Update app.py

app.py

@@ -1,33 +1,21 @@
 import gradio as gr
-from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification
+from transformers import pipeline
 import pandas as pd
 import os
 import re
 
-# -----------------------------
-# Load Models
-# -----------------------------
-english_model = pipeline(
-    "sentiment-analysis",
-    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"
-)
-
-roman_urdu_model = pipeline(
-    "sentiment-analysis",
-    model="tahamueed23/fine_tuned_cardiffnlp_urdu_and_roman-urdu"
-)
+# --- models (keep yours) ---
+english_model = pipeline("sentiment-analysis", model="siebert/sentiment-roberta-large-english")
+urdu_model = pipeline("sentiment-analysis", model="tahamueed23/fine_tuned_cardiffnlp_urdu_and_roman-urdu")
+roman_urdu_model = pipeline("sentiment-analysis", model="tahamueed23/fine_tuned_cardiffnlp_urdu_and_roman-urdu")
 
+# --- CSV setup (UTF-8 with BOM) ---
 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)
+    df_init = pd.DataFrame(columns=["Sentence", "Language", "Sentiment", "Confidence"])
+    df_init.to_csv(SAVE_FILE, index=False, encoding="utf-8-sig")   # write BOM + UTF-8
 
+# --- helper functions (keep yours) ---
 def detect_language(text):
     urdu_chars = set("ابتثجحخدذرزسشصضطظعغفقکلمنوہیءآؤئۀ")
     if any(ch in urdu_chars for ch in text):
@@ -48,20 +36,20 @@ def normalize_label(label):
 
 def sentiment_with_tips(sentiment):
     tips = {
-        "Positive": "😊 Great! Keep spreading positivity.",
-        "Negative": "😞 It seems negative. Try to focus on solutions.",
-        "Neutral": "😐 Neutral statement. Could go either way."
+        "Positive": "😊 Great! Keep it up.",
+        "Negative": "😞 Looks negative. Consider constructive changes.",
+        "Neutral": "😐 Neutral — neither strongly positive nor negative."
     }
     return tips.get(sentiment, "")
 
+# --- main analyze function (writes UTF-8 rows safely) ---
 def analyze_sentiment(text, lang_hint):
-    if not text.strip():
+    if not text or 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
+    # Choose model
     if lang == "English":
         result = english_model(text)[0]
     elif lang == "Urdu":
@@ -69,45 +57,15 @@ def analyze_sentiment(text, lang_hint):
     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
-    df = pd.read_csv(SAVE_FILE)
-    new_row = pd.DataFrame([[text, lang, sentiment, score]], 
+    # Prepare row and append using utf-8-sig (Excel-friendly)
+    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)
-
-    return f"{sentiment}", f"{score}", f"{explanation}", SAVE_FILE
-
-with gr.Blocks() as demo:
-    gr.Markdown(
-        "## 🌍 Multilingual Sentiment Analysis (English • Urdu • Roman Urdu)\n"
-        "Detect sentiment as **Positive, Neutral, or Negative** with confidence score.\n\n"
-        "📌 Features:\n"
-        "- Choose language (or Auto Detect)\n"
-        "- Download all results as CSV\n"
-        "- Emojis + Tips for better understanding 🎯"
-    )
-
-    with gr.Row():
-        with gr.Column():
-            user_text = gr.Textbox(label="✍️ Enter text", placeholder="Type in English, Urdu, or Roman Urdu...")
-            lang_dropdown = gr.Dropdown(["Auto Detect", "English", "Urdu", "Roman Urdu"],
-                                        label="🌐 Language", value="Auto Detect")
-            btn = gr.Button("🔍 Analyze")
-
-        with gr.Column():
-            out_sent = gr.Textbox(label="Sentiment")
-            out_conf = gr.Textbox(label="Confidence (0–1)")
-            out_exp  = gr.Textbox(label="Explanation")
-            out_file = gr.File(label="⬇️ Download Logs (.csv)", type="filepath")
 
-    btn.click(analyze_sentiment, inputs=[user_text, lang_dropdown],
-              outputs=[out_sent, out_conf, out_exp, out_file])
+    # Append: header only if file missing (safe even if file exists)
+    new_row.to_csv(SAVE_FILE, mode="a", index=False, header=not os.path.exists(SAVE_FILE), encoding="utf-8-sig")
 
-if __name__ == "__main__":
-    demo.launch()
+    return sentiment, str(score), explanation, SAVE_FILE