import streamlit as st
import numpy as np
import cv2
from PIL import Image
import requests
import face_recognition
from keras.models import load_model
import os

# Set page title and description
st.set_page_config(
    page_title="Face Recognition Attendance System With Emotion Detection",
    page_icon="📷",
    layout="centered",
    initial_sidebar_state="collapsed"
)
st.title("Attendance System Using Face Recognition and Emotion Detection 📷")
st.markdown("This app recognizes faces in an image, detects emotions, and updates attendance records with the current timestamp.")

# Load emotion detection model
@st.cache_resource
def load_emotion_model():
    model = load_model('CNN_Model_acc_75.h5')
    return model

emotion_model = load_emotion_model()

# Emotion labels
emotion_labels = ['angry', 'fear', 'happy', 'neutral', 'sad', 'surprise']

# Load known faces and classnames
Images = []   
classnames = []  

directory = "photos"
myList = os.listdir(directory)

for cls in myList:
    if os.path.splitext(cls)[1] in [".jpg", ".jpeg"]:
        img_path = os.path.join(directory, cls)
        curImg = cv2.imread(img_path)
        Images.append(curImg)
        classnames.append(os.path.splitext(cls)[0])

# Function to update attendance data
def update_data(name, emotion):
    url = "https://huggingface.glitch.me"
    url1 = "/update"
    
    data = {'name': name, 'emotion': emotion}
    try:
        response = requests.post(url + url1, data=data)
        if response.status_code == 200:
            st.success("Attendance updated successfully!")
        else:
            st.warning("Failed to update attendance!")
    except Exception as e:
        st.error(f"Error updating attendance: {e}")

# Function to display image with overlay
def display_image_with_overlay(image, name, emotion):
    cv2.putText(image, f"{name} is feeling {emotion}", (20, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 0, 0), 2)
    st.image(image, use_column_width=True, output_format="PNG")

# Load images for face recognition
encodeListknown = [face_recognition.face_encodings(img)[0] for img in Images]

# Upload image using the file uploader
img_file_buffer = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png"])

if img_file_buffer is not None:
    test_image = Image.open(img_file_buffer)
    image = np.asarray(test_image)

    imgS = cv2.resize(image, (0, 0), None, 0.25, 0.25)
    imgS = cv2.cvtColor(imgS, cv2.COLOR_BGR2RGB)
    facesCurFrame = face_recognition.face_locations(imgS)
    encodesCurFrame = face_recognition.face_encodings(imgS, facesCurFrame)

    name = "Unknown"  # Default name for unknown faces
    match_found = False  # Flag to track if a match is found

    # Emotion detection part
    face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml')
    emotion = "Neutral"  # Default emotion

    if len(encodesCurFrame) > 0:
        for encodeFace, faceLoc in zip(encodesCurFrame, facesCurFrame):
            # Emotion detection
            y1, x2, y2, x1 = faceLoc
            roi = imgS[y1:y2, x1:x2]
            roi = cv2.resize(roi, (48, 48))  # Resize to fit model
            roi = cv2.cvtColor(roi, cv2.COLOR_BGR2RGB)
            roi = np.expand_dims(roi, axis=0) / 255.0  # Preprocess the image
            emotion_predictions = emotion_model.predict(roi)
            emotion = emotion_labels[np.argmax(emotion_predictions)]

            # Face recognition logic
            matches = face_recognition.compare_faces(encodeListknown, encodeFace)
            faceDis = face_recognition.face_distance(encodeListknown, encodeFace)
            matchIndex = np.argmin(faceDis)

            if matches[matchIndex]:
                name = classnames[matchIndex].upper()
                update_data(name, emotion)
                match_found = True
                
            y1, x2, y2, x1 = faceLoc
            y1, x2, y2, x1 = y1 * 4, x2 * 4, y2 * 4, x1 * 4
            cv2.rectangle(image, (x1, y1), (x2, y2), (0, 255, 0), 2)
            cv2.rectangle(image, (x1, y2 - 35), (x2, y2), (0, 255, 0), cv2.FILLED)
            cv2.putText(image, name, (x1 + 6, y2 - 6), cv2.FONT_HERSHEY_COMPLEX, 1, (255, 255, 255), 2)

        display_image_with_overlay(image, name, emotion)

        if match_found:
            st.success(f"Face recognized: {name} and Emotion: {emotion}")
        else:
            st.warning("Face not detected, or no match found in the database.")
    else:
        st.warning("No faces detected in the image. Face recognition failed.")