Update app.py

app.py

@@ -1,29 +1,27 @@
 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
+# Load Pretrained Models
 @st.cache_resource
 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),
+        "sentiment": pipeline("text-classification", model="nlptown/bert-base-multilingual-uncased-sentiment"),
+        "summarization": pipeline("summarization", model="facebook/bart-large-cnn"),
+        "ner": pipeline("ner", model="dbmdz/bert-large-cased-finetuned-conll03-english", grouped_entities=True),
         "toxicity": pipeline("text-classification", model="unitary/unbiased-toxic-roberta"),
         "keyword_extraction": KeyBERT()
     }
 
-models=load_models()
+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
+    return {r['label']: round(r['score'], 2) for r in results[0]}
 
 # Function: Sentiment Analysis
 def analyze_sentiment(text):
@@ -32,23 +30,21 @@ def analyze_sentiment(text):
 
 # Function: Text Summarization
 def summarize_text(text):
-    summary = models["summarization"](text[:1024])[0]['summary_text']      # Limit input to 1024 tokens
-    return summary
+    return models["summarization"](text[:1024])[0]['summary_text']
 
 # Function: Keyword Extraction
 def extract_keywords(text):
-    return models["keyword_extraction"].extract_keywords(text, keyphrase_ngram_range(1, 2), stop_words='english')
+    return models["keyword_extraction"].extract_keywords(text, 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
+# Function: Language Detection
 def detect_language(text):
     try:
-        lang = langdetect.detect(text)
-        return lang
+        return langdetect.detect(text)
     except:
         return "Error detecting language"
 
@@ -57,7 +53,6 @@ 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!")
@@ -68,46 +63,36 @@ 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.json(analyze_emotions(text_input))
 
         st.subheader("🔹 Sentiment Analysis")
-        sentiment = analyze_sentiment(text_input)
-        st.json(sentiment)
+        st.json(analyze_sentiment(text_input))
 
         st.subheader("🔹 Text Summarization")
-        summary = summarize_text(text_input)
-        st.write(summary)
+        st.write(summarize_text(text_input))
 
         st.subheader("🔹 Keyword Extraction")
-        keywords = extract_keywords(text_input)
-        st.json(keywords)
+        st.json(extract_keywords(text_input))
 
         st.subheader("🔹 Named Entity Recognition (NER)")
-        ner_data = analyze_ner(text_input)
-        st.json(ner_data)
+        st.json(analyze_ner(text_input))
 
         st.subheader("🔹 Language Detection")
-        lang = detect_language(text_input)
-        st.write(f"Detected Language: `{lang}`")
+        st.write(f"Detected Language: `{detect_language(text_input)}`")
 
         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
+        st.json(detect_toxicity(text_input))
+
+        # Save results to JSON
+        results = {
+            "emotion": analyze_emotions(text_input),
+            "sentiment": analyze_sentiment(text_input),
+            "summary": summarize_text(text_input),
+            "keywords": extract_keywords(text_input),
+            "ner": analyze_ner(text_input),
+            "language": detect_language(text_input),
+            "toxicity": detect_toxicity(text_input)
         }
-
-        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")
+        st.download_button("Download JSON Report", json.dumps(results, indent=2), "text_analysis.json", "application/json")
     else:
-        st.warning("⚠️ Please enter some text to analyze")
+        st.warning("⚠️ Please enter some text to analyze.")