def run(xml_data="../xml/RTE2_dev.xml"):
#the ML, learning and classifying the data set.
# the classifier imports and runs the features.py file to extract the features.
# remember to out comment the two run statements at end of file.
classifier.run()
classifier.run(False)
#evaluating the results of part3 classification.
os.system(os.getcwd() + "/eval_rte.py "+ xml_data+ " " + os.getcwd()+"/results_part3.txt")
def main():
data_folder = 'data/sources/wikipedia'
models_folder = 'classifier/models'
save_loc = '/usr/share/nginx/html/wiki'
if not os.path.exists(data_folder):
os.makedirs(data_folder)
if next(os.walk(data_folder))[1]:
retrain = True
if retrain:
input, target, classes = data.sample(data_folder)
model = classifier.build(input.shape, target.shape)
classifier.train(model, input, target)
classifier.save(models_folder, model, classes)
else:
model, classes = classifier.load(models_folder, sorted(os.listdir(models_folder))[-1])
for root, dirs, files in os.walk(data_folder):
for file in files:
if not file.startswith('.'):
with open(root+'/'+file) as f:
input = data.str2mat(f.read())
output = classifier.run(model, input)
data.backtest(save_loc+'/'+file, classes, input, output)
else:
print("""\nNo data found.\nPut subfolders of files by class, within the 'data' folder.""")
def predict():
try:
data = request.get_json()
query = data['Title'] + ' ' + data['Body']
stance = data['Stance']
except Exception as e:
return 'bad input or could not process.', 400
return jsonify(run('oraw1_15k', query).tolist())
def main():
xs_train = np.loadtxt(FLAGS.path_to_xtrain)
xs_test = np.loadtxt(FLAGS.path_to_xtest)
kms = build_kmeans_model_with_random_input(FLAGS.model_dir, 'kmeans',
xs_train,
FLAGS.depict_output_dim)
outputs_train = kms.predict(xs_train)
output_test = kms.predict(xs_test)
metrics = classifier.run(outputs_train, output_test, FLAGS)
# print(metrics)
pprint.pprint(metrics)
def k_fold_cross_validation(docs, class_labels, type_of_classifier='knn', n_splits=2, k_neighbors=3):
print 'k_neighbors:', k_neighbors
vocabulary = build_vocabulary()
# n-fold cross validation
seed = 1
enable_shuffle = False
k_fold = KFold(n_splits=n_splits, random_state=seed, shuffle=enable_shuffle)
m_accuracy = 0.0
m_f1_score = 0.0
iteration = 0
# # ros = RandomOverSampler(random_state=1)
# ros = EditedNearestNeighbours(random_state=1)
for train_index, test_index in k_fold.split(docs, class_labels):
iteration += 1
train = []
test = []
for i in train_index:
train.append(docs[i])
for i in test_index:
test.append(docs[i])
tf_idf_train, train_vocabulary = preprocess.get_tf_idf_training(train)
tf_idf_test = preprocess.get_tf_idf_testing(train_vocabulary, test)
train_labels = []
for i in train_index:
train_labels.append(class_labels[i])
test_labels = []
for i in test_index:
test_labels.append(class_labels[i])
# random sampling
# tf_idf_train_ros, train_labels_ros = ros.fit_sample(tf_idf_train, train_labels)
predict_labels = classifier.run(tf_idf_train, train_labels, tf_idf_test, type_of_classifier, k_neighbors=k_neighbors)
accuracy = calculate_accuracy(test_labels, predict_labels)
m_accuracy += accuracy
m_f1_score += f1_score(test_labels, predict_labels, average='weighted')
print 'iteration:', iteration
print '\taccuracy:', accuracy
print '\tf1-score: ', f1_score(test_labels, predict_labels, average='weighted')
return m_accuracy / n_splits, m_f1_score / n_splits
if type == 'train':
print('training......')
accuracy, f1_score = k_fold_cross_validation(
train_docs,
train_labels,
type_of_classifier=type_of_classifier,
n_splits=10,
k_neighbors=k_neighbors
)
print 'average accuracy = ', accuracy
print 'average f1_score = ', f1_score
if type == 'test':
print('testing......')
tf_idf_train, train_vocabulary = preprocess.get_tf_idf_training(train_docs)
tf_idf_test = preprocess.get_tf_idf_testing(train_vocabulary, test_docs)
predict_labels = classifier.run(
tf_idf_train,
train_labels,
tf_idf_test,
type_of_classifier,
k_neighbors=k_neighbors
)
print len(predict_labels)
output_file_name = '../data/format.dat'
with open(output_file_name, 'w') as raw_text:
for label in predict_labels:
raw_text.write(label + '\n')
import numpy as np
from matplotlib import pyplot
import classifier
X_train, X_test, y_train, y_test = classifier.getdata()
# accuracy vs hyperparameter graphs
#comparing number of epochs with overall accuracy
resEp100 = classifier.run(X_train, X_test, y_train, y_test, 100, 0.01, 0.5)
y = []
x = []
for i, l in enumerate(resEp100):
y.append(np.mean(resEp100[i]))
x.append(i + 1)
pyplot.plot(x, y)
pyplot.title('Number of Epochs vs Overall Accuracy')
pyplot.xlabel('Number of Epochs')
pyplot.ylabel('Accuracy')
pyplot.ylim(0.94, 0.98)
pyplot.show()
#comparing overall accuracy with different penalty
y = []
x = []
penalties = [0.1, 0.2, 0.5, 1, 2, 5]
for p in penalties:
import numpy as np
import classifier
from loadMNIST_py import MnistDataloader
mnistDataLoader = MnistDataloader(
'train-images.idx3-ubyte',
'train-labels.idx1-ubyte',
't10k-images.idx3-ubyte',
't10k-labels.idx1-ubyte')
(trainImages, trainLabels), (t10kImages, t10kLabels) = mnistDataLoader.load_data()
print("1st run: ")
initial_centroids = np.random.randn(10, 28 * 28)
classifier.run(initial_centroids, trainImages, trainLabels, t10kImages, t10kLabels)
print("2nd run: ")
initial_centroids = np.random.randn(10, 28 * 28)
classifier.run(initial_centroids, trainImages, trainLabels, t10kImages, t10kLabels)
print("3rd run: ")
initial_centroids = np.random.randn(10, 28 * 28)
initial_centroids = classifier.run(initial_centroids, trainImages, trainLabels, t10kImages, t10kLabels)
print("4th run with chosen initialized centroids: ")
# F)
classifier.run(initial_centroids, trainImages, trainLabels, t10kImages, t10kLabels)
def main():
tf.logging.set_verbosity(tf.logging.INFO)
prepare_file_system()
# FLAGS.eval_step_interval = 1
# FLAGS.infer_step_interal = 10
# TODO: OOP
train_graph = tf.Graph()
with train_graph.as_default():
train_filenames, train_iterator, train_elements = \
build_text_line_reader(shuffle=True, batch_size=FLAGS.train_batch_size)
train_inputs, train_cost, optimizer = build_train_graph(
train_elements,
FLAGS.depict_input_dim,
FLAGS.depict_output_dim,
func=FLAGS.loss_function)
train_saver = tf.train.Saver()
train_merger = tf.summary.merge_all()
train_initializer = tf.global_variables_initializer()
# train_parameters = tf.trainable_variables()
eval_graph = tf.Graph()
with eval_graph.as_default():
eval_filenames, eval_iterator, eval_elements = \
build_text_line_reader(shuffle=True, batch_size=FLAGS.eval_batch_size)
eval_inputs, eval_outputs = build_eval_graph(eval_elements,
FLAGS.depict_input_dim,
FLAGS.depict_output_dim)
eval_saver = tf.train.Saver()
eval_merger = tf.summary.merge_all()
eval_initializer = tf.global_variables_initializer()
# eval_parameters = tf.trainable_variables()
infer_graph = tf.Graph()
with infer_graph.as_default():
infer_filenames, infer_iterator, infer_elements = \
build_text_line_reader(shuffle=False, batch_size=FLAGS.infer_batch_size)
infer_inputs, infer_outputs = build_infer_graph(
infer_elements, FLAGS.depict_input_dim, FLAGS.depict_output_dim)
rbfnn_metrics = build_metrics_graph('rbfnn')
# kmeans_metrics = build_metrics_graph('kmeans')
infer_saver = tf.train.Saver()
infer_merger = tf.summary.merge_all()
infer_initializer = tf.global_variables_initializer()
config = tf.ConfigProto(device_count={"CPU": 24, "GPU": 0})
train_sess = tf.Session(graph=train_graph, config=config)
eval_sess = tf.Session(graph=eval_graph, config=config)
