def test_method_param(self):
self.assertTrue('learning_rate' in Config(method='perceptron')['parameter'])
self.assertTrue('sensitivity' in Config(method='PA')['parameter'])
self.assertTrue('sensitivity' in Config(method='PA1')['parameter'])
self.assertTrue('regularization_weight' in Config(method='PA1')['parameter'])
self.assertTrue('nearest_neighbor_num' in Config(method='NN')['parameter'])
self.assertTrue('nearest_neighbor_num' in Config(method='cosine')['parameter'])
self.assertTrue('nearest_neighbor_num' in Config(method='euclidean')['parameter'])
# Load a CSV file.
loader = CSVLoader('wine.csv')
# Define a Schema that defines types for each columns of the CSV file.
schema = Schema({
'quality': Schema.TARGET,
}, Schema.NUMBER)
# Create a Dataset
dataset = Dataset(loader, schema).shuffle()
n_samples = len(dataset)
n_train_samples = int(n_samples * 0.75)
# Create a Regression Service
cfg = Config.default()
regression = Regression.run(cfg)
print("Started Service: {0}".format(regression))
# Train the regression using the first half of the dataset.
train_ds = dataset[:n_train_samples]
print("Training...: {0}".format(train_ds))
for _ in regression.train(train_ds):
pass
# Test the regression using the last half of the dataset.
test_ds = dataset[n_train_samples:]
print("Testing...: {0}".format(test_ds))
mse, mae = 0, 0
for (idx, label, result) in regression.estimate(test_ds):
# Load a CSV file.
loader = CSVLoader('wine.csv')
# Define a Schema that defines types for each columns of the CSV file.
schema = Schema({
'quality': Schema.TARGET,
}, Schema.NUMBER)
# Create a Dataset
dataset = Dataset(loader, schema).shuffle()
n_samples = len(dataset)
n_train_samples = int(n_samples * 0.75)
# Create a Regression Service
cfg = Config.default()
regression = Regression.run(cfg)
print("Started Service: {0}".format(regression))
# Train the regression using the first half of the dataset.
train_ds = dataset[:n_train_samples]
print("Training...: {0}".format(train_ds))
for _ in regression.train(train_ds): pass
# Test the regression using the last half of the dataset.
test_ds = dataset[n_train_samples:]
print("Testing...: {0}".format(test_ds))
mse, mae = 0, 0
for (idx, label, result) in regression.estimate(test_ds):
diff = np.abs(label - result)
def test_default(self):
config = Config.default()
self.assertEqual('AROW', config['method'])
def test_methods(self): config = Config() self.assertTrue(isinstance(config.methods(), list))
def test_simple(self):
config = Config()
self.assertEqual('AROW', config['method'])
def test_embedded(self): regression = Regression.run(Config(), embedded=True)
from jubakit.regression import Regression, Dataset, Config
# Load the boston dataset.
boston = sklearn.datasets.load_boston()
X = boston.data
y = boston.target
# Create a Dataset
dataset = Dataset.from_array(boston.data, boston.target).shuffle()
n_samples = len(dataset)
n_train_samples = int(n_samples * 0.75)
# Create a Regression Service
cfg = Config(method='AROW',
parameter={
'regularization_weight': 1.0,
'sensitivity': 1.0
})
regression = Regression.run(cfg)
print("Started Service: {0}".format(regression))
# Train the regression using the first half of the dataset.
train_ds = dataset[:n_train_samples]
print("Training...: {0}".format(train_ds))
for _ in regression.train(train_ds):
pass
# Test the regression using the last half of the dataset.
test_ds = dataset[n_train_samples:]
print("Testing...: {0}".format(test_ds))