def create_prior(dim, mean_prior, mean_str, cov_prior, cov_str):
"""
Creates a gaussian prior, if cov_prior is a scalar, then creates an isotropic prior scaled to that, if its a matrix
uses it as covariance
:param dim: data dimension
:param mean_prior: if a scalar, will create a vector scaled to that, if its a vector then use it as the prior mean
:param mean_str: prior mean psuedo count
:param cov_prior: if a scalar, will create an isotropic covariance scaled to cov_prior, if a matrix will use it as
the covariance.
:param cov_str: prior covariance psuedo counts
:return: DPMMSubClusters.niw_hyperparams prior
"""
if isinstance(mean_prior, (int, float)):
prior_mean = np.ones(dim) * mean_prior
else:
prior_mean = mean_prior
if isinstance(cov_prior, (int, float)):
prior_covariance = np.eye(dim) * cov_prior
else:
prior_covariance = cov_prior
prior = niw(mean_str, prior_mean, dim + cov_str, prior_covariance)
return prior
def run_synthetic_data_comparisons(
D: int,
K: int,
N: int,
var_scale: int,
alpha: int,
iters: int,
burnout: int,
repeats: int,
):
results = {
"method": [],
"k_mae": [],
"NMI": [],
"ARI": [],
"Time": [],
}
i = 0
while i < repeats:
# generate dataset
data, labels = DPMMPython.generate_gaussian_data(N, D, K, var_scale)
prior = niw(1, np.zeros(D), 100, np.eye(D) * 0.5)
# run DPGMM
if D == 2:
start = timer()
dpmm_splitnet_results = DPMMPython.fit(
data,
alpha,
iterations=iters,
burnout=burnout,
verbose=False,
init_type="splitnet_2d",
)[0]
dpmm_net_time = timer() - start
elif D <= 10:
start = timer()
dpmm_splitnet_results = DPMMPython.fit(
data,
alpha,
iterations=ITERS,
burnout=BURNOUT,
verbose=False,
init_type="splitnet_10d",
)[0]
dpmm_net_time = timer() - start
else:
start = timer()
dpmm_splitnet_results = DPMMPython.fit(
data,
alpha,
iterations=ITERS,
burnout=BURNOUT,
verbose=False,
init_type="splitnet_128d",
)[0]
dpmm_net_time = timer() - start
if len(np.unique(dpmm_splitnet_results)) < K // 2:
print("failed.")
else:
start = timer()
dpmm_rand_results = DPMMPython.fit(
data,
alpha,
iterations=iters,
burnout=burnout,
verbose=False,
init_type="none",
)[0]
dpmm_rand_time = timer() - start
start = timer()
dpmm_kmeans_results = DPMMPython.fit(
data,
alpha,
iterations=iters,
burnout=burnout,
verbose=False,
init_type="kmeans",
)[0]
dpmm_kmeans_time = timer() - start
# run kmeans
start = timer()
kmeans = KMeans(n_clusters=K).fit(data.T)
kmeans_time = timer() - start
kmeans_labels = kmeans.labels_
# run GMM
start = timer()
gmm = GaussianMixture(n_components=K,
covariance_type="full").fit(data.T)
gmm_labels = gmm.predict(data.T)
gmm_time = timer() - start
# sklearn DPGMM
start = timer()
dpgmm = BayesianGaussianMixture(
n_components=2 * K,
covariance_type="full",
weight_concentration_prior=alpha,
weight_concentration_prior_type="dirichlet_process",
mean_precision_prior=1e2,
covariance_prior=1e0 * np.eye(D),
init_params="kmeans",
max_iter=iters,
verbose=0,
).fit(data.T)
dpgmm_labels = dpgmm.predict(data.T)
dpgmmsk_time = timer() - start
# moVB
# pass data NxD
data_bnpy = bnpy.data.XData(data.T)
start = timer()
model, run_info = bnpy.run(
data_bnpy,
"DPMixtureModel",
"Gauss",
"memoVB",
nTask=1,
nBatch=1,
K=1,
nLap=iters,
moves="birth,merge,shuffle",
gt=labels,
gamma0=alpha,
)
moVB_time = timer() - start
LP = model.calc_local_params(data_bnpy)
moVB_labels = LP["resp"].argmax(axis=1)
# calc metrics and aggregate
results = add_results(results, "k-means", labels, kmeans_labels,
kmeans_time)
results = add_results(results, "EM-GMM", labels, gmm_labels,
gmm_time)
results = add_results(results, "DPGMM (SKlearn's)", labels,
dpgmm_labels, dpgmmsk_time)
results = add_results(results, "DPGMM-Random", labels,
dpmm_rand_results, dpmm_rand_time)
results = add_results(results, "DPGMM-k-means", labels,
dpmm_kmeans_results, dpmm_kmeans_time)
results = add_results(results, "DPGMM-SplitNet", labels,
dpmm_splitnet_results, dpmm_net_time)
results = add_results(results, "moVB", labels, moVB_labels,
moVB_time)
i += 1
print(f"Finished iteration {i}")
return results
def run_datasets_comparisons(data, labels, alpha: int, iters: int,
burnout: int, repeats: int):
results = {
"method": [],
"k_mae": [],
"NMI": [],
"ARI": [],
# "Acc": [],
}
N, D = data.shape
K = len(np.unique(labels))
for i in range(repeats):
# run kmeans
kmeans = KMeans(n_clusters=K).fit(data)
kmeans_labels = kmeans.labels_
# run GMM
gmm = GaussianMixture(n_components=K, covariance_type="full").fit(data)
gmm_labels = gmm.predict(data)
# sklearn DPGMM
dpgmm = BayesianGaussianMixture(
n_components=2 * K,
covariance_type="full",
weight_concentration_prior=1e2,
weight_concentration_prior_type="dirichlet_process",
mean_precision_prior=1e2,
covariance_prior=1e0 * np.eye(D),
init_params="kmeans",
max_iter=ITERS,
verbose=0,
).fit(data)
dpgmm_labels = dpgmm.predict(data)
prior = niw(1, np.zeros(D), D + 2, np.eye(D) * 0.5)
# run DPGMM
# dpmm_rand_results = DPMMPython.fit(data.T ,alpha, prior = prior, iterations=iters, burnout=burnout, verbose=False, init_type="none")[0]
# dpmm_kmeans_results = DPMMPython.fit(data.T ,alpha, prior = prior, iterations=iters, burnout=burnout, verbose=False, init_type="kmeans")[0]/
dpmm_rand_results = DPMMPython.fit(
data.T,
alpha,
iterations=iters,
burnout=burnout,
verbose=False,
init_type="none",
)[0]
dpmm_kmeans_results = DPMMPython.fit(
data.T,
alpha,
iterations=iters,
burnout=burnout,
verbose=False,
init_type="kmeans",
)[0]
if D == 2:
dpmm_splitnet_results = DPMMPython.fit(
data.T,
alpha,
iterations=iters,
burnout=burnout,
verbose=False,
init_type="splitnet_2d",
)[0]
elif D <= 10:
dpmm_splitnet_results = DPMMPython.fit(
data.T,
alpha,
iterations=ITERS,
burnout=BURNOUT,
verbose=False,
init_type="splitnet_10d",
)[0]
else:
dpmm_splitnet_results = DPMMPython.fit(
data.T,
alpha,
iterations=ITERS,
burnout=BURNOUT,
verbose=False,
init_type="splitnet_128d",
)[0]
# calc metrics and aggregate
results = add_results(results, "k-means", labels, kmeans_labels)
results = add_results(results, "EM-GMM", labels, gmm_labels)
results = add_results(results, "DPGMM (SKlearn's)", labels,
dpgmm_labels)
results = add_results(results, "DPGMM-Random", labels,
dpmm_rand_results)
results = add_results(results, "DPGMM-k-means", labels,
dpmm_kmeans_results)
results = add_results(results, "DPGMM-SplitNet", labels,
dpmm_splitnet_results)
print(f"Finished iteration {i}")
return results
# Plotting the data
#
# Note that as Julia is a column first language, the data generated is $DxN$
fig = plt.figure(figsize=(16, 10))
plt.scatter(data[0, :], data[1, :], c=labels, s=2, alpha=0.5, cmap="tab20")
# plt.colorbar()
# fig.colorbar(mpl.cm.ScalarMappable(norm=norm, cmap=cmap))
plt.show()
# ### Fiting DPGMM Model to the data
#
# Start by defining a niw prior and $\alpha$
prior = niw(1, np.zeros(D), 1000, np.eye(D))
alpha = 1000.0
# Fit the model and store the results in `results`.
# When working from Jupyter Notebook/Lab you will not see Julia prints. However when running python from terminal you will see all the prints (as in the Julia packages)
# results = DPMMPython.fit(data,alpha,prior=prior, iterations=300, burnout=5, verbose=False, init_type="kmeans")
# results = DPMMPython.fit(data,alpha, iterations=200, burnout=3, verbose=False, init_type="kmeans")
#
results = DPMMPython.fit(data,
alpha,
iterations=100,
burnout=5,
verbose=False,
init_type="splitnet_2d")
# results = DPMMPython.fit(data, alpha, prior=prior, iterations=300, burnout=3, verbose=False, init_type="splitnet_2d")
data = DPMMSubClusters.generate_gaussian_data(sample_count, dim,
components, var)
gt = data[1]
data = data[0]
return data, gt
@staticmethod
def predict(model, data):
'''
Given a DPMM Model (which is located in fit(...)[2][-1] for backwards compatibility),
predict the clusters for a data. The predict is using each cluster predictive posterior,
in contrary to the model itself during training, which sample from the posterior.
:params model: a DPMM (Julia object) model, returned from fit
:data: The data in which to predict, DxN (similar to the fit argument)
:return: labels
'''
return DPMMSubClusters.predict(model, data)
if __name__ == "__main__":
j = julia.Julia()
data, gt = DPMMPython.generate_gaussian_data(10000, 2, 10, 100.0)
prior = niw(kappa=1, mu=np.ones(2) * 0, nu=3, psi=np.eye(2))
# labels_j,_,sub_labels= DPMMPython.fit(data, 100, prior = prior, verbose = True, gt = gt, gpu = False)
labels_j, _, sub_labels = DPMMPython.fit(data,
100,
prior=prior,
verbose=True,
gt=gt,
gpu=True)