def fit(self, X, y=None, features=None):
"""
Constructs DAG according to `self.dag_method`.
Parameters
----------
X: `numpy.ndarray` or `scipy.sparse.csr_matrix`
Matrix with rows corresponding to all of the samples that
define the DAG and columns corresponding to features.
y
Ignored
features: `numpy.ndarray` of `str`
A list of strings with feature labels.
"""
if features is None:
self.features = np.array(range(X.shape[1]))
if self.reduce_dim is not None:
if issubclass(type(self.reduce_dim), np.ndarray):
X_ = self.reduce_dim
elif isinstance(self.reduce_dim, int):
X_ = reduce_dimensionality(X, dim_red_k=self.reduce_dim)
else:
raise ValueError('`reduce_dim` has invalid type {}'.format(
type(self.reduce_dim)))
else:
X_ = X
X_ = self.check_and_sketch(X_)
if self.verbose:
tprint('Constructing DAG...')
if self.dag_method == 'agg_ward':
from sklearn.cluster.hierarchical import ward_tree
ret = ward_tree(X_, n_clusters=None, return_distance=True)
children, n_components, n_leaves, parent, distances = ret
assert (n_components == 1)
self.create_dag_agg(children, X_.shape[0])
elif self.dag_method == 'louvain':
self.create_dag_louvain(X_)
else:
raise ValueError('Invalid DAG construction method {}'.format(
self.dag_method))
if len(self.sample_idx) != X.shape[0]:
warnings.warn(
'