Update app.py

app.py

@@ -12,8 +12,10 @@ from transformers import AutoModelForSequenceClassification, AutoTokenizer, Auto
 from deap import base, creator, tools, algorithms
 import nltk
 from nltk.sentiment import SentimentIntensityAnalyzer
+from nltk.tokenize import word_tokenize
+from nltk.tag import pos_tag
+from nltk.chunk import ne_chunk
 from textblob import TextBlob
-import spacy
 import matplotlib.pyplot as plt
 import seaborn as sns
 
@@ -22,28 +24,9 @@ warnings.filterwarnings('ignore', category=FutureWarning, module='huggingface_hu
 # Download necessary NLTK data
 nltk.download('vader_lexicon', quiet=True)
 nltk.download('punkt', quiet=True)
-
-def download_spacy_model():
-    subprocess.check_call([sys.executable, "-m", "spacy", "download", "en_core_web_sm"])
-
-try:
-    import spacy
-    try:
-        nlp = spacy.load("en_core_web_sm")
-    except OSError:
-        print("Downloading spaCy model...")
-        download_spacy_model()
-        nlp = spacy.load("en_core_web_sm")
-except ImportError:
-    print("Error: Unable to import spaCy. NLP features will be disabled.")
-    nlp = None
-
-def extract_entities(text):
-    if nlp is None:
-        return []
-    doc = nlp(text)
-    entities = [(ent.text, ent.label_) for ent in doc.ents]
-    return entities
+nltk.download('averaged_perceptron_tagger', quiet=True)
+nltk.download('maxent_ne_chunker', quiet=True)
+nltk.download('words', quiet=True)
 
 # Initialize Example Dataset (For Emotion Prediction)
 data = {
@@ -239,8 +222,11 @@ def sentiment_analysis(text):
     return sentiment_scores
 
 def extract_entities(text):
-    doc = nlp(text)
-    entities = [(ent.text, ent.label_) for ent in doc.ents]
+    chunked = ne_chunk(pos_tag(word_tokenize(text)))
+    entities = []
+    for chunk in chunked:
+        if hasattr(chunk, 'label'):
+            entities.append(((' '.join(c[0] for c in chunk)), chunk.label()))
     return entities
 
 def analyze_text_complexity(text):
@@ -301,15 +287,15 @@ def interactive_interface(input_text):
 def gradio_interface(input_text):
     response = interactive_interface(input_text)
     if isinstance(response, str):
-        return response
+        return response, None
     else:
         return (
             f"Predicted Emotion: {response['predicted_emotion']}\n"
             f"Sentiment: {response['sentiment_scores']}\n"
             f"Entities: {response['entities']}\n"
             f"Text Complexity: {response['text_complexity']}\n"
-            f"Response: {response['response']}\n"
-            f"Emotion Visualization: {response['emotion_visualization']}"
+            f"Response: {response['response']}\n",
+            response['emotion_visualization']
         )
 
 # Create Gradio interface
@@ -323,3 +309,4 @@ iface = gr.Interface(
 
 if __name__ == "__main__":
     iface.launch()
+