infer_sess = tf.Session(graph=infer_graph, config=config)
# train_writer = tf.summary.FileWriter(FLAGS.summaries_dir + '/train', train_graph)
# validation_writer = tf.summary.FileWriter(FLAGS.summaries_dir + '/validation', eval_graph)
# infer_writer = tf.summary.FileWriter(FLAGS.summaries_dir + '/inference', infer_graph)
results = dict()
train_sess.run(train_initializer)
train_sess.run(train_iterator.initializer,
feed_dict={train_filenames: [FLAGS.path_to_xtrain]})
# train_sess.run(train_iterator.initializer)
for i in itertools.count():
if i > FLAGS.how_many_training_steps:
break
try:
xs_train = train_sess.run(train_elements)
# print(xs_train)
except tf.errors.OutOfRangeError:
train_sess.run(train_iterator.initializer,
feed_dict={train_filenames: [FLAGS.path_to_xtrain]})
xs_train = train_sess.run(train_elements)
# train_summary, _ = train_sess.run([optimizer, train_merger]) #
_, training_cost, train_summary = train_sess.run(
[optimizer, train_cost, train_merger],
feed_dict={train_inputs: xs_train})
# train_writer.add_summary(train_summary, i)
# print('epoch: %6d, training cost: %.8f'%(i, training_cost))
# time.sleep(1)
# if i % FLAGS.eval_step_interval == 0:
if i % pow(10, len(str(i)) - 1) == 0:
# print(train_sess.run(train_parameters[0]))
checkpoint_path = train_saver.save(train_sess,
FLAGS.checkpoints_dir +
'/checkpoints',
global_step=i)
eval_saver.restore(eval_sess, checkpoint_path)
# print(eval_sess.run(eval_parameters[0]))
eval_sess.run(eval_iterator.initializer,
feed_dict={eval_filenames: [FLAGS.path_to_xtest]})
while FLAGS.data_to_eval:
try:
xs_eval = eval_sess.run(eval_elements)
except tf.errors.OutOfRangeError:
# eval_sess.run(eval_iterator.initializer,
# feed_dict={eval_filenames: [r'../../data/x_1000_128.txt']})
# xs_eval = eval_sess.run(eval_elements)
break
# training_outputs = eval_sess.run(eval_outputs, feed_dict={eval_inputs: xs_train})
# evaluation_outputs = eval_sess.run(eval_outputs, feed_dict={eval_inputs: xs_eval})
evaluation_cost, eval_summary = train_sess.run(
[train_cost, train_merger],
feed_dict={train_inputs: xs_eval})
tf.logging.info("epoch: %d, training cost: %f" %
(i, training_cost))
tf.logging.info("epoch: %d, evaluation cost: %f" %
(i, evaluation_cost))
# validation_writer.add_summary(eval_summary, i)
break
# if i % FLAGS.infer_step_interval == 0:
if i % pow(10, len(str(i)) - 1) == 0:
checkpoint_path = train_saver.save(train_sess,
FLAGS.checkpoints_dir +
'/checkpoints',
global_step=i)
train_saver.save(train_sess,
FLAGS.saved_model_dir + '/checkpoints_' +
str(FLAGS.depict_output_dim),
global_step=i)
infer_saver.restore(infer_sess, checkpoint_path)
infers_train = []
infer_sess.run(infer_iterator.initializer,
feed_dict={infer_filenames: [FLAGS.path_to_xtrain]})
while FLAGS.data_to_infer:
try:
xs_infer = infer_sess.run(infer_elements)
except tf.errors.OutOfRangeError:
break
ys_infer = infer_sess.run(infer_outputs,
feed_dict={infer_inputs: xs_infer})
infers_train.extend(ys_infer)
# print(infers_train)
infers_test = []
infer_sess.run(infer_iterator.initializer,
feed_dict={infer_filenames: [FLAGS.path_to_xtest]})
while FLAGS.data_to_infer:
try:
xs_infer = infer_sess.run(infer_elements)
except tf.errors.OutOfRangeError:
break
ys_infer = infer_sess.run(infer_outputs,
feed_dict={infer_inputs: xs_infer})
print(xs_infer.shape, xs_infer.flatten())
print(ys_infer.shape, ys_infer.flatten())
infers_test.extend(ys_infer)
# print(infers_test)
metrics = classifier.run(infers_train, infers_test, FLAGS)
pprint.pprint(metrics)
# infer_summary = metrics_to_metrics(infer_sess, infer_merger, rbfnn_metrics, metrics)
# infer_writer.add_summary(infer_summary, i)
results[i] = metrics
# TODO:
with open('../../results/results.txt', 'a') as f:
line = list()
line.extend(
[FLAGS.rbfnn_num_center, FLAGS.depict_output_dim, i])
line.extend(metrics['err_train'].tolist())
