def cpca_cluster(request):
if request.method == 'POST':
request_data = json.loads(request.body)
alpha = None
if 'alpha' in request_data.keys():
alpha = request_data['alpha']
bg_data_idx = request_data['dataIndex']
data = rs.state['data']
homo_idx = rs.state['outputs_server'] == rs.state['outputs_client']
bg = data[bg_data_idx]
if bg.shape[0] == 1:
return JsonResponse(rs.state['cpca_all_result'])
fg = np.concatenate((data[homo_idx], bg))
local_data, _ = load_samples(dataset=rs['dataset'],
client_name=rs['client'],
sampling_type='local')
if USE_GPU:
with torch.no_grad():
cPCA = CPCA_GPU(n_components=2)
cPCA.fit(target=fg, background=bg, alpha=alpha)
projected_data = cPCA.transform(local_data)
components = cPCA.get_components()
alpha = cPCA.get_alpha()
else:
cPCA = CPCA(n_components=2)
cPCA.fit(target=fg, background=bg, alpha=alpha)
projected_data = cPCA.transform(local_data)
components = cPCA.get_components()
alpha = cPCA.get_alpha()
projected_data = np.round(projected_data, 6).astype(float)
components = np.round(components, 6).astype(float)
alpha = np.round(alpha, 6).astype(float)
data = {
'alpha': alpha,
'cPC1': components[0].tolist(),
'cPC2': components[1].tolist(),
'projectedData': projected_data.tolist(),
}
return JsonResponse(data)
def cpca_all(request):
if request.method == 'POST':
request_data = json.loads(request.body)
alpha = None
if 'alpha' in request_data.keys():
alpha = request_data['alpha']
data = rs.state['data']
hetero_labels = rs.state['outputs_server'] != rs.state['outputs_client']
if USE_GPU:
with torch.no_grad():
cPCA = CPCA_GPU(n_components=2)
projected_data = cPCA.fit_transform(
target=data, background=data[hetero_labels], alpha=alpha)
components = cPCA.get_components()
alpha = cPCA.get_alpha()
else:
cPCA = CPCA(n_components=2)
projected_data = cPCA.fit_transform(target=data,
background=data[hetero_labels],
alpha=alpha)
components = cPCA.get_components()
alpha = cPCA.get_alpha()
projected_data = np.round(projected_data, 6).astype(float)
components = np.round(components, 6).astype(float)
alpha = np.round(alpha, 6).astype(float)
data = {
'alpha': alpha,
'cPC1': components[0].tolist(),
'cPC2': components[1].tolist(),
'projectedData': projected_data.tolist(),
}
rs.set('cpca_all_result', data)
return JsonResponse(data)
import time
import matplotlib.pyplot as plt
import numpy as np
from sklearn import datasets, preprocessing
from cpca import CPCA
from ccpca import CCPCA
dataset = datasets.load_wine()
X = dataset.data
y = dataset.target
X = preprocessing.scale(X)
cpca = CPCA()
cpca.fit(fg=X[y == 0], bg=X[y != 0], alpha=2.15)
X_r = cpca.transform(X)
plt.figure()
colors = ['navy', 'turquoise', 'darkorange']
lw = 2
for color, i, target_name in zip(colors, [0, 1, 2], [0, 1, 2]):
plt.scatter(X_r[y == i, 0],
X_r[y == i, 1],
color=color,
alpha=.8,
lw=lw,
label=target_name)
import time
import matplotlib.pyplot as plt
import numpy as np
from sklearn import datasets, preprocessing
from cpca import CPCA
from ccpca import CCPCA
dataset = datasets.load_wine()
X = dataset.data
y = dataset.target
X = preprocessing.scale(X)
cpca = CPCA()
# manual alpha selection
# cpca.fit(fg=X[y == 0], bg=X[y != 0], alpha=2.15)
# auto alpha selection
cpca.fit(fg=X[y == 0], bg=X[y != 0])
X_r = cpca.transform(X)
plt.figure()
colors = ['navy', 'turquoise', 'darkorange']
lw = 2
for color, i, target_name in zip(colors, [0, 1, 2], [0, 1, 2]):
plt.scatter(X_r[y == i, 0],
X_r[y == i, 1],
# Load data. Refer to http://www-personal.umich.edu/~mejn/netdata/ for the details of datasets
tg = gt.load_graph('./data/dolphin.xml.gz')
bg = gt.load_graph('./data/karate.xml.gz')
# Prepare network representation learning method
nrl = DeepGL(base_feat_defs=[
'total_degree', 'betweenness', 'closeness', 'eigenvector', 'pagerank',
'katz'
],
rel_feat_ops=['mean', 'sum', 'maximum', 'lp_norm'],
nbr_types=['all'],
ego_dist=3,
lambda_value=0.7)
# Prepare contrastive learning method
cl = CPCA()
# Set network representation and contrastive learning methods
# using DeepGL and cPCA is i-cNRL (interpretable cNRL)
cnrl = CNRL(nrl, cl)
# Learning
cnrl.fit(tg, bg)
# Obtain results for plotting
tg_feat_mat = preprocessing.scale(cnrl.tg_feat_mat)
bg_feat_mat = preprocessing.scale(cnrl.bg_feat_mat)
tg_emb = cnrl.transform(feat_mat=tg_feat_mat)
bg_emb = cnrl.transform(feat_mat=bg_feat_mat)
feat_defs = cnrl.feat_defs