import streamlit as st
from st_audiorec import st_audiorec
import matplotlib.pyplot as plt
import sounddevice as sd
import numpy as np
import pandas as pd
import torch
import torchaudio

# MODEL LOADING and INITIALISATION
# model = torch.jit.load("snorenetv1_small.ptl")
# model.eval()

# Session state
if 'text' not in st.session_state:
    st.session_state['text'] = 'Listening...'
    st.session_state['run'] = False

# Audio parameters
st.sidebar.header('Audio Parameters')

FRAMES_PER_BUFFER = int(st.sidebar.text_input('Frames per buffer', 3200))
FORMAT = 'audio/wav'
CHANNELS = 1
RATE = int(st.sidebar.text_input('Rate', 16000))

# Open an audio stream

monitoring = False
audio_data = []

def start_monitoring():
    global monitoring
    st.session_state['run'] = True
    monitoring = True

def stop_monitoring():
    global monitoring
    st.session_state['run'] = False
    monitoring = False

st.title('🎙️ Real-Time Snore Detection App')

with st.expander('About this App'):
    st.markdown('''
    This streamlit app from Hypermind Labs Helps users detect
    how much they are snoring during their sleep.
    ''')



wav_audio_data = st_audiorec()
if wav_audio_data is not None:
    # np_wav = np.frombuffer(wav_audio_data, dtype=np.int16)
    # num_segments = len(np_wav)//100000
    # segments_list = []
    # for i in range(num_segments):
    #     start_sample = i * 100000
    #     end_sample = (i + 1) * 100000
    #     segment = np_wav[start_sample:end_sample]
    #     segments_list.append(segment)
    
    # wav_tensor = torch.tensor(np_wav, dtype=torch.float32)
    # segment_samples = int(44100 * 1)
    # num_segments = len(wav_tensor) // segment_samples
    # segments_list = []
    # for i in range(num_segments):
    #     start_sample = i * segment_samples
    #     end_sample = (i + 1) * segment_samples
    #     segment = wav_tensor[start_sample:end_sample]
    #     segments_list.append(segment)
    st.write(type(wav_audio_data))
    # PERCENTAGE OF SNORING PLOT


    
    # waveform, sample_rate = torchaudio.load('test/0_10.wav')
    # resampler = T.Resample(sample_rate, RESAMPLE_RATE, dtype=waveform.dtype)
    # signal = resampler(waveform)
    # signal = torch.mean(signal, dim=0, keepdim=True)
    # ptl_model(signal)

    # snore = 0
    # other = 0

    # for row in model:
    #     for element in row:
    #         if element > 0.5:
    #             snore += 1
    #         else:
    #             other += 1

    # total = snore + other
    # snore_percentage = (snore / total) * 100
    # other_percentage = (other / total) * 100

    # categories = ["Snore", "Other"]
    # percentages = [snore_percentage, other_percentage]

    # plt.figure(figsize=(8, 4))
    # plt.barh(categories, percentages, color=['#ff0033', '#00ffee'])
    # plt.xlabel('Percentage')
    # plt.title('Percentage of "Snore" and "Other"')
    # plt.xlim(0, 100)

    # for i, percentage in enumerate(percentages):
    #     plt.text(percentage, i, f' {percentage:.2f}%', va='center')

    # st.pyplot(plt)