logs.append("STEP 2/2: Python Analysis")
-    logs.append("=" * 50)
-    logs.append(run_pythonanalysis())
-    return "\n".join(logs)
-
-
-# =========================================================
-# GALLERY LOADERS
-# =========================================================
-
-def _load_all_figures() -> List[Tuple[str, str]]:
-    items = []
-    for p in sorted(PY_FIG_DIR.glob("*.png")):
-        items.append((str(p), p.stem.replace("_", " ").title()))
-    return items
-
-
-def _load_table_safe(path: Path) -> pd.DataFrame:
-    try:
-        if path.suffix == ".json":
-            obj = _read_json(path)
-            if isinstance(obj, dict):
-                return pd.DataFrame([obj])
-            return pd.DataFrame(obj)
-        return _read_csv(path)
-    except Exception as e:
-        return pd.DataFrame([{"error": str(e)}])
-
-
-def refresh_gallery():
-    figures = _load_all_figures()
-    idx = artifacts_index()
-    table_choices = list(idx["python"]["tables"])
-
-    default_df = pd.DataFrame()
-    if table_choices:
-        default_df = _load_table_safe(PY_TAB_DIR / table_choices[0])
-
-    return (
-        figures if figures else [],
-        gr.update(
-            choices=table_choices,
-            value=table_choices[0] if table_choices else None
-        ),
-        default_df,
-    )
-
-
-def on_table_select(choice: str):
-    if not choice:
-        return pd.DataFrame([{"hint": "Select a table above."}])
-    path = PY_TAB_DIR / choice
-    if not path.exists():
-        return pd.DataFrame([{"error": f"File not found: {choice}"}])
-    return _load_table_safe(path)
-
-
-# =========================================================
-# DASHBOARD + PREDICTION
-# =========================================================
-
-def render_kpi_cards(city: str = "All", vehicle: str = "All") -> str:
-    df = normalize_dashboard_df(load_dashboard_df())
-    df = filter_dashboard_df(df, city, vehicle)
-
-    if df.empty:
-        return """
-        <div style="padding:16px;background:#fef2f2;border-radius:12px;">
-            <h4>No data available for the selected filters.</h4>
-        </div>
-        """
-
-    avg_price = df["avg_final_price_eur"].mean()
-    avg_rating = df["avg_rating"].mean()
-    avg_sentiment = df["avg_sentiment"].mean()
-    avg_cancel = df["cancellation_rate"].mean()
-
-    positive_reviews_pct = 53.8
-    if "avg_sentiment" in df.columns:
-        positive_reviews_pct = round((df["avg_sentiment"] > 0.05).mean() * 100, 1)
-
-    return f"""
-    <div style="display:grid;grid-template-columns:repeat(4,1fr);gap:12px;">
-      <div style="padding:16px;background:#f5f5f5;border-radius:12px;">
-        <h4>Avg Final Price</h4><p>€{avg_price:.2f}</p>
-      </div>
-      <div style="padding:16px;background:#f5f5f5;border-radius:12px;">
-        <h4>Avg Rating</h4><p>{avg_rating:.2f} / 5</p>
-      </div>
-      <div style="padding:16px;background:#f5f5f5;border-radius:12px;">
-        <h4>Cancellation Rate</h4><p>{avg_cancel * 100:.1f}%</p>
-      </div>
-      <div style="padding:16px;background:#f5f5f5;border-radius:12px;">
-        <h4>Positive Segments</h4><p>{positive_reviews_pct:.1f}%</p>
-      </div>
-    </div>
-    """
-
-
-def refresh_dashboard(city: str = "All", vehicle: str = "All"):
-    df = normalize_dashboard_df(load_dashboard_df())
-    df = filter_dashboard_df(df, city, vehicle)
-
-    if df.empty:
-        empty_fig = go.Figure()
-        empty_fig.update_layout(title="No data for selected filters")
-        return render_kpi_cards(city, vehicle), empty_fig, empty_fig, empty_fig
-
-    by_segment = df.groupby(["city", "vehicle_type"], as_index=False).agg(
-        avg_final_price_eur=("avg_final_price_eur", "mean"),
-        avg_sentiment=("avg_sentiment", "mean"),
-        avg_rating=("avg_rating", "mean"),
-        cancellation_rate=("cancellation_rate", "mean"),
-    )
-
-    fig1 = go.Figure()
-    fig1.add_bar(
