import gradio as gr
from transformers import pipeline
import pandas as pd
from datetime import datetime
import os

# ----------------------------------------------------
# Load pretrained Hugging Face emotion model
# ----------------------------------------------------
model_name = "superb/hubert-large-superb-er"
emotion_classifier = pipeline("audio-classification", model=model_name)

# Emotion mapping
EMOTION_MAP = {
    "ang": ("Angry", "😡"),
    "hap": ("Happy", "😄"),
    "neu": ("Neutral", "😐"),
    "sad": ("Sad", "😢"),
    "exc": ("Excited", "🤩"),
    "fru": ("Frustrated", "😤"),
    "fea": ("Fearful", "😨"),
    "sur": ("Surprised", "😲"),
    "dis": ("Disgusted", "🤢"),
}

# ----------------------------------------------------
# Setup data storage
# ----------------------------------------------------
os.makedirs("data", exist_ok=True)
CSV_PATH = "data/customer_complaints_emotion.csv"

ORDER_ISSUES = [
    "Late Delivery",
    "Damaged Package",
    "Wrong Product Delivered",
    "Missing Items",
    "Rude Delivery Staff",
    "Payment Issue",
    "Return/Refund Request",
    "Order Cancelled Automatically",
    "Other Complaint"
]

# ----------------------------------------------------
# Priority estimation
# ----------------------------------------------------
def get_priority(label, score):
    if label in ["Angry", "Frustrated", "Fearful", "Disgusted"] and score >= 60:
        return "🔴 High Priority"
    elif label in ["Sad", "Surprised", "Excited"] and score >= 50:
        return "🟠 Medium Priority"
    else:
        return "🟢 Low Priority"

# ----------------------------------------------------
# Main analysis function
# ----------------------------------------------------
def analyze_complaint(audio_file, complaint_type, order_id):
    if audio_file is None or not complaint_type or not order_id:
        return (
            "⚠️ Please upload an audio complaint, select issue type, and enter Order ID.",
            "",
            None
        )

    # Run model
    results = emotion_classifier(audio_file)
    results = sorted(results, key=lambda x: x['score'], reverse=True)
    top = results[0]
    label, emoji = EMOTION_MAP.get(top['label'], (top['label'], "🎭"))
    score = round(top['score'] * 100, 2)
    priority = get_priority(label, score)

    # Dashboard summary (markdown)
    summary = f"""
### 🎯 Detected Emotion: {emoji} **{label.upper()} ({score}%)**
### ⚡ Priority Level: {priority}
---
**Complaint Type:** {complaint_type}  
**Order ID:** {order_id}  
**Timestamp:** {datetime.now().strftime("%Y-%m-%d %H:%M:%S")}  
"""

    # Detailed emotion breakdown
    breakdown = "### 📊 Emotion Breakdown\n"
    for r in results:
        lbl, emo = EMOTION_MAP.get(r['label'], (r['label'], "🎭"))
        scr = round(r['score'] * 100, 2)
        bar = "█" * int(scr / 5)
        breakdown += f"{emo} **{lbl}**: {scr}%  \n{bar}\n\n"

    # Save log to CSV
    df = pd.DataFrame({
        "datetime": [datetime.now().strftime("%Y-%m-%d %H:%M:%S")],
        "order_id": [order_id],
        "complaint_type": [complaint_type],
        "emotion": [label],
        "score": [score],
        "priority": [priority]
    })
    if os.path.exists(CSV_PATH):
        df.to_csv(CSV_PATH, mode="a", header=False, index=False)
    else:
        df.to_csv(CSV_PATH, index=False)

    # Display updated log
    try:
        log_df = pd.read_csv(CSV_PATH).tail(10)
    except:
        log_df = pd.DataFrame()

    return summary, breakdown, log_df


# ----------------------------------------------------
# Gradio Interface with Blocks
# ----------------------------------------------------
with gr.Blocks(theme=gr.themes.Soft(), title="Customer Complaint Emotion Analyzer") as app:
    gr.Markdown(
        """
    # 🎧 Customer Complaint Emotion Analyzer  
    Analyze customer **voice complaints** to detect emotional tone and **auto-prioritize** based on urgency.  
    Ideal for logistics, delivery, and supply chain customer service operations.  
    ---
    """
    )

    with gr.Row():
        audio_input = gr.Audio(type="filepath", label="🎙️ Upload Complaint Audio")
        complaint_type = gr.Dropdown(ORDER_ISSUES, label="🚚 Complaint Type", interactive=True)
        order_id = gr.Textbox(label="📦 Order ID / Reference Number", placeholder="e.g., ORD123456")

    analyze_btn = gr.Button("🔍 Analyze Complaint", variant="primary")

    with gr.Row():
        summary_output = gr.Markdown(label="Summary")
        breakdown_output = gr.Markdown(label="Detailed Breakdown")

    with gr.Accordion("📁 Recent Complaint Logs (Last 10 Entries)", open=False):
        log_table = gr.Dataframe(headers=["datetime", "order_id", "complaint_type", "emotion", "score", "priority"], interactive=False)

    analyze_btn.click(
        fn=analyze_complaint,
        inputs=[audio_input, complaint_type, order_id],
        outputs=[summary_output, breakdown_output, log_table],
    )

    gr.Markdown("---")
    gr.Markdown("👨‍💼 **Developed for Supply Chain Customer Service Emotion Monitoring.**")

# ----------------------------------------------------
# Run app
# ----------------------------------------------------
if __name__ == "__main__":
    app.launch()