def train_svm(name='svm', dataset='wine', C=1.0, problem='classification', **kwargs):
data = get_dataset(dataset, split=True, discrete=False, one_hot=True)
train_x, train_y, test_x, test_y, feature_names = \
data['train_x'], data['train_y'], data['test_x'], data['test_y'], data['feature_names']
if rebalance:
print("balancing training data")
train_x, train_y = sample_balance(train_x, train_y)
print("#data after balancing:", len(train_y))
one_hot_encoder, is_categorical = data['one_hot_encoder'], data['is_categorical']
model_name = '-'.join([dataset, name])
svm = SVM(name=model_name, problem=problem, C=C, one_hot_encoder=one_hot_encoder, **kwargs)
svm.train(train_x, train_y)
svm.evaluate(train_x, train_y, stage='train')
acc, loss, auc = svm.test(test_x, test_y)
return svm, acc
def train_nn(name='nn', dataset='wine', neurons=(20,), alpha=0.01, problem='classification', **kwargs):
data = get_dataset(dataset, split=True, discrete=False, one_hot=True)
train_x, train_y, test_x, test_y, feature_names = \
data['train_x'], data['train_y'], data['test_x'], data['test_y'], data['feature_names']
if rebalance:
print("balancing training data")
train_x, train_y = sample_balance(train_x, train_y)
print("#data after balancing:", len(train_y))
one_hot_encoder, is_categorical = data['one_hot_encoder'], data['is_categorical']
model_name = '-'.join([dataset, name] + [str(neuron) for neuron in neurons])
nn = NeuralNet(name=model_name, problem=problem, neurons=neurons, max_iter=5000, alpha=alpha,
one_hot_encoder=one_hot_encoder, **kwargs)
nn.train(train_x, train_y)
nn.evaluate(train_x, train_y, stage='train')
acc, loss, auc = nn.test(test_x, test_y)
return nn, acc
def train_nn(name='nn', dataset='wine', neurons=(20,), alpha=0.01, **kwargs):
from sklearn.neural_network import MLPClassifier
data = get_dataset(dataset, split=True, discrete=False, one_hot=True)
train_x, train_y, test_x, test_y, feature_names = \
data['train_x'], data['train_y'], data['test_x'], data['test_y'], data['feature_names']
if rebalance:
print("balancing training data")
train_x, train_y = sample_balance(train_x, train_y)
print("#data after balancing:", len(train_y))
one_hot_encoder, is_categorical = data['one_hot_encoder'], data['is_categorical']
model_name = '-'.join([dataset, name] + [str(neuron) for neuron in neurons])
model = MLPClassifier(hidden_layer_sizes=neurons, max_iter=5000, alpha=alpha, **kwargs)
nn = SKClassifier(model, name=model_name, standardize=True, one_hot_encoder=one_hot_encoder)
nn.train(train_x, train_y)
nn.evaluate(train_x, train_y, stage='train')
nn.test(test_x, test_y)
nn.save()
def train_svm(name='svm', dataset='wine', C=1.0, problem='classification', **kwargs):
from sklearn.svm import SVC
data = get_dataset(dataset, split=True, discrete=False, one_hot=True)
train_x, train_y, test_x, test_y, feature_names = \
data['train_x'], data['train_y'], data['test_x'], data['test_y'], data['feature_names']
if rebalance:
print("balancing training data")
train_x, train_y = sample_balance(train_x, train_y)
print("#data after balancing:", len(train_y))
one_hot_encoder, is_categorical = data['one_hot_encoder'], data['is_categorical']
model_name = '-'.join([dataset, name])
model = SVC(C=C, probability=True, **kwargs)
svm = SKClassifier(model, name=model_name, one_hot_encoder=one_hot_encoder)
svm.train(train_x, train_y)
svm.evaluate(train_x, train_y, stage='train')
svm.test(test_x, test_y)
svm.save()
def train_tree(name='tree', dataset='wine', max_depth=None, min_samples_leaf=0.005, **kwargs):
data = get_dataset(dataset, split=True, discrete=False, one_hot=True)
train_x, train_y, test_x, test_y, feature_names, one_hot_encoder = \
data['train_x'], data['train_y'], data['test_x'], data['test_y'], data['feature_names'], data['one_hot_encoder']
if rebalance:
print("balancing training data")
train_x, train_y = sample_balance(train_x, train_y)
print("#data after balancing:", len(train_y))
model_name = '-'.join([dataset, name])
tree = Tree(name=model_name, max_depth=max_depth, min_samples_leaf=min_samples_leaf,
one_hot_encoder=one_hot_encoder, **kwargs)
tree.train(train_x, train_y)
tree.evaluate(train_x, train_y, stage='train')
tree.test(test_x, test_y)
tree.describe()
tree.export(get_path('models', '{}.json'.format(model_name)))
tree.save()
def train_rule(name='rule', dataset='breast_cancer', rule_max_len=2, **kwargs):
data = get_dataset(dataset, split=True, discrete=True)
train_x, train_y, test_x, test_y, feature_names = \
data['train_x'], data['train_y'], data['test_x'], data['test_y'], data['feature_names']
from iml.models.rule_model import RuleList
if rebalance:
print("balancing training data")
train_x, train_y = sample_balance(train_x, train_y)
print("#data after balancing:", len(train_y))
# print(train_x.shape, train_x.dtype)
discretizer = data['discretizer']
model_name = '-'.join([dataset, name])
brl = RuleList(name=model_name, rule_maxlen=rule_max_len, discretizer=discretizer, **kwargs)
brl.train(train_x, train_y)
brl.evaluate(train_x, train_y, stage='train')
# print(brl.infer(test_x))
brl.test(test_x, test_y)
brl.describe(feature_names=feature_names)
brl.save()