-        x=[f"{r['city']} - {r['vehicle_type']}" for _, r in by_segment.iterrows()],
-        y=by_segment["avg_final_price_eur"],
-    )
-    fig1.update_layout(
-        title="Average Final Price by City / Vehicle",
-        xaxis_title="Segment",
-        yaxis_title="EUR",
-    )
-
-    fig2 = go.Figure()
-    fig2.add_bar(
-        x=[f"{r['city']} - {r['vehicle_type']}" for _, r in by_segment.iterrows()],
-        y=by_segment["avg_sentiment"],
-    )
-    fig2.update_layout(
-        title="Average Sentiment by City / Vehicle",
-        xaxis_title="Segment",
-        yaxis_title="Sentiment",
-    )
-
-    city_group = df.groupby("city", as_index=False).agg(
-        avg_rating=("avg_rating", "mean"),
-        cancellation_rate=("cancellation_rate", "mean"),
-    )
-
-    fig3 = go.Figure()
-    fig3.add_bar(name="Avg Rating", x=city_group["city"], y=city_group["avg_rating"])
-    fig3.add_bar(
-        name="Cancellation Rate",
-        x=city_group["city"],
-        y=city_group["cancellation_rate"] * 100,
-    )
-    fig3.update_layout(
-        title="Average Rating / Cancellation View",
-        xaxis_title="City",
-        yaxis_title="Value",
-        barmode="group",
-    )
-
-    return render_kpi_cards(city, vehicle), fig1, fig2, fig3
-
-
-def predict_satisfaction(
-    city,
-    vehicle,
-    distance_km,
-    duration_min,
-    final_price_eur,
-    discount_pct,
-    time_slot,
-    cancellation_flag,
-):
-    score = 0.50
-
-    if final_price_eur <= 4.5:
-        score += 0.15
-    else:
-        score -= 0.10
-
-    if discount_pct >= 10:
-        score += 0.10
-
-    if cancellation_flag == 1:
-        score -= 0.25
-
-    if time_slot == "Night":
-        score -= 0.10
-
-    if vehicle == "E-Bike":
-        score += 0.05
-
-    if distance_km <= 4:
-        score += 0.03
-
-    if duration_min > 25:
-        score -= 0.05
-
-    score = max(0.0, min(1.0, score))
-
-    return {
-        "city": city,
-        "vehicle_type": vehicle,
-        "high_satisfaction_probability": round(score, 3),
-        "low_satisfaction_probability": round(1 - score, 3),
-        "predicted_label": (
-            "High Satisfaction" if score >= 0.5 else "Low Satisfaction"
-        ),
-    }
-
-
-def get_pricing_recommendation(city, vehicle):
-    if city in ["Berlin", "Warsaw"] and vehicle == "E-Scooter":
-        return {
-            "decision": "Price Review",
-            "reason": "Lower sentiment and higher price sensitivity in this segment.",
-            "city": city,
-            "vehicle_type": vehicle,
-        }
-
-    if city == "Madrid":
-        return {
-            "decision": "Maintain Pricing",
-            "reason": "Strong satisfaction profile and positive sentiment.",
-            "city": city,
-            "vehicle_type": vehicle,
-        }
-
-    return {
-        "decision": "Maintain Pricing",
-        "reason": "Segment looks stable based on current sentiment and pricing.",
-        "city": city,
-        "vehicle_type": vehicle,
-    }
-
-
-# =========================================================
-# PRE-LOAD CHARTS AT STARTUP (fix for gradio 4.31 compatibility)
-# =========================================================
-_kpi_init = render_kpi_cards()
-_, _fig1_init, _fig2_init, _fig3_init = refresh_dashboard()
-
-
-# =========================================================
-# APP UI
-# =========================================================
-
-with gr.Blocks(title="Urban Mobility AI App", css=load_css()) as demo:
-    gr.Markdown(
-        "# Urban Mobility Pricing & Satisfaction App\n"
-        "*AI-enhanced dashboard for Group 08*",
-        elem_id="escp_title",
-    )
-
-    # ===========================================================
-    # TAB 1 -- Pipeline Runner
-    # ===========================================================
-    with gr.Tab("Pipeline Runner"):
-        gr.Markdown("Run the data creation and analysis notebooks.")
