def auto_encode(x, y):
from sknn import ae, mlp
# Initialize auto-encoder for unsupervised learning.
myae = ae.AutoEncoder(
layers=[ae.Layer("Tanh", units=8),
ae.Layer("Sigmoid", units=4)],
learning_rate=0.002,
n_iter=10)
# Layerwise pre-training using only the input data.
myae.fit(x)
# Initialize the multi-layer perceptron with same base layers.
mymlp = mlp.Regressor(layers=[
mlp.Layer("Tanh", units=8),
mlp.Layer("Sigmoid", units=4),
mlp.Layer("Linear")
])
# Transfer the weights from the auto-encoder.
myae.transfer(mymlp)
# Now perform supervised-learning as usual.
mymlp.fit(x, y)
return mymlp
def autoEncoderOptimization(data):
rbm = ae.AutoEncoder(layers=[
ae.Layer("Tanh", units=300),
ae.Layer("Sigmoid", units=200),
ae.Layer("Tanh", units=100)
],
learning_rate=0.002,
n_iter=10)
rbm.fit(data["train"])
model = Classifier(layers=[
Layer("Tanh", units=300),
Layer("Sigmoid", units=200),
Layer("Tanh", units=100),
Layer("Rectifier", units=100),
Layer("Rectifier", units=50),
Layer("Softmax")
], )
rbm.transfer(model)
model.fit(data["train"], data["label"])
prediction = model.predict(data["train"])
print accuracy_score(data["label"], prediction)
traindata = traindata[:1000]
traindata = traindata.values
# train split uses default gini node, split using train_test_split
X = traindata[1:, 1:]
Y = traindata[1:, 0]
cv = train_test_split(X, Y, test_size=.33, random_state=20)
X_train, X_test, Y_train, Y_test = train_test_split(X,
Y,
test_size=.33,
random_state=20)
#Finding the optimal component
AELayers = [
ae.Layer("Sigmoid", units=1000),
ae.Layer("Sigmoid", units=500),
ae.Layer("Sigmoid", units=250)
]
NNLayers = [
mlp.Layer("Sigmoid", units=1000),
mlp.Layer("Sigmoid", units=500),
mlp.Layer("Softmax", units=15)
]
##
##for each in complist:
## comp = each
t0 = time.clock()
print("Time started")
nn = mlp.Classifier(layers=[
mlp.Layer("Tanh", units=n_feat * 2 / 3),
mlp.Layer("Sigmoid", units=n_feat * 1 / 3),
mlp.Layer("Softmax", units=n_targets)
],
n_iter=50,
n_stable=10,
learning_rate=0.001,
valid_size=0.5,
verbose=1)
if PRETRAIN:
from sknn import ae
ae = ae.AutoEncoder(layers=[
ae.Layer("Tanh", units=n_feat * 2 / 3),
ae.Layer("Sigmoid", units=n_feat * 2 / 3)
],
learning_rate=0.002,
n_iter=10,
verbose=1)
ae.fit(data_train)
ae.transfer(nn)
nn.fit(data_train, labels_train)
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
expected = labels_test
predicted = net.predict(data_test)
nn = mlp.Classifier(layers=[
mlp.Layer("Tanh", units=n_feat / 8),
mlp.Layer("Sigmoid", units=n_feat / 16),
mlp.Layer("Softmax", units=n_targets)
],
n_iter=50,
n_stable=10,
learning_rate=0.002,
learning_rule="momentum",
valid_size=0.1,
verbose=1)
if PRETRAIN:
from sknn import ae
ae = ae.AutoEncoder(layers=[
ae.Layer("Tanh", units=n_feat / 8),
ae.Layer("Sigmoid", units=n_feat / 16)
],
learning_rate=0.002,
n_iter=10,
verbose=1)
ae.fit(data_train)
ae.transfer(nn)
nn.fit(data_train, labels_train)
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
expected = labels_test
predicted = nn.predict(data_test)
traindata = traindata[:1000]
traindata = traindata.values
# train split uses default gini node, split using train_test_split
X = traindata[1:, 1:]
Y = traindata[1:, 0]
cv = train_test_split(X, Y, test_size=.33, random_state=20)
X_train, X_test, Y_train, Y_test = train_test_split(X,
Y,
test_size=.33,
random_state=20)
#Finding the optimal component
AELayers = [
ae.Layer("Sigmoid", units=120),
ae.Layer("Sigmoid", units=60),
ae.Layer("Sigmoid", units=30)
]
NNLayers = [
mlp.Layer("Sigmoid", units=120),
mlp.Layer("Sigmoid", units=75),
mlp.Layer("Softmax", units=5)
]
##
##for each in complist:
## comp = each
t0 = time.clock()
print("Time started")