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)
if args.dataset is None:
args.dataset = "transformed_dbs/"+args.collection_name+".db"
if not os.path.exists(args.dataset):
print "Dataset '%s' not found" % args.dataset
sys.exit(-1)
if args.training_metadata is None:
args.training_metadata = "train/"+args.collection_name+"_metadata.tsv"
if not os.path.exists(args.training_metadata):
print "Training metadata file '%s' not found" % args.training_metadata
sys.exit(-1)
if args.test_features is None:
args.test_features = "test/"+args.collection_name+"_features.tsv"
if not os.path.exists(args.test_features):
print "Test features file '%s' not found" % args.test_features
sys.exit(-1)
if args.output is None:
args.output = "test/"+args.collection_name+"_output.tsv"
print args
autotagger = Autotagger()
autotagger.train(args.dataset, args.training_metadata)
autotagger.classify(args.test_features, args.output, args.metric, args.num_sim, args.threshold, args.ranked_tags)
