First commit

.dockerignore

@@ -0,0 +1,27 @@
+.git
+.gitignore
+.gitattributes
+README.md
+.env
+.env.local
+__pycache__
+*.pyc
+*.pyo
+*.pyd
+.Python
+env/
+venv/
+.venv
+*.egg-info/
+dist/
+build/
+.pytest_cache/
+.coverage
+htmlcov/
+*.egg
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+.DS_Store

Dockerfile

@@ -0,0 +1,35 @@
+FROM python:3.12-slim
+
+# Force rebuild - cache busting
+LABEL build_date="$(date)"
+
+# Install system dependencies as root
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    build-essential \
+    && rm -rf /var/lib/apt/lists/*
+
+# Create a non-root user
+RUN useradd -m -u 1000 user
+USER user
+ENV PATH="/home/user/.local/bin:$PATH"
+
+WORKDIR /app
+
+# Cache busting - force rebuild on new push
+ARG BUILD_DATE
+RUN echo "Build date: ${BUILD_DATE}"
+
+# Copy source code and dependency files FIRST (needed by flit)
+COPY --chown=user pyproject.toml ./
+COPY --chown=user nygaardcodecommentclassification ./nygaardcodecommentclassification
+COPY --chown=user app.py ./
+
+# Install Python dependencies
+RUN pip install --no-cache-dir --upgrade pip && \
+    pip install --no-cache-dir -e ".[frontend]"
+
+# Expose port
+EXPOSE 7860
+
+# Run gradio on port 7860
+CMD ["python", "app.py"]

README.md

@@ -1,10 +1,39 @@
 ---
 title: NygaardCodeComment Frontend
-emoji: 🔥
-colorFrom: yellow
-colorTo: blue
+emoji: 🏆
+colorFrom: blue
+colorTo: red
 sdk: docker
+docker:
+  dockerfile: ./Dockerfile
+  port: 7860
+env:
+  - name: API_URL
+    default: https://se4ai2526-uniba-nygaard-nygaardcodecomment-backend.hf.space/
 pinned: false
 ---
 
+# 🔍 Nygaard Code Comment Classifier - Frontend
+
+This is the frontend interface for the Nygaard Code Comment Classification system, built with Gradio.
+
+## Overview
+
+This Gradio application provides a user-friendly interface to classify code comments into multiple categories across different programming languages (Java, Python, Pharo).
+
+## Deployment on Hugging Face Spaces
+
+The application is configured to run on Hugging Face Spaces using Docker. The frontend connects to the backend API hosted at `https://se4ai2526-uniba-nygaard-nygaardcodecomment-backend.hf.space/`.
+
+### Configuration
+
+- **SDK**: Docker
+- **Port**: 7860
+- **Python Version**: 3.12
+- **Backend API**: https://se4ai2526-uniba-nygaard-nygaardcodecomment-backend.hf.space/
+
+### Environment Variables
+
+- `API_URL`: URL of the backend API (default: https://se4ai2526-uniba-nygaard-nygaardcodecomment-backend.hf.space/)
+
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,12 @@
+"""Gradio Frontend Application Entry Point for Hugging Face Spaces.
+
+This file serves as the entry point for the Gradio application when deployed
+on Hugging Face Spaces. HF Spaces expects an app.py file in the root directory.
+"""
+
+from nygaardcodecommentclassification.api.frontend import gradio_app
+
+if __name__ == "__main__":
+    # Launch the Gradio app
+    # HF Spaces automatically sets the correct port and host
+    gradio_app.launch(server_name="0.0.0.0", server_port=7860)

nygaardcodecommentclassification/__init__.py

@@ -0,0 +1,15 @@
+"""Nygaard Code Comment Classification package.
+
+This package provides utilities to download, clean, featurize, train, and
+evaluate models for code comment classification across multiple languages
+(`java`, `python`, and `pharo`).
+
+Available submodules
+--------------------
+- `config`: Project paths, constants, and logging setup.
+- `dataset`: Dataset download and cleaning routines.
+- `features`: Feature extraction (embeddings and labels) utilities.
+- `plots`: Basic plotting CLI scaffold.
+- `modeling.train`: Training entry points (CatBoost and SetFit).
+- `modeling.predict`: Evaluation and MLflow logging utilities.
+"""

