Upload 3 files

README.md

@@ -0,0 +1,23 @@
+---
+title: Interactive Notebook Runner
+emoji: 📓
+colorFrom: blue
+colorTo: purple
+sdk: gradio
+app_file: app.py
+pinned: false
+---
+
+# Interactive Notebook Runner
+
+Upload a Jupyter notebook and two CSV files, preview them, then run the notebook.
+
+## Important build note
+Do **not** pin `gradio` in `requirements.txt` on this Space template.
+Hugging Face already installs a managed Gradio version during the build.
+
+## How to use
+1. Upload a notebook in the app, or add `analysis_notebook.ipynb` to the Space root.
+2. Upload two CSV files in the app, or add the default CSVs to the Space root.
+3. Adjust the execution filenames if your notebook expects specific names.
+4. Click **Run notebook**.

app.py

@@ -0,0 +1,245 @@
+# AI-Assisted Code — Academic Integrity Notice
+# Generated with The App Builder. ESCP coursework.
+# Student must be able to explain all code when asked.
+
+"""Interactive Hugging Face Space to run a Jupyter notebook on two CSV files."""
+
+from __future__ import annotations
+
+import io
+import os
+import re
+import shutil
+import tempfile
+import traceback
+import zipfile
+from pathlib import Path
+
+import gradio as gr
+import nbformat
+import pandas as pd
+from nbclient import NotebookClient
+
+
+DEFAULT_NOTEBOOK = "analysis_notebook.ipynb"
+DEFAULT_CSV_1 = "synthetic_book_reviews.csv"
+DEFAULT_CSV_2 = "synthetic_sales_data.csv"
+
+
+def locate_default_file(file_name: str) -> Path | None:
+    """Return a default file path if it exists in the Space root."""
+    candidate = Path(file_name)
+    return candidate if candidate.exists() else None
+
+
+def safe_copy(source_path: str | Path, target_path: Path) -> None:
+    """Copy a file into the execution folder."""
+    shutil.copy2(str(source_path), str(target_path))
+
+
+def read_csv_preview(file_obj, rows: int = 8) -> pd.DataFrame:
+    """Load a preview of a CSV file for the UI."""
+    if file_obj is None:
+        return pd.DataFrame({"message": ["No file selected."]})
+    return pd.read_csv(file_obj.name).head(rows)
+
+
+def prepare_inputs(
+    notebook_file,
+    csv_file_1,
+    csv_file_2,
+    notebook_name: str,
+    csv_name_1: str,
+    csv_name_2: str,
+) -> tuple[Path, Path]:
+    """Create a temporary run folder and place notebook/data files inside it."""
+    run_dir = Path(tempfile.mkdtemp(prefix="hf_notebook_run_"))
+
+    resolved_notebook = notebook_file.name if notebook_file else None
+    resolved_csv_1 = csv_file_1.name if csv_file_1 else None
+    resolved_csv_2 = csv_file_2.name if csv_file_2 else None
+
+    if resolved_notebook is None:
+        default_notebook = locate_default_file(DEFAULT_NOTEBOOK)
+        if default_notebook is None:
+            raise FileNotFoundError(
+                "Notebook missing. Upload a .ipynb file in the app or add "
+                f"{DEFAULT_NOTEBOOK} to the Space root."
+            )
+        resolved_notebook = default_notebook
+
+    if resolved_csv_1 is None:
+        default_csv_1 = locate_default_file(DEFAULT_CSV_1)
+        if default_csv_1 is None:
+            raise FileNotFoundError(
+                "CSV 1 missing. Upload a CSV in the app or add "
+                f"{DEFAULT_CSV_1} to the Space root."
+            )
+        resolved_csv_1 = default_csv_1
+
+    if resolved_csv_2 is None:
+        default_csv_2 = locate_default_file(DEFAULT_CSV_2)
+        if default_csv_2 is None:
+            raise FileNotFoundError(
+                "CSV 2 missing. Upload a CSV in the app or add "
+                f"{DEFAULT_CSV_2} to the Space root."
+            )
+        resolved_csv_2 = default_csv_2
+
+    notebook_target = run_dir / notebook_name.strip()
+    csv_target_1 = run_dir / csv_name_1.strip()
+    csv_target_2 = run_dir / csv_name_2.strip()
+
+    safe_copy(resolved_notebook, notebook_target)
+    safe_copy(resolved_csv_1, csv_target_1)
+    safe_copy(resolved_csv_2, csv_target_2)
+
+    return run_dir, notebook_target
+
+
+def clean_notebook_cells(notebook) -> None:
+    """Remove shell install commands that often break in managed Spaces."""
+    filtered_cells = []
+    for cell in notebook.cells:
+        if cell.get("cell_type") != "code":
+            filtered_cells.append(cell)
+            continue
+        source = cell.get("source", "")
+        if "!pip install" in source or "%pip install" in source:
+            continue
+        filtered_cells.append(cell)
+    notebook.cells = filtered_cells
+
+
+def collect_text_output(executed_notebook) -> str:
+    """Extract text outputs from notebook cells for display in the UI."""
+    collected = []
