import streamlit as st
import cv2
import numpy as np
import time
from keras.models import load_model
from PIL import Image
from huggingface_hub import HfApi, Repository
import os
import tempfile

# Page configuration
st.set_page_config(page_title="Emotion Detection", layout="centered")

# Title and Subtitle
st.markdown("<h1 style='text-align: center;'>Emotion Detection</h1>", unsafe_allow_html=True)
st.markdown("<h3 style='text-align: center;'>angry, fear, happy, neutral, sad, surprise</h3>", unsafe_allow_html=True)

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

start_time = time.time()
model = load_emotion_model()
st.write(f"Model loaded in {time.time() - start_time:.2f} seconds.")

# Emotion labels and constants
emotion_labels = ['angry', 'fear', 'happy', 'neutral', 'sad', 'surprise']
img_shape = 48
face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml')

def process_frame(frame):
    """Detect faces and predict emotions."""
    gray_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
    faces = face_cascade.detectMultiScale(gray_frame, scaleFactor=1.1, minNeighbors=5, minSize=(30, 30))
    for (x, y, w, h) in faces:
        roi_gray = gray_frame[y:y+h, x:x+w]
        roi_color = frame[y:y+h, x:x+w]
        face_roi = cv2.resize(roi_color, (img_shape, img_shape))
        face_roi = np.expand_dims(face_roi, axis=0)
        face_roi = face_roi / float(img_shape)
        predictions = model.predict(face_roi)
        emotion = emotion_labels[np.argmax(predictions[0])]

        # Draw rectangle and emotion label
        cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 2)
        cv2.putText(frame, emotion, (x, y + h + 20), cv2.FONT_HERSHEY_SIMPLEX, 0.8, (0, 255, 0), 2)
    return frame

# Sidebar for input selection
st.sidebar.title("Choose Input Source")
upload_choice = st.sidebar.radio("Select:", ["Camera", "Upload Video", "Upload Image", "Upload to Hugging Face"])

if upload_choice == "Camera":
    # Use Streamlit's camera input widget
    st.sidebar.info("Click a picture to analyze emotion.")
    picture = st.camera_input("Take a picture")
    if picture:
        image = Image.open(picture)
        frame = np.array(image)
        frame = process_frame(frame)
        st.image(frame, caption="Processed Image", use_column_width=True)

elif upload_choice == "Upload Video":
    uploaded_video = st.file_uploader("Upload Video", type=["mp4", "mov", "avi", "mkv", "webm"])
    if uploaded_video:
        with tempfile.NamedTemporaryFile(delete=False) as tfile:
            tfile.write(uploaded_video.read())
            video_source = cv2.VideoCapture(tfile.name)
            frame_placeholder = st.empty()
            while video_source.isOpened():
                ret, frame = video_source.read()
                if not ret:
                    break
                frame = process_frame(frame)
                frame_placeholder.image(frame, channels="BGR", use_column_width=True)
            video_source.release()

elif upload_choice == "Upload Image":
    uploaded_image = st.file_uploader("Upload Image", type=["png", "jpg", "jpeg"])
    if uploaded_image:
        image = Image.open(uploaded_image)
        frame = np.array(image)
        frame = process_frame(frame)
        st.image(frame, caption="Processed Image", use_column_width=True)

elif upload_choice == "Upload to Hugging Face":
    st.sidebar.info("Upload images to the 'known_faces' directory in the Hugging Face repository.")

    # Configure Hugging Face Repository
    REPO_NAME = "face_emotion_detection2"
    REPO_ID = "LovnishVerma/" + REPO_NAME
    hf_token = os.getenv("uploadphoto1")  # Set your Hugging Face token as an environment variable

    if not hf_token:
        st.error("Hugging Face token not found. Please set it as an environment variable named 'HF_TOKEN'.")
        st.stop()

    # Initialize Hugging Face API
    api = HfApi()

    def create_hugging_face_repo():
        """Create or verify the Hugging Face repository."""
        try:
            api.create_repo(repo_id=REPO_ID, repo_type="dataset", token=hf_token, exist_ok=True)
            st.success(f"Repository '{REPO_NAME}' is ready on Hugging Face!")
        except Exception as e:
            st.error(f"Error creating Hugging Face repository: {e}")

    def upload_to_hugging_face(file):
        """Upload a file to the Hugging Face repository."""
        try:
            with tempfile.NamedTemporaryFile(delete=False, suffix=".jpg") as temp_file:
                temp_file.write(file.read())
                temp_file_path = temp_file.name

            api.upload_file(
                path_or_fileobj=temp_file_path,
                path_in_repo=f"known_faces/{os.path.basename(temp_file_path)}",
                repo_id=REPO_ID,
                token=hf_token,
            )
            st.success("File uploaded successfully to Hugging Face!")
        except Exception as e:
            st.error(f"Error uploading file to Hugging Face: {e}")

    # Create the repository if it doesn't exist
    create_hugging_face_repo()

    # Upload image file
    hf_uploaded_image = st.file_uploader("Upload Image to Hugging Face", type=["png", "jpg", "jpeg"])
    if hf_uploaded_image:
        upload_to_hugging_face(hf_uploaded_image)

st.sidebar.write("Emotion Labels: Angry, Fear, Happy, Neutral, Sad, Surprise")