def part_e(plotting=False):
x_train, y_train, x_test, y_test = real_data(file_number=2, plotting=False)
for method in ['ols', 'ridge', 'lasso']:
designMatrix = DesignMatrix('polynomial2D', 10)
leastSquares = LeastSquares(backend='manual', method=method)
leastSquares.setLambda(1e-3)
if method == 'lasso':
leastSquares.setLambda(1e-4)
X = designMatrix.getMatrix(x_train)
leastSquares.fit(X, y_train)
X_test = designMatrix.getMatrix(x_test)
leastSquares.predict()
leastSquares.y = y_test
print(leastSquares.MSE())
if plotting:
x = np.linspace(0, 1, 60)
y = np.copy(x)
XX, YY = np.meshgrid(x, y)
ZZ = np.reshape(leastSquares.yHat, XX.shape)
fig = plt.figure()
ax = fig.gca(projection='3d')
ax.plot_surface(XX,
YY,
ZZ,
cmap=cm.coolwarm,
linewidth=0,
antialiased=False)
ax.set_zlim(-0.10, 1.40)
ax.zaxis.set_major_locator(LinearLocator(5))
ax.zaxis.set_major_formatter(FormatStrFormatter('%.02f'))
ax.view_init(30, 45 + 90)
#plt.savefig(os.path.join(os.path.dirname(__file__), 'figures', method+'terrain.png'), transparent=True, bbox_inches='tight')
plt.show()
if plotting:
x = np.linspace(0, 1, 60)
y = np.copy(x)
XX, YY = np.meshgrid(x, y)
ZZ = np.reshape(y_test, XX.shape)
fig = plt.figure()
ax = fig.gca(projection='3d')
ax.plot_surface(XX,
YY,
ZZ,
cmap=cm.coolwarm,
linewidth=0,
antialiased=False)
ax.set_zlim(-0.10, 1.40)
ax.zaxis.set_major_locator(LinearLocator(5))
ax.zaxis.set_major_formatter(FormatStrFormatter('%.02f'))
ax.view_init(30, 45 + 90)
#plt.savefig(os.path.join(os.path.dirname(__file__), 'figures', 'test_terrain.png'), transparent=True, bbox_inches='tight')
plt.show()
def test_bootstrap_resample():
"""Tests the resample method of the Bootstrap class
Tests comprise of simple resampling cases for which we can evalue
the exact answer by hand.
"""
# All data is the same, variance should be zero.
OLS = LeastSquares()
DM = DesignMatrix('polynomial', 3)
bootstrap = Bootstrap(OLS, DM)
x = np.ones(10) * 2.25
y = x**3
#bootstrap.resample(x, y, 10)
# This fails with an raise LinAlgError("Singular matrix") error on
# TravisCI, but passes locally. Removing for now.
#assert bootstrap.betaVariance == pytest.approx(np.zeros(4), abs=1e-15)
# Ensure that larger noise in the data set gives larger computed
# variance in the beta values from resampling.
functions = {
0: lambda x: np.sin(x),
1: lambda x: np.cos(x),
2: lambda x: np.sin(2 * x),
3: lambda x: np.cos(2 * x),
4: lambda x: np.sin(3 * x),
5: lambda x: np.cos(3 * x),
6: lambda x: np.sin(4 * x),
7: lambda x: np.cos(4 * x),
8: lambda x: np.sin(5 * x),
9: lambda x: np.cos(5 * x),
10: lambda x: np.sin(x)**2,
11: lambda x: np.cos(x)**2,
12: lambda x: np.sin(2 * x)**2,
13: lambda x: np.cos(2 * x)**2,
14: lambda x: np.sin(3 * x)**2,
15: lambda x: np.cos(3 * x)**2,
}
DM = DesignMatrix(lambda j, x: functions[j](x), 9)
OLS = LeastSquares()
bootstrap = Bootstrap(OLS, DM)
