Update app.py

app.py

@@ -1,50 +1,131 @@
 import gradio as gr
-import pandas as pd
 from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification
-from langdetect import detect
-
-# Load models
-models = {
-    "en": pipeline("sentiment-analysis", model="siebert/sentiment-roberta-large-english"),
-    "ur": pipeline("sentiment-analysis", model="tahamueed23/fine_tuned_cardiffnlp_urdu_and_roman-urdu"),  # replace with your trained Urdu model
-    "roman-ur": pipeline("sentiment-analysis", model="tahamueed23/fine_tuned_cardiffnlp_urdu_and_roman-urdu")  # replace with your trained Roman Urdu model
-}
-
-CSV_FILE = "sentiment_results.csv"
-
-def analyze_text(text):
-    try:
-        lang = detect(text)
-    except:
-        lang = "en"
-
-    if lang.startswith("ur"):
-        model = models["ur"]
-    elif any(word.isascii() for word in text):  # crude roman urdu check
-        model = models["roman-ur"]
+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"
+)
+
+# -----------------------------
+# CSV Setup
+# -----------------------------
+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)
+
+# -----------------------------
+# Language Detection (simple rule-based)
+# -----------------------------
+def detect_language(text):
+    urdu_chars = set("ابتثجحخدذرزسشصضطظعغفقکلمنوہیءآؤئۀ")
+    if any(ch in urdu_chars for ch in text):
+        return "Urdu"
+    roman_urdu_pattern = r"\b(hai|kia|kyun|nahi|bohot|acha|galat|sahi|parhai|ustad|pyar|dil|insaan)\b"
+    if re.search(roman_urdu_pattern, text.lower()):
+        return "Roman Urdu"
+    return "English"
+
+# -----------------------------
+# Normalize Sentiment Labels
+# -----------------------------
+def normalize_label(label):
+    label = label.lower()
+    if "positive" in label:
+        return "Positive"
+    elif "negative" in label:
+        return "Negative"
+    else:
+        return "Neutral"
+
+# -----------------------------
+# Add Emojis + Tips
+# -----------------------------
+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."
+    }
+    return tips.get(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:
-        model = models["en"]
+        result = roman_urdu_model(text)[0]
 
-    result = model(text)[0]
-    sentiment = result["label"]
+    # Process results
+    sentiment = normalize_label(result["label"])
     score = round(result["score"], 3)
+    explanation = sentiment_with_tips(sentiment)
 
     # Save to CSV
-    df = pd.DataFrame([[text, lang, sentiment, score]], 
-                      columns=["Sentence", "Language", "Sentiment", "Confidence"])
-    try:
-        old = pd.read_csv(CSV_FILE, encoding="utf-8-sig")
-        df = pd.concat([old, df], ignore_index=True)
-    except:
-        pass
-    df.to_csv(CSV_FILE, index=False, encoding="utf-8-sig")
-
-    return f"Language: {lang} | Sentiment: {sentiment} ({score})"
-
-demo = gr.Interface(fn=analyze_text, 
-                    inputs="text", 
-                    outputs="text", 
-                    title="Multilingual Sentiment Analysis")
+    df = pd.read_csv(SAVE_FILE)
+    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
+
+# -----------------------------
+# Gradio UI
+# -----------------------------
+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])
 
 if __name__ == "__main__":
     demo.launch()