nygaardcodecommentclassification/api/frontend.py

@@ -0,0 +1,230 @@
+"""Gradio Frontend Application.
+
+This module provides a web-based user interface for the code comment classification API.
+Users can input code comments and get real-time predictions through an interactive interface.
+"""
+
+import os
+
+import gradio as gr
+import requests
+
+# API configuration for deploy
+API_URL = os.getenv("API_URL", "https://se4ai2526-uniba-nygaard-nygaardcodecomment-backend.hf.space/")
+
+
+def get_categories_for_language(language: str) -> str:
+    """Get supported categories for a specific programming language.
+
+    Args:
+        language: The programming language
+
+    Returns:
+        Formatted string with supported categories
+    """
+    categories = {
+        "Java": [
+            "summary: A brief description of the behavior of the code",
+            "Ownership: Describes the authors and ownership",
+            "Expand: Aims to describe the associated code",
+            "usage: Describes how to use the code",
+            "Pointer: Points to related code or resources",
+            "deprecation: Indicates deprecated code",
+            "rational: Explains the reasoning behind the implementation",
+        ],
+        "Python": [
+            "Usage: Describes usage of the code",
+            "Parameters: Documents function/method parameters",
+            "DevelopmentNotes: Contains notes for developers",
+            "Expand: Provides detailed explanations",
+            "Summary: Summarizes the functionality",
+        ],
+        "Pharo": [
+            "Keyimplementationpoints: Highlights key implementation details",
+            "Example: Provides code examples",
+            "Responsibilities: Describes object responsibilities",
+            "Intent: Explains the intent or purpose",
+            "Keymessages: Documents key messages or methods",
+            "Collaborators: Lists collaborating objects/classes",
+        ],
+    }
+
+    lang_categories = categories.get(language, [])
+    if lang_categories:
+        return f"**Supported Categories for {language}:**\n" + "\n".join(
+            f"- {cat}" for cat in lang_categories
+        )
+    return "**Supported Categories:** Not available"
+
+
+def predict_gradio(text: str, language: str) -> str:
+    """Gradio interface function for single text prediction.
+
+    Args:
+        text: The code comment to classify
+        language: The programming language
+
+    Returns:
+        Formatted HTML string with prediction results
+    """
+    if not text.strip():
+        return """
+        <div style="background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
+                    border-radius: 10px; padding: 20px; margin: 10px 0;
+                    color: white; text-align: center; font-weight: bold;">
+            ⚠️ Please enter a code comment to classify.
+        </div>
+        """
+
+    try:
+        # Call the API
+        response = requests.post(
+            f"{API_URL}/predict",
+            json={"texts": [text], "language": language.lower(), "model_type": "catboost"},
+            timeout=30,
+        )
+
+        if response.status_code == 200:
+            data = response.json()
+            results = data.get("data", {}).get("results", [])
+
+            if results and len(results) > 0:
+                labels = results[0].get("labels", [])
+                if labels:
+                    labels_html = "".join(
+                        [
+                            f'<span style="background: #4CAF50; color: white; padding: 4px 8px; '
+                            f'margin: 2px; border-radius: 12px; font-size: 14px; display: inline-block;">'
+                            f"🏷️ {label}</span>"
+                            for label in labels
+                        ]
+                    )
+                    return f"""
+                    <div style="background: linear-gradient(135deg, #4CAF50 0%, #45a049 100%);
+                                border-radius: 15px; padding: 20px; margin: 10px 0;
+                                box-shadow: 0 4px 6px rgba(0,0,0,0.1);">
+                        <h3 style="color: white; margin: 0 0 15px 0; text-align: center;">
+                            ✅ Prediction Successful
+                        </h3>
+                        <div style="text-align: center;">
+                            {labels_html}
+                        </div>
+                    </div>
+                    """
+                return """
+                <div style="background: linear-gradient(135deg, #ff9800 0%, #f57c00 100%);
+                            border-radius: 10px; padding: 20px; margin: 10px 0;
+                            color: white; text-align: center; font-weight: bold;">
+                    📊 No labels predicted (below threshold)
+                </div>
+                """
+            return """
+            <div style="background: linear-gradient(135deg, #9c27b0 0%, #7b1fa2 100%);
+                        border-radius: 10px; padding: 20px; margin: 10px 0;
+                        color: white; text-align: center; font-weight: bold;">
+                🔍 No prediction results available
+            </div>
+            """
+        else:
+            return f"""
+            <div style="background: linear-gradient(135deg, #f44336 0%, #d32f2f 100%);
+                        border-radius: 10px; padding: 20px; margin: 10px 0;
+                        color: white; text-align: center; font-weight: bold;">
+                ❌ API Error: {response.status_code}<br>
+                <small style="font-weight: normal;">{response.text}</small>
+            </div>
+            """
+
+    except requests.exceptions.ConnectionError:
+        return f"""
+        <div style="background: linear-gradient(135deg, #607d8b 0%, #455a64 100%);
+                    border-radius: 10px; padding: 20px; margin: 10px 0;
+                    color: white; text-align: center; font-weight: bold;">
+            🌐 Connection Error<br>
+            <small style="font-weight: normal;">Cannot connect to API at {API_URL}</small>
+        </div>
+        """
+    except requests.exceptions.Timeout:
+        return """
+        <div style="background: linear-gradient(135deg, #ff5722 0%, #d84315 100%);
+                    border-radius: 10px; padding: 20px; margin: 10px 0;
+                    color: white; text-align: center; font-weight: bold;">
+            ⏱️ Timeout Error<br>
+            <small style="font-weight: normal;">The request took too long</small>
+        </div>
+        """
+    except Exception as e:
+        return f"""
+        <div style="background: linear-gradient(135deg, #9e9e9e 0%, #757575 100%);
+                    border-radius: 10px; padding: 20px; margin: 10px 0;
+                    color: white; text-align: center; font-weight: bold;">
+            ⚠️ Unexpected Error<br>
+            <small style="font-weight: normal;">{str(e)}</small>
+        </div>
+        """
+
+
+def update_categories(language: str) -> str:
+    """Update the categories display when language changes.
+
+    Args:
+        language: The selected programming language
+
+    Returns:
+        Updated description text with categories
+    """
+    return get_categories_for_language(language)
+
+
+# Create Gradio interface with dynamic categories
+with gr.Blocks(title="🔍 Nygaard Code Comment Classifier") as gradio_app:
+    gr.Markdown("# 🔍 Nygaard Code Comment Classifier")
+    gr.Markdown("Classify code comments into multiple categories using machine learning.")
+
+    # Language selector
+    language_dropdown = gr.Dropdown(
+        choices=["Java", "Python", "Pharo"], label="Programming Language", value="Python"
+    )
+
+    # Dynamic categories display
+    categories_display = gr.Markdown(value=get_categories_for_language("Python"))
+
+    # Connect language change to categories update
+    language_dropdown.change(
+        fn=update_categories, inputs=language_dropdown, outputs=categories_display
+    )
+
+    # Input components
+    with gr.Row():
+        text_input = gr.Textbox(
+            label="Code Comment", placeholder="Enter your code comment here...", lines=5
+        )
+
+    # Output
+    output_display = gr.HTML(label="Prediction Result")
+
+    # Buttons
+    with gr.Row():
+        clear_btn = gr.Button("Clear", variant="secondary")
+        submit_btn = gr.Button("Submit", variant="primary")
+
+    gr.Examples(
+        examples=[
+            ["@deprecated Use newMethod() instead", "Java"],
+            ["This method calculates the factorial of a number", "Python"],
+            ["Returns the sum of all elements in the collection", "Pharo"],
+        ],
+        inputs=[text_input, language_dropdown],
+    )
+
+    # Connect clear button to reset inputs
+    clear_btn.click(fn=lambda: ("", "Python"), inputs=[], outputs=[text_input, language_dropdown])
+
+    # Connect submit button to prediction function
+    submit_btn.click(
+        fn=predict_gradio, inputs=[text_input, language_dropdown], outputs=output_display
+    )
+
+
+if __name__ == "__main__":
+    gradio_app.launch(server_name="0.0.0.0", server_port=7860)

