def compare_models(self, n_clusters, score_func):
"""Compare the model performance with respect to a score metric.
Args:
random_state (int):
n_clusters (int):
Returns:
(tuple): The name and score of the selected model, in addition to
a model instance with the optimal hyperparameter settings.
"""
# Shuffle data matrix, row and col indicators for random state.
_train, self.row_idx, self.col_idx = sgen._shuffle(
self._data, random_state=self.random_state)
# NB: Subtract mean and divide by std.
_train_std = self.scaler.fit_transform(_train)
best_score = -np.float('inf')
winning_model, best_params = None, None
for model, params in self.models_and_params:
if isinstance(n_clusters, (tuple, list)):
if not isinstance(model, SpectralBiclustering):
n_clusters = min(n_clusters)
# Determine the best hyperparameter combo for that model
_grid = GridSearchCV(model(random_state=self.random_state,
n_clusters=n_clusters),
param_grid=params,
scoring=score_func,
n_jobs=16,
cv=self.dummy_cv,
return_train_score=True,
refit=False)
_grid.fit(_train_std, y=None)
if self.verbose > 1:
print('Model performance:\nName: {}\nScore: {}\n'
''.format(model.__name__, _grid.best_score_))
if _grid.best_score_ > best_score:
winner_model = model.__name__
best_score = _grid.best_score_
winner_params = _grid.best_params_
return (winner_model, winner_params, best_score)
from sklearn.datasets import make_biclusters
from sklearn.datasets import samples_generator as sg
from sklearn.cluster.bicluster import SpectralCoclustering
from sklearn.metrics import consensus_score
data, rows, columns = make_biclusters(shape=(300, 300),
n_clusters=5,
noise=5,
shuffle=False,
random_state=0)
plt.matshow(data, cmap=plt.cm.Blues)
plt.title("Original dataset")
data, row_idx, col_idx = sg._shuffle(data, random_state=0)
plt.matshow(data, cmap=plt.cm.Blues)
plt.title("Shuffled dataset")
model = SpectralCoclustering(n_clusters=6, random_state=0)
model.fit(data)
score = consensus_score(model.biclusters_,
(rows[:, row_idx], columns[:, col_idx]))
print("consensus score: {:.3f}".format(score))
fit_data = data[np.argsort(model.row_labels_)]
fit_data = fit_data[:, np.argsort(model.column_labels_)]
plt.matshow(fit_data, cmap=plt.cm.Blues)
plt.title("After biclustering; rearranged to show biclusters")
os.remove(temppath)
size(W, HEIGHT+dy+40)
else:
def pltshow(mplpyplot):
mplpyplot.show()
# nodebox section end
n_clusters = (4, 3)
data, rows, columns = make_checkerboard(
shape=(300, 300), n_clusters=n_clusters, noise=10,
shuffle=False, random_state=0)
plt.matshow(data, cmap=plt.cm.Blues)
plt.title("Original dataset")
data, row_idx, col_idx = sg._shuffle(data, random_state=0)
plt.matshow(data, cmap=plt.cm.Blues)
plt.title("Shuffled dataset")
model = SpectralBiclustering(n_clusters=n_clusters, method='log',
random_state=0)
model.fit(data)
score = consensus_score(model.biclusters_,
(rows[:, row_idx], columns[:, col_idx]))
print("consensus score: {:.1f}".format(score))
fit_data = data[np.argsort(model.row_labels_)]
fit_data = fit_data[:, np.argsort(model.column_labels_)]
plt.matshow(fit_data, cmap=plt.cm.Blues)
def test_co_clustering():
import numpy as np
import nibabel as nb
from matplotlib import pyplot as plt
import sklearn as sk
from sklearn.datasets import make_biclusters
from sklearn.datasets import samples_generator as sg
from sklearn.cluster.bicluster import SpectralCoclustering
from sklearn.metrics import consensus_score
# REAL DATA
subject_file = '/Users/aki.nikolaidis/Desktop/NKI_SampleData/A00060280/3mm_bandpassed_demeaned_filtered_antswarp.nii.gz'
roi_mask_file = home + '/git_repo/basc/masks/BG_3mm.nii.gz'
roi2_mask_file = home + '/git_repo/basc/masks/yeo2_3mm.nii.gz'
data = nb.load(subject_file).get_data().astype('float32')
print('Data Loaded')
