feat: initial commit

pyproject.toml

@@ -0,0 +1,24 @@
+[tool.poetry]
+name = "submission-template"
+version = "0.1.0"
+description = ""
+authors = ["clemdesr <[email protected]>"]
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = "^3.11"
+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"
+gradio = ">=4.0.0"
+requests = ">=2.31.0"
+librosa = "0.10.2.post1"
+
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

tasks/text.py

@@ -1,23 +1,24 @@
-from fastapi import APIRouter
+import random
 from datetime import datetime
+
 from datasets import load_dataset
+from fastapi import APIRouter
 from sklearn.metrics import accuracy_score
-import random
 
+from .utils.emissions import clean_emissions_data, get_space_info, tracker
 from .utils.evaluation import TextEvaluationRequest
-from .utils.emissions import tracker, clean_emissions_data, get_space_info
 
 router = APIRouter()
 
-DESCRIPTION = "Random Baseline"
+DESCRIPTION = "Setup Baseline"
 ROUTE = "/text"
 
-@router.post(ROUTE, tags=["Text Task"], 
-             description=DESCRIPTION)
+
+@router.post(ROUTE, tags=["Text Task"], description=DESCRIPTION)
 async def evaluate_text(request: TextEvaluationRequest):
     """
     Evaluate text classification for climate disinformation detection.
-    
+
     Current Model: Random Baseline
     - Makes random predictions from the label space (0-7)
     - Used as a baseline for comparison
@@ -34,7 +35,7 @@ async def evaluate_text(request: TextEvaluationRequest):
         "4_solutions_harmful_unnecessary": 4,
         "5_science_unreliable": 5,
         "6_proponents_biased": 6,
-        "7_fossil_fuels_needed": 7
+        "7_fossil_fuels_needed": 7,
     }
 
     # Load and prepare the dataset
@@ -46,31 +47,30 @@ async def evaluate_text(request: TextEvaluationRequest):
     # 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")
 
-    #--------------------------------------------------------------------------------------------
+    # --------------------------------------------------------------------------------------------
     # YOUR MODEL INFERENCE CODE HERE
     # Update the code below to replace the random baseline by your model inference within the inference pass where the energy consumption and emissions are tracked.
-    #--------------------------------------------------------------------------------------------   
-    
+    # --------------------------------------------------------------------------------------------
+
     # Make random predictions (placeholder for actual model inference)
     true_labels = test_dataset["label"]
     predictions = [random.randint(0, 7) for _ in range(len(true_labels))]
 
-    #--------------------------------------------------------------------------------------------
+    # --------------------------------------------------------------------------------------------
     # YOUR MODEL INFERENCE STOPS HERE
-    #--------------------------------------------------------------------------------------------   
+    # --------------------------------------------------------------------------------------------
 
-    
     # Stop tracking emissions
     emissions_data = tracker.stop_task()
-    
+
     # Calculate accuracy
     accuracy = accuracy_score(true_labels, predictions)
-    
+
     # Prepare results dictionary
     results = {
         "username": username,
@@ -85,8 +85,8 @@ async def evaluate_text(request: TextEvaluationRequest):
         "dataset_config": {
             "dataset_name": request.dataset_name,
             "test_size": request.test_size,
-            "test_seed": request.test_seed
-        }
+            "test_seed": request.test_seed,
+        },
     }
-    
-    return results 
+
+    return results