N = 100
x = np.linspace(0, 2 * np.pi, N)
meanBetaVariance = np.zeros(6)
ind = 0
for noiseScale in [0.0, 0.1, 1.0]:
y = np.sin(1.5 * x) - 0.5 * np.cos(2 * x)**2 + np.random.normal(
0, noiseScale, N)
bootstrap.resample(x, y, 100)
meanBetaVariance[ind] = np.mean(bootstrap.betaVariance)
if ind > 0:
assert meanBetaVariance[ind - 1] < meanBetaVariance[ind]
ind += 1
def plot_MSE_R2() :
leastSquares = LeastSquares(backend='manual')
N = int(1e4)
x = np.random.rand(N)
y = np.random.rand(N)
x_data = np.zeros(shape=(N,2))
x_data[:,0] = x
x_data[:,1] = y
y_data = np.zeros(shape=(N))
@jit(nopython=True, cache=True)
def computeFrankeValues(x_data, y) :
N = x_data.shape[0]
for i in range(N) :
y[i] = franke(x_data[i,0], x_data[i,1])
computeFrankeValues(x_data, y_data)
p_max = 10
p = [i for i in range(2, p_max+1)]
R2 = [None for i in range(2, p_max+1)]
MSE = [None for i in range(2, p_max+1)]
for degree in p :
designMatrix = DesignMatrix('polynomial2D', degree)
X = designMatrix.getMatrix(x_data)
leastSquares.fit(X, y_data)
_ = leastSquares.predict()
R2[degree-2] = leastSquares.R2()
MSE[degree-2] = leastSquares.MSE()
print(R2[degree-2])
print(MSE[degree-2])
p = np.array(p)
plt.semilogy(p, 1-np.array(R2),'b-o', markersize=3)
plt.rc('text', usetex=True)
plt.xlabel(r"$p$", fontsize=10)
plt.ylabel(r"$1-(R^2$ score$)$", fontsize=10)
plt.subplots_adjust(left=0.2,bottom=0.2)
#plt.savefig(os.path.join(os.path.dirname(__file__), 'figures', 'OLS_R2.png'), transparent=True, bbox_inches='tight')
plt.show()
plt.figure()
ax = plt.gca()
plt.semilogy(p, MSE, 'r-o', markersize=3)
plt.rc('text', usetex=True)
plt.xlabel(r"$p$", fontsize=10)
plt.ylabel(r"MSE", fontsize=10)
plt.subplots_adjust(left=0.2,bottom=0.2)
#plt.savefig(os.path.join(os.path.dirname(__file__), 'figures', 'OLS_MSE.png'), transparent=True, bbox_inches='tight')
plt.show()
def test_DesignMatrix_polynomial2D():
"""Tests the polynomial2D method of the DesignMatrix class
The tests comprise setting up design matrices of different
polynomials orders and comparing to manually setup matrices.
"""
x = np.array([[2.0, 3.0], [4.0, 5.0], [6.0, 7.0], [8.0, 9.0]])
DM = DesignMatrix('polynomial2D', 2)
X = DM.getMatrix(x)
X_true = np.array([[1.0, 2.0, 3.0, 2.0**2, 2.0 * 3.0, 3.0**2],
[1.0, 4.0, 5.0, 4.0**2, 4.0 * 5.0, 5.0**2],
[1.0, 6.0, 7.0, 6.0**2, 6.0 * 7.0, 7.0**2],
[1.0, 8.0, 9.0, 8.0**2, 8.0 * 9.0, 9.0**2]])
assert X == pytest.approx(X_true, abs=1e-15)
def test_DesignMatrix_function():
"""Tests the function method of the DesignMatrix class
The tests comprise setting up design matrices with different
functions and comparing to manually setup matrices.
"""
class f1:
def __init__(self, degree):
self.degree = degree
def __call__(self, i, x):
if i > self.degree:
raise ValueError(
"Specified function index is larger than the number of available functions."
)
if i == 0:
return self._f0(x)
elif i == 1:
return self._f1(x)
elif i == 2:
return self._f2(x)
elif i == 3:
return self._f3(x)
elif i == 4:
return self._f4(x)
elif i == 5:
return self._f5(x)
elif i == 6:
return self._f6(x)
def _f1(self, x):
return np.cos(x)
def _f2(self, x):
return np.sin(x)
def _f3(self, x):
return np.tan(x)
def _f4(self, x):
return np.cosh(x)
def _f5(self, x):
return np.sinh(x)
def _f6(self, x):
return np.tanh(x)
# 1 function
numberOfFunctions = 1
f = f1(numberOfFunctions)
x = np.array([np.pi / 2])
DM = DesignMatrix(f, numberOfFunctions)
X = DM.getMatrix(x)
X_true = np.array([[1.0, np.cos(np.pi / 2)]])
assert X == pytest.approx(X_true, abs=1e-15)
# 2 functions
numberOfFunctions = 2
f = f1(numberOfFunctions)
x = np.array([np.pi / 2, np.pi / 3])
DM = DesignMatrix(f, numberOfFunctions)
X = DM.getMatrix(x)
X_true = np.array([[1.0, np.cos(np.pi / 2),
np.sin(np.pi / 2)],
[1.0, np.cos(np.pi / 3),
np.sin(np.pi / 3)]])
assert X == pytest.approx(X_true, abs=1e-15)
# 3 functions
numberOfFunctions = 3
f = f1(numberOfFunctions)
x = np.array([np.pi / 2, np.pi / 3, np.pi / 4, np.pi / 5, np.pi / 6])
DM = DesignMatrix(f, numberOfFunctions)
X = DM.getMatrix(x)
X_true = np.array(
[[1.0, np.cos(np.pi / 2),
np.sin(np.pi / 2),
np.tan(np.pi / 2)],
[1.0, np.cos(np.pi / 3),
np.sin(np.pi / 3),
np.tan(np.pi / 3)],
[1.0, np.cos(np.pi / 4),
np.sin(np.pi / 4),
np.tan(np.pi / 4)],
[1.0, np.cos(np.pi / 5),
np.sin(np.pi / 5),
np.tan(np.pi / 5)],
[1.0, np.cos(np.pi / 6),
np.sin(np.pi / 6),
np.tan(np.pi / 6)]])
assert X == pytest.approx(X_true, abs=1e-15)
# 4 functions
numberOfFunctions = 4
f = f1(numberOfFunctions)
x = np.array([np.pi / 2, np.pi / 3])
DM = DesignMatrix(f, numberOfFunctions)
X = DM.getMatrix(x)
X_true = np.array([[
1.0,
np.cos(np.pi / 2),
np.sin(np.pi / 2),
np.tan(np.pi / 2),
np.cosh(np.pi / 2)
],
[
1.0,
np.cos(np.pi / 3),
np.sin(np.pi / 3),
np.tan(np.pi / 3),
np.cosh(np.pi / 3)
]])
assert X == pytest.approx(X_true, abs=1e-15)
# 6 functions
numberOfFunctions = 6
f = f1(numberOfFunctions)
x = np.array([
np.pi / 2, np.pi / 3, np.pi / 4, np.pi / 5, np.pi / 6, np.pi / 7,
np.pi / 8, np.pi / 9
])
DM = DesignMatrix(f, numberOfFunctions)
X = DM.getMatrix(x)
X_true = np.array([[
1.0,
np.cos(np.pi / 2),
np.sin(np.pi / 2),
np.tan(np.pi / 2),
np.cosh(np.pi / 2),
np.sinh(np.pi / 2),
np.tanh(np.pi / 2)
],
[
1.0,
np.cos(np.pi / 3),
np.sin(np.pi / 3),
np.tan(np.pi / 3),
np.cosh(np.pi / 3),
np.sinh(np.pi / 3),
np.tanh(np.pi / 3)
],
[
1.0,
np.cos(np.pi / 4),
np.sin(np.pi / 4),
np.tan(np.pi / 4),
np.cosh(np.pi / 4),
np.sinh(np.pi / 4),
np.tanh(np.pi / 4)
],
[
1.0,
np.cos(np.pi / 5),
np.sin(np.pi / 5),
np.tan(np.pi / 5),
np.cosh(np.pi / 5),
np.sinh(np.pi / 5),
np.tanh(np.pi / 5)
],
[
1.0,
np.cos(np.pi / 6),
np.sin(np.pi / 6),
np.tan(np.pi / 6),
np.cosh(np.pi / 6),
np.sinh(np.pi / 6),
np.tanh(np.pi / 6)
],
[
1.0,
np.cos(np.pi / 7),
np.sin(np.pi / 7),
np.tan(np.pi / 7),
np.cosh(np.pi / 7),
np.sinh(np.pi / 7),
np.tanh(np.pi / 7)
],
[
1.0,
np.cos(np.pi / 8),
np.sin(np.pi / 8),
np.tan(np.pi / 8),
np.cosh(np.pi / 8),
np.sinh(np.pi / 8),
np.tanh(np.pi / 8)
],
[
1.0,
np.cos(np.pi / 9),
np.sin(np.pi / 9),
np.tan(np.pi / 9),
np.cosh(np.pi / 9),
np.sinh(np.pi / 9),
np.tanh(np.pi / 9)
]])
assert X == pytest.approx(X_true, abs=1e-15)
def test_DesignMatrix_polynomial():
"""Tests the polynomial method of the DesignMatrix class
The tests comprise setting up design matrices of different
polynomials orders and comparing to manually setup matrices.