-
-        with gr.Row():
-            with gr.Column(scale=1):
-                btn_nb1 = gr.Button("Step 1: Data Creation", variant="secondary")
-            with gr.Column(scale=1):
-                btn_nb2 = gr.Button("Step 2: Python Analysis", variant="secondary")
-
-        with gr.Row():
-            btn_all = gr.Button("Run Full Pipeline (Both Steps)", variant="primary")
-
-        run_log = gr.Textbox(
-            label="Execution Log",
-            lines=18,
-            max_lines=30,
-            interactive=False,
-        )
-
-        btn_nb1.click(run_datacreation, outputs=[run_log])
-        btn_nb2.click(run_pythonanalysis, outputs=[run_log])
-        btn_all.click(run_full_pipeline, outputs=[run_log])
-
-    # ===========================================================
-    # TAB 2 -- Urban Mobility Dashboard
-    # ===========================================================
-    with gr.Tab("Urban Mobility Dashboard"):
-        gr.Markdown("### Urban Mobility KPIs & Visual Insights")
-
-        kpi_html = gr.HTML(value=_kpi_init)
-
-        with gr.Row():
-            city_filter = gr.Dropdown(
-                label="Select City",
-                choices=["All", "Paris", "Berlin", "Madrid", "Warsaw", "Turin"],
-                value="All",
-                interactive=True,
-            )
-            vehicle_filter = gr.Dropdown(
-                label="Select Vehicle Type",
-                choices=["All", "E-Scooter", "E-Bike", "Shared-EV", "Bus-Connect"],
-                value="All",
-                interactive=True,
-            )
-
-        refresh_btn = gr.Button("Refresh Dashboard", variant="primary")
-
-        gr.Markdown("#### Interactive Charts")
-        chart_price    = gr.Plot(value=_fig1_init, label="Average Final Price by City / Vehicle")
-        chart_sentiment = gr.Plot(value=_fig2_init, label="Sentiment by City / Vehicle")
-        chart_rating   = gr.Plot(value=_fig3_init, label="Average Rating / Cancellation View")
-
-        gr.Markdown("#### Static Figures (from notebooks)")
-        gallery = gr.Gallery(
-            label="Generated Figures",
-            columns=2,
-            height=480,
-            object_fit="contain",
-        )
-
-        gr.Markdown("#### Data Tables")
-        table_dropdown = gr.Dropdown(
-            label="Select a table to view",
-            choices=[],
-            interactive=True,
-        )
-        table_display = gr.Dataframe(
-            label="Table Preview",
-            interactive=False,
-        )
-
-        def _on_refresh(city, vehicle):
-            kpi, c1, c2, c3 = refresh_dashboard(city, vehicle)
-            figs, dd, df = refresh_gallery()
-            return kpi, c1, c2, c3, figs, dd, df
-
-        refresh_btn.click(
-            _on_refresh,
-            inputs=[city_filter, vehicle_filter],
-            outputs=[
-                kpi_html,
-                chart_price,
-                chart_sentiment,
-                chart_rating,
-                gallery,
-                table_dropdown,
-                table_display,
-            ],
-        )
-
-        table_dropdown.change(
-            on_table_select,
-            inputs=[table_dropdown],
-            outputs=[table_display],
-        )
-
-    # ===========================================================
-    # TAB 3 -- Prediction + Recommendation
-    # ===========================================================
-    with gr.Tab("Prediction + Recommendation"):
-        _ai_status = (
-            "Connected to your **n8n workflow**." if N8N_WEBHOOK_URL
-            else "**LLM active.**" if LLM_ENABLED
-            else "Using local logic. Add `N8N_WEBHOOK_URL` later for workflow integration."
-        )
-
-        gr.Markdown(
-            "### Predict user satisfaction and generate pricing recommendations\n\n"
-            f"{_ai_status}"
-        )
-
-        with gr.Row():
-            with gr.Column():
-                pred_city = gr.Dropdown(
-                    label="City",
-                    choices=["Paris", "Berlin", "Madrid", "Warsaw", "Turin"],
-                    value="Berlin",
-                )
-                pred_vehicle = gr.Dropdown(
-                    label="Vehicle Type",
-                    choices=["E-Scooter", "E-Bike", "Shared-EV", "Bus-Connect"],
-                    value="E-Scooter",
-                )
-                pred_distance = gr.Number(label="Distance (km)", value=3.5)
-                pred_duration = gr.Number(label="Duration (min)", value=12)
-                pred_final_price = gr.Number(label="Final Price (EUR)", value=4.2)
-                pred_discount = gr.Number(label="Discount (%)", value=10)
-                pred_time_slot = gr.Dropdown(
-                    label="Time Slot",
-                    choices=["Morning", "Afternoon", "Evening", "Night"],
-                    value="Evening",
-                )
-                pred_cancel = gr.Dropdown(
-                    label="Cancellation Flag",
-                    choices=[0, 1],
-                    value=0,
-                )
-
-                predict_btn = gr.Button("Predict Satisfaction", variant="primary")
-                recommend_btn = gr.Button("Get Pricing Recommendation")
-
-            with gr.Column():
-                prediction_output = gr.JSON(label="Prediction Output")
-                recommendation_output = gr.JSON(label="Recommendation Output")
-
-        predict_btn.click(
-            predict_satisfaction,
-            inputs=[
-                pred_city,
-                pred_vehicle,
-                pred_distance,
-                pred_duration,
-                pred_final_price,
-                pred_discount,
-                pred_time_slot,
-                pred_cancel,
-            ],
-            outputs=[prediction_output],
-        )
-
-        recommend_btn.click(
-            get_pricing_recommendation,
-            inputs=[pred_city, pred_vehicle],
-            outputs=[recommendation_output],
-        )
 
+def ping():
+    return "OK"
 
-ensure_dirs()
+with gr.Blocks() as demo:
+    gr.Markdown("# Test Gradio")
+    btn = gr.Button("Ping")
+    out = gr.Textbox()
+    btn.click(ping, outputs=out)
 
 if __name__ == "__main__":
-    demo.queue().launch(allowed_paths=[str(BASE_DIR)])
+    demo.launch()