main.py

import librosa.feature
import pandas as pd
import numpy as np
from pathlib import Path
from os import chdir
import os
import csv
from tensorflow import keras
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder, StandardScaler
from keras import models
from keras import layers
import matplotlib.pyplot as plt
from sklearn.metrics import classification_report
import constants


def create_csv_header():
    header = 'filename '
    for i in range(constants.MFCC_FEATURE_START, constants.MFCC_FEATURE_END):
        header += f' mfcc{i}'
    header += ' label'
    header = header.split()
    file = open(constants.FEATURES_CSV_NAME, 'w', newline='')
    with file:
        writer = csv.writer(file)
        writer.writerow(header)


def extract_features(trainingDataDir, trainingDataSubDirs):
    create_csv_header()
    # Looping over every file inside the subdirectories for feature extraction
    for trainingDataSubDir in trainingDataSubDirs:
        for fileName in os.listdir(trainingDataDir/f'{trainingDataSubDir}'):
            if fileName.endswith(".wav"):
                audioFile = trainingDataDir/f'{trainingDataSubDir}/{fileName}'
                print("Extracting Features from Directory "+trainingDataSubDir+" and file "+audioFile.name)
                y, sr = librosa.load(audioFile, mono=True)
                mfcc = librosa.feature.mfcc(y=y, sr=sr, n_mfcc=(constants.MFCC_FEATURE_END - constants.MFCC_FEATURE_START))
                to_append = f'{audioFile.name}'
                for g in mfcc:
                    to_append += f' {np.mean(g)}'
                if trainingDataSubDir == constants.CAR:
                    to_append += f' {constants.LIGHT_WEIGHT}'
                elif trainingDataSubDir == constants.BUS:
                    to_append += f' {constants.MEDIUM_WEIGHT}'
                elif trainingDataSubDir == constants.TRUCK:
                    to_append += f' {constants.HEAVY_WEIGHT}'
                elif trainingDataSubDir == constants.MOTORCYCLE:
                    to_append += f' {constants.TWO_WHEELED}'
                elif trainingDataSubDir == constants.TRAM:
                    to_append += f' {constants.RAIL_BOUND}'

                file = open(constants.FEATURES_CSV_NAME, 'a', newline='')
                with file:
                    writer = csv.writer(file)
                    writer.writerow(to_append.split())


def preprocessing_csv_data():
    print("Reading Features... ")
    data = pd.read_csv(constants.FEATURES_CSV_NAME)
    data.head()
    # Dropping unnecessary columns (Column Filename is dropped)
    data = data.drop(['filename'], axis=1)
    data.head()
    return data


def encode_labels(data):