Update app.py

app.py

@@ -2,66 +2,118 @@ import gradio as gr
 from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification
 import pandas as pd
 import os
+import re
 
 # -----------------------------
 # Load Models
 # -----------------------------
-# English sentiment model (CardiffNLP)
-en_model = pipeline("sentiment-analysis", model="cardiffnlp/twitter-roberta-base-sentiment")
+english_model = pipeline(
+    "sentiment-analysis",
+    model="cardiffnlp/twitter-roberta-base-sentiment-latest"
+)
 
-# Urdu / Roman Urdu fine-tuned model (replace with your Hugging Face repo ID)
-ur_model_name = "tahamueed23/roman-urdu-sentiment"  
-ur_tokenizer = AutoTokenizer.from_pretrained(ur_model_name)
-ur_model = AutoModelForSequenceClassification.from_pretrained(ur_model_name)
-ur_pipeline = pipeline("sentiment-analysis", model=ur_model, tokenizer=ur_tokenizer)
+# Replace with your own fine-tuned models
+urdu_model = pipeline(
+    "sentiment-analysis",
+    model="tahamueed23/urdu-roman-urdu-sentiment"
+)
+
+roman_urdu_model = pipeline(
+    "sentiment-analysis",
+    model="tahamueed23/urdu-roman-urdu-sentiment"
+)
 
 # -----------------------------
 # CSV Setup
 # -----------------------------
-csv_file = "sentiment_logs.csv"
-if not os.path.exists(csv_file):
-    df = pd.DataFrame(columns=["Sentence", "Language", "Sentiment"])
-    df.to_csv(csv_file, index=False)
+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)
 
 # -----------------------------
-# Processing Function
+# Language Detection (simple rule-based)
 # -----------------------------
-def analyze_sentiment(sentence, language):
-    try:
-        if language == "English":
-            result = en_model(sentence)[0]
-        else:
-            # Urdu or Roman Urdu
-            result = ur_pipeline(sentence)[0]
-
-        label = result["label"]
-        score = round(result["score"], 3)
-
-        # Save to CSV
-        new_row = pd.DataFrame([[sentence, language, f"{label} ({score})"]],
-                               columns=["Sentence", "Language", "Sentiment"])
-        df = pd.read_csv(csv_file)
-        df = pd.concat([df, new_row], ignore_index=True)
-        df.to_csv(csv_file, index=False)
-
-        # Output
-        return f"**Language Selected:** {language}\n**Sentiment:** {label}\n**Confidence:** {score}"
-
-    except Exception as e:
-        return f"⚠️ Error: {str(e)}"
+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"
+
+def normalize_label(label):
+    label = label.lower()
+    if "positive" in label:
+        return "Positive"
+    elif "negative" in label:
+        return "Negative"
+    else:
+        return "Neutral"
+
+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, "")
+
+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
+    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 App
-# -----------------------------
 with gr.Blocks() as demo:
-    gr.Markdown("## 🌍 Multilingual Sentiment Analysis (English, Urdu, Roman Urdu)")
-    gr.Markdown("Enter a sentence and select the language to detect sentiment.")
+    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")
 
-    input_text = gr.Textbox(label="Enter your sentence:")
-    lang_dropdown = gr.Dropdown(choices=["English", "Urdu", "Roman Urdu"], label="Select Language")
-    output_text = gr.Markdown(label="Result")
+        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 = gr.Button("Analyze Sentiment")
-    btn.click(analyze_sentiment, inputs=[input_text, lang_dropdown], outputs=output_text)
+    btn.click(analyze_sentiment, inputs=[user_text, lang_dropdown],
+              outputs=[out_sent, out_conf, out_exp, out_file])
 
-demo.launch()
+if __name__ == "__main__":
+    demo.launch()