line.extend([metrics['acc_train']])
line.extend(metrics['stsm_train'].tolist())
line.extend(metrics['err_test'].tolist())
line.extend([metrics['acc_test']])
line = [str(item) for item in line]
line = ' '.join(line)
f.write(line)
f.write('\n')
train_sess.close()
eval_sess.close()
infer_sess.close()
return results
def main():
tf.logging.set_verbosity(tf.logging.INFO)
prepare_file_system()
# FLAGS.eval_step_interval = 1
# FLAGS.infer_step_interal = 10
# TODO: OOP
train_graph = tf.Graph()
with train_graph.as_default():
train_filenames, train_iterator, train_elements = \
build_text_line_reader(shuffle=True, batch_size=FLAGS.train_batch_size)
train_inputs, train_cost, optimizer = build_train_graph(
train_elements,
FLAGS.depict_input_dim,
FLAGS.depict_output_dim,
func=FLAGS.loss_function)
train_saver = tf.train.Saver()
train_merger = tf.summary.merge_all()
train_initializer = tf.global_variables_initializer()
# train_parameters = tf.trainable_variables()
eval_graph = tf.Graph()
with eval_graph.as_default():
eval_filenames, eval_iterator, eval_elements = \
build_text_line_reader(shuffle=True, batch_size=FLAGS.eval_batch_size)
eval_inputs, eval_outputs = build_eval_graph(eval_elements,
FLAGS.depict_input_dim,
FLAGS.depict_output_dim)
eval_saver = tf.train.Saver()
eval_merger = tf.summary.merge_all()
eval_initializer = tf.global_variables_initializer()
# eval_parameters = tf.trainable_variables()
infer_graph = tf.Graph()
with infer_graph.as_default():
infer_filenames, infer_iterator, infer_elements = \
build_text_line_reader(shuffle=False, batch_size=FLAGS.infer_batch_size)
infer_inputs, infer_outputs = build_infer_graph(
infer_elements, FLAGS.depict_input_dim, FLAGS.depict_output_dim)
rbfnn_metrics = build_metrics_graph('rbfnn')
# kmeans_metrics = build_metrics_graph('kmeans')
infer_saver = tf.train.Saver()
infer_merger = tf.summary.merge_all()
infer_initializer = tf.global_variables_initializer()
config = tf.ConfigProto(device_count={"GPU": 1})
train_sess = tf.Session(graph=train_graph, config=config)
eval_sess = tf.Session(graph=eval_graph, config=config)
infer_sess = tf.Session(graph=infer_graph, config=config)
# train_writer = tf.summary.FileWriter(FLAGS.summaries_dir + '/train', train_graph)
# validation_writer = tf.summary.FileWriter(FLAGS.summaries_dir + '/validation', eval_graph)
# infer_writer = tf.summary.FileWriter(FLAGS.summaries_dir + '/inference', infer_graph)
train_sess.run(train_initializer)
# eval_sess.run(eval_initializer)
# infer_sess.run(infer_initializer)
import utils
results = dict()
for epoch in itertools.count():
if epoch > FLAGS.how_many_training_epoches:
break
train_generator = utils.build_data_generator(
xtrain, shuffle=True, batch_size=FLAGS.train_batch_size)
for batch, xs_train in enumerate(train_generator):
_, training_cost = train_sess.run(
[optimizer, train_cost], feed_dict={train_inputs: xs_train})
if epoch % 1 == 0:
checkpoint_path = train_saver.save(train_sess,
FLAGS.checkpoints_dir +
'/checkpoints',
global_step=epoch)
# train_saver.save(train_sess, FLAGS.saved_model_dir + '/checkpoints_' + str(FLAGS.depict_output_dim), global_step=epoch)
infer_saver.restore(infer_sess, checkpoint_path)
infers_train = []
infer_generator = utils.build_data_generator(
xtrain, shuffle=False, batch_size=FLAGS.infer_batch_size)
for batch, xs_infer in enumerate(infer_generator):
ys_infer = infer_sess.run(infer_outputs,
feed_dict={infer_inputs: xs_infer})
infers_train.extend(ys_infer)
infers_test = []
infer_generator = utils.build_data_generator(
xtest, shuffle=False, batch_size=FLAGS.infer_batch_size)
for batch, xs_infer in enumerate(infer_generator):
ys_infer = infer_sess.run(infer_outputs,
feed_dict={infer_inputs: xs_infer})
infers_test.extend(ys_infer)
print(len(infers_train), len(infers_test))
metrics = classifier.run(infers_train, infers_test, FLAGS)
