Spaces:
Running
Running
| import streamlit as st | |
| from transformers import pipeline | |
| import matplotlib.pyplot as plt | |
| import json | |
| import langdetect | |
| from keybert import KeyBERT | |
| # Load models with caching | |
| def load_models(): | |
| return { | |
| "emotion": pipeline("text-classification", model="j-hartmann/emotion-english-distilroberta-base", return_all_scores=True), | |
| "sentiment": pipeline("sentiment-analysis"), | |
| "summarization": pipeline("summarization"), | |
| "ner": pipeline("ner", grouped_entities=True), | |
| "toxicity": pipeline("text-classification", model="unitary/unbiased-toxic-roberta"), | |
| "keyword_extraction": KeyBERT() | |
| } | |
| models=load_models() | |
| # Function: Emotion Detection | |
| def analyze_emotions(text): | |
| results = models["emotion"](text) | |
| emotions = {r['label']: round(r['score'], 2) for r in results[0]} | |
| return emotions | |
| # Function: Sentiment Analysis | |
| def analyze_sentiment(text): | |
| result = models["sentiment"](text)[0] | |
| return {result['label']: round(result['score'], 2)} | |
| # Function: Text Summarization | |
| def summarize_text(text): | |
| summary = models["summarization"](text[:1024])[0]['summary_text'] # Limit input to 1024 tokens | |
| return summary | |
| # Function: Keyword Extraction | |
| def extract_keywords(text): | |
| return models["keyword_extraction"].extract_keywords(text, keyphrase_ngram_range(1, 2), stop_words='english') | |
| # Function: Named Entity Recognition (NER) | |
| def analyze_ner(text): | |
| entities = models["ner"](text) | |
| return {entity["word"]: entity["entity_group"] for entity in entities} | |
| # Function: Language Detection and Translation | |
| def detect_language(text): | |
| try: | |
| lang = langdetect.detect(text) | |
| return lang | |
| except: | |
| return "Error detecting language" | |
| # Function: Toxicity Detection | |
| def detect_toxicity(text): | |
| results = models["toxicity"](text) | |
| return {results[0]['label']: round(results[0]['score'], 2)} | |
| # Streamlit UI | |
| st.title("🚀 AI-Powered Text Intelligence App") | |
| st.markdown("Analyze text with multiple NLP features: Emotion Detection, Sentiment Analysis, Summarization, NER, Keywords, Language Detection, and more!") | |
| # User Input | |
| text_input = st.text_area("Enter text to analyze:", "") | |
| if st.button("Analyze Text"): | |
| if text_input.strip(): | |
| st.subheader("🔹 Emotion Detection") | |
| emotions = analyze_emotions(text_input) | |
| st.json(emotions) | |
| st.subheader("🔹 Sentiment Analysis") | |
| sentiment = analyze_sentiment(text_input) | |
| st.json(sentiment) | |
| st.subheader("🔹 Text Summarization") | |
| summary = summarize_text(text_input) | |
| st.write(summary) | |
| st.subheader("🔹 Keyword Extraction") | |
| keywords = extract_keywords(text_input) | |
| st.json(keywords) | |
| st.subheader("🔹 Named Entity Recognition (NER)") | |
| ner_data = analyze_ner(text_input) | |
| st.json(ner_data) | |
| st.subheader("🔹 Language Detection") | |
| lang = detect_language(text_input) | |
| st.write(f"Detected Language: `{lang}`") | |
| st.subheader("🔹 Toxicity Detection") | |
| toxicity = detect_toxicity(text_input) | |
| st.json(toxicity) | |
| # JSON Download | |
| result_data = { | |
| "emotion": emotions, | |
| "sentiment": sentiment, | |
| "summary": summary, | |
| "keywords": keywords, | |
| "ner": ner_data, | |
| "language": lang, | |
| "toxicity": toxicity | |
| } | |
| json_result = json.dumps(result_data, indent=2) | |
| st.download_button("Download Analysis Report", data=json_result, file_name="text_analysis.json", mime="application/json") | |
| else: | |
| st.warning("⚠️ Please enter some text to analyze") |