def training_and_classification_with_kfold_cross_validation(collection_name, k):
'''
Training and classification of an autotagger using k-fold cross validation
'''
_split_metadata_and_features(collection_name, k)
for i in range(1,k+1):
# Create a gaia dataset with the training set
print "----------------------- DATASET CREATION (FOLD %d)-----------------------" % i
training_features='train/%s_features__fold%d.tsv' % (collection_name, i)
chunk_size=5000
dataset_suffix="fold%d" % i
replace_dataset=True
dataset_creator = DatasetCreator(collection_name)
dataset_creator.create(training_features, chunk_size, dataset_suffix, replace_dataset)
# Feature selection over the gaia dataset
print "----------------------- FEATURE SELECTION (FOLD %d)-----------------------" % i
dataset='dbs/%s__fold%d.db' % (collection_name, i)
pca_covered_variance=75
include_highlevel=True
feature_selector = FeatureSelector()
feature_selector.select(dataset, pca_covered_variance, include_highlevel)
# Autotag a given test set
print "----------------------- AUTOTAGGING (FOLD %d)-----------------------" % i
dataset='transformed_dbs/%s__fold%d.db' % (collection_name, i)
training_metadata='train/%s_metadata__fold%d.tsv' % (collection_name, i)
test_features='test/%s_features__fold%d.tsv' % (collection_name, i)
output_binary='test/%s_output_binary__fold%d.tsv' % (collection_name, i)
output_affinity='test/%s_output_affinity__fold%d.tsv' % (collection_name, i)
metric='LC'
num_sim=18
threshold=0.2
autotagger = Autotagger()
autotagger.train(dataset, training_metadata)
autotagger.classify(test_features, output_binary, metric, num_sim, threshold, ranked=False)
autotagger.classify(test_features, output_affinity, metric, num_sim, threshold, ranked=True)
# You should have received a copy of the GNU General Public License
# along with music-autotagging-msordo. If not, see <http://www.gnu.org/licenses/>.
# Written by Mohamed Sordo (@neomoha)
# Email: mohamed ^dot^ sordo ^at^ gmail ^dot^ com
# Website: http://msordo.weebly.com
import os, sys, argparse
from DatasetCreator import DatasetCreator
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Create a Gaia Dataset given a list of feature files')
parser.add_argument('collection_name', help='Name of the collection')
parser.add_argument('--training-features', default=None, help='A file containing paths to the features of the audios used for training (default="train/COLLECTIONNAME_features.txt")')
parser.add_argument('--chunk-size', type=int, default=5000, help='The dataset will be created in chunks of N songs at a time (default=5000)')
parser.add_argument('--dataset-suffix', default=None, help='suffix to add to the dataset filename (useful when doing k-fold cross validation, for example) (default=None)')
parser.add_argument('-r', '--replace-dataset', help='Replace old dataset (if it exists)', action="store_true")
args = parser.parse_args()
if args.training_features is None:
args.training_features = "train/"+args.collection_name+"_features.tsv"
if not os.path.exists(args.training_features):
print "Taining features file '%s' not found" % args.training_features
sys.exit(-1)
print args
dataset_creator = DatasetCreator(args.collection_name)
dataset_creator.create(args.training_features, args.chunk_size, args.dataset_suffix, args.replace_dataset)
parser.add_argument(
'--chunk-size',
type=int,
default=5000,
help=
'The dataset will be created in chunks of N songs at a time (default=5000)'
)
parser.add_argument(
'--dataset-suffix',
default=None,
help=
'suffix to add to the dataset filename (useful when doing k-fold cross validation, for example) (default=None)'
)
parser.add_argument('-r',
'--replace-dataset',
help='Replace old dataset (if it exists)',
action="store_true")
args = parser.parse_args()
if args.training_features is None:
args.training_features = "train/" + args.collection_name + "_features.tsv"
if not os.path.exists(args.training_features):
print "Taining features file '%s' not found" % args.training_features
sys.exit(-1)
print args
dataset_creator = DatasetCreator(args.collection_name)
dataset_creator.create(args.training_features, args.chunk_size,
args.dataset_suffix, args.replace_dataset)
