def test_lmdb_creation(self):
params = nn_params.copy()
params.update({'nclasses': n_classes})
# Create dataset
X, Y = datasets.load_digits(return_X_y=True)
X = preprocessing.StandardScaler().fit_transform(X)
x_train, x_test, y_train, y_test = model_selection.train_test_split(
X, Y, test_size=test_size, random_state=seed)
# Save data in .svm format
tr_svm_f, tr_lmdb_f = os.path.abspath('x_train.svm'), os.path.abspath(
'x_train.lmdb')
te_svm_f, te_lmdb_f = os.path.abspath('x_test.svm'), os.path.abspath(
'x_test.lmdb')
vocab_path = os.path.abspath('vocab.dat')
datasets.dump_svmlight_file(x_train, y_train, tr_svm_f)
datasets.dump_svmlight_file(x_test, y_test, te_svm_f)
lmdb_utils.create_lmdb_from_svm(svm_path=tr_svm_f,
lmdb_path=tr_lmdb_f,
vocab_path=vocab_path,
**params)
lmdb_utils.create_lmdb_from_svm(svm_path=te_svm_f,
lmdb_path=te_lmdb_f,
**params)
tr_lmdb = SVMConnector(path=tr_svm_f,
lmdb_path=tr_lmdb_f,
vocab_path=vocab_path)
te_lmdb = SVMConnector(path=te_svm_f, lmdb_path=te_lmdb_f)
optimizer = GenericSolver(solver_type='SGD',
base_lr=0.01,
iterations=100)
clf = MLP(**params)
clf.fit(tr_lmdb, validation_data=[te_lmdb], solver=optimizer)
ytr_prob = clf.predict_proba(tr_lmdb)
acc = metrics.accuracy_score(y_train, ytr_prob.argmax(-1))
assert acc > 0.7
os_utils._remove_files([tr_svm_f, te_svm_f, vocab_path])
os_utils._remove_dirs([tr_lmdb_f, te_lmdb_f])
def create_lmdb_from_svm(svm_path,
lmdb_path,
vocab_path=None,
host='localhost',
port=8085,
nclasses=2,
gpu=True,
tmp_folder=None):
if os.path.exists(lmdb_path):
print("warning: {} exist, overwriting it".format(lmdb_path))
tmp_folder = tempfile.mkdtemp(
prefix="pydd_", dir=tmp_folder) if tmp_folder else tempfile.mkdtemp(
prefix="pydd_")
train_data = SVMConnector(path=svm_path)
optimizer = GenericSolver(solver_type='SGD', base_lr=0.01, iterations=1)
clf = MLP(host=host,
port=port,
nclasses=nclasses,
gpu=gpu,
repository=tmp_folder)
clf.fit(train_data, solver=optimizer)
shutil.move(os.path.join(tmp_folder, "train.lmdb"), lmdb_path)
if vocab_path:
shutil.move(os.path.join(tmp_folder, "vocab.dat"), vocab_path)
# delete service
clf.delete_service(clf.sname, clear='lib')
# delete tmp_folder
shutil.rmtree(tmp_folder)
return lmdb_path, vocab_path
# create dataset
X, y = datasets.load_digits(n_class=n_classes, return_X_y=True)
X = preprocessing.StandardScaler().fit_transform(X)
xtr, xte, ytr, yte = model_selection.train_test_split(X, y, **split_params)
# create and save train.svm and test.svm
tr_f = os.path.abspath('x_train.svm')
te_f = os.path.abspath('x_test.svm')
datasets.dump_svmlight_file(xtr, ytr, tr_f)
datasets.dump_svmlight_file(xte, yte, te_f)
# Define models and class weights
clf = MLP(**params)
train_data, test_data = SVMConnector(path=tr_f), SVMConnector(path=te_f)
logs = clf.fit(train_data,
validation_data=[test_data],
solver=solver,
class_weights=class_weights,
batch_size=128)
params.update({"resume": True})
clf = MLP(**params)
logs = clf.fit(train_data,
validation_data=[test_data],
solver=solver,
class_weights=class_weights,
batch_size=128)
yte_pred = clf.predict(test_data)
X = preprocessing.StandardScaler().fit_transform(X)
xtr, xte, ytr, yte = model_selection.train_test_split(X,
Y,
test_size=test_size,
random_state=seed)
tr_f = os.path.abspath('x_train.svm')
te_f = os.path.abspath('x_test.svm')
#####################
# create connectors #
#####################
# array connector
xtr_arr, xte_arr = ArrayConnector(xtr, ytr), ArrayConnector(xte, yte)
# svm connector
xtr_svm, xte_svm = SVMConnector(tr_f), SVMConnector(te_f)
# array sparse connector
xtr_sparse, xte_sparse = ArrayConnector(csc_matrix(xtr), ytr), ArrayConnector(
csc_matrix(xte), yte)
class TestSVM(object):
def test_classification(self):
params = nn_params.copy()
params.update({'nclasses': n_classes})
optimizer = GenericSolver(**solver_param)
datasets.dump_svmlight_file(xtr, ytr, tr_f)
datasets.dump_svmlight_file(xte, yte, te_f)
port = 8080
iteration=100
lr=0.01
gpu=False
X, y = datasets.load_digits(n_class=n_classes, return_X_y=True)
X = preprocessing.StandardScaler().fit_transform(X)
x_train, x_test, y_train, y_test = model_selection.train_test_split(X, y, test_size=test_size, random_state=seed)
tr_f = os.path.abspath('x_train.svm')
te_f = os.path.abspath('x_test.svm')
datasets.dump_svmlight_file(x_train, y_train, tr_f)
datasets.dump_svmlight_file(x_test, y_test, te_f)
# train_data = ArrayConnector(x_train, y_train)
# val_data = ArrayConnector(x_train, y_train)
train_data = SVMConnector(tr_f)
val_data = SVMConnector(te_f)
clf = MLP(host=host, port=port, nclasses=n_classes, layers=[100], gpu=gpu)
solver = GenericSolver(iterations=iteration, test_interval=30, solver_type="SGD", base_lr=lr)
clf.fit(train_data, validation_data=[val_data], solver=solver)
clf.predict_proba(train_data)
clf.fit(train_data, validation_data=[val_data], solver=solver)
y_pred = clf.predict_proba(train_data)
clf = LR(host=host, port=port, nclasses=n_classes, gpu=gpu)
solver = GenericSolver(iterations=iteration, solver_type="SGD", base_lr=lr)
clf.fit(train_data, solver=solver)
y_pred = clf.predict_proba(train_data)
x_train, x_test, y_train, y_test = model_selection.train_test_split(
X, Y, test_size=test_size, random_state=seed)
# Save data in .svm format
tr_svm_f, tr_lmdb_f = os.path.abspath('x_train.svm'), os.path.abspath(
'x_train.lmdb')
te_svm_f, te_lmdb_f = os.path.abspath('x_test.svm'), os.path.abspath(
'x_test.lmdb')
vocab_path = os.path.abspath('vocab.dat')
datasets.dump_svmlight_file(x_train, y_train, tr_svm_f)
datasets.dump_svmlight_file(x_test, y_test, te_svm_f)
# create lmdb and vocab file
create_lmdb_from_svm(svm_path=tr_svm_f,
lmdb_path=tr_lmdb_f,
vocab_path=vocab_path,
**params)
create_lmdb_from_svm(svm_path=te_svm_f, lmdb_path=te_lmdb_f, **params)
tr_data = SVMConnector(path=tr_svm_f,
lmdb_path=tr_lmdb_f,
vocab_path=vocab_path)
te_data = SVMConnector(path=tr_svm_f, lmdb_path=tr_lmdb_f)
optimizer = GenericSolver(solver_type='SGD', base_lr=0.01, iterations=100)
clf = MLP(**params)
clf.fit(tr_data, validation_data=[te_data], solver=optimizer)
y_pred_lmdb = clf.predict_proba(te_data)
# create and save train.svm and test.svm
tr_f = os.path.abspath("{}/x_train.svm".format(folder))
te_f = os.path.abspath("{}/x_test.svm".format(folder))
datasets.dump_svmlight_file(xtr, ytr, tr_f)
datasets.dump_svmlight_file(xte, yte, te_f)
# create lmdb dataset
tr_lmdb = os.path.abspath("{}/train.lmdb".format(folder))
te_lmdb = os.path.abspath("{}/test.lmdb".format(folder))
vocab_path = os.path.abspath("{}/vocab.dat".format(folder))
lmdb_utils.create_lmdb_from_svm(tr_f, tr_lmdb, vocab_path, **params)
lmdb_utils.create_lmdb_from_svm(te_f, te_lmdb, **params)
# create lmdb connectors
train_data = SVMConnector(path=tr_f, lmdb_path=tr_lmdb, vocab_path=vocab_path)
test_data = SVMConnector(path=te_f, lmdb_path=te_lmdb)
# Training model from lmdb data
clf = MLP(**params)
optimizer = GenericSolver(solver_type='SGD', iterations=500, base_lr=0.01)
logs = clf.fit(train_data, validation_data=[test_data], solver=optimizer)
yte_pred = clf.predict(test_data)
report = metrics.classification_report(yte, yte_pred)
print(report)
os_utils._remove_dirs([folder])
port = 8080
np.random.seed(seed) # for reproducibility
split_params = {'test_size': 0.2, 'random_state': seed}
booster_params = {"max_depth": 10, "subsample": 0.8, "eta": 0.3}
# create dataset
X, y = datasets.make_classification(n_samples=n_samples,
class_sep=0.4,
n_features=n_features,
n_classes=n_classes,
random_state=seed)
x_train, x_test, y_train, y_test = model_selection.train_test_split(
X, y, **split_params)
# store dataset
train_path = os.path.abspath('x_train.svm')
test_path = os.path.abspath('x_test.svm')
datasets.dump_svmlight_file(x_train, y_train, train_path)
datasets.dump_svmlight_file(x_test, y_test, test_path)
# train model
train_data, val_data = SVMConnector(train_path), SVMConnector(test_path)
clf = XGB(host=host, port=port, nclasses=n_classes)
clf.fit(train_data, validation_data=[val_data], **booster_params)
# predict/metrics
y_test_prob = clf.predict_proba(test_path)
y_test_pred = y_test_prob.argmax(-1)
print(metrics.classification_report(y_test, y_test_pred))
