Update tasks/text.py

tasks/text.py

@@ -1,29 +1,31 @@
 from fastapi import APIRouter
 from datetime import datetime
 from datasets import load_dataset
-from sklearn.feature_extraction.text import TfidfVectorizer
-from sklearn.naive_bayes import MultinomialNB
-from sklearn.svm import SVC
 from sklearn.metrics import accuracy_score
+import random
 
 from .utils.evaluation import TextEvaluationRequest
 from .utils.emissions import tracker, clean_emissions_data, get_space_info
 
-# Define the router for text tasks
 router = APIRouter()
 
-DESCRIPTION_NAIVE_BAYES = "Naive Bayes Text Classifier"
-DESCRIPTION_SVM = "SVM Text Classifier with TF-IDF"
+DESCRIPTION = "Random Baseline"
+ROUTE = "/text"
 
-# Naive Bayes Endpoint
-@router.post("/text", tags=["Text Task"], description=DESCRIPTION_NAIVE_BAYES)
+@router.post(ROUTE, tags=["Text Task"], 
+             description=DESCRIPTION)
 async def evaluate_text(request: TextEvaluationRequest):
     """
-    Evaluate text classification using Naive Bayes.
+    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
     """
+    # Get space info
     username, space_url = get_space_info()
 
-    # Label Mapping
+    # Define the label mapping
     LABEL_MAPPING = {
         "0_not_relevant": 0,
         "1_not_happening": 1,
@@ -35,114 +37,56 @@ async def evaluate_text(request: TextEvaluationRequest):
         "7_fossil_fuels_needed": 7
     }
 
-    # Load and prepare dataset
+    # Load and prepare the dataset
     dataset = load_dataset(request.dataset_name)
-    dataset = dataset.map(lambda x: {"label": LABEL_MAPPING[x["label"]]})
-
-    # Train-Test Split
-    train_test = dataset["train"].train_test_split(test_size=request.test_size, seed=request.test_seed)
-    train_texts = [x["text"] for x in train_test["train"]]
-    train_labels = [x["label"] for x in train_test["train"]]
-    test_texts = [x["text"] for x in train_test["test"]]
-    test_labels = [x["label"] for x in train_test["test"]]
-
-    # TF-IDF Vectorization
-    vectorizer = TfidfVectorizer(max_features=5000)
-    train_vectors = vectorizer.fit_transform(train_texts)
-    test_vectors = vectorizer.transform(test_texts)
-
-    # Train Naive Bayes Classifier
-    model = MultinomialNB()
-    model.fit(train_vectors, train_labels)
-
-    # Track emissions
-    tracker.start()
-    tracker.start_task("inference")
-    predictions = model.predict(test_vectors)
-    emissions_data = tracker.stop_task()
-
-    # Calculate Accuracy
-    accuracy = accuracy_score(test_labels, predictions)
-
-    return {
-        "username": username,
-        "space_url": space_url,
-        "submission_timestamp": datetime.now().isoformat(),
-        "model_description": DESCRIPTION_NAIVE_BAYES,
-        "accuracy": float(accuracy),
-        "energy_consumed_wh": emissions_data.energy_consumed * 1000,
-        "emissions_gco2eq": emissions_data.emissions * 1000,
-        "emissions_data": clean_emissions_data(emissions_data),
-        "api_route": "/text",
-        "dataset_config": {
-            "dataset_name": request.dataset_name,
-            "test_size": request.test_size,
-            "test_seed": request.test_seed
-        }
-    }
 
-# SVM Endpoint
-@router.post("/text_svm", tags=["Text Task"], description=DESCRIPTION_SVM)
-async def evaluate_text_svm(request: TextEvaluationRequest):
-    """
-    Evaluate text classification using SVM.
-    """
-    username, space_url = get_space_info()
-
-    # 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 dataset
-    dataset = load_dataset(request.dataset_name)
+    # Convert string labels to integers
     dataset = dataset.map(lambda x: {"label": LABEL_MAPPING[x["label"]]})
 
-    # Train-Test Split
-    train_test = dataset["train"].train_test_split(test_size=request.test_size, seed=request.test_seed)
-    train_texts = [x["text"] for x in train_test["train"]]
-    train_labels = [x["label"] for x in train_test["train"]]
-    test_texts = [x["text"] for x in train_test["test"]]
-    test_labels = [x["label"] for x in train_test["test"]]
-
-    # TF-IDF Vectorization
-    vectorizer = TfidfVectorizer(max_features=5000)
-    train_vectors = vectorizer.fit_transform(train_texts)
-    test_vectors = vectorizer.transform(test_texts)
-
-    # Train SVM Classifier
-    model = SVC(kernel="linear", probability=True)
-    model.fit(train_vectors, train_labels)
-
-    # Track emissions
+    # Split dataset
+    train_test = dataset["train"]
+    test_dataset = dataset["test"]
+    
+    # Start tracking emissions
     tracker.start()
     tracker.start_task("inference")
-    predictions = model.predict(test_vectors)
-    emissions_data = tracker.stop_task()
 
-    # Calculate Accuracy
-    accuracy = accuracy_score(test_labels, predictions)
-
-    return {
+    #--------------------------------------------------------------------------------------------
+    # 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,
         "space_url": space_url,
         "submission_timestamp": datetime.now().isoformat(),
-        "model_description": DESCRIPTION_SVM,
+        "model_description": 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),
-        "api_route": "/text_svm",
+        "api_route": ROUTE,
         "dataset_config": {
             "dataset_name": request.dataset_name,
             "test_size": request.test_size,
             "test_seed": request.test_seed
         }
     }
+    
+    return results