import gradio as gr import torch # import nltk # from nltk.corpus import stopwords # from nltk.stem import WordNetLemmatizer from nltk.tokenize import word_tokenize import string from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification, AutoModelForTokenClassification, AutoConfig # Load your model and tokenizer from local paths using SafeTensors model_NER = AutoModelForTokenClassification.from_pretrained("./NER_model") tokenizer_NER = AutoTokenizer.from_pretrained("./tokenizer_NER") model_path = './model' tokenizer_path = './tokenizer' model_sentiment = AutoModelForSequenceClassification.from_pretrained(model_path) tokenizer_sentiment = AutoTokenizer.from_pretrained(tokenizer_path) clf_sentiment = pipeline("text-classification", model=model_sentiment, tokenizer=tokenizer_sentiment) clf_ner = pipeline("ner", model=model_NER, tokenizer=tokenizer_NER) config = AutoConfig.from_pretrained("./NER_model") label_list = config.id2label # def preprocess(text): # stop_words = set(stopwords.words('english')) # lemmatizer = WordNetLemmatizer() # tokens = word_tokenize(text) # processed = [lemmatizer.lemmatize(word.lower()) for word in tokens if word.isalpha() and word not in stop_words] # return ' '.join(processed) def analyze_sentiment(text): # text = preprocess(text) predictions = clf_sentiment(text) label_mapping = {'LABEL_0': 'Negative', 'LABEL_1': 'Neutral', 'LABEL_2': 'Positive'} predicted_label = label_mapping[predictions[0]['label']] confidence = f"{predictions[0]['score'] * 100:.2f}%" return f"Predicted Label: {predicted_label}\nConfidence: {confidence}" LABEL = ['O', 'B-storage', 'I-storage', 'B-performance', 'I-performance', 'B-battery', 'I-battery', 'B-camera', 'I-camera', 'B-charging', 'I-charging', 'B-screen', 'I-screen', 'B-audio', 'I-audio', 'B-feature', 'I-feature', 'B-connection', 'I-connection', 'B-button', 'I-button'] def analyze_ner(text): text = word_tokenize(text) text = [word for word in text if word not in string.punctuation] text = ' '.join(text) predictions = clf_ner(text) print(predictions) # Debugging statement to see the structure of the output keys = [] values = [] for i, label in enumerate(LABEL): keys.append(f'LABEL_{i}') values.append(label) label_mapping = { k:v for (k,v) in zip(keys, values) } results = [] for pred in predictions: result = f"""Word: {pred['word']} Predicted Tag: {label_mapping[pred['entity']]} Confidence Probability: {pred['score']}\n""" results.append(result) return "\n".join(results) def analyze_text(text): sentiment_result = analyze_sentiment(text) ner_result = analyze_ner(text) return sentiment_result, ner_result interface = gr.Interface( fn=analyze_text, inputs=gr.Textbox(lines=2, placeholder="Enter text here..."), outputs=[ gr.Textbox(label="Sentiment Analysis Result"), gr.Textbox(label="Named Entity Recognition Result") ], title="Text Analysis", description="This interface allows you to perform Sentiment Analysis and Named Entity Recognition (NER) on text." ) if __name__ == "__main__": interface.launch(share=True)