"""
# Degree 1 polynomial
x = np.array([2.0])
DM = DesignMatrix('polynomial', 1)
X = DM.getMatrix(x)
X_true = np.array([[1.0, 2.0]])
assert X == pytest.approx(X_true, abs=1e-15)
# Degree 2 polynomial
x = np.array([2.0, 3.0])
DM = DesignMatrix('polynomial', 2)
X = DM.getMatrix(x)
X_true = np.array([[1.0, 2.0, 4.0], [1.0, 3.0, 9.0]])
assert X == pytest.approx(X_true, abs=1e-15)
# Degree 3 polynomial
x = np.array([2.0, 3.0, 4.0])
DM = DesignMatrix('polynomial', 3)
X = DM.getMatrix(x)
X_true = np.array([[1.0, 2.0, 4.0, 8.0], [1.0, 3.0, 9.0, 27.0],
[1.0, 4.0, 16.0, 64.0]])
assert X == pytest.approx(X_true, abs=1e-15)
# Degree 4 polynomial
x = np.array([2.0, 3.0, 4.0, 5.0])
DM = DesignMatrix('polynomial', 4)
X = DM.getMatrix(x)
X_true = np.array([[1.0, 2.0, 4.0, 8.0, 16.0], [1.0, 3.0, 9.0, 27.0, 81.0],
[1.0, 4.0, 16.0, 64.0, 256.0],
[1.0, 5.0, 25.0, 125.0, 625.0]])
assert X == pytest.approx(X_true, abs=1e-15)
# Degree 5 polynomial
x = np.array([2.0, 3.0, 4.0, 5.0, 6.0])
DM = DesignMatrix('polynomial', 5)
X = DM.getMatrix(x)
X_true = np.array([[1.0, 2.0, 4.0, 8.0, 16.0, 32.0],
[1.0, 3.0, 9.0, 27.0, 81.0, 243.0],
[1.0, 4.0, 16.0, 64.0, 256.0, 1024.0],
[1.0, 5.0, 25.0, 125.0, 625.0, 3125.0],
[1.0, 6.0, 36.0, 216.0, 1296.0, 7776.0]])
assert X == pytest.approx(X_true, abs=1e-15)
# Degree 6 polynomial
x = np.array([2.0, 3.0, 4.0, 5.0, 6.0, 7.0])
DM = DesignMatrix('polynomial', 6)
X = DM.getMatrix(x)
X_true = np.array([[1.0, 2.0, 4.0, 8.0, 16.0, 32.0, 64.0],
[1.0, 3.0, 9.0, 27.0, 81.0, 243.0, 729.0],
[1.0, 4.0, 16.0, 64.0, 256.0, 1024.0, 4096.0],
[1.0, 5.0, 25.0, 125.0, 625.0, 3125.0, 15625.0],
[1.0, 6.0, 36.0, 216.0, 1296.0, 7776.0, 46656.0],
[1.0, 7.0, 49.0, 343.0, 2401.0, 16807.0, 117649.0]])
assert X == pytest.approx(X_true, abs=1e-15)
np.mean(MSE_train)
]
return averages
if __name__ == '__main__':
Degree = 1 + np.arange(20)
train_MSE = []
test_MSE = []
print("#########################################################")
for degree in Degree:
degree = int(degree)
designMatrix = DesignMatrix('polynomial2D', degree)
leastSquares = LeastSquares(method="ridge", backend='manual')
Lambda = 4
leastSquares.setLambda(Lambda)
crossvalidation = CrossValidation(leastSquares, designMatrix)
N = int(1e4)
x = np.random.rand(N)
y = np.random.rand(N)
x_data = np.zeros(shape=(N, 2))
x_data[:, 0] = x
x_data[:, 1] = y
y_data = np.zeros(shape=(N))
X = designMatrix.getMatrix(x_data)
XT_X = np.dot(X.T, X)
def part_a(plotting=False) :
MSE_degree = []
R2_degree = []
betaVariance_degree = []
for degree in [2,3,4,5]: #,6,7,8,9] :
designMatrix = DesignMatrix('polynomial2D', degree)
leastSquares = LeastSquares(backend='manual')
bootstrap = Bootstrap(leastSquares, designMatrix)
N = int(1e4)
x = np.random.rand(N)
y = np.random.rand(N)
x_data = np.zeros(shape=(N,2))
x_data[:,0] = x
x_data[:,1] = y
y_data = np.zeros(shape=(N))
@jit(nopython=True, cache=True)
def computeFrankeValues(x_data, y) :
N = x_data.shape[0]
for i in range(N) :
y[i] = franke(x_data[i,0], x_data[i,1])
computeFrankeValues(x_data, y_data)
bootstrap.resample(x_data, y_data, 1000)
MSE_degree. append(leastSquares.MSE())
R2_degree. append(leastSquares.R2())
betaVariance_degree.append(bootstrap.betaVariance)
if plotting :
print("MSE: ", MSE_degree[-1])
print("R2: ", R2_degree[-1])
print("Beta Variance: ")
for b in betaVariance_degree[-1] : print(b)
print("Beta: ")
for b in leastSquares.beta : print(b)
print(" ")
M = 100
fig = plt.figure()
ax = fig.gca(projection='3d')
x = np.linspace(0, 1, M)
y = np.linspace(0, 1, M)
X, Y = np.meshgrid(x,y)
x_data = np.vstack([X.ravel(), Y.ravel()]).T
# When plotting the Franke function itself, we use these lines.
yy_data = np.zeros(shape=(x_data.data.shape[0]))
computeFrankeValues(x_data, yy_data)
# When plotting the linear regression model:
XX = designMatrix.getMatrix(x_data)
leastSquares.X = XX
y_data = leastSquares.predict()
Z = np.reshape(y_data.T, X.shape)
ZF = np.reshape(yy_data.T, X.shape)
#ax.plot_surface(X,Y,Z,cmap=cm.coolwarm,linewidth=0, antialiased=False)
ax.plot_surface(X,Y,abs(Z-ZF),cmap=cm.coolwarm,linewidth=0, antialiased=False)
ax.set_zlim(-0.10, 1.40)
ax.zaxis.set_major_locator(LinearLocator(5))
ax.zaxis.set_major_formatter(FormatStrFormatter('%.02f'))
ax.view_init(30, 45)
#plt.savefig(os.path.join(os.path.dirname(__file__), 'figures', 'franke.png'), transparent=True, bbox_inches='tight')
#plt.savefig(os.path.join(os.path.dirname(__file__), 'figures', 'OLS'+str(degree)+'.png'), transparent=True, bbox_inches='tight')
#plt.savefig(os.path.join(os.path.dirname(__file__), 'figures', 'OLS'+str(degree)+'_diff.png'), transparent=True, bbox_inches='tight')
plt.show()
print("\nMSE :")
print(MSE_degree)
print("\nR2 :")
print(R2_degree)
print("\nσ²(β) :")
print(betaVariance_degree)
return MSE_degree, R2_degree, betaVariance_degree
def fit_franke_noise() :
R2 = []
MSE = []
R2_noise = []
MSE_noise = []
beta_noise = []
betaVariance_noise = []
noise = np.logspace(-4,0,50)
k = 1
@jit(nopython=True, cache=True)
def computeFrankeValues(x_data, y) :
N = x_data.shape[0]
for i in range(N) :
y[i] = franke(x_data[i,0], x_data[i,1])
for eta in noise :
designMatrix = DesignMatrix('polynomial2D', 10)
leastSquares = LeastSquares(backend='manual')
bootstrap = Bootstrap(leastSquares, designMatrix)
N = int(1e5)
x = np.random.rand(N)
y = np.random.rand(N)
x_data = np.zeros(shape=(N,2))
x_data[:,0] = x
x_data[:,1] = y
y_data = np.zeros(shape=(N))
computeFrankeValues(x_data, y_data)
y_data_noise = y_data + eta * np.random.standard_normal(size=N)
bootstrap.resample(x_data, y_data_noise, k)
MSE_noise. append(leastSquares.MSE())
R2_noise. append(leastSquares.R2())
beta_noise. append(bootstrap.beta)
betaVariance_noise.append(bootstrap.betaVariance)
leastSquares.y = y_data
MSE.append(leastSquares.MSE())
R2. append(leastSquares.R2())
"""
betaVariance_noise = np.array(betaVariance_noise)
for beta in betaVariance_noise :
print(beta)
colors = ['b', 'g', 'r', 'c', 'm', 'y', 'k','#1f77b4', '#ff7f0e', '#2ca02c', '#d62728',