+    for index, cell in enumerate(executed_notebook.cells, start=1):
+        if cell.get("cell_type") != "code":
+            continue
+        outputs = cell.get("outputs", [])
+        for output in outputs:
+            if output.get("output_type") == "stream":
+                text = output.get("text", "").strip()
+                if text:
+                    collected.append(f"Cell {index}\n{text}")
+            if output.get("output_type") == "execute_result":
+                data = output.get("data", {})
+                text = data.get("text/plain", "")
+                if text:
+                    collected.append(f"Cell {index}\n{text}")
+    return "\n\n" + ("\n\n".join(collected[:20]) if collected else "No text output captured.")
+
+
+def build_output_zip(run_dir: Path) -> str:
+    """Zip run artifacts so the user can download them."""
+    zip_path = run_dir / "run_outputs.zip"
+    with zipfile.ZipFile(zip_path, "w", zipfile.ZIP_DEFLATED) as archive:
+        for item in run_dir.iterdir():
+            if item.is_file():
+                archive.write(item, arcname=item.name)
+    return str(zip_path)
+
+
+def run_notebook(
+    notebook_file,
+    csv_file_1,
+    csv_file_2,
+    notebook_name: str,
+    csv_name_1: str,
+    csv_name_2: str,
+):
+    """Execute the notebook and return logs, summary, and downloadable files."""
+    try:
+        run_dir, notebook_path = prepare_inputs(
+            notebook_file,
+            csv_file_1,
+            csv_file_2,
+            notebook_name,
+            csv_name_1,
+            csv_name_2,
+        )
+
+        with open(notebook_path, "r", encoding="utf-8") as handle:
+            notebook = nbformat.read(handle, as_version=4)
+
+        clean_notebook_cells(notebook)
+        client = NotebookClient(notebook, timeout=900, kernel_name="python3")
+        executed_notebook = client.execute(cwd=str(run_dir))
+
+        executed_path = run_dir / "executed_notebook.ipynb"
+        with open(executed_path, "w", encoding="utf-8") as handle:
+            nbformat.write(executed_notebook, handle)
+
+        summary = collect_text_output(executed_notebook)
+        output_zip = build_output_zip(run_dir)
+        log = "Execution successful."
+        return log, summary, str(executed_path), output_zip
+
+    except Exception:
+        error_text = traceback.format_exc()
+        return f"Execution failed.\n\n{error_text}", "", None, None
+
+
+with gr.Blocks(title="Interactive Notebook Runner") as demo:
+    gr.Markdown(
+        """
+        # Interactive Notebook Runner
+
+        Upload a Jupyter notebook and two CSV files, preview the datasets,
+        choose the execution file names, then run the notebook inside the Space.
+        """
+    )
+
+    with gr.Row():
+        notebook_input = gr.File(label="Notebook (.ipynb)", file_types=[".ipynb"])
+        csv_input_1 = gr.File(label="CSV file 1", file_types=[".csv"])
+        csv_input_2 = gr.File(label="CSV file 2", file_types=[".csv"])
+
+    with gr.Row():
+        notebook_name = gr.Textbox(
+            label="Notebook filename during execution",
+            value=DEFAULT_NOTEBOOK,
+        )
+        csv_name_1 = gr.Textbox(
+            label="CSV 1 filename during execution",
+            value=DEFAULT_CSV_1,
+        )
+        csv_name_2 = gr.Textbox(
+            label="CSV 2 filename during execution",
+            value=DEFAULT_CSV_2,
+        )
+
+    preview_button = gr.Button("Refresh previews")
+    with gr.Row():
+        preview_1 = gr.Dataframe(label="Preview CSV 1")
+        preview_2 = gr.Dataframe(label="Preview CSV 2")
+
+    run_button = gr.Button("Run notebook")
+    status_box = gr.Textbox(label="Execution log", lines=14)
+    summary_box = gr.Textbox(label="Notebook output summary", lines=14)
+    executed_file = gr.File(label="Executed notebook")
+    zip_file = gr.File(label="Download outputs ZIP")
+
+    preview_button.click(
+        fn=lambda a, b: (read_csv_preview(a), read_csv_preview(b)),
+        inputs=[csv_input_1, csv_input_2],
+        outputs=[preview_1, preview_2],
+    )
+
+    run_button.click(
+        fn=run_notebook,
+        inputs=[
+            notebook_input,
+            csv_input_1,
+            csv_input_2,
+            notebook_name,
+            csv_name_1,
+            csv_name_2,
+        ],
+        outputs=[status_box, summary_box, executed_file, zip_file],
+    )
+
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,8 @@
+pandas==2.2.2
+nbformat==5.10.4
+nbclient==0.10.0
+ipykernel==6.29.5
+jupyter-core==5.7.2
+vaderSentiment==3.3.2
+matplotlib==3.9.2
+numpy==2.1.1