Update app.py

app.py

@@ -1,5 +1,5 @@
 import gradio as gr
-from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification
+from transformers import pipeline
 import pandas as pd
 import os
 import re
@@ -12,7 +12,6 @@ english_model = pipeline(
     model="siebert/sentiment-roberta-large-english"
 )
 
-# Replace with your own fine-tuned models
 urdu_model = pipeline(
     "sentiment-analysis",
     model="tahamueed23/fine_tuned_cardiffnlp_urdu_and_roman-urdu"
@@ -28,8 +27,9 @@ roman_urdu_model = pipeline(
 # -----------------------------
 SAVE_FILE = "sentiment_logs.csv"
 if not os.path.exists(SAVE_FILE):
-    df = pd.DataFrame(columns=["Sentence", "Language", "Sentiment", "Confidence"])
-    df.to_csv(SAVE_FILE, index=False)
+    pd.DataFrame(columns=["Sentence", "Language", "Sentiment", "Confidence"]).to_csv(
+        SAVE_FILE, index=False, encoding="utf-8-sig"
+    )
 
 # -----------------------------
 # Language Detection (simple rule-based)
@@ -48,9 +48,9 @@ def detect_language(text):
 # -----------------------------
 def normalize_label(label):
     label = label.lower()
-    if "positive" in label:
+    if "pos" in label or "positive" in label:
         return "Positive"
-    elif "negative" in label:
+    elif "neg" in label or "negative" in label:
         return "Negative"
     else:
         return "Neutral"
@@ -70,38 +70,41 @@ def sentiment_with_tips(sentiment):
 # Main Sentiment Function
 # -----------------------------
 def analyze_sentiment(text, lang_hint):
-    if not text.strip():
-        return "⚠️ Please enter a sentence.", "", "", SAVE_FILE
-
-    # Auto detect if language hint is not clear
-    lang = lang_hint if lang_hint != "Auto Detect" else detect_language(text)
-
-    # Select model
-    if lang == "English":
-        result = english_model(text)[0]
-    elif lang == "Urdu":
-        result = urdu_model(text)[0]
-    else:
-        result = roman_urdu_model(text)[0]
-
-    # Process results
-    sentiment = normalize_label(result["label"])
-    score = round(result["score"], 3)
-    explanation = sentiment_with_tips(sentiment)
-
-    # Save to CSV
     try:
-        df = pd.read_csv(SAVE_FILE, encoding="utf-8-sig")
-    except:
-        df = pd.DataFrame(columns=["Sentence", "Language", "Sentiment", "Confidence"])
-
-    new_row = pd.DataFrame([[text, lang, sentiment, score]], 
-                           columns=["Sentence", "Language", "Sentiment", "Confidence"])
-    df = pd.concat([df, new_row], ignore_index=True)
-
-    # Save with proper encoding for Urdu
-    df.to_csv(SAVE_FILE, index=False, encoding="utf-8-sig")
-
+        if not text.strip():
+            return "⚠️ Please enter a sentence.", "", "", SAVE_FILE
+
+        # Auto detect if language hint is not selected
+        lang = lang_hint if lang_hint != "Auto Detect" else detect_language(text)
+
+        # Select model
+        if lang == "English":
+            result = english_model(text)[0]
+        elif lang == "Urdu":
+            result = urdu_model(text)[0]
+        else:
+            result = roman_urdu_model(text)[0]
+
+        # Process results
+        sentiment = normalize_label(result["label"])
+        score = round(float(result["score"]), 3)
+        explanation = sentiment_with_tips(sentiment)
+
+        # Save to CSV (UTF-8 safe)
+        try:
+            df = pd.read_csv(SAVE_FILE, encoding="utf-8-sig")
+        except:
+            df = pd.DataFrame(columns=["Sentence", "Language", "Sentiment", "Confidence"])
+
+        new_row = pd.DataFrame([[text, lang, sentiment, score]],
+                               columns=["Sentence", "Language", "Sentiment", "Confidence"])
+        df = pd.concat([df, new_row], ignore_index=True)
+        df.to_csv(SAVE_FILE, index=False, encoding="utf-8-sig")
+
+        return sentiment, str(score), explanation, SAVE_FILE
+
+    except Exception as e:
+        return f"⚠️ Error: {str(e)}", "", "", SAVE_FILE
 
 # -----------------------------
 # Gradio UI