def run_for_all_datasets(self, algorithm_classes, algorithm_kwargs):
datasets = self.get_datasets()
accuracies = np.zeros([len(datasets), len(algorithm_classes)])
datasets_names = []
for index, item in enumerate(datasets):
if item.get("label") is not None:
datasets_names.append(item["label"])
print("Dataset: ", item.get("label"))
else:
datasets_names.append(item["name"])
print("Dataset: ", item.get("name"))
if item.get("type") == "sklearn":
mod = __import__(self.convert_from_path_to_module(item['path']), fromlist=[item["name"]])
klass = getattr(mod, item["name"])
dataset = klass()
accuracies[index] = self.accuracies_of_different_methods(dataset.data, dataset.target,
algorithm_classes,
algorithm_kwargs)
else:
with open(item['path'], 'r') as f:
if item.get('dtype') is None:
item['dtype'] = int
if item.get('label_index') is None:
item['label_index'] = None
else:
item['label_index'] = int(item['label_index'])
if item.get('labels_numeric') is None:
item['labels_numeric'] = True
dataset, labels = tools.load_text_file(f, label_index=item['label_index'], dtype=item['dtype'],
labels_numeric=bool(item['labels_numeric']))
accuracies[index] = self.accuracies_of_different_methods(dataset, labels, algorithm_classes,
algorithm_kwargs)
return accuracies, datasets_names
def accuracy_for_letters():
with open('../../data_sources/letter-recognition.data', 'r') as f:
dataset, labels = tools.load_text_file(f,
label_index=0,
labels_numeric=False)
folds = 3
data_split, labels_split = tools.cross_validation_split(
dataset=dataset, labels=labels, folds=folds)
# iris = load_iris()
print("Multinomial:")
accuracy_of_multinomial(data_split, labels_split, num_of_bins=11)
print("Gaussian:")
accuracy_of_gaussian(data_split, labels_split)
def accuracy_for_cancer():
with open('../../data_sources/kag_risk_factors_cervical_cancer.csv',
'r') as f:
dataset, labels = tools.load_text_file(f, label_index=28, dtype=float)
# labels = np.array(dataset[:,28], dtype=int)
# dataset=np.append(dataset[:,:28], dataset[:, 29:], axis=1)
# iris = load_iris()
# labels -= 1
folds = 3
data_split, labels_split = tools.cross_validation_split(
dataset=dataset, labels=labels, folds=folds)
# iris = load_iris()
print("Multinomial:")
accuracy_of_multinomial(data_split, labels_split)
print("Gaussian:")
accuracy_of_gaussian(data_split, labels_split)
def accuracy_for_trees():
with open('../../data_sources/covtype.csv', 'r') as f:
dataset, labels = tools.load_text_file(f,
label_index=-1,
dtype=float,
labels_numeric=True)
# iris = load_iris()
# labels -= 1
folds = 3
data_split, labels_split = tools.cross_validation_split(
dataset=dataset, labels=labels, folds=folds)
# iris = load_iris()
print("Multinomial:")
accuracy_of_multinomial(data_split, labels_split)
print("Gaussian:")
accuracy_of_gaussian(data_split, labels_split)