'''Copyright 2024 Ashok Kumar

Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at

    http://www.apache.org/licenses/LICENSE-2.0

Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.'''


import os
import matplotlib.pyplot as plt
plt.style.use('dark_background')
import seaborn as sns
import numpy as np
import librosa
from IPython.display import Audio
import pandas as pd


# Function to extract features from audio file
def extract_features(file_path):
    # Load audio file
    audio, sample_rate = librosa.load(file_path)
    # Extract features using Mel-Frequency Cepstral Coefficients (MFCC)
    mfccs = librosa.feature.mfcc(y=audio, sr=sample_rate, n_mfcc=40)
    # Flatten the features into a 1D array
    flattened_features = np.mean(mfccs.T, axis=0)
    
    return flattened_features

# Function to load dataset and extract features
def load_data_and_extract_features(data_dir):
    labels = []
    features = []
    # Loop through each audio file in the dataset directory
    for filename in os.listdir(data_dir):
        if filename.endswith('.wav'):
            file_path = os.path.join(data_dir, filename)
            # Extract label from filename
            label = filename.split('-')[0]
            labels.append(label)
            # Extract features from audio file
            feature = extract_features(file_path)
            features.append(feature)
            
    return np.array(features), np.array(labels)