def test_gowl_vs_glasso_duality_gap_3(self):
"""
Duality Gap goes negative in this case. Should that happen?
"""
np.random.seed(680)
p = 10
blocks = [
Block(dim=p,
idx=0,
block_min_size=2,
block_max_size=6,
block_value=0.9),
Block(dim=p,
idx=1,
block_min_size=2,
block_max_size=6,
block_value=-0.9),
Block(dim=p,
idx=3,
block_min_size=2,
block_max_size=6,
block_value=-0.5),
]
theta_star, blocks, theta_blocks = generate_theta_star_gowl(p=p,
alpha=0.5,
noise=0.1,
blocks=blocks)
lam1 = 0.001 # controls sparsity
lam2 = 0.01 # encourages equality of coefficients
rho = oscar_weights(lam1, lam2, (p ** 2 - p) / 2)
theta_star = theta_star[0]
sigma = np.linalg.inv(theta_star)
n = 100
X = np.random.multivariate_normal(np.zeros(p), sigma, n)
X = standardize(X)
S = np.cov(X.T)
theta_0 = np.linalg.inv(S)
model = GOWLModel(X, S, theta_0, lam1, lam2, 'backtracking', max_iters=100000)
model.fit()
theta_gowl = model.theta_hat
gl = GraphicalLasso(max_iter=200)
gl.fit(S)
theta_glasso = gl.get_precision()
print('Non zero entries in precision matrix {}'.format(np.count_nonzero(theta_gowl)))
plot_multiple_theta_matrices_2d([theta_blocks, theta_star, theta_glasso, theta_gowl],
[f"Blocks: {len(blocks)}", 'True Theta', 'GLASSO', 'GOWL'])
_fit_evaluations(theta_star, theta_glasso, 3, 'GLASSO')
_fit_evaluations(theta_star, theta_gowl, 3, 'GOWL')
y_hat_gowl = spectral_clustering(theta=theta_gowl, K=4)
y_hat_glasso = spectral_clustering(theta=theta_glasso, K=4)
y_true = spectral_clustering(theta=theta_blocks, K=4).flatten()
_cluster_evaluations(y_true, y_hat_gowl, 'GOWL')
_cluster_evaluations(y_true, y_hat_glasso, 'GLASSO')
def predict(self,
data: pd.DataFrame,
alpha: float = 0.01,
max_iter: int = 2000,
**kwargs) -> nx.Graph:
"""Predict the graph structure """
edge_model = GraphicalLasso(alpha=alpha, max_iter=max_iter)
edge_model.fit(data.values)
return nx.relabel_nodes(nx.DiGraph(edge_model.get_precision()),
{idx: i
for idx, i in enumerate(data.columns)})
def predict(self, data, alpha=0.01, max_iter=2000, **kwargs):
""" Predict the graph skeleton.
Args:
data (pandas.DataFrame): observational data
alpha (float): regularization parameter
max_iter (int): maximum number of iterations
Returns:
networkx.Graph: Graph skeleton
"""
edge_model = GraphicalLasso(alpha=alpha, max_iter=max_iter)
edge_model.fit(data.values)
return nx.relabel_nodes(nx.DiGraph(edge_model.get_precision()),
{idx: i
for idx, i in enumerate(data.columns)})
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.covariance import GraphicalLasso
filename = "expr_ceph_utah_1000.txt"
data = pd.read_csv(filename, delimiter='\t', index_col=0)
n_rows = data.shape[0]
n_cols = data.shape[1]
cov_matrix = np.cov(data.T)
np.savetxt("cov_matrix.csv", cov_matrix, delimiter=',')
model = GraphicalLasso(alpha=0.55)
model.fit(data)
prec_matrix = model.get_precision()
# print(prec_matrix)
np.savetxt("precision_matrix.csv", prec_matrix, delimiter=',')
n = n_cols
adj_matrix = np.zeros((n, n))
n_edges = 0
for i in range(n):
for j in range(i, n):
if prec_matrix[i, j] != 0:
adj_matrix[i, j] = 1
adj_matrix[j, i] = 1
n_edges += 1
np.savetxt("glasso_adj_matrix.csv", adj_matrix, delimiter=',')
degree_list = np.sum(adj_matrix, axis=0) - 1
