def test_highlight(self):
def test(G):
s = np.arange(G.N)
G.plot_signal(s, backend='matplotlib', highlight=0)
G.plot_signal(s, backend='matplotlib', highlight=[0])
G.plot_signal(s, backend='matplotlib', highlight=[0, 1])
# Test for 1, 2, and 3D graphs.
G = graphs.Ring()
test(G)
G = graphs.Ring()
G.set_coordinates('line1D')
test(G)
G = graphs.Torus(Nv=5)
test(G)
def test_indices(self):
def test(G):
G.plot(backend='matplotlib', indices=False)
G.plot(backend='matplotlib', indices=True)
# Test for 2D and 3D graphs.
G = graphs.Ring(10)
test(G)
G = graphs.Torus(Nv=5)
test(G)
def test_regression_tikhonov_1(self):
"""Solve a trivial regression problem."""
G = graphs.Ring(N=8)
signal = np.array([0, np.nan, 4, np.nan, 4, np.nan, np.nan, np.nan])
mask = np.array([True, False, True, False, True, False, False, False])
truth = np.array([0, 2, 4, 4, 4, 3, 2, 1])
recovery = learning.regression_tikhonov(G, signal, mask, tau=0)
np.testing.assert_allclose(recovery, truth)
# Test the numpy solution.
G = graphs.Graph(G.W.toarray())
recovery = learning.regression_tikhonov(G, signal, mask, tau=0)
np.testing.assert_allclose(recovery, truth)
def test_ring(self):
graphs.Ring()
graphs.Ring(N=32, k=16)
self.assertRaises(ValueError, graphs.Ring, 2)
self.assertRaises(ValueError, graphs.Ring, 5, k=3)
def test_ring(self):
graphs.Ring()
graphs.Ring(N=32, k=16)
def test_Ring():
G = graphs.Ring()
"""
Instantiate and plot wavelet filter banks on graphs
Author: Shashwat Shukla
Date: 2nd June 2020
"""
# Import libraries
import numpy as np
import matplotlib.pyplot as plt
from pygsp import graphs, filters, plotting, utils
# Meyer wavelets on a ring
G = graphs.Ring(400)
G.estimate_lmax()
g = filters.Meyer(G, Nf=6)
fig, ax = plt.subplots(figsize=(10, 5))
g.plot(ax=ax)
_ = ax.set_title('Filter bank of Meyer wavelets')
DELTA = 255
s = g.localize(DELTA)
fig = plt.figure(figsize=(10, 2.5))
for i in range(4):
ax = fig.add_subplot(1, 4, i + 1, projection='3d')
G.plot_signal(s[:, i], ax=ax)
_ = ax.set_title('Wavelet {}'.format(i + 1))
ax.set_axis_off()
fig.tight_layout()
plt.show()
# Mexican hat wavelets on a torus
return [X_out_, A_out_, I_out_]
upsampling_from_mask_op = Lambda(upsampling_from_mask)
upsampling_from_matrix_op = Lambda(upsampling_from_matrix)
# HYPERPARAMS
ITER = 10000
ACTIV = 'tanh'
dataset = 'grid'
gnn_channels = 32
es_patience = 1000
# LOAD DATASET
if dataset == 'ring':
G = graphs.Ring(N=200)
elif dataset == 'grid':
G = graphs.Grid2d(N1=30, N2=30)
X = G.coords.astype(np.float32)
A = G.W
y = np.zeros(X.shape[0]) # X[:,0] + X[:,1]
n_classes = np.unique(y).shape[0]
n_feat = X.shape[-1]
n_nodes = A.shape[0]
# MODEL DEFINITION
X_in = Input(
tensor=tf.placeholder(tf.float32, shape=(None, n_feat), name='X_in'))
A_in = Input(tensor=tf.sparse_placeholder(tf.float32, shape=(None, None)),
name='A_in')
I_in = Input(
def test_Ring():
G = graphs.Ring()
needed_attributes_testing(G)
