Update functions.py

functions.py

@@ -15,6 +15,7 @@ from nltk.stem import WordNetLemmatizer
 import re
 from sklearn.metrics.pairwise import cosine_similarity
 from sklearn.feature_extraction.text import TfidfVectorizer
+from nltk.corpus import wordnet
 
 
 # In[47]:
@@ -188,51 +189,6 @@ def recommend_from_dataset(query):
     return recommendations
 
 
-# In[36]:
-
-
-# def fine_tune_model(model_name, train_dataset, validation_dataset, epochs=3):
-#     # Load model and tokenizer
-#     model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
-#     tokenizer = AutoTokenizer.from_pretrained(model_name)
-
-#     # Define training arguments (adjust parameters as needed)
-#     training_args = TrainingArguments(
-#         output_dir="./results",  # Adjust output directory
-#         per_device_train_batch_size=8,
-#         per_device_eval_batch_size=8,
-#         num_train_epochs=epochs,
-#         save_steps=10_000,
-#     )
-
-#     # Create a Trainer instance for fine-tuning
-#     trainer = Trainer(
-#         model=model,
-#         args=training_args,
-#         train_dataset=train_dataset,
-#         eval_dataset=validation_dataset,
-#         tokenizer=tokenizer,
-#     )
-
-#     # Train the model
-#     trainer.train()
-
-#     return model
-
-
-# In[39]:
-
-
-# train_dataset = ...  # Prepare your training dataset
-# validation_dataset = ...  # Prepare your validation dataset
-
-# # Fine-tune the model (replace model name if needed)
-# fine_tuned_model = fine_tune_model("facebook/bart-base", train_dataset, validation_dataset)
-
-# # Update summarization pipeline with the fine-tuned model
-# summarizer1 = pipeline("text-generation", model=fine_tuned_model, tokenizer=fine_tuned_model.tokenizer)
-
-
 # In[45]: