def elm_coates_stacked(directory):
self_name = 'elm_coates_stacked'
logger = new_logger(self_name, directory=directory)
X, y = get_mnist(directory)
logger.info('Loaded MNIST successfully with {0} records'.format(
X.shape[0]))
label_encoder = LabelEncoder().fit(y)
y_encoded = label_encoder.transform(y)
# scale X so X in [0, 1]
X /= 255.
# setup parameter grid
param_grid = {
'chunk_size': [10000],
'input_scaling': np.logspace(start=-3, stop=1, base=10, num=3),
'bias_scaling': [0.], # np.logspace(start=-3, stop=1, base=10, num=6),
'input_activation': ['relu'],
'alpha': [1e-5],
'random_state': [42]
}
# read input matrices from files
list_filepaths = []
predefined_input_weights = np.empty((784, 0))
for filepath in glob.glob(os.path.join(directory, '*kmeans1*matrix.npy')):
logger.info('matrix file found: {0}'.format(filepath))
list_filepaths.append(filepath)
predefined_input_weights = np.append(predefined_input_weights,
np.load(filepath),
axis=1)
# setup estimator
estimator = ELMClassifier(
PredefinedWeightsInputToNode(
predefined_input_weights=predefined_input_weights),
IncrementalRegression())
logger.info('Estimator params: {0}'.format(estimator.get_params().keys()))
# return
# setup grid search
cv = GridSearchCV(estimator=estimator,
param_grid=param_grid,
scoring='accuracy',
n_jobs=1,
verbose=1,
cv=[(np.arange(0,
train_size), np.arange(train_size,
70000))])
# run!
cv.fit(X, y_encoded)
cv_best_params = cv.best_params_
del cv_best_params['input_to_nodes__predefined_input_weights']
# refine best params
logger.info('best parameters: {0} (score: {1})'.format(
cv_best_params, cv.best_score_))
# refine results
cv_results = cv.cv_results_
del cv_results['params']
del cv_results['param_input_to_nodes__predefined_input_weights']
# save results
try:
with open(os.path.join(directory, '{0}.csv'.format(self_name)),
'w') as f:
f.write(','.join(cv_results.keys()) + '\n')
for row in list(map(list, zip(*cv_results.values()))):
f.write(','.join(map(str, row)) + '\n')
except PermissionError as e:
print('Missing privileges: {0}'.format(e))
if not list_filepaths:
logger.warning('no input weights matrices found')
return
def elm_coates(directory):
self_name = 'elm_coates'
logger = new_logger(self_name, directory=directory)
X, y = get_mnist(directory)
logger.info('Loaded MNIST successfully with {0} records'.format(
X.shape[0]))
label_encoder = LabelEncoder().fit(y)
y_encoded = label_encoder.transform(y)
filepath_label_encoder = os.path.join(
directory, 'label_encoder_{0}.pickle'.format(self_name))
# save label_encoder
try:
with open(filepath_label_encoder, 'wb') as f:
pickle.dump(label_encoder, f)
except Exception as e:
logger.error('Unexpected error: {0}'.format(e))
exit(1)
# scale X so X in [0, 1]
X /= 255.
X_train, X_test, y_train, y_test = (X[:train_size, ...], X[train_size:],
y_encoded[:train_size],
y_encoded[train_size:])
csv_filepath = os.path.join(directory, '{0}.csv'.format(self_name))
# read input matrices from files
list_filepaths = []
for filepath in glob.glob(
os.path.join(directory, '*pca*+kmeans*_matrix.npy')):
logger.info('matrix file found: {0}'.format(filepath))
list_filepaths.append(filepath)
filename = os.path.splitext(os.path.basename(filepath))[0]
est_filepath = os.path.join(directory,
'est_coates-{0}.pickle'.format(filename))
pred_filpath = os.path.join(
directory, 'est_coates-{0}-predicted.npz'.format(filename))
# only if files do not exist yet
if (not os.path.isfile(csv_filepath)
or not os.path.isfile(est_filepath)
or not os.path.isfile(pred_filpath)):
# setup estimator
estimator = ELMClassifier(
input_to_node=PredefinedWeightsInputToNode(
predefined_input_weights=np.load(filepath),
input_scaling=1.0,
bias_scaling=0.0,
input_activation='relu',
random_state=42),
chunk_size=1000)
logger.info('Estimator params: {0}'.format(
estimator.get_params().keys()))
# !run
time_start = time.time()
estimator.fit(X_train, y_train)
time_fitted = time.time()
y_pred = estimator.predict(X_test)
time_predicted = time.time()
# !run
# results
dict_results = estimator.get_params()
dict_results.update({
'filename': filename,
'fit_time': time_fitted - time_start,
'score_time': time_predicted - time_fitted,
'score': accuracy_score(y_test, y_pred)
})
# drop data
dict_results.pop('input_to_nodes__predefined_input_weights')
dict_results.pop('input_to_nodes')
dict_results.pop('regressor')
logger.info('fitted time {1}, score on test set: {0}'.format(
dict_results['score'], dict_results['fit_time']))
# save estimator
try:
with open(est_filepath, 'wb') as f:
pickle.dump(estimator, f)
except Exception as e:
logger.error('Unexpected error: {0}'.format(e))
exit(1)
# save results
try:
if not os.path.isfile(csv_filepath):
with open(csv_filepath, 'a') as f:
f.write(','.join(dict_results.keys()))
f.write('\n')
f.write(','.join(
[str(item) for item in dict_results.values()]))
f.write('\n')
else:
with open(csv_filepath, 'a') as f:
f.write(','.join(
[str(item) for item in dict_results.values()]))
f.write('\n')
except PermissionError as e:
print('Missing privileges: {0}'.format(e))
# save prediction
np.savez_compressed(pred_filpath,
X_test=X_test,
y_test=label_encoder.inverse_transform(y_test),
y_pred=label_encoder.inverse_transform(y_pred))
if not list_filepaths:
logger.warning('no input weights matrices found')
return
def elm_pca(directory):
self_name = 'elm_pca'
logger = new_logger(self_name, directory=directory)
X, y = get_mnist(directory)
logger.info('Loaded MNIST successfully with {0} records'.format(
X.shape[0]))
# scale X
X /= 255.
# split train test
X_train, X_test, y_train, y_test = train_test_split(X[:train_size],
y[:train_size],
train_size=50000,
random_state=42)
# prepare parameter grids
param_grid_basic = {
'hidden_layer_size': 2000,
'input_scaling': 1.,
'bias_scaling': 0.,
'input_activation': 'relu',
'alpha': 1e-5,
'random_state': 42
}
# setup estimator
estimator = ELMClassifier(regressor=Ridge())
# initialize filepath
filepath = os.path.join(directory, '{0}_basic.csv'.format(self_name))
# initialize param dict
param_dict_job = estimator.get_params().copy()
param_dict_job.update(param_grid_basic)
# initialize results dict
results_dict_job = param_dict_job.copy()
# add dummy results
results_dict_job.update({
'time_fit': 0,
'time_pred': 0,
'score': 0,
'pca_n_components': 0
})
# preprocessing pca
try:
# write header
with open(filepath, 'w') as f:
writer = csv.DictWriter(f, fieldnames=results_dict_job.keys())
writer.writeheader()
for pca_n_components in [10, 20, 50, 100, 200, 500, 784]:
results_dict_job.update({'pca_n_components': pca_n_components})
estimator.set_params(**param_dict_job)
# preprocessing
pca = PCA(n_components=pca_n_components).fit(X_train)
X_train_pca, X_test_pca = \
pca.transform(X_train), pca.transform(X_test)
# run!
time_start = time.time()
estimator.fit(X_train_pca, y_train)
time_fit = time.time()
y_pred = estimator.predict(X_test_pca)
time_pred = time.time()
# run end!
results_dict_job.update({
'time_fit': time_fit - time_start,
'time_pred': time_pred - time_fit,
'score': accuracy_score(y_test, y_pred)
})
logger.info('pca.n_components_: {0}, score: {1}'.format(
pca_n_components, results_dict_job['score']))
with open(filepath, 'a') as f:
writer = csv.DictWriter(f, fieldnames=results_dict_job.keys())
writer.writerow(results_dict_job)
except MemoryError as e:
logger.error('Memory error: {0}'.format(e))
except PermissionError as e:
logger.error('Missing privileges: {0}'.format(e))
except Exception as e:
logger.error('Unexpected exception: {0}'.format(e))
def elm_hidden_layer_size(directory):
self_name = 'elm_hidden_layer_size'
logger = new_logger(self_name, directory=directory)
X, y = get_mnist(directory)
logger.info('Loaded MNIST successfully with {0} records'.format(
X.shape[0]))
# encode y
label_encoder = LabelEncoder().fit(y)
y_encoded = label_encoder.transform(y)
# scale X
X /= 255.
# split train test
X_train, X_test, y_train, y_test = (X[:train_size, :], X[train_size:, :],
y_encoded[:train_size],
y_encoded[train_size:])
# fan-out from paper
fan_out = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 12, 15, 20]
# prepare parameter grids
param_grid_basic = {
'hidden_layer_size': 0,
'input_scaling': 1.,
'bias_scaling': 0.,
'activation': 'relu',
'chunk_size': 1000,
'alpha': 1e-5,
'random_state': 42
}
param_grid_pca = {
'hidden_layer_size': 0,
'input_scaling': 1.,
'bias_scaling': 0.,
'activation': 'relu',
'chunk_size': 1000,
'alpha': 1e-5,
'random_state': 42
}
# setup estimator
estimator = ELMClassifier()
# basic
try:
# initialize filepath
csv_filepath = os.path.join(directory,
'{0}_basic.csv'.format(self_name))
# initialize param dict
param_dict_job = estimator.get_params().copy()
param_dict_job.update(param_grid_basic)
# initialize results dict
results_dict_job = param_dict_job.copy()
# add dummy results
results_dict_job.update({'time_fit': 0, 'time_pred': 0, 'score': 0})
# write header
with open(csv_filepath, 'w') as f:
writer = csv.DictWriter(f, fieldnames=results_dict_job.keys())
writer.writeheader()
for hls in 784 * np.array(fan_out):
param_dict_job.update({'hidden_layer_size': hls})
estimator.set_params(**param_dict_job)
# run!
time_start = time.time()
estimator.fit(X_train, y_train)
time_fit = time.time()
y_pred = estimator.predict(X_test)
time_pred = time.time()
# run end!
results_dict_job.update(estimator.get_params())
results_dict_job.update({
'time_fit': time_fit - time_start,
'time_pred': time_pred - time_fit,
'score': accuracy_score(y_test, y_pred)
})
logger.info('hidden_layer_size: {0}, score: {1}'.format(
hls, results_dict_job['score']))
with open(csv_filepath, 'a') as f:
writer = csv.DictWriter(f, fieldnames=results_dict_job.keys())
writer.writerow(results_dict_job)
del estimator.input_to_node._hidden_layer_state
with open(
os.path.join(directory,
'elmc_hls{0}_basic.pickle'.format(hls)),
'wb') as f:
pickle.dump(estimator, f)
except MemoryError as e:
logger.error('Memory error: {0}'.format(e))
pass
except PermissionError as e:
logger.error('Missing privileges: {0}'.format(e))
pass
# preprocessing pca
try:
# initialize filepath
csv_filepath = os.path.join(directory, '{0}_pca.csv'.format(self_name))
# preprocessing
pca50 = PCA(n_components=50).fit(X_train)
X_train_pca50, X_test_pca50 = (pca50.transform(X_train),
pca50.transform(X_test))
pca100 = PCA(n_components=100).fit(X_train)
X_train_pca100, X_test_pca100 = (pca100.transform(X_train),
pca100.transform(X_test))
list_dict_pca = [{
'n_components': 50,
'X_train': X_train_pca50,
'X_test': X_test_pca50
}, {
'n_components': 100,
'X_train': X_train_pca100,
'X_test': X_test_pca100
}]
logger.info('Preprocessing successful!')
# initialize param dict
param_dict_job = estimator.get_params().copy()
param_dict_job.update(param_grid_pca)
# initialize results dict
results_dict_job = param_dict_job.copy()
# add dummy results
results_dict_job.update({
'time_fit': 0,
'time_pred': 0,
'score': 0,
'pca_n_components': 0
})
# write header
with open(csv_filepath, 'w') as f:
writer = csv.DictWriter(f, fieldnames=results_dict_job.keys())
writer.writeheader()
for dict_pca in list_dict_pca:
results_dict_job.update(
{'pca_n_components': dict_pca['n_components']})
for hls in np.concatenate(
(100 * np.array(fan_out), 784 * np.array(fan_out)), axis=0):
param_dict_job.update({'hidden_layer_size': hls})
estimator.set_params(**param_dict_job)
# run!
time_start = time.time()
estimator.fit(dict_pca['X_train'], y_train)
time_fit = time.time()
y_pred = estimator.predict(dict_pca['X_test'])
time_pred = time.time()
# run end!
results_dict_job.update(estimator.get_params())
results_dict_job.update({
'time_fit': time_fit - time_start,
'time_pred': time_pred - time_fit,
'score': accuracy_score(y_test, y_pred)
})
logger.info(
'n_components: {2}, hidden_layer_size: {0}, score:'
' {1}'.format(hls, results_dict_job['score'],
results_dict_job['pca_n_components']))
with open(csv_filepath, 'a') as f:
writer = csv.DictWriter(f,
fieldnames=results_dict_job.keys())
writer.writerow(results_dict_job)
with open(
os.path.join(
directory, 'elmc_hls{0}_pca{1}.pickle'.format(
hls, results_dict_job['pca_n_components'])),
'wb') as f:
pickle.dump(estimator, f)
except MemoryError as e:
logger.error('Memory error: {0}'.format(e))
pass
except PermissionError as e:
logger.error('Missing privileges: {0}'.format(e))
pass
def test_elm_get_params() -> None:
print('\ntest_elm_get_params():')
elm = ELMClassifier()
elm_params = elm.get_params()
print(elm_params)