predicted_labels

predicted_labels = [tokenizer.decode(pred, skip_special_tokens=True) for pred in predictions] # Ground truth labels true_labels = [item['text'] for item in tokenized_datasets['test']] # Calculate accuracy accuracy = accuracy_score(true_la…

dense_scores = np.array([0.7, 0.3, 0.1]) # Normalize and compute hybrid scores hybrid_scores = hybrid_ranking(sparse_scores, dense_scores) print(hybrid_scores) # Optionally, sort documents based on hybrid scores sorted_indices = np.argsor…

dense_scores = np.random.rand(num_queries, num_documents) # Test queries test_queries = np.random.rand(num_queries, num_documents) predictions = [] for i in range(num_queries): query = test_queries[i] sparse_scores_i = sparse_scor…

prediction = rank_documents(query, sparse_scores_i, dense_scores_i) if prediction is not None: predictions.append(prediction) # Evaluate precision true_labels = np.random.randint(0, 2, size=(num_queries, num_documents)) # …

precision = precision_score(true_labels.ravel(), predicted_labels.ravel()) print(f"Precision: {precision:.2f}") ``` ### Explanation 1. **Hybrid Search Function:** - Combines sparse and dense scores using adaptive weights. - Handles …

dense_scores = get_embeddings([query]).dot(embeddings.T) combined_scores = 0.5 * sparse_scores + 0.5 * dense_scores return combined_scores # Example usage documents = ["This is a sample document.", "Este es un documento de mues…

2. **Loop Through Folds**: The `kf.split(X)` method generates indices for the training and validation sets. For each fold, the data is split into `X_train`, `X_val`, `y_train`, and `y_val`. 3. **Fit and Predict**: The model is fitted on th…

logging_dir='./logs', logging_steps=10, evaluation_strategy="epoch", save_total_limit=2, ) # Define Trainer trainer = Trainer( model=model, args=training_args, train_dataset=train_dataset, eval_dataset=test_…