'#9467bd', '#8c564b', '#e377c2', '#7f7f7f',
'#bcbd22', '#17becf']
for i in range(6) :
plt.loglog(noise, betaVariance_noise[:,i], colors[i]+'-o', markersize=2)
plt.rc('text', usetex=True)
#plt.rc('font',**{'family':'sans-serif','sans-serif':['Helvetica']})
## for Palatino and other serif fonts use:
#plt.rc('font',**{'family':'serif','serif':['Palatino']}) plt.xlabel(r"$p$", fontsize=16)
plt.xlabel(r"noise scale $\eta$", fontsize=10)
plt.ylabel(r"$ \sigma^2(\beta_j)$", fontsize=10)
plt.legend([r"intercept",
r"$\beta_{x}$",
r"$\beta_{y}$",
r"$\beta_{x^2}$",
r"$\beta_{xy}$",
r"$\beta_{y^2}$"], fontsize=10)
plt.subplots_adjust(left=0.2,bottom=0.2)
#plt.savefig(os.path.join(os.path.dirname(__file__), 'figures', 'beta_variance_OLS_noise.png'), transparent=True, bbox_inches='tight')
#plt.show()
"""
print(R2_noise)
print(1-np.array(R2_noise))
fig, ax1 = plt.subplots()
ax1.loglog(noise, 1-np.array(R2_noise),'k-o',markersize=2)
ax1.loglog(noise, 1-np.array(R2),'k--',markersize=2)
plt.xlabel(r"noise scale $\eta$", fontsize=10)
plt.ylabel(r"$1-R^2$", color='k', fontsize=10)
ax2 = ax1.twinx()
ax2.loglog(noise, np.array(MSE_noise), 'b-o',markersize=2)
ax2.loglog(noise, np.array(MSE), 'b--',markersize=2)
plt.ylabel(r"MSE", color='b', fontsize=10)
plt.subplots_adjust(left=0.2,bottom=0.2,right=0.9)
ax1.set_ylim([0.95*min(min(MSE_noise), min(R2_noise)), 1.05*(max(max(MSE_noise), max(R2_noise)))])
ax2.set_ylim([0.95*min(min(MSE_noise), min(R2_noise)), 1.05*(max(max(MSE_noise), max(R2_noise)))])
ax2.get_yaxis().set_ticks([])
plt.savefig(os.path.join(os.path.dirname(__file__), 'figures', 'R2MSE_OLS_noise.png'), transparent=True, bbox_inches='tight')
plt.show()
def part_e_2():
x_train, y_train, x_test, y_test = real_data(file_number=2, plotting=False)
degree = 10
designMatrix = DesignMatrix('polynomial2D', degree)
leastSquares = LeastSquares(backend='manual', method='ols')
X = designMatrix.getMatrix(x_train)
leastSquares.fit(X, y_train)
X_test = designMatrix.getMatrix(x_test)
leastSquares.predict()
leastSquares.y = y_test
ols_MSE = leastSquares.MSE()
print(ols_MSE)
ols_MSE = np.array([ols_MSE, ols_MSE])
ols_lambda = np.array([1e-5, 1])
ridge_lambda = np.logspace(-5, 0, 20)
ridge_MSE = []
for lambda_ in ridge_lambda:
print("ridge " + str(lambda_))
designMatrix = DesignMatrix('polynomial2D', degree)
leastSquares = LeastSquares(backend='manual', method='ridge')
leastSquares.setLambda(lambda_)
X = designMatrix.getMatrix(x_train)
leastSquares.fit(X, y_train)
X_test = designMatrix.getMatrix(x_test)
leastSquares.predict()
leastSquares.y = y_test
ridge_MSE.append(leastSquares.MSE())
print(leastSquares.MSE())
ridge_MSE = np.array(ridge_MSE)
lasso_lambda = np.logspace(-4, 0, 20)
lasso_MSE = []
for lambda_ in lasso_lambda:
print("lasso " + str(lambda_))
designMatrix = DesignMatrix('polynomial2D', degree)
leastSquares = LeastSquares(backend='manual', method='lasso')
leastSquares.setLambda(lambda_)
X = designMatrix.getMatrix(x_train)
leastSquares.fit(X, y_train)
X_test = designMatrix.getMatrix(x_test)
leastSquares.predict()
leastSquares.y = y_test
lasso_MSE.append(leastSquares.MSE())
lasso_MSE = np.array(ridge_MSE)
########################################################
plt.rc('text', usetex=True)
plt.loglog(ols_lambda,
ols_MSE,
'k--o',
markersize=1,
linewidth=1,
label=r'OLS')
plt.loglog(ridge_lambda,
ridge_MSE,
'r-o',
markersize=1,
linewidth=1,
label=r'Ridge')
plt.loglog(lasso_lambda,
lasso_MSE,
'b-o',
markersize=1,
linewidth=1,
label=r'Lasso')
plt.xlabel(r"$\lambda$", fontsize=10)
plt.ylabel(r"MSE", fontsize=10)
#plt.subplots_adjust(left=0.2,bottom=0.2)
plt.legend(fontsize=10)
plt.savefig(os.path.join(os.path.dirname(__file__), 'figures',
'lambda_terrain.png'),
transparent=True,
bbox_inches='tight')
plt.show()
def part_b():
R2 = []
MSE = []
R2_noise = []
MSE_noise = []
beta_noise = []
betaVariance_noise = []
noise = np.linspace(0, 1.0, 50)
k = 1
fig, ax1 = plt.subplots()
plt.rc('text', usetex=True)
@jit(nopython=True, cache=True)
def computeFrankeValues(x_data, y):
N = x_data.shape[0]
for i in range(N):
y[i] = franke(x_data[i, 0], x_data[i, 1])
ind = -1
for lambda_ in np.logspace(-2, 0, 3):
ind += 1
MSE_noise = []
for eta in noise:
designMatrix = DesignMatrix('polynomial2D', 10)
if ind == 0:
leastSquares = LeastSquares(backend='manual', method='ols')
else:
leastSquares = LeastSquares(backend='manual', method='ridge')
leastSquares.setLambda(lambda_)
bootstrap = Bootstrap(leastSquares, designMatrix)
N = int(1000)
x = np.random.rand(N)
y = np.random.rand(N)
x_data = np.zeros(shape=(N, 2))
x_data[:, 0] = x
x_data[:, 1] = y
y_data = np.zeros(shape=(N))
computeFrankeValues(x_data, y_data)
y_data_noise = y_data + eta * np.random.standard_normal(size=N)
bootstrap.resample(x_data, y_data_noise, k)
MSE_noise.append(leastSquares.MSE())
R2_noise.append(leastSquares.R2())
beta_noise.append(bootstrap.beta)
betaVariance_noise.append(bootstrap.betaVariance)
# Different noise, test data
N = int(1000)
x = np.random.rand(N)
y = np.random.rand(N)
x_data = np.zeros(shape=(N, 2))
x_data[:, 0] = x
x_data[:, 1] = y
y_data = np.zeros(shape=(N))
computeFrankeValues(x_data, y_data)
y_data_noise = y_data + eta * np.random.standard_normal(size=N)
X = designMatrix.getMatrix(x_data)
leastSquares.X = X
leastSquares.predict()
leastSquares.y = y_data_noise
MSE.append(leastSquares.MSE())
R2.append(leastSquares.R2())
colors = ['b', 'g', 'r', 'c', 'm', 'y', 'k']
if ind == 0:
ax1.loglog(noise,
np.array(MSE_noise),
colors[ind] + '--',
markersize=1,
label=r"OLS")
else:
ax1.loglog(noise,
np.array(MSE_noise),
colors[ind] + '-',
markersize=1,
label=r"$\lambda=10^{%d}$" % (int(np.log10(lambda_))))
plt.ylabel(r"MSE", fontsize=10)
plt.xlabel(r"noise scale $\eta$", fontsize=10)
plt.subplots_adjust(left=0.2, bottom=0.2)
#ax1.set_ylim([0.95*min(min(MSE_noise), min(R2_noise)), 1.05*(max(max(MSE_noise), max(R2_noise)))])
ax1.legend()
