import librosa
import numpy as np
import scipy

def preprocess_audio(audio):
    y, sr = librosa.load(audio, sr=16000)
    return y, sr

def clean_audio(y, sr):
    y = librosa.effects.trim(y)[0]
    y = librosa.util.normalize(y)
    return y

def extract_features(y, sr):
    features = {
        "mfcc": librosa.feature.mfcc(y=y, sr=sr, n_mfcc=13).mean(axis=1),
        "chroma": librosa.feature.chroma_stft(y=y, sr=sr).mean(axis=1),
        "mel": librosa.feature.melspectrogram(y=y, sr=sr).mean(axis=1),
        "contrast": librosa.feature.spectral_contrast(y=y, sr=sr).mean(axis=1),
        "tonnetz": librosa.feature.tonnetz(y=y, sr=sr).mean(axis=1)
    }
    return features

def store_preprocessed_data(features, filename):
    np.savez(filename, **features)