Upload 4 files

README.md

@@ -1,12 +1,43 @@
 ---
-title: '123'
-emoji: 🏢
-colorFrom: pink
-colorTo: green
+title: ESCP Notebook Runner
+emoji: 📊
+colorFrom: indigo
+colorTo: blue
 sdk: gradio
 sdk_version: 6.9.0
+python_version: 3.10.13
 app_file: app.py
 pinned: false
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# ESCP Notebook Runner
+
+This Hugging Face Space runs one bundled Jupyter notebook on two bundled CSV datasets and shows the outputs in a Gradio dashboard.
+
+## Included files
+
+- `app.py` — Gradio app
+- `analysis.ipynb` — bundled notebook
+- `synthetic_book_reviews.csv` — bundled reviews dataset
+- `synthetic_sales_data.csv` — bundled sales dataset
+- `requirements.txt` — Python dependencies
+- `style.css` — clean styling with no background images
+- `artifacts/` — where notebook outputs are saved
+- `runs/` — executed notebook copies
+
+## Why this update was needed
+
+The previous version built the image, but the app could still fail at runtime because:
+1. CSS was passed to `demo.launch(...)` instead of `gr.Blocks(..., css=...)`
+2. the Space image used a newer Gradio runtime than the app code expected
+3. Python 3.13 can break notebook/data-science dependencies more often than Python 3.10
+
+## How to use it
+
+1. Create a new Hugging Face **Gradio** Space.
+2. Upload all files from this folder.
+3. Wait for the build to finish.
+4. Open the Space and click **Run Full Pipeline**.
+5. Open **Dashboard** and click **Refresh Dashboard**.
+
+You can leave the three upload fields empty to use the bundled notebook and CSV files.

