Update code to be 1 task only

app.py

@@ -1,56 +1,27 @@
 import pandas as pd
-import spacy
-import gradio as gr
-from nrclex import NRCLex
 from transformers import pipeline
-from rake_nltk import Rake
+import gradio as gr
 import io
-import spacy.cli
-
-# Download the spaCy model
-spacy.cli.download("en_core_web_sm")
 
-# Initialize objects
-emotion_pipeline = pipeline('sentiment-analysis', model='nlptown/bert-base-multilingual-uncased-sentiment')
-nlp = spacy.load('en_core_web_sm')
-rake = Rake()
+# Initialize sentiment analysis pipeline
+sentiment_pipeline = pipeline('sentiment-analysis')
 
 def process_csv(file):
     df = pd.read_csv(io.StringIO(file.decode('utf-8')))
-    emotions = []
     sentiments = []
-    entities = []
-    keywords = []
     for _, row in df.iterrows():
         text = row['Content']
-        nrc_obj = NRCLex(text)
-        emotion_scores = nrc_obj.affect_frequencies
-        emotions.append(emotion_scores)
-        sentiment = analyze_emotion(text)
+        sentiment = analyze_sentiment(text)
         sentiments.append(sentiment)
-        entities.append(analyze_entities(text))
-        keywords.append(extract_keywords(text))
 
-    df['emotions'] = emotions
     df['sentiment'] = sentiments
-    df['entities'] = entities
-    df['keywords'] = keywords
 
     return df.to_csv(index=False)
 
-def analyze_emotion(text):
-    result = emotion_pipeline(text)[0]
+def analyze_sentiment(text):
+    result = sentiment_pipeline(text)[0]
     sentiment = result['label']
     return sentiment
 
-def analyze_entities(text):
-    doc = nlp(text)
-    entities = [(ent.text, ent.label_) for ent in doc.ents]
-    return entities
-
-def extract_keywords(text):
-    rake.extract_keywords_from_text(text)
-    return rake.get_ranked_phrases()
-
 iface = gr.Interface(fn=process_csv, inputs=gr.inputs.Textbox(lines=13, label="Paste CSV Here"), outputs="text")
 iface.launch()