def test_monk1(self):
nn = NN(seed=4,
epochs_limit=400,
learning_algorithm=batch,
error_calculator=ErrorCalculator.MSE,
architecture=MultilayerPerceptron(
4,
activation=sigmoid,
activation_hidden=relu,
eta=0.5,
alambd=0,
alpha=0.8,
))
train_data, test_data = read_monk(1)
nn.fit(train_data)
train_errs = nn.compute_learning_curve(train_data, ErrorCalculator.MIS)
test_errs = nn.compute_learning_curve(test_data, ErrorCalculator.MIS)
error_train = 0
for x, d in train_data:
error_train += (round(nn(x)[0][-1]) - d[0])**2
error_test = 0
for x, d in test_data:
error_test += (round(nn(x)[0][-1]) - d[0])**2
print(
'train:',
str(((len(train_data) - error_train) / len(train_data)) * 100) +
'%')
print(
'test: ',
str(((len(test_data) - error_test) / len(test_data)) * 100) + '%')
self.assertEqual(error_train, 0)
self.assertEqual(error_test, 0)
nn.error_calculator = ErrorCalculator.MIS
self.assertEqual(nn.compute_error(train_data), 0)
self.assertEqual(nn.compute_error(test_data), 0)
from typing import Mapping, Sequence, Any, Dict
from nn import ErrorCalculator
from nn import sigmoid, batch
from nn.utilities import read_monk
from nn.activation_functions import relu, tanh, tanh_classification
from nn.validation import grid_search, write_on_file
import multiprocessing as mp
train_data, test_data = read_monk(1)
params_nn: Dict[str, Sequence[Any]] = dict(
error_calculator=[ErrorCalculator.MSE],
learning_algorithm=[batch],
epochs_limit=[1000],
n_init=[10],
epsilon=[1e-05],
patience=[10],
)
params_architecture: Mapping[str, Sequence[Any]] = dict(
size_hidden_layers=[(2, )],
activation=[tanh_classification],
activation_hidden=[relu],
eta=[0.1, 0.01, 0.001],
alpha=[0, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9],
alambd=[0, 0.0001, 0.001, 0.01],
eta_decay=[0],
)
cv_params: Mapping[str, Any] = dict(