kde_on_X_test_log_likelihood = np.sum(kde_on_X.score_samples(X_test))
normal_dist_on_X = stats.multivariate_normal(mean=np.mean(X_train, axis=0),
cov=np.cov(X_train.T))
normal_dist_on_X_test_log_likelihood = np.sum(normal_dist_on_X.logpdf(X_test))
print("X shape: ", X.shape)
initial_dags = [
random_graph.random_dag(X.shape[1], max_deg) for i in range(0, 1)
]
kernel = 'gaussian'
print("kde_on_X_test_log_likelihood: ", kde_on_X_test_log_likelihood)
print("normal dist test log likelihood: ",
normal_dist_on_X_test_log_likelihood)
#placeholders. Phillip, pls pick good values for these
initial_temp = kde_bayesian_net_log_likelihood.bayesian_net_log_likelihood(
X_train, X_test, kernel, 0, 0, negative=True)(initial_dags[0])
#generally seems to be the case that the baseline log likelihood as at the least half the intial temperature
final_temp = initial_temp / 2
alpha = (initial_temp - final_temp) / 5000
opt_dag = simulated_annealing.simulated_annealing(initial_dags[0], \
initial_temp,\
final_temp,\
alpha, \
kde_bayesian_net_log_likelihood.bayesian_net_log_likelihood(X_train, X_test, kernel, 0, 0, negative = True),\
simulated_annealing_dag.degree_constrained_neighbors_func(max_deg),\
print_iters = 10)
kde_on_X_test_log_likelihood = np.sum(np.log(kde_on_X.evaluate(X_test.T)))
def get_P_binary(proj_sep, delta_v_trans, num_sys=100000, method='kde', kde_method='sklearn'):
""" This function calculates the probability of a
random star having the observed proper motion
Parameters
----------
proj_sep : float
Projected separation between two stars
delta_v_trans : float
Transverse velocity difference between two stars
method : string
Method to perform 2D interpolation (options:kde)
kde_method : string
Which KDE algorithm to use (options: scipy, sklearn)
Returns
-------
P(proj_sep, delta_v_trans) : float
Probability that angular separation, pm separation
is due to a genuine binary
"""
# Catalog check
global binary_set
if binary_set is None:
generate_binary_set(num_sys=num_sys)
if method is 'kde':
# Use a Gaussian KDE
global binary_kde
#if binary_kde is None: binary_kde = gaussian_kde((binary_set["proj_sep"], binary_set["delta_v_trans"]))
# We work in log space for the set of binaries
if kde_method is not 'sklearn' and kde_method is not 'scipy':
print("Must use a valid kde algorithm: options are 'sklearn' and 'scipy'")
print("NOTE: sklean's KDE is the Lotus to scipy's 3-cylinder Pinto")
return
if binary_kde is None:
if kde_method is 'sklearn':
kwargs = {'kernel':'tophat'}
binary_kde = KernelDensity(bandwidth=0.1, **kwargs)
binary_kde.fit( np.array([np.log10(binary_set['proj_sep']), np.log10(binary_set['delta_v_trans'])]).T )
else:
binary_kde = gaussian_kde((np.log10(binary_set["proj_sep"]), np.log10(binary_set["delta_v_trans"])))
if isinstance(delta_v_trans, np.ndarray) and isinstance(proj_sep, np.ndarray):
if kde_method is 'sklearn':
values = np.array([np.log10(proj_sep), np.log10(delta_v_trans)]).T
prob_binary = np.exp(binary_kde.score_samples(values))
else:
values = np.array([np.log10(proj_sep), np.log10(delta_v_trans)])
prob_binary = binary_kde.evaluate(values)
elif isinstance(delta_v_trans, np.ndarray):
if kde_method is 'sklearn':
values = np.array([np.log10(proj_sep)*np.ones(len(delta_v_trans)), np.log10(delta_v_trans)]).T
prob_binary = np.exp(binary_kde.score_samples(values))
else:
values = np.array([np.log10(proj_sep)*np.ones(len(delta_v_trans)), np.log10(delta_v_trans)])
prob_binary = binary_kde.evaluate(values)
else:
if kde_method is 'sklearn':
prob_binary = np.exp(binary_kde.score_samples([np.log10(proj_sep), np.log10(delta_v_trans)]))
else:
prob_binary = binary_kde.evaluate([np.log10(proj_sep), np.log10(delta_v_trans)])
else:
print("You must input an appropriate method.")
print("Options: 'kde' only")
return
# Convert back from log10-space to linear-space
# the log(10) terms convert from log10 to ln
prob_binary = prob_binary / (proj_sep*np.log(10.)) / (delta_v_trans*np.log(10.))
return prob_binary
def get_P_binary(proj_sep,
delta_v_trans,
num_sys=100000,
method='kde',
kde_method='sklearn'):
""" This function calculates the probability of a
random star having the observed proper motion
Parameters
----------
proj_sep : float
Projected separation between two stars
delta_v_trans : float
Transverse velocity difference between two stars
method : string
Method to perform 2D interpolation (options:kde)
kde_method : string
Which KDE algorithm to use (options: scipy, sklearn)
Returns
-------
P(proj_sep, delta_v_trans) : float
Probability that angular separation, pm separation
is due to a genuine binary
"""
# Catalog check
global binary_set
if binary_set is None:
generate_binary_set(num_sys=num_sys)
if method is 'kde':
# Use a Gaussian KDE
global binary_kde
#if binary_kde is None: binary_kde = gaussian_kde((binary_set["proj_sep"], binary_set["delta_v_trans"]))
# We work in log space for the set of binaries
if kde_method is not 'sklearn' and kde_method is not 'scipy':
print(
"Must use a valid kde algorithm: options are 'sklearn' and 'scipy'"
)
print(
"NOTE: sklean's KDE is the Lotus to scipy's 3-cylinder Pinto")
return
if binary_kde is None:
if kde_method is 'sklearn':
kwargs = {'kernel': 'tophat'}
binary_kde = KernelDensity(bandwidth=0.1, **kwargs)
binary_kde.fit(
np.array([
np.log10(binary_set['proj_sep']),
np.log10(binary_set['delta_v_trans'])
]).T)
else:
binary_kde = gaussian_kde(
(np.log10(binary_set["proj_sep"]),
np.log10(binary_set["delta_v_trans"])))
if isinstance(delta_v_trans, np.ndarray) and isinstance(
proj_sep, np.ndarray):
if kde_method is 'sklearn':
values = np.array(
[np.log10(proj_sep),
np.log10(delta_v_trans)]).T
prob_binary = np.exp(binary_kde.score_samples(values))
else:
values = np.array(
[np.log10(proj_sep),
np.log10(delta_v_trans)])
prob_binary = binary_kde.evaluate(values)
elif isinstance(delta_v_trans, np.ndarray):
if kde_method is 'sklearn':
values = np.array([
np.log10(proj_sep) * np.ones(len(delta_v_trans)),
np.log10(delta_v_trans)
]).T
prob_binary = np.exp(binary_kde.score_samples(values))
else:
values = np.array([
np.log10(proj_sep) * np.ones(len(delta_v_trans)),
np.log10(delta_v_trans)
])
prob_binary = binary_kde.evaluate(values)
else:
if kde_method is 'sklearn':
prob_binary = np.exp(
binary_kde.score_samples(
[np.log10(proj_sep),
np.log10(delta_v_trans)]))
else:
prob_binary = binary_kde.evaluate(
[np.log10(proj_sep),
np.log10(delta_v_trans)])
else:
print("You must input an appropriate method.")
print("Options: 'kde' only")
return
# Convert back from log10-space to linear-space
# the log(10) terms convert from log10 to ln
prob_binary = prob_binary / (proj_sep * np.log(10.)) / (delta_v_trans *
np.log(10.))
return prob_binary