pyproject.toml

@@ -0,0 +1,89 @@
+[build-system]
+requires = ["flit_core >=3.2,<4"]
+build-backend = "flit_core.buildapi"
+
+[project]
+name = "nygaardcodecommentclassification"
+version = "0.0.1"
+description = "This task is about Code Comment Classification for 3 different programming languages. This task is inspired by a challenge and will be used for the SEAES course"
+authors = [
+  { name = "Your name (or your organization/company/team)" },
+]
+
+classifiers = [
+    "Programming Language :: Python :: 3",
+    
+]
+dependencies = []
+requires-python = "~=3.12.0"
+
+[project.optional-dependencies]
+api = [
+    "catboost>=1.2.8",
+    "dagshub>=0.6.3",
+    "fastapi>=0.115.0",
+    "joblib>=1.4.0",
+    "loguru",
+    "mlflow==2.22.0",
+    "numpy>=1.26.0",
+    "python-multipart>=0.0.20",
+    "setfit>=1.1.3",
+    "torch>=2.7.0",
+    "uvicorn>=0.32.0",
+    "python-dotenv",
+]
+
+dev = [
+    "mkdocs",
+    "pre-commit>=4.3.0",
+    "pytest",
+    "ruff",
+]
+
+training = [
+    "datasets==4.3.0",
+    "deepchecks[nlp]>=0.19.1",
+    "optuna>=4.5.0",
+    "tqdm",
+    "typer",
+]
+
+frontend = [
+    "gradio>=5.0.0",
+    "requests",
+]
+
+all = [
+    "nygaardcodecommentclassification[api,dev,training,frontend]",
+]
+
+[tool.uv]
+override-dependencies = ["pyarrow==21.0.0"]
+
+[tool.ruff]
+line-length = 99
+src = ["nygaardcodecommentclassification"]
+include = ["pyproject.toml", "nygaardcodecommentclassification/**/*.py", "tests/**/*.py"]
+
+[tool.ruff.lint]
+extend-select = ["I"]  # Add import sorting
+# Enable all `pydocstyle` rules, limiting to those that adhere to the
+# Google convention via `convention = "google"`, below.
+select = ["D"]
+
+[tool.ruff.lint.isort]
+known-first-party = ["nygaardcodecommentclassification"]
+force-sort-within-sections = true
+
+[tool.ruff.lint.pydocstyle]
+convention = "google"
+
+[tool.uv.sources]
+torch = [
+    { index = "pytorch-gpu" },
+]
+
+[[tool.uv.index]]
+name = "pytorch-gpu"
+url = "https://download.pytorch.org/whl/cu130"
+explicit = true