print('Setting up NIS')
roi_mask_file_nb = nb.load(roi_mask_file)
roi2_mask_file_nb = nb.load(roi2_mask_file)
roi_mask_nparray = nb.load(roi_mask_file).get_data().astype(
'float32').astype('bool')
roi2_mask_nparray = nb.load(roi2_mask_file).get_data().astype(
'float32').astype('bool')
roi1data = data[roi_mask_nparray]
roi2data = data[roi2_mask_nparray]
#add code that uploads the roi1data and roi2data, divides by the mean and standard deviation of the timeseries
roi1data = sk.preprocessing.normalize(roi1data, norm='l2')
roi2data = sk.preprocessing.normalize(roi2data, norm='l2')
dist_btwn_data_1_2 = np.array(
sp.spatial.distance.cdist(roi1data, roi2data, metric='correlation'))
sim_btwn_data_1_2 = 1 - dist_btwn_data_1_2
sim_btwn_data_1_2[np.isnan(sim_btwn_data_1_2)] = 0
sim_btwn_data_1_2[sim_btwn_data_1_2 < 0] = 0
sim_btwn_data_1_2 = sim_btwn_data_1_2 + (np.random.rand(
len(sim_btwn_data_1_2), len(sim_btwn_data_1_2[1, :]))) / 100
sim_btwn_data_1_2[sim_btwn_data_1_2 > 1] = 1
sum(sum(sim_btwn_data_1_2 == np.inf))
sum(sum(sim_btwn_data_1_2 == np.nan))
model = SpectralCoclustering(n_clusters=5, random_state=0, n_init=100)
model.fit(sim_btwn_data_1_2)
fit_data = sim_btwn_data_1_2[np.argsort(model.row_labels_)]
fit_data = fit_data[:, np.argsort(model.column_labels_)]
plt.matshow(fit_data, cmap=plt.cm.Blues)
plt.title("After biclustering; rearranged to show biclusters")
plt.show()
#SIMULATION DATA
import numpy as np
from matplotlib import pyplot as plt
from sklearn.datasets import make_biclusters
from sklearn.datasets import samples_generator as sg
from sklearn.cluster.bicluster import SpectralCoclustering
from sklearn.metrics import consensus_score
#Creating Simulated Data
data, rows, columns = make_biclusters(shape=(300, 100),
n_clusters=5,
noise=5,
shuffle=False,
random_state=0)
plt.matshow(data, cmap=plt.cm.Blues)
plt.title("Original dataset")
data, row_idx, col_idx = sg._shuffle(data, random_state=0)
plt.matshow(data, cmap=plt.cm.Blues)
plt.title("Shuffled dataset")
#Creating Model
model = SpectralCoclustering(n_clusters=5, random_state=0)
model.fit(data)
score = consensus_score(model.biclusters_,
(rows[:, row_idx], columns[:, col_idx]))
print("consensus score: {:.3f}".format(score))
fit_data = data[np.argsort(model.row_labels_)]
fit_data = fit_data[:, np.argsort(model.column_labels_)]
plt.matshow(fit_data, cmap=plt.cm.Blues)
plt.title("After biclustering; rearranged to show biclusters")
plt.show()
####################################################################
####################################################################
from sklearn import cluster
import scipy as sp
import time
from sklearn import cluster, datasets
import numpy as np
from matplotlib import pyplot as plt
from sklearn.datasets import make_biclusters
from sklearn.datasets import samples_generator as sg
from sklearn.cluster.bicluster import SpectralCoclustering
from sklearn.metrics import consensus_score
data1 = generate_simple_blobs(27)
data2 = generate_simple_blobs(27)
data2 = data2[0:150, :]
print("Calculating Cross-clustering")
print("Calculating pairwise distances between areas")
dist_btwn_data_1_2 = np.array(
sp.spatial.distance.cdist(roi1data, roi2data, metric='correlation'))
sim_btwn_data_1_2 = 1 - dist_btwn_data_1_2
sim_btwn_data_1_2[sim_btwn_data_1_2 < 0] = 0
co_cluster = cluster.SpectralCoclustering()
co_cluster.fit(sim_btwn_data_1_2)
score = consensus_score(co_cluster.biclusters_,
(rows[:, row_idx], columns[:, col_idx]))
print("consensus score: {:.3f}".format(score))
fit_data = data[np.argsort(co_cluster.row_labels_)]
fit_data = fit_data[:, np.argsort(co_cluster.column_labels_)]
plt.matshow(fit_data, cmap=plt.cm.Blues)
plt.title("After biclustering; rearranged to show biclusters")
plt.show()
