def test():
# data
cal_housing = fetch_california_housing()
X = cal_housing['data']
Y = np.reshape(cal_housing['target'], (-1, 1))
# train models
iters = 100
name = ["0", "1", "2", "3", "4"]
model = [
SCNN(8, 1, 0, update=Update.Rprop()),
SCNN(8, 1, 1, update=Update.Rprop()),
SCNN(8, 1, 2, update=Update.Rprop()),
SCNN(8, 1, 3, update=Update.Rprop()),
SCNN(8, 1, 4, update=Update.Rprop())
]
error = np.zeros((len(model), iters))
for i in range(iters):
for m in range(len(model)):
error[m, i] = model[m].partial_fit(X, Y)
print(i + 1, "complete")
# plot results
plt.figure()
plt.title('Error Curves')
for m in range(len(model)):
plt.semilogy(error[m], label=name[m])
plt.legend()
plt.show()
def linearMnist():
model = LLS(n_components,
10,
outputAct=Activation.Softmax(),
update=Update.Rprop(),
error=Error.JsDivergence(),
regularization=Regularize.Ridge())
testMnist(model)
def scnnMnist():
model = SCNN(n_components,
10,
hiddenSize=1,
hiddenAct=Activation.Selu(),
iweight=Initialize.lecun_normal,
outputAct=Activation.Softmax(),
update=Update.Rprop(),
error=Error.JsDivergence(),
regularization=Regularize.Ridge())
testMnist(model)
def test():
# base data
X = np.random.randn( 1000, 1 ) * 10 + 50
Y = X * 2 - 10
# add noise
X += np.random.randn( 1000, 1 ) * 2
Y += np.random.randn( 1000, 1 ) * 2
# split
trainX = X[ :900 ]
trainY = Y[ :900 ]
testX = X[ 900: ]
testY = Y[ 900: ]
# for prediction line
plotX = np.array( [ min( X ), max( X ) ] )
iters = 2000
name = [ "RMSProp", "Momentum", "Nesterov", "SGD", "Rprop", "Adam" ]
model = [ LLS( 1, 1, update=Update.RmsProp() ),
LLS( 1, 1, update=Update.Momentum( 1e-7 ) ),
LLS( 1, 1, update=Update.NesterovMomentum( 1e-7 ) ),
LLS( 1, 1, update=Update.Sgd( 1e-7 ) ),
LLS( 1, 1, update=Update.Rprop() ),
LLS( 1, 1, update=Update.Adam() ) ]
error = np.zeros( ( len( model ), iters ) )
for i in range( iters ):
for m in range( len( model ) ):
error[ m, i ] = model[ m ].partial_fit( trainX, trainY )
print( i + 1, "complete" )
# plot results
plt.figure()
plt.title( 'Data Space' )
plt.scatter( trainX, trainY, label='train' )
plt.scatter( testX, testY, label='test' )
plt.plot( plotX, model[ 4 ].predict( plotX ).x_, label='prediction' )
plt.legend()
plt.figure()
plt.title( 'Error Curves' )
for m in range( len( model ) ):
plt.semilogy( error[ m ], label=name[ m ] )
plt.legend()
plt.show()
