for s in range(0, args.samples):
print("#")
# >> 5. Prepare training and test set.
training_set_indexes = np.arange(0, 100, 1)[s:s+args.training_size]
test_set_indexes = np.delete(np.arange(0, 100, 1), training_set_indexes, axis=0)[:args.test_size]
# >> 6. Create Echo Word Classifier
classifier = RCNLPEchoWordClassifier(size=rc_size, input_scaling=rc_input_scaling, leak_rate=rc_leak_rate,
input_sparsity=rc_input_sparsity, converter=converter, n_classes=2,
spectral_radius=rc_spectral_radius, w_sparsity=rc_w_sparsity, w=w)
# >> 7. 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:
classifier.add_example(os.path.join(author_path, str(file_index) + ".txt"), author_index)
# end for
# end for
# >> 8. Train model
classifier.train()
# >> 9. Test model performance
success = 0.0
count = 0.0
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 test_set_indexes:
author_pred, _, _ = classifier.pred(os.path.join(author_path, str(file_index) + ".txt"))
if author_pred == author_index:
success += 1.0
# >> 5. Prepare training and test set.
training_set_indexes = np.random.choice(np.arange(0, 100), size=1, replace=False)
test_set_indexes = np.delete(np.arange(0, 100, 1), training_set_indexes)[:args.test_size]
negatives_set_indexes = np.arange(0, args.negatives, 1)
other_authors = np.delete(np.arange(1, 51, 1), the_author-1)
# >> 6. Create Echo Word Classifier
classifier = RCNLPEchoWordClassifier(size=rc_size, input_scaling=rc_input_scaling, leak_rate=rc_leak_rate,
input_sparsity=rc_input_sparsity, converter=converter, n_classes=2,
spectral_radius=rc_spectral_radius, w_sparsity=rc_w_sparsity, w=w)
# >> 7. Add authors examples
author_path = os.path.join(args.dataset, "total", str(the_author))
for file_index in training_set_indexes:
file_path = os.path.join(author_path, str(file_index) + ".txt")
classifier.add_example(file_path, 0)
n_token += get_n_token(file_path)
# end for
# >> 8. Add negative examples
others_path = os.path.join(args.dataset, "total", "others")
for file_index in negatives_set_indexes:
file_path = os.path.join(others_path, str(file_index) + ".txt")
classifier.add_example(file_path, 1)
# end for
# >> 8. Train model
classifier.train()
# >> 9. Test model performances
success = 0.0
test_set_indexes = indexes[k]
training_set_indexes = indexes
training_set_indexes = np.delete(training_set_indexes, k, axis=0)
training_set_indexes.shape = (n_texts - n_fold_samples)
# Create Echo Word Classifier
classifier = RCNLPEchoWordClassifier(size=rc_size, input_scaling=rc_input_scaling, leak_rate=rc_leak_rate,
input_sparsity=rc_input_sparsity, converter=converter, n_classes=2,
spectral_radius=rc_spectral_radius, w_sparsity=rc_w_sparsity)
# Add examples
print(u"Adding examples...")
for training_index in training_set_indexes:
training_text_path = os.path.join(args.dataset, text_codes[training_index] + ".txt")
training_text_author = texts_data[text_codes[training_index]]
classifier.add_example(training_text_path, training_text_author)
# end for
# Train model
print(u"Training...")
classifier.train()
# Test model performance
success = 0.0
count = 1.0
for test_index in test_set_indexes:
test_text_path = os.path.join(args.dataset, text_codes[test_index] + ".txt")
observed_author = texts_data[text_codes[test_index]]
predicted_author = classifier.pred(test_text_path)
if observed_author == predicted_author:
success += 1
leak_rate=rc_leak_rate,
input_sparsity=rc_input_sparsity,
converter=converter,
n_classes=2,
spectral_radius=rc_spectral_radius,
w_sparsity=rc_w_sparsity)
# >> 7. Add authors examples
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 training_set_indexes:
file_path = os.path.join(author_path,
str(file_index) + ".txt")
classifier.add_example(file_path, author_index)
n_token += get_n_token(file_path)
# end for
# end for
# >> 8. Train model
classifier.train()
# >> 9. Test model performance
success = 0.0
count = 0.0
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: