def main():
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument("-f", "--file-path", help="Path to the audio file")
parser.add_argument("-a",
"--artist",
help="Name of the artist of the song")
parser.add_argument("-t", "--title", help="title of the song")
args = parser.parse_args()
if args.file_path is None or not os.path.exists(args.file_path):
print("invalid file path")
return
if args.artist is None:
print("no artist provided")
return
if args.title is None:
print("no title provided")
return
md = MusicData(args.file_path, title=args.title, artist=args.artist)
md.detect_beats()
md.detect_onsets()
md.save_beat_diagram()
md.save_onsets_diagram()
upload_files_s3(args.file_path)
save_to_dynamodb(md)
from gradient_descent import plot_history, plot_history_train_validation
from music_data import MusicData
from normal_equation import solve_normal_equation
from normalize import z_norm
import numpy as np
from compute_accuracy import compute_accuracy, compute_accuracy_year
if __name__ == '__main__':
'''
Read music data.
'''
print "Loading data."
#music_train = MusicData("resources/YearPredictionMSD_samples_train.txt")
#music_test = MusicData("resources/YearPredictionMSD_samples_test.txt")
music_train = MusicData("resources/YearPredictionMSD_train.txt")
#music_train.add_features(2)
#music_test.add_features(max_degree)
#music_validation.add_features(max_degree)
# Normalize data.
print "Normalize data."
#music_train.X = z_norm(music_train.X)
#music_validation = MusicData("resources/YearPredictionMSD_validation.txt")
#music_test = MusicData("resources/YearPredictionMSD_test.txt")
year1 = 1985
year2 = 2000
for year1 in range(1980, 2010):
from compute_cost import compute_cost
from gradient_descent import gradient_descent, gradient_descent_with_J_history, \
plot_history
from music_data import MusicData
from normal_equation import solve_normal_equation
from normalize import z_norm, z_norm_by_feature
if __name__ == '__main__':
'''
Read music data.
'''
print "Loading data."
# music_train = MusicData("resources/YearPredictionMSD_samples_train.txt")
# music_test = MusicData("resources/YearPredictionMSD_samples_test.txt")
music_train = MusicData("resources/YearPredictionMSD_train.txt")
music_validation = MusicData("resources/YearPredictionMSD_validation.txt")
music_test = MusicData("resources/YearPredictionMSD_test.txt")
# Normalize data.
print "Normalize data."
# music_train.X = z_norm(music_train.X)
# music_validation.X = z_norm(music_validation.X)
# music_test.X = z_norm(music_test.X)
music_train.balance_data_oversampling_smote_regular()
music_train.X, mean_X, std_X = z_norm_by_feature(music_train.X)
#music_train.balance_data_undersampling_custom()
music_validation.X = z_norm_by_feature(music_validation.X, mean_X, std_X)
music_test.X = z_norm_by_feature(music_test.X, mean_X, std_X)
# Balacing train data.
from gradient_descent import plot_history, plot_history_train_validation
from music_data import MusicData
from normal_equation import solve_normal_equation
from normalize import z_norm
import numpy as np
if __name__ == '__main__':
'''
Read music data.
'''
print "Loading data."
#music_train = MusicData("resources/YearPredictionMSD_samples_train.txt")
#music_test = MusicData("resources/YearPredictionMSD_samples_test.txt")
music_train = MusicData("resources/YearPredictionMSD_train.txt")
music_validation = MusicData("resources/YearPredictionMSD_validation.txt")
music_test = MusicData("resources/YearPredictionMSD_test.txt")
max_degree = 3
# Add polynomial features.
print "Adding polynomial features."
music_train.add_features(max_degree)
music_test.add_features(max_degree)
music_validation.add_features(max_degree)
## Normalize data.
print "Normalize data."
#music_train.X = z_norm(music_train.X)
#music_validation.X = z_norm(music_validation.X)
#music_test.X = z_norm(music_test.X)
from compute_cost import compute_cost
from gradient_descent import plot_history, plot_history_train_validation
from music_data import MusicData
from normal_equation import solve_normal_equation
from normalize import z_norm, z_norm_by_feature
import numpy as np
if __name__ == '__main__':
'''
Read music data.
'''
print "Loading data."
# music_train = MusicData("resources/YearPredictionMSD_samples_train.txt")
# music_test = MusicData("resources/YearPredictionMSD_samples_test.txt")
music_train = MusicData("resources/YearPredictionMSD_train.txt")
music_validation = MusicData("resources/YearPredictionMSD_validation.txt")
music_test = MusicData("resources/YearPredictionMSD_test.txt")
max_degree = 3
# Add polynomial features.
print "Adding polynomial features."
music_train.add_features(max_degree)
music_test.add_features(max_degree)
music_validation.add_features(max_degree)
# Normalize data.
print "Normalize data."
# music_train.X = z_norm(music_train.X)
# music_validation.X = z_norm(music_validation.X)
# music_test.X = z_norm(music_test.X)