Updated API submission

.gitignore

@@ -0,0 +1,17 @@
+.ipynb_checkpoints/sandbox-checkpoint.ipynb
+
+auto_evals/
+venv/
+__pycache__/
+.env
+.ipynb_checkpoints
+*ipynb
+.vscode/
+
+eval-queue/
+eval-results/
+eval-queue-bk/
+eval-results-bk/
+logs/
+
+emissions.csv

Dockerfile

@@ -0,0 +1,16 @@
+# Read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
+# you will also find guides on how best to write your Dockerfile
+
+FROM python:3.9
+
+RUN useradd -m -u 1000 user
+USER user
+ENV PATH="/home/user/.local/bin:$PATH"
+
+WORKDIR /app
+
+COPY --chown=user ./requirements.txt requirements.txt
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+COPY --chown=user . /app
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,27 @@
+from fastapi import FastAPI
+from dotenv import load_dotenv
+from tasks import text, image, audio
+
+# Load environment variables
+load_dotenv()
+
+app = FastAPI(
+    title="Frugal AI Challenge API",
+    description="API for the Frugal AI Challenge evaluation endpoints"
+)
+
+# Include all routers
+app.include_router(text.router)
+app.include_router(image.router)
+app.include_router(audio.router)
+
+@app.get("/")
+async def root():
+    return {
+        "message": "Welcome to the Frugal AI Challenge API",
+        "endpoints": {
+            "text": "/text - Text classification task",
+            "image": "/image - Image classification task (coming soon)",
+            "audio": "/audio - Audio classification task (coming soon)"
+        }
+    } 

requirements.txt

@@ -0,0 +1,7 @@
+fastapi>=0.68.0
+uvicorn>=0.15.0
+codecarbon>=2.3.1
+datasets>=2.14.0
+scikit-learn>=1.0.2
+pydantic>=1.10.0
+python-dotenv>=1.0.0

tasks/audio.py

@@ -0,0 +1,23 @@
+from fastapi import APIRouter
+from .utils.evaluation import AudioEvaluationRequest
+from .utils.emissions import get_space_info
+
+router = APIRouter()
+
+@router.post("/audio", tags=["Audio Task"])
+async def evaluate_audio(request: AudioEvaluationRequest):
+    """
+    Placeholder for audio task evaluation.
+    """
+    username, space_url = get_space_info()
+    return {
+        "message": "Audio evaluation endpoint not yet implemented",
+        "username": username,
+        "space_url": space_url,
+        "received_config": {
+            "dataset_name": request.dataset_name,
+            "test_size": request.test_size,
+            "test_seed": request.test_seed,
+            "model_description": request.model_description
+        }
+    } 

tasks/image.py

@@ -0,0 +1,23 @@
+from fastapi import APIRouter
+from .utils.evaluation import ImageEvaluationRequest
+from .utils.emissions import get_space_info
+
+router = APIRouter()
+
+@router.post("/image", tags=["Image Task"])
+async def evaluate_image(request: ImageEvaluationRequest):
+    """
+    Placeholder for image task evaluation.
+    """
+    username, space_url = get_space_info()
+    return {
+        "message": "Image evaluation endpoint not yet implemented",
+        "username": username,
+        "space_url": space_url,
+        "received_config": {
+            "dataset_name": request.dataset_name,
+            "test_size": request.test_size,
+            "test_seed": request.test_seed,
+            "model_description": request.model_description
+        }
+    } 

tasks/text.py

@@ -0,0 +1,73 @@
+from fastapi import APIRouter
+from datetime import datetime
+from datasets import load_dataset
+from sklearn.metrics import accuracy_score
+import random
+
+from .utils.evaluation import TextEvaluationRequest
+from .utils.emissions import tracker, clean_emissions_data, get_space_info
+
+router = APIRouter()
+
+@router.post("/text", tags=["Text Task"])
+async def evaluate_text(request: TextEvaluationRequest):
+    """
+    Evaluate a text classification model for climate disinformation detection.
+    """
+    # Get space info
+    username, space_url = get_space_info()
+
+    # Define the label mapping
+    LABEL_MAPPING = {
+        "0_not_relevant": 0,
+        "1_not_happening": 1,
+        "2_not_human": 2,
+        "3_not_bad": 3,
+        "4_solutions_harmful_unnecessary": 4,
+        "5_science_unreliable": 5,
+        "6_proponents_biased": 6,
+        "7_fossil_fuels_needed": 7
+    }
+
+    # Load and prepare the dataset
+    dataset = load_dataset(request.dataset_name)
+
+    # Convert string labels to integers
+    dataset = dataset.map(lambda x: {"label": LABEL_MAPPING[x["label"]]})
+
+    # Split dataset
+    train_test = dataset["train"].train_test_split(test_size=request.test_size, seed=request.test_seed)
+    test_dataset = train_test["test"]
+    
+    # Start tracking emissions
+    tracker.start()
+    tracker.start_task("inference")
+    
+    # Make random predictions (placeholder for actual model inference)
+    true_labels = test_dataset["label"]
+    predictions = [random.randint(0, 7) for _ in range(len(true_labels))]
+    
+    # Stop tracking emissions
+    emissions_data = tracker.stop_task()
+    
+    # Calculate accuracy
+    accuracy = accuracy_score(true_labels, predictions)
+    
+    # Prepare results dictionary
+    results = {
+        "username": username,
+        "space_url": space_url,
+        "submission_timestamp": datetime.now().isoformat(),
+        "model_description": request.model_description,
+        "accuracy": float(accuracy),
+        "energy_consumed_wh": emissions_data.energy_consumed * 1000,
+        "emissions_gco2eq": emissions_data.emissions * 1000,
+        "emissions_data": clean_emissions_data(emissions_data),
+        "dataset_config": {
+            "dataset_name": request.dataset_name,
+            "test_size": request.test_size,
+            "test_seed": request.test_seed
+        }
+    }
+    
+    return results 

tasks/utils/emissions.py

@@ -0,0 +1,28 @@
+from codecarbon import EmissionsTracker
+import os
+
+# Initialize tracker
+tracker = EmissionsTracker(allow_multiple_runs=True)
+
+class EmissionsData:
+    def __init__(self, energy_consumed: float, emissions: float):
+        self.energy_consumed = energy_consumed
+        self.emissions = emissions
+
+def clean_emissions_data(emissions_data):
+    """Remove unwanted fields from emissions data"""
+    data_dict = emissions_data.__dict__
+    fields_to_remove = ['timestamp', 'project_name', 'experiment_id', 'latitude', 'longitude']
+    return {k: v for k, v in data_dict.items() if k not in fields_to_remove}
+
+def get_space_info():
+    """Get the space username and URL from environment variables"""
+    space_name = os.getenv("SPACE_ID", "")
+    if space_name:
+        try:
+            username = space_name.split("/")[0]
+            space_url = f"https://huggingface.co/spaces/{space_name}"
+            return username, space_url
+        except Exception as e:
+            print(f"Error getting space info: {e}")
+    return "local-user", "local-development" 

tasks/utils/evaluation.py

@@ -0,0 +1,19 @@
+from typing import Optional
+from pydantic import BaseModel, Field
+
+class BaseEvaluationRequest(BaseModel):
+    test_size: float = Field(0.2, ge=0.0, le=1.0, description="Size of the test split (between 0 and 1)")
+    test_seed: int = Field(42, ge=0, description="Random seed for reproducibility")
+    model_description: Optional[str] = Field("No description provided", description="Description of the model being evaluated")
+
+class TextEvaluationRequest(BaseEvaluationRequest):
+    dataset_name: str = Field("QuotaClimat/frugalaichallenge-text-train", 
+                            description="The name of the dataset on HuggingFace Hub")
+
+class ImageEvaluationRequest(BaseEvaluationRequest):
+    dataset_name: str = Field("placeholder/frugalaichallenge-image-train", 
+                            description="The name of the dataset on HuggingFace Hub")
+
+class AudioEvaluationRequest(BaseEvaluationRequest):
+    dataset_name: str = Field("placeholder/frugalaichallenge-audio-train", 
+                            description="The name of the dataset on HuggingFace Hub")