app.py

@@ -0,0 +1,261 @@
+# AI-Assisted Code — Academic Integrity Notice
+# Generated with The App Builder. ESCP coursework.
+# Student must be able to explain all code when asked.
+
+import shutil
+import time
+import traceback
+from pathlib import Path
+
+import gradio as gr
+import pandas as pd
+import papermill as pm
+import plotly.graph_objects as go
+
+BASE_DIR = Path(__file__).resolve().parent
+RUNS_DIR = BASE_DIR / "runs"
+ART_DIR = BASE_DIR / "artifacts"
+FIG_DIR = ART_DIR / "py" / "figures"
+TAB_DIR = ART_DIR / "py" / "tables"
+
+DEFAULT_NOTEBOOK = BASE_DIR / "analysis.ipynb"
+DEFAULT_REVIEWS = BASE_DIR / "synthetic_book_reviews.csv"
+DEFAULT_SALES = BASE_DIR / "synthetic_sales_data.csv"
+
+PAPERMILL_TIMEOUT = 1800
+MAX_PREVIEW_ROWS = 50
+
+
+def ensure_dirs() -> None:
+    """Create folders used by the app."""
+    for path in [RUNS_DIR, FIG_DIR, TAB_DIR]:
+        path.mkdir(parents=True, exist_ok=True)
+
+
+def load_css() -> str:
+    """Read local CSS once at startup."""
+    css_path = BASE_DIR / "style.css"
+    return css_path.read_text(encoding="utf-8") if css_path.exists() else ""
+
+
+def timestamp() -> str:
+    return time.strftime("%Y%m%d-%H%M%S")
+
+
+def copy_input(source_path: str | None, fallback: Path, target: Path) -> None:
+    """Copy the uploaded file or reuse the bundled default file."""
+    source = Path(source_path) if source_path else fallback
+    if not source.exists():
+        raise FileNotFoundError(f"Missing required file: {source.name}")
+    shutil.copy2(source, target)
+
+
+def prepare_inputs(notebook_path: str | None, reviews_path: str | None, sales_path: str | None) -> None:
+    """Normalize filenames so the notebook can use fixed paths."""
+    copy_input(notebook_path, DEFAULT_NOTEBOOK, BASE_DIR / "analysis.ipynb")
+    copy_input(reviews_path, DEFAULT_REVIEWS, BASE_DIR / "synthetic_book_reviews.csv")
+    copy_input(sales_path, DEFAULT_SALES, BASE_DIR / "synthetic_sales_data.csv")
+
+
+def run_pipeline(notebook_path: str | None, reviews_path: str | None, sales_path: str | None) -> str:
+    """Execute the notebook with papermill and return a readable log."""
+    ensure_dirs()
+    try:
+        prepare_inputs(notebook_path, reviews_path, sales_path)
+        output_nb = RUNS_DIR / f"run_{timestamp()}_analysis.ipynb"
+        pm.execute_notebook(
+            input_path=str(BASE_DIR / "analysis.ipynb"),
+            output_path=str(output_nb),
+            cwd=str(BASE_DIR),
+            log_output=True,
+            progress_bar=False,
+            request_save_on_cell_execute=True,
+            execution_timeout=PAPERMILL_TIMEOUT,
+        )
+        figures = sorted(p.name for p in FIG_DIR.glob("*") if p.is_file())
+        tables = sorted(p.name for p in TAB_DIR.glob("*") if p.is_file())
+        return (
+            "Pipeline completed successfully.\n\n"
+            f"Notebook output: {output_nb.name}\n"
+            f"Figures: {', '.join(figures) or '(none)'}\n"
+            f"Tables: {', '.join(tables) or '(none)'}"
+        )
+    except Exception as exc:
+        return f"Pipeline failed: {exc}\n\n{traceback.format_exc()[-5000:]}"
+
+
+def read_json(path: Path) -> dict:
+    import json
+    with path.open(encoding="utf-8") as file:
+        return json.load(file)
+
+
+def load_table(path: Path) -> pd.DataFrame:
+    """Safely preview a CSV or JSON artifact."""
+    try:
+        if path.suffix.lower() == ".json":
+            obj = read_json(path)
+            return pd.DataFrame([obj]) if isinstance(obj, dict) else pd.DataFrame(obj)
+        return pd.read_csv(path, nrows=MAX_PREVIEW_ROWS)
+    except Exception as exc:
+        return pd.DataFrame([{"error": str(exc)}])
+
+
+def list_tables() -> list[str]:
+    return sorted(p.name for p in TAB_DIR.glob("*") if p.suffix.lower() in {".csv", ".json"})
+
+
+def gallery_items() -> list[tuple[str, str]]:
+    return [(str(path), path.stem.replace("_", " ").title()) for path in sorted(FIG_DIR.glob("*.png"))]
+
+
+def load_kpis() -> dict:
+    for candidate in [TAB_DIR / "kpis.json", FIG_DIR / "kpis.json"]:
+        if candidate.exists():
+            try:
+                return read_json(candidate)
+            except Exception:
+                return {}
+    return {}
+
+
+def kpi_cards_html() -> str:
+    """Render compact KPI cards without any background image."""
+    kpis = load_kpis()
+    if not kpis:
+        return '<div class="card-grid"><div class="card"><b>No data yet</b><br>Run the pipeline first.</div></div>'
+    config = [
+        ("n_titles", "Book Titles"),
+        ("n_months", "Time Periods"),
+        ("total_units_sold", "Units Sold"),
+        ("total_revenue", "Revenue"),
+    ]
+    cards = []
+    for key, label in config:
+        if key in kpis:
+            value = kpis[key]
+            if isinstance(value, (int, float)) and abs(value) >= 100:
+                value = f"{value:,.0f}"
+            cards.append(f'<div class="card"><div class="label">{label}</div><div class="value">{value}</div></div>')
+    return '<div class="card-grid">' + "".join(cards) + "</div>"
+
+
+def empty_chart(title: str) -> go.Figure:
+    fig = go.Figure()
+    fig.update_layout(
+        title=title,
+        template="plotly_white",
+        height=420,
+        paper_bgcolor="white",
+        plot_bgcolor="white",
+        annotations=[dict(text="Run the pipeline first", x=0.5, y=0.5, xref="paper", yref="paper", showarrow=False)],
+    )
+    return fig
+
+
+def build_sales_chart() -> go.Figure:
+    path = TAB_DIR / "df_dashboard.csv"
+    if not path.exists():
+        return empty_chart("Monthly Overview")
+    df = pd.read_csv(path)
+    date_col = next((c for c in df.columns if "month" in c.lower() or "date" in c.lower()), None)
+    val_cols = [c for c in df.columns if c != date_col and pd.api.types.is_numeric_dtype(df[c])]
+    if not date_col or not val_cols:
+        return empty_chart("Monthly Overview")
+    df[date_col] = pd.to_datetime(df[date_col], errors="coerce")
+    fig = go.Figure()
+    for col in val_cols:
+        fig.add_trace(go.Scatter(x=df[date_col], y=df[col], mode="lines+markers", name=col.replace("_", " ").title()))
+    fig.update_layout(title="Monthly Overview", template="plotly_white", height=450, paper_bgcolor="white", plot_bgcolor="white")
+    return fig
+
+
+def build_sentiment_chart() -> go.Figure:
+    path = TAB_DIR / "sentiment_counts_sampled.csv"
+    if not path.exists():
+        return empty_chart("Sentiment Distribution")
+    df = pd.read_csv(path)
+    title_col = df.columns[0]
+    fig = go.Figure()
+    for col in [c for c in ["negative", "neutral", "positive"] if c in df.columns]:
+        fig.add_trace(go.Bar(y=df[title_col], x=df[col], orientation="h", name=col.title()))
+    fig.update_layout(title="Sentiment Distribution", barmode="stack", template="plotly_white", height=max(420, len(df) * 28), paper_bgcolor="white", plot_bgcolor="white")
+    fig.update_yaxes(autorange="reversed")
+    return fig
+
+
+def build_top_sellers_chart() -> go.Figure:
+    path = TAB_DIR / "top_titles_by_units_sold.csv"
+    if not path.exists():
+        return empty_chart("Top Sellers")
+    df = pd.read_csv(path).head(15)
+    title_col = next((c for c in df.columns if "title" in c.lower()), df.columns[0])
+    value_col = next((c for c in df.columns if "unit" in c.lower() or "sold" in c.lower()), df.columns[-1])
+    fig = go.Figure(go.Bar(y=df[title_col], x=df[value_col], orientation="h"))
+    fig.update_layout(title="Top Sellers", template="plotly_white", height=max(420, len(df) * 28), paper_bgcolor="white", plot_bgcolor="white")
+    fig.update_yaxes(autorange="reversed")
+    return fig
+
+
+def refresh_table(choice: str | None) -> pd.DataFrame:
+    if not choice:
+        return pd.DataFrame([{"hint": "Choose a table first."}])
+    return load_table(TAB_DIR / choice)
+
+
+def refresh_dashboard() -> tuple:
+    choices = list_tables()
+    selected = choices[0] if choices else None
+    table_df = refresh_table(selected) if selected else pd.DataFrame()
+    return (
+        kpi_cards_html(),
+        build_sales_chart(),
+        build_sentiment_chart(),
+        build_top_sellers_chart(),
+        gallery_items(),
+        gr.update(choices=choices, value=selected),
+        table_df,
+    )
+
+
+ensure_dirs()
+
+with gr.Blocks(title="Notebook Runner Space", css=load_css()) as demo:
+    gr.Markdown(
+        "# ESCP Notebook Runner\n"
+        "Run the bundled notebook on the two bundled CSV datasets, or replace them with your own files."
+    )
+
+    with gr.Tab("1. Run Notebook"):
+        gr.Markdown(
+            "Default project files already included in the Space:\n"
+            "- `analysis.ipynb`\n"
+            "- `synthetic_book_reviews.csv`\n"
+            "- `synthetic_sales_data.csv`\n\n"
+            "You can leave all upload fields empty to use the bundled files."
+        )
+        notebook_file = gr.File(label="Optional notebook (.ipynb)", file_types=[".ipynb"], type="filepath")
+        reviews_file = gr.File(label="Optional reviews CSV", file_types=[".csv"], type="filepath")
+        sales_file = gr.File(label="Optional sales CSV", file_types=[".csv"], type="filepath")
+        run_button = gr.Button("Run Full Pipeline", variant="primary")
+        run_log = gr.Textbox(label="Execution Log", lines=18, interactive=False)
+        run_button.click(run_pipeline, inputs=[notebook_file, reviews_file, sales_file], outputs=run_log)
+
+    with gr.Tab("2. Dashboard"):
+        kpis = gr.HTML(value=kpi_cards_html())
+        refresh_button = gr.Button("Refresh Dashboard", variant="primary")
+        chart_sales = gr.Plot(label="Monthly Overview")
+        chart_sentiment = gr.Plot(label="Sentiment Distribution")
+        chart_top = gr.Plot(label="Top Sellers")
+        gallery = gr.Gallery(label="Generated Figures", columns=2, height=420, object_fit="contain")
+        table_name = gr.Dropdown(label="Generated Tables", choices=[], interactive=True)
+        table_preview = gr.Dataframe(label="Table Preview", interactive=False)
+        refresh_button.click(refresh_dashboard, outputs=[kpis, chart_sales, chart_sentiment, chart_top, gallery, table_name, table_preview])
+        table_name.change(refresh_table, inputs=table_name, outputs=table_preview)
+
+    with gr.Tab("3. Project Files"):
+        gr.Markdown(
+            "The package includes the notebook, the two CSV datasets, `requirements.txt`, `style.css`, and the `artifacts/` folders."
+        )
+
+demo.launch(allowed_paths=[str(BASE_DIR)])

