import pandas as pd
import matplotlib.pyplot as plt
#import random
from glob import glob
import numpy as np
import librosa as lr
from sklearn.neural_network import MLPClassifier
import os

reader = pd.read_csv(open('C:/Users/Douglas/Desktop/train_label.csv'))
print(reader['Label'][1])

train_audio_files = glob('C:/Users/Douglas/Desktop/Train/Train/PAEP-******.wav')
print(len(train_audio_files))

test_audio_files = glob('C:/Users/Douglas/Desktop/Public_Test/Public_Test/PAEP-******.wav')
print(len(test_audio_files))

data, sampling_rate = lr.load(train_audio_files)

import time

path = 'C:/Users/Douglas/Desktop/Train/Train/'
lst = []

start_time = time.time()

for subdir, dirs, files in os.walk(path):
  for file in files:
      try:
        #Load librosa array, obtain mfcss, store the file and the mcss information in a new array
        X, sample_rate = lr.load(os.path.join(path, 'PAEP-******.wav'), res_type='kaiser_fast')
        mfccs = np.mean(lr.feature.mfcc(y=X, sr=sample_rate, n_mfcc=40).T,axis=0)
        # The instruction below converts the labels (from 1 to 8) to a series from 0 to 7
        # This is because our predictor needs to start from 0 otherwise it will try to predict also 0.
        file = int(file[7:8]) - 1
        arr = mfccs, file
        lst.append(arr)
      # If the file is not valid, skip it
      except ValueError:
        continue

#print("--- Data loaded. Loading time: %s seconds ---" % (time.time() - start_time))
X, y = zip(*lst)
X = np.array(X)
y = np.array(y)


print(X.shape)
print(y.shape)

#
#
#
#train_audio_files = np.array(train_audio_files)
#print(train_audio_files.shape)
#np.reshape(train_audio_files, (len(train_audio_files), 1))
#
#emotions={
#  '01':'neutral',
#  '02':'calm',
#  '03':'happy',
#  '04':'sad',
#  '05':'angry',
#  '06':'fearful',
#  '07':'disgust',
#  '08':'surprised'
#}
#
#
##DataFlair - Initialize the Multi Layer Perceptron Classifier
#model=MLPClassifier(alpha=0.01, batch_size=256, epsilon=1e-08, hidden_layer_sizes=(300,), learning_rate='adaptive', max_iter=500)
#
##DataFlair - Train the model
#model.fit(train_audio_files, reader['Label'])
##DataFlair - Predict for the test set
##y_pred=model.predict(test_audio_files)
#print('Predict:', model.predict(test_audio_files[:5]))
#