Show code cell source
MAKE_BOOK_FIGURES=Trueimport numpy as npimport scipy.stats as stimport matplotlib as mplimport matplotlib.pyplot as plt%matplotlib inlineimport matplotlib_inlinematplotlib_inline.backend_inline.set_matplotlib_formats('svg')import seaborn as snssns.set_context("paper")sns.set_style("ticks")def set_book_style(): plt.style.use('seaborn-v0_8-white') sns.set_style("ticks") sns.set_palette("deep") mpl.rcParams.update({ # Font settings 'font.family': 'serif', # For academic publishing 'font.size': 8, # As requested, 10pt font 'axes.labelsize': 8, 'axes.titlesize': 8, 'xtick.labelsize': 7, # Slightly smaller for better readability 'ytick.labelsize': 7, 'legend.fontsize': 7, # Line and marker settings for consistency 'axes.linewidth': 0.5, 'grid.linewidth': 0.5, 'lines.linewidth': 1.0, 'lines.markersize': 4, # Layout to prevent clipped labels 'figure.constrained_layout.use': True, # Default DPI (will override when saving) 'figure.dpi': 600, 'savefig.dpi': 600, # Despine - remove top and right spines 'axes.spines.top': False, 'axes.spines.right': False, # Remove legend frame 'legend.frameon': False, # Additional trim settings 'figure.autolayout': True, # Alternative to constrained_layout 'savefig.bbox': 'tight', # Trim when saving 'savefig.pad_inches': 0.1 # Small padding to ensure nothing gets cut off })def set_notebook_style(): plt.style.use('seaborn-v0_8-white') sns.set_style("ticks") sns.set_palette("deep") mpl.rcParams.update({ # Font settings - using default sizes 'font.family': 'serif', 'axes.labelsize': 10, 'axes.titlesize': 10, 'xtick.labelsize': 9, 'ytick.labelsize': 9, 'legend.fontsize': 9, # Line and marker settings 'axes.linewidth': 0.5, 'grid.linewidth': 0.5, 'lines.linewidth': 1.0, 'lines.markersize': 4, # Layout settings 'figure.constrained_layout.use': True, # Remove only top and right spines 'axes.spines.top': False, 'axes.spines.right': False, # Remove legend frame 'legend.frameon': False, # Additional settings 'figure.autolayout': True, 'savefig.bbox': 'tight', 'savefig.pad_inches': 0.1 })def save_for_book(fig, filename, is_vector=True, **kwargs): """ Save a figure with book-optimized settings. Parameters: ----------- fig : matplotlib figure The figure to save filename : str Filename without extension is_vector : bool If True, saves as vector at 1000 dpi. If False, saves as raster at 600 dpi. **kwargs : dict Additional kwargs to pass to savefig """ # Set appropriate DPI and format based on figure type if is_vector: dpi = 1000 ext = '.pdf' else: dpi = 600 ext = '.tif' # Save the figure with book settings fig.savefig(f"{filename}{ext}", dpi=dpi, **kwargs)def make_full_width_fig(): return plt.subplots(figsize=(4.7, 2.9), constrained_layout=True)def make_half_width_fig(): return plt.subplots(figsize=(2.35, 1.45), constrained_layout=True)if MAKE_BOOK_FIGURES: set_book_style()else: set_notebook_style()make_full_width_fig = make_full_width_fig if MAKE_BOOK_FIGURES else lambda: plt.subplots()make_half_width_fig = make_half_width_fig if MAKE_BOOK_FIGURES else lambda: plt.subplots()
The point-predictive Distribution - Separating Epistemic and Aleatory Uncertainty#
We will demonstrate how we can separate epistemic and aleatory uncertainty.
Example (Quadratic)#
Let’s repeat what we did above with a quadratic example. Here are some synthetic data:
np.random.seed(12345)
num_obs = 10
x = -1.0 + 2 * np.random.rand(num_obs)
w0_true = -0.5
w1_true = 2.0
w2_true = 2.0
sigma_true = 0.1
y = (
w0_true
+ w1_true * x
+ w2_true * x ** 2
+ sigma_true * np.random.randn(num_obs)
)
fig, ax = plt.subplots()
ax.plot(x, y, 'x', label='Observed data')
ax.set_xlabel('$x$')
ax.set_ylabel('$y$')
plt.legend(loc='best', frameon=False)
sns.despine(trim=True);
Let’s also copy-paste the code from previous hands-on activities for generating the design matrix and fitting the models.
import scipy
def get_polynomial_design_matrix(x, degree):
"""Return the polynomial design matrix of ``degree`` evaluated at ``x``.
Arguments:
x -- A 2D array with only one column.
degree -- An integer greater than zero.
"""
assert isinstance(x, np.ndarray), 'x is not a numpy array.'
assert x.ndim == 2, 'You must make x a 2D array.'
assert x.shape[1] == 1, 'x must be a column.'
cols = []
for i in range(degree+1):
cols.append(x ** i)
return np.hstack(cols)
def get_fourier_design_matrix(x, L, num_terms):
"""Fourier expansion with ``num_terms`` cosines and sines.
Arguments:
x -- A 2D array with only one column.
L -- The "length" of the domain.
num_terms -- How many Fourier terms do you want.
This is not the number of basis
functions you get. The number of basis functions
is 1 + num_terms / 2. The first one is a constant.
"""
assert isinstance(x, np.ndarray), 'x is not a numpy array.'
assert x.ndim == 2, 'You must make x a 2D array.'
assert x.shape[1] == 1, 'x must be a column.'
N = x.shape[0]
cols = [np.ones((N, 1))]
for i in range(int(num_terms / 2)):
cols.append(np.cos(2 * (i+1) * np.pi / L * x))
cols.append(np.sin(2 * (i+1) * np.pi / L * x))
return np.hstack(cols)
def get_rbf_design_matrix(x, x_centers, ell):
"""Radial basis functions design matrix.
Arguments:
x -- The input points on which you want to evaluate the
design matrix.
x_center -- The centers of the radial basis functions.
ell -- The lengthscale of the radial basis function.
"""
assert isinstance(x, np.ndarray), 'x is not a numpy array.'
assert x.ndim == 2, 'You must make x a 2D array.'
assert x.shape[1] == 1, 'x must be a column.'
N = x.shape[0]
cols = [np.ones((N, 1))]
for i in range(x_centers.shape[0]):
cols.append(np.exp(-(x - x_centers[i]) ** 2 / ell))
return np.hstack(cols)
def find_m_and_S(Phi, y, sigma2, alpha):
"""Return the posterior mean and covariance of the weights
of a Bayesian linear regression problem.
Arguments:
Phi -- The design matrix.
y -- The observed targets.
sigma2 -- The noise variance.
alpha -- The prior weight precision.
"""
A = (
Phi.T @ Phi / sigma2
+ alpha * np.eye(Phi.shape[1])
)
L = scipy.linalg.cho_factor(A)
m = scipy.linalg.cho_solve(
L,
Phi.T @ y / sigma2
)
S = scipy.linalg.cho_solve(
L,
np.eye(Phi.shape[1])
)
return m, S
Fit a \(7\) degree polynomial:
Show code cell source
import scipy.stats as st
# Parameters
degree = 7
sigma2 = 0.1 ** 2
alpha = 5.0
# Weight prior
w_prior = st.multivariate_normal(
mean=np.zeros(degree+1),
cov=np.eye(degree+1) / alpha
)
# Design matrix
Phi = get_polynomial_design_matrix(x[:, None], degree)
# Fit
m, S = find_m_and_S(Phi, y, sigma2, alpha)
# Weight posterior
w_post = st.multivariate_normal(mean=m, cov=S)
As we discussed in the video, it is possible to get the posterior point predictive distribution for \(y\) conditioned on \(\mathbf{x}\) and to separate aleatory from epistemic uncertainty. The posterior point predictive is:
\(\sigma^2\) corresponds to the measurement noise.
\(\boldsymbol{\phi}(\mathbf{x})^T\mathbf{S}\boldsymbol{\phi}(\mathbf{x})\) is the epistemic uncertainty induced by limited data.
Here is how to visualize both of these:
Show code cell source
xx = np.linspace(-1, 1, 100)
Phi_xx = get_polynomial_design_matrix(xx[:, None], degree)
# Posterior predictive mean
yy_mean = Phi_xx @ m
# Posterior predictive epistemic variance
yy_var = np.einsum(
'ij,jk,ik->i',
Phi_xx,
S,
Phi_xx
)
# Posterior predictive epistemic + aleatory variance
yy_measured_var = yy_var + sigma2
# 95% posterior predictive credible interval
yy_std = np.sqrt(yy_var)
yy_measured_std = np.sqrt(yy_measured_var)
# Epistemic only
yy_le = yy_mean - 2.0 * yy_std
yy_ue = yy_mean + 2.0 * yy_std
# Epistemic + aleatory
yy_lae = yy_mean - 2.0 * yy_measured_std
yy_uae = yy_mean + 2.0 * yy_measured_std
# The true response for plotting
yy_true = w0_true + w1_true * xx + w2_true * xx ** 2
# Plot
fig, ax = plt.subplots()
ax.plot(xx, yy_mean, 'r', label="Posterior mean")
ax.fill_between(
xx,
yy_le,
yy_ue,
color='red',
alpha=0.25,
label="95% epistemic credible interval"
)
ax.fill_between(
xx,
yy_lae,
yy_le,
color='green',
alpha=0.25
)
ax.fill_between(
xx,
yy_ue,
yy_uae,
color='green',
alpha=0.25,
label="95% epistemic + aleatory credible interval"
)
ax.plot(x, y, 'kx', label='Observed data')
ax.set_xlabel('$x$')
ax.set_ylabel('$y$')
plt.legend(loc="best", frameon=False)
sns.despine(trim=True);
Questions#
Rerun the code cells above with a very small \(\alpha\). What happens?
Rerun he code cells above with a very big \(\alpha\). What happens?
Fix \(\alpha\) to \(5\) and rerun the code cells above with a very small and very big value for \(\sigma\). What happens in each case