requirements.txt

@@ -0,0 +1,18 @@
+gradio==6.9.0
+pandas==2.2.3
+papermill==2.6.0
+plotly==6.0.1
+matplotlib==3.10.1
+seaborn==0.13.2
+numpy==2.2.4
+statsmodels==0.14.4
+vaderSentiment==3.3.2
+textblob==0.19.0
+faker==37.1.0
+transformers==4.49.0
+huggingface_hub==0.30.2
+requests==2.32.3
+nbformat==5.10.4
+nbclient==0.10.2
+ipykernel==6.29.5
+jupyter-client==8.6.3

style.css

@@ -0,0 +1,33 @@
+body {
+  font-family: Arial, sans-serif;
+}
+
+.card-grid {
+  display: grid;
+  grid-template-columns: repeat(auto-fit, minmax(160px, 1fr));
+  gap: 12px;
+  margin-bottom: 16px;
+}
+
+.card {
+  background: #ffffff;
+  border: 1px solid #e5e7eb;
+  border-radius: 14px;
+  padding: 14px;
+  text-align: center;
+  box-shadow: 0 1px 4px rgba(0,0,0,0.06);
+}
+
+.card .label {
+  font-size: 12px;
+  color: #6b7280;
+  margin-bottom: 6px;
+  text-transform: uppercase;
+  letter-spacing: 0.04em;
+}
+
+.card .value {
+  font-size: 22px;
+  font-weight: 700;
+  color: #111827;
+}