def test_fs_csv_loader(self):
sample_data = "sample_data/iris/iris.csv"
self.tlog("loading matrix => " + sample_data)
dmat_train, dlabel_train, dmat_test, dlabel_test \
= fs.csv_loader(sample_data, 0.2)
self.tlog('iris train data size : ' + str(len(dmat_train)))
self.tlog('iris test data size : ' + str(len(dmat_test)))
self.set_global_value('iris_mat_train', dmat_train)
self.set_global_value('iris_label_train', dlabel_train)
self.set_global_value('iris_mat_test', dmat_test)
self.set_global_value('iris_label_test', dlabel_test)
def test_fs_csv_loader(self):
sample_data = "sample_data/iris/iris.csv"
self.tlog("loading matrix => " + sample_data)
dmat_train, dlabel_train, dmat_test, dlabel_test \
= fs.csv_loader(sample_data, 0.2)
self.tlog('iris train data size : ' + str(len(dmat_train)))
self.tlog('iris test data size : ' + str(len(dmat_test)))
self.set_global_value('iris_mat_train', dmat_train)
self.set_global_value('iris_label_train', dlabel_train)
self.set_global_value('iris_mat_test', dmat_test)
self.set_global_value('iris_label_test', dlabel_test)
def load_mnist(path=".", dataset="training", one_hot=False):
data_path = download_data(path, "mnist")
train_data = os.path.join(data_path, "MNIST_train.small.csv")
dmat_train, dlabel_train = fs.csv_loader(train_data, 0)
test_data = os.path.join(data_path, "MNIST_test.small.csv")
dmat_test, dlabel_test = fs.csv_loader(test_data, 0)
dmat_train = map(lambda row: map(float, row), dmat_train)
dmat_test = map(lambda row: map(float, row), dmat_test)
if one_hot:
one_hot_label = map(list, list(np.eye(10)))
temp_dlabel_train = []
temp_dlabel_test = []
for l in dlabel_train:
temp_dlabel_train.append(one_hot_label[int(l)])
for l in dlabel_test:
temp_dlabel_test.append(one_hot_label[int(l)])
dlabel_train = temp_dlabel_train
dlabel_test = temp_dlabel_test
if dataset == "training":
return dmat_train, dlabel_train
elif dataset == "testing":
return dmat_test, dlabel_test
else:
raise ValueError("dataset must be 'testing' or 'training'")
def load_iris(path=".", dataset="training", one_hot = False):
data_path = download_data(path, "iris")
sample_data = os.path.join(data_path, "iris.csv")
dmat_train, dlabel_train, dmat_test, dlabel_test \
= fs.csv_loader(sample_data, 0.2)
if one_hot:
one_hot_label = [[1,0,0], [0,1,0], [0,0,1]]
temp_dlabel_train = []
temp_dlabel_test = []
for l in dlabel_train:
temp_dlabel_train.append(one_hot_label[int(l)])
for l in dlabel_test:
temp_dlabel_test.append(one_hot_label[int(l)])
dlabel_train = temp_dlabel_train
dlabel_test = temp_dlabel_test
if dataset == "training":
return dmat_train, dlabel_train
elif dataset == "testing":
return dmat_test, dlabel_test
else:
raise ValueError("dataset must be 'testing' or 'training'")
def load_iris(path=".", dataset="training", one_hot=False):
data_path = download_data(path, "iris")
sample_data = os.path.join(data_path, "iris.csv")
dmat_train, dlabel_train, dmat_test, dlabel_test \
= fs.csv_loader(sample_data, 0.2)
dmat_train = map(lambda row: map(float, row), dmat_train)
dmat_test = map(lambda row: map(float, row), dmat_test)
if one_hot:
one_hot_label = map(list, list(np.eye(3)))
temp_dlabel_train = []
temp_dlabel_test = []
for l in dlabel_train:
temp_dlabel_train.append(one_hot_label[int(l)])
for l in dlabel_test:
temp_dlabel_test.append(one_hot_label[int(l)])
dlabel_train = temp_dlabel_train
dlabel_test = temp_dlabel_test
if dataset == "training":
return dmat_train, dlabel_train
elif dataset == "testing":
return dmat_test, dlabel_test
else:
raise ValueError("dataset must be 'testing' or 'training'")