pprint.pprint(metrics)
results[i] = metrics
utils.write_results(FLAGS, metrics, epoch)
train_sess.close()
eval_sess.close()
infer_sess.close()
return results
def main():
tf.logging.set_verbosity(tf.logging.INFO)
prepare_file_system()
FLAGS.eval_step_interval = 1
FLAGS.infer_step_interal = 10
# TODO: OOP
train_graph = tf.Graph()
with train_graph.as_default():
train_filenames, train_iterator, train_elements = \
build_text_line_reader(shuffle=True, batch_size=FLAGS.train_batch_size)
train_inputs, train_cost, optimizer = build_train_graph(
train_elements,
FLAGS.depict_input_dim,
FLAGS.depict_output_dim,
func='func_02')
train_saver = tf.train.Saver()
train_merger = tf.summary.merge_all()
train_initializer = tf.global_variables_initializer()
# train_parameters = tf.trainable_variables()
eval_graph = tf.Graph()
with eval_graph.as_default():
eval_filenames, eval_iterator, eval_elements = \
build_text_line_reader(shuffle=True, batch_size=FLAGS.eval_batch_size)
eval_inputs, eval_outputs = build_eval_graph(eval_elements,
FLAGS.depict_input_dim,
FLAGS.depict_output_dim)
eval_saver = tf.train.Saver()
eval_merger = tf.summary.merge_all()
eval_initializer = tf.global_variables_initializer()
# eval_parameters = tf.trainable_variables()
infer_graph = tf.Graph()
with infer_graph.as_default():
infer_filenames, infer_iterator, infer_elements = \
build_text_line_reader(shuffle=False, batch_size=FLAGS.infer_batch_size)
infer_inputs, infer_outputs = build_infer_graph(
infer_elements, FLAGS.depict_input_dim, FLAGS.depict_output_dim)
rbfnn_metrics = build_metrics_graph('rbfnn')
# kmeans_metrics = build_metrics_graph('kmeans')
infer_saver = tf.train.Saver()
infer_merger = tf.summary.merge_all()
infer_initializer = tf.global_variables_initializer()
train_sess = tf.Session(graph=train_graph)
eval_sess = tf.Session(graph=eval_graph)
infer_sess = tf.Session(graph=infer_graph)
train_writer = tf.summary.FileWriter(FLAGS.summaries_dir + '/train',
train_graph)
validation_writer = tf.summary.FileWriter(
FLAGS.summaries_dir + '/validation', eval_graph)
infer_writer = tf.summary.FileWriter(FLAGS.summaries_dir + '/inference',
infer_graph)
train_sess.run(train_initializer)
train_sess.run(train_iterator.initializer,
feed_dict={train_filenames: [FLAGS.path_to_xtrain]})
# train_sess.run(train_iterator.initializer)
for i in itertools.count():
try:
xs_train = train_sess.run(train_elements)
# print(xs_train)
except tf.errors.OutOfRangeError:
train_sess.run(train_iterator.initializer,
feed_dict={train_filenames: [FLAGS.path_to_xtrain]})
xs_train = train_sess.run(train_elements)
# train_summary, _ = train_sess.run([optimizer, train_merger]) #
_, training_cost, train_summary = train_sess.run(
[optimizer, train_cost, train_merger],
feed_dict={train_inputs: xs_train})
train_writer.add_summary(train_summary, i)
# print('epoch: %6d, training cost: %.8f'%(i, training_cost))
# time.sleep(1)
# if i % FLAGS.eval_step_interval == 0:
if i % pow(10, len(str(i)) - 1) == 0:
# print(train_sess.run(train_parameters[0]))
checkpoint_path = train_saver.save(train_sess,
FLAGS.checkpoints_dir +
'/checkpoints',
global_step=i)
eval_saver.restore(eval_sess, checkpoint_path)
# print(eval_sess.run(eval_parameters[0]))
eval_sess.run(eval_iterator.initializer,
feed_dict={eval_filenames: [FLAGS.path_to_xtest]})
while FLAGS.data_to_eval:
try:
xs_eval = eval_sess.run(eval_elements)
except tf.errors.OutOfRangeError:
# eval_sess.run(eval_iterator.initializer,
# feed_dict={eval_filenames: [r'../../data/x_1000_128.txt']})
# xs_eval = eval_sess.run(eval_elements)
break
# training_outputs = eval_sess.run(eval_outputs, feed_dict={eval_inputs: xs_train})
# evaluation_outputs = eval_sess.run(eval_outputs, feed_dict={eval_inputs: xs_eval})
evaluation_cost, eval_summary = train_sess.run(
[train_cost, train_merger],
feed_dict={train_inputs: xs_eval})
tf.logging.info("epoch: %d, training cost: %f" %
(i, training_cost))
tf.logging.info("epoch: %d, evaluation cost: %f" %
(i, evaluation_cost))
validation_writer.add_summary(eval_summary, i)
break
# if i % FLAGS.infer_step_interval == 0:
if i % pow(10, len(str(i)) - 1) == 0:
checkpoint_path = train_saver.save(train_sess,
FLAGS.checkpoints_dir +
'/checkpoints',
global_step=i)
infer_saver.restore(infer_sess, checkpoint_path)
infers_train = []
infer_sess.run(infer_iterator.initializer,
feed_dict={infer_filenames: [FLAGS.path_to_xtrain]})
while FLAGS.data_to_infer:
try:
xs_infer = infer_sess.run(infer_elements)
except tf.errors.OutOfRangeError:
break
ys_infer = infer_sess.run(infer_outputs,
feed_dict={infer_inputs: xs_infer})
infers_train.extend(ys_infer)
# print(infers_train)
infers_test = []
infer_sess.run(infer_iterator.initializer,
feed_dict={infer_filenames: [FLAGS.path_to_xtest]})
while FLAGS.data_to_infer:
try:
xs_infer = infer_sess.run(infer_elements)
except tf.errors.OutOfRangeError:
break
ys_infer = infer_sess.run(infer_outputs,
feed_dict={infer_inputs: xs_infer})
print(xs_infer.shape, xs_infer.flatten())
print(ys_infer.shape, ys_infer.flatten())
infers_test.extend(ys_infer)
# print(infers_test)
metrics = classifier.run(infers_train, infers_test, FLAGS)
# print(metrics)
pprint.pprint(metrics)
infer_summary = metrics_to_metrics(infer_sess, infer_merger,
rbfnn_metrics, metrics)
infer_writer.add_summary(infer_summary, i)
xrand = np.loadtxt(FLAGS.path_to_xrand)
print(xtrain.shape, xtest.shape, xrand.shape)
FLAGS.rbfnn_num_center = 120
for i in range(7, 15 + 1):
num_cluster = 1 << i
print(num_cluster)
FLAGS.depict_output_dim = num_cluster
FLAGS.rbfnn_input_dim = num_cluster
pprint.pprint(FLAGS)
# kms = cluster.build_kmeans_model_with_fixed_input(FLAGS, xrand)
kms = cluster.build_kmeans_model_with_random_input(FLAGS, xtrain)
ca_train = kms.predict(xtrain)
ca_test = kms.predict(xtest)
metrics = classifier.run(ca_train, ca_test, FLAGS)
pprint.pprint(metrics)
# TODO:
if not os.path.exists(FLAGS.saved_results_dir):
os.makedirs(FLAGS.saved_results_dir)
outfile = os.path.join(
FLAGS.saved_results_dir,
'%s_r%d_kmeans_results.txt' % (FLAGS.database_name, FLAGS.split_round))
with open(outfile, 'a') as f:
line = list()
line.extend([FLAGS.rbfnn_num_center, FLAGS.depict_output_dim, 0])
line.extend(metrics['err_train'].tolist())
line.extend([metrics['acc_train']])
line.extend(metrics['stsm_train'].tolist())
line.extend(metrics['err_test'].tolist())
#data_path = 'articles.csv' if args.full else 'split80/test.csv'
data = {seed: setup(seed, path=f'data/articles.csv') for seed in SEEDS}
from utils import LABELS
analysis = {'embedding': [], 'truth': [], 'text': [], 'pred': [], LABELS: []}
for dim in DIMS:
for vector in VECTORS:
#cols['embedding'].append(f'{dim}d_{vector}')
results = np.zeros(len(METRICS), dtype='float')
for seed in SEEDS:
TEXT, LABEL, train_data, test_data = data[seed]
if vector == 'RANDOM':
test_results_a = run(seed, 'a', analysis, DIR, None, dim, TEXT, LABEL, train_data, test_data, randomize=True, saved=SAVED)
test_results_b = run(seed, 'b', analysis, DIR, None, dim, TEXT, LABEL, test_data, train_data, randomize=True, saved=SAVED)
else:
test_results_a = run(seed, 'a', analysis, DIR, vector, dim, TEXT, LABEL, train_data, test_data, randomize=RANDOMIZE, saved=SAVED)
test_results_b = run(seed, 'b', analysis, DIR, vector, dim, TEXT, LABEL, test_data, train_data, randomize=RANDOMIZE, saved=SAVED)
cols['embedding'].append(f'{vector}.{dim}d_{seed}a')
cols['embedding'].append(f'{vector}.{dim}d_{seed}b')
for j, metric in enumerate(METRICS):
cols[metric].append(test_results_a[j])
cols[metric].append(test_results_b[j])
print(f'finished {vector}.{dim}d')
df = pd.DataFrame(cols)
with open(os.path.join('results', DIR, 'results.pkl'), 'wb') as f:
pickle.dump(df, f)
def run(progress=True,
verbose=False,
loadFile=False,
printtweets=False,
causeFilename="causeSunWedFri",
outputDivider=900,
produceResult=False,
chunkScatter=False):
if progress:
classifier.run(Covid=True,
verbose=verbose) #this gets the reference accuracy
"""
various file input options as [dates]
"""
#dates = ["../2020-04-19 Coronavirus Tweets.csv","../2020-04-21 Coronavirus Tweets.csv","../2020-04-22 Coronavirus Tweets.csv"]#,"../2020-04-24 Coronavirus Tweets.csv" ]
# April overall Sun/Wed
dates = ([
"../2020-03-29 Coronavirus Tweets.csv",
"../2020-04-01 Coronavirus Tweets.csv",
"../2020-04-05 Coronavirus Tweets.csv",
"../2020-04-08 Coronavirus Tweets.csv"
] + [
"../2020-04-{} Coronavirus Tweets.csv".format(i)
for i in range(12, 31, 7)
] + [
"../2020-04-{} Coronavirus Tweets.csv".format(i)
for i in range(15, 31, 7)
])
# April overall Mon/Thu
#dates = (["../2020-03-30 Coronavirus Tweets.csv","../2020-04-02 Coronavirus Tweets.csv","../2020-04-06 Coronavirus Tweets.csv","../2020-04-09 Coronavirus Tweets.csv"]
# +["../2020-04-{} Coronavirus Tweets.csv".format(i) for i in range(13,31,7)]
# +["../2020-04-{} Coronavirus Tweets.csv".format(i) for i in range(16,31,7)])
# April overall Sun/Wed/Fri
#dates = (["../2020-03-29 Coronavirus Tweets.csv","../2020-04-01 Coronavirus Tweets.csv","../2020-04-03 Coronavirus Tweets.csv","../2020-04-06 Coronavirus Tweets.csv","../2020-04-08 Coronavirus Tweets.csv"]
# +["../2020-04-{} Coronavirus Tweets.csv".format(i) for i in range(10,31,7)]
# +["../2020-04-{} Coronavirus Tweets.csv".format(i) for i in range(12,31,7)]
# +["../2020-04-{} Coronavirus Tweets.csv".format(i) for i in range(15,31,7)])
# April overall Mon/Thu/Sat
#dates = (["../2020-03-30 Coronavirus Tweets.csv","../2020-04-02 Coronavirus Tweets.csv","../2020-04-04 Coronavirus Tweets.csv","../2020-04-06 Coronavirus Tweets.csv","../2020-04-09 Coronavirus Tweets.csv"]
# +["../2020-04-{} Coronavirus Tweets.csv".format(i) for i in range(13,31,7)]
# +["../2020-04-{} Coronavirus Tweets.csv".format(i) for i in range(16,31,7)]
# +["../2020-04-{} Coronavirus Tweets.csv".format(i) for i in range(11,31,7)])
# This part handles the loading/saving of the cause file for feedback usage.
# Because the cause.run(heavily running code) doesn't run when you loadFile=True, this would be helpful.
# If you don't have the files or don't have computation power, set loadFile=True and use the preset cause.pkl.
if loadFile:
loading = open(causeFilename + ".pkl", 'rb')
xA, xF, xJ, xS, cmFJS, cmAJS, cmAFS, cmAFJ, _A, _F, _J, _S, cm4 = load(
loading)
loading.close()
else:
xA, xF, xJ, xS, cmFJS, cmAJS, cmAFS, cmAFJ, _A, _F, _J, _S, cm4 = cause.run(
verbose=verbose,
dates=dates,
printtweets=printtweets,
chunkScatter=chunkScatter)
saving = open(causeFilename + ".pkl", "wb")
dump((xA, xF, xJ, xS, cmFJS, cmAJS, cmAFS, cmAFJ, _A, _F, _J, _S,
cm4), saving, -1)
saving.close()
# This part shows you the accuracy information.
""" Feedback sandbox examples
set scorefactor => sf
sf = 0.2 : exclusive cause reinforce
classifier.run(Covid = True, verbose = verbose, feed_back = [xA, xF, xJ, xS],sf=0.2)
sf = -0.4 : non-cause deduction *(Sun/Wed => 0.84)
classifier.run(Covid = True, verbose = verbose, feed_back = [cmFJS, cmAJS, cmAFS, cmAFJ],sf=-0.4)
sf = -0.2 : inclusive cause reinforce *(Sun/Wed/Fri => 0.85)
classifier.run(Covid = True, verbose = verbose, feed_back = [_A,_F,_J,_S],sf=-0.2)
sf = ? : inclusive cause reinforce
classifier.run(Covid = True, verbose = verbose, feed_back = [cm4,cm4,cm4,cm4],sf=0)"""
fb = [cmFJS, cmAJS, cmAFS, cmAFJ]
scoreFactor = -0.4
classifier.run(Covid=True,
verbose=verbose,
feed_back=fb,
sf=scoreFactor)
# ^this part only tries the feedback on evaluation. This is just to show how accurate the classifier we will use on the bottom will be.
# vThe real work is right below.
#This part produces result(ex: 03-00 - Anger:4000, Fear: 1000, ...).
if loadFile and produceResult:
dateChunks = [ # weekly analysis
#["../2020-03-00 Coronavirus Tweets (pre 2020-03-12).csv"],
#["../2020-03-12 Coronavirus Tweets.csv"],
#["../2020-03-15 Coronavirus Tweets.csv"],
#["../2020-03-00 Coronavirus Tweets (pre 2020-03-12).csv"]+["../2020-03-12 Coronavirus Tweets.csv"]+["../2020-03-15 Coronavirus Tweets.csv"],
#["../2020-03-20 Coronavirus Tweets.csv"],
#["../2020-03-25 Coronavirus Tweets.csv"],
#["../2020-03-28 Coronavirus Tweets.csv"],
#["../2020-03-29 Coronavirus Tweets.csv"],
#["../2020-03-25 Coronavirus Tweets.csv","../2020-03-28 Coronavirus Tweets.csv","../2020-03-29 Coronavirus Tweets.csv"],
#["../2020-03-30 Coronavirus Tweets.csv","../2020-03-31 Coronavirus Tweets.csv"]
#+["../2020-04-0{} Coronavirus Tweets.csv".format(i) for i in range(1,6)],
[
"../2020-04-0{} Coronavirus Tweets.csv".format(i)
for i in range(6, 10)
] + [
"../2020-04-{} Coronavirus Tweets.csv".format(i)
for i in range(10, 13)
],
[
"../2020-04-{} Coronavirus Tweets.csv".format(i)
for i in range(13, 20)
],
[
"../2020-04-{} Coronavirus Tweets.csv".format(i)
for i in range(20, 27)
],
[
"../2020-04-{} Coronavirus Tweets.csv".format(i)
for i in range(27, 31)
]
]
# This part will run and get the percentage informations.
# REMEMBER, you should have all the files listed in dateChunks to run this part.
# If you don't have them, set produceResult = False.
for d in dateChunks:
check.run(dates=d,
verbose=False,
outDeminish=outputDivider,
feedback=fb,
num_samples=3375,
printtweets=printtweets)
# Sidenote! The return of check is the cause chunks in list form from the dataset.
# -go to a for loop in check_classifier on line 106 ("for check in checks") for more info.
# -the check in checks are tweets as list in each emotions.(The exact format can be learned from line 81 to 96 check_classifier.py)
else:
# the list "dates" contain the path of the tweets' files
# original
# dates = ["../2020-04-19 Coronavirus Tweets.csv","../2020-04-21 Coronavirus Tweets.csv","../2020-04-22 Coronavirus Tweets.csv"]#,"../2020-04-24 Coronavirus Tweets.csv" ]
# April 16~30
#dates = ["../2020-04-{} Coronavirus Tweets.csv".format(i) for i in range(16,31)]
# April 01~15
#dates = (["../2020-04-{} Coronavirus Tweets.csv".format(i) for i in range(10,16)]+["../2020-04-0{} Coronavirus Tweets.csv".format(i) for i in range(1,10)])
check_classifier.run(verbose=verbose)
e_fn = e_fn + 1
elif name == 'NEUTROPHIL':
n_fn = n_fn + 1
elif name == 'LYMPHOCYTE':
l_fn = l_fn + 1
elif name == 'BASOPHIL':
b_fn = b_fn + 1
elif name == 'MONOCYTE':
m_fn = m_fn + 1
classified = []
with open('./output', 'w') as writer:
for image_path in os.listdir('./images'):
#print image_path
name = classifier.run(image_path)
writer.write(image_path + ', ' + name + '\n')
#print(name)
classified.append(name)
with open('./cell_classes') as file:
lines = file.readlines()
lines = [l.strip() for l in lines]
correct = 0
total = 0
i = 0
for line in lines:
import os
path_ad = "D:/Alzheimers/PET_AD_CLEAN"
path_normal = "D:/Alzheimers/PET_NORMAL_CLEAN/"
nr_ad = 48
nr_normal = 48
# CREDIT: https://stackoverflow.com/questions/6687660/keep-persistent-variables-in-memory-between-runs-of-python-script
# Peter Lyons Jul 14 '11
cache = None
if __name__ == "__main__":
while True:
if not cache:
pet_ad = imageutils.read_pet_images(path_ad, nr_ad)
pet_normal = imageutils.read_pet_images(path_normal, nr_normal)
cache = (pet_ad, pet_normal)
try:
classifier.run(cache, nr_ad, nr_normal)
except Exception as e:
print("Error in classifier.py")
print(e)
print("Press enter to re-run the script, CTRL-C to exit")
sys.stdin.readline()
os.remove(getattr(classifier, '__cached__', 'classifier.pyc'))
reload(classifier)