#plt.savefig(os.path.join(os.path.dirname(__file__), 'figures', 'MSE_ridge_noise.png'), transparent=True, bbox_inches='tight')
plt.show()
def plot_beta_ridge():
beta = []
betaVariance = []
MSE = []
R2 = []
k = 10000
fig, ax1 = plt.subplots()
plt.rc('text', usetex=True)
@jit(nopython=True, cache=True)
def computeFrankeValues(x_data, y):
N = x_data.shape[0]
for i in range(N):
y[i] = franke(x_data[i, 0], x_data[i, 1])
ind = -1
lam = np.logspace(-3, 5, 20)
for lambda_ in lam:
if ind == 0:
leastSquares = LeastSquares(backend='manual', method='ols')
else:
leastSquares = LeastSquares(backend='manual', method='ridge')
designMatrix = DesignMatrix('polynomial2D', 3)
bootstrap = Bootstrap(leastSquares, designMatrix)
leastSquares.setLambda(lambda_)
ind += 1
N = int(1e4)
x = np.random.rand(N)
y = np.random.rand(N)
x_data = np.zeros(shape=(N, 2))
x_data[:, 0] = x
x_data[:, 1] = y
y_data = np.zeros(shape=(N))
computeFrankeValues(x_data, y_data)
eta = 1.0
y_data_noise = y_data + eta * np.random.standard_normal(size=N)
bootstrap.resample(x_data, y_data_noise, k)
MSE.append(leastSquares.MSE())
R2.append(leastSquares.R2())
beta.append(bootstrap.beta)
betaVariance.append(bootstrap.betaVariance)
leastSquares.y = y_data
MSE.append(leastSquares.MSE())
R2.append(leastSquares.R2())
beta = np.array(beta)
betaVariance = np.array(betaVariance)
monomial = [
'1', 'x', 'y', 'x^2', 'xy', 'y^2', 'x^3', 'x^2y', 'xy^2', 'y^3'
]
colors = [
'#1f77b4', '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b',
'#e377c2', '#7f7f7f', '#bcbd22', '#17becf'
]
for i in range(10):
plt.errorbar(lam[1:],
beta[1:, i],
yerr=2 * betaVariance[1:, i],
fmt='-o',
markersize=2,
linewidth=1,
color=colors[i],
elinewidth=0.5,
capsize=2,
capthick=0.5,
label=r"$\beta_{%s}$" % (monomial[i]))
plt.rc('text', usetex=True)
plt.ylabel(r"$\beta_j$", fontsize=10)
plt.xlabel(r"shrinkage parameter $\lambda$", fontsize=10)
plt.subplots_adjust(left=0.2, bottom=0.2)
plt.legend(fontsize=8)
for i in range(10):
plt.errorbar(1e-3,
beta[0, i],
yerr=2 * betaVariance[0, i],
fmt='-o',
markersize=2,
linewidth=1,
color=colors[i],
elinewidth=0.5,
capsize=2,
capthick=0.5)
fig.gca().set_xscale('log')
#plt.savefig(os.path.join(os.path.dirname(__file__), 'figures', 'beta_ridge.png'), transparent=True, bbox_inches='tight')
plt.show()
max_degree = 20
Degree = []
for i in range(1, max_degree + 1):
Degree.append(i)
Bias_vec = []
Var_vec = []
MSE_vec = []
print("#########################################################")
for degree in Degree:
degree = int(degree)
designMatrix = DesignMatrix('polynomial2D', degree)
X = designMatrix.getMatrix(X)
XT_X = np.dot(X.T, X)
print("det(X^T*X): %g" %
(np.linalg.det(XT_X + Lambda * np.eye(XT_X.shape[0]))))
X_test_deg = designMatrix.getMatrix(X_test)
# The following (m x n_bootstraps) matrix holds the column vectors y_pred
# for each bootstrap iteration.
X_train = np.zeros(shape=(x1_train.shape[0], 2))
n_bootstraps = 100
y_pred = np.empty((y_test.shape[0], n_bootstraps))
for i in range(n_bootstraps):