def generate_data_package(fold: int, tenfolds: list, regression: bool,
du: DataUtility):
test_data, test_labels = copy.deepcopy(tenfolds[fold])
remaining_data = [
x[0] for i, x in enumerate(copy.deepcopy(tenfolds)) if i != fold
]
remaining_labels = [
y[1] for i, y in enumerate(copy.deepcopy(tenfolds)) if i != fold
]
#Store off a set of the remaining dataset
training_data = np.concatenate(remaining_data, axis=1)
#Store the remaining data set labels
training_labels = np.concatenate(remaining_labels, axis=1)
if regression == True:
#The number of output nodes is 1
output_size = 1
#else it is a classification data set
else:
#Count the number of classes in the label data set
output_size = du.CountClasses(training_labels)
#Get the test data labels in one hot encoding
test_labels = du.ConvertLabels(test_labels, output_size)
#Get the Labels into a One hot encoding
training_labels = du.ConvertLabels(training_labels, output_size)
input_size = training_data.shape[0]
return [
test_data, test_labels, training_data, training_labels, output_size,
input_size
]
def generate_data_package(fold: int, tenfolds: list, regression: bool, du: DataUtility):
# get the fold we are going to use for testing
test_data, test_labels = copy.deepcopy(tenfolds[fold])
# squish the rest of the data and ground truth labels into one numpy array, respectively
remaining_data = [x[0] for i, x in enumerate(copy.deepcopy(tenfolds)) if i!=fold]
remaining_labels = [y[1] for i, y in enumerate(copy.deepcopy(tenfolds)) if i!=fold]
training_data = np.concatenate(remaining_data, axis=1)
training_labels = np.concatenate(remaining_labels, axis=1)
# determine how many output nodes the network has (1 if regression)
if regression == True:
#The number of output nodes is 1
output_size = 1
#else it is a classification data set
else:
#Count the number of classes in the label data set
output_size = du.CountClasses(training_labels)
#Get the test data labels in one hot encoding
test_labels = du.ConvertLabels(test_labels, output_size)
#Get the Labels into a One hot encoding
training_labels = du.ConvertLabels(training_labels, output_size)
input_size = training_data.shape[0]
return [test_data, test_labels, training_data, training_labels, output_size, input_size]