leak_rate=rc_leak_rate,
input_sparsity=rc_input_sparsity,
converter=converter,
spectral_radius=rc_spectral_radius,
w_sparsity=rc_w_sparsity,
use_sparse_matrix=args.sparse)
# Add examples
document_index = 0
for author_id in np.arange(1, args.n_authors + 1):
author_path = os.path.join(args.dataset, "total", str(author_id))
for file_index in range(args.n_documents):
file_path = os.path.join(author_path, str(file_index) + ".txt")
logger.info(u"Adding document {} as {}".format(
file_path, document_index))
classifier.train(io.open(file_path, 'r').read(), document_index)
document_index += 1
# end for
# end for
# Finalize model training
classifier.finalize(verbose=args.verbose)
# Get documents embeddings
document_embeddings = classifier.get_embeddings()
logger.info(u"Document embeddings shape : {}".format(
document_embeddings.shape))
# Display similar doc for the first document of each author with each distance measure
for distance_measure in ["euclidian", "cosine", "cosine_abs"]:
print(u"###################### {} ######################".format(
training_set_indexes = indexes
training_set_indexes = np.delete(training_set_indexes, args.k, axis=0)
training_set_indexes.shape = (100 - n_fold_samples)
# Classifier
classifier = EchoWordClassifier(classes=[0, 1], size=rc_size, input_scaling=rc_input_scaling,
leak_rate=rc_leak_rate,
input_sparsity=rc_input_sparsity, converter=wv_converter,
spectral_radius=rc_spectral_radius, w_sparsity=rc_w_sparsity)
# Add examples
for author_index, author_id in enumerate((args.author1, args.author2)):
author_path = os.path.join(args.dataset, "total", author_id)
for file_index in training_set_indexes:
file_path = os.path.join(author_path, str(file_index) + ".txt")
classifier.train(io.open(file_path, 'r').read(), author_index)
# end for
# end for
# Finalize model training
classifier.finalize(verbose=True)
# Init test epoch
test_set = list()
# Get text
for author_index, author_id in enumerate((args.author1, args.author2)):
author_path = os.path.join(args.dataset, "total", str(author_id))
for file_index in test_set_indexes:
file_path = os.path.join(author_path, str(file_index) + ".txt")
test_set.append((io.open(file_path, 'r').read(), author_index))
print("Adding negative example %s" % text_path)
classifier.add_example(text_path, 1)
author_index += 1
n_negative_samples += 1
if author_index >= len(negative_authors):
author_index = 0
text_index += 1
if text_index >= len(training_set_indexes):
break
# end if
# end if
# end while
# >> 8. Train model
print("Training model...")
classifier.train()
# >> 9. Test model performance
print("Testing model performances with text files from %s..." % os.path.join(args.dataset, "total"))
print(test_set_indexes)
success = 0.0
count = 0.0
# For each authors
for author_id in np.arange(1, 51, 1):
author_path = os.path.join(args.dataset, "total", str(author_id))
print("Testing model performances with %d text files for author from %s..." % (test_set_indexes.shape[0],
author_path))
test_count = 0
for file_index in test_set_indexes:
author_pred = classifier.pred(os.path.join(author_path, str(file_index) + ".txt"), True)
if author_id == args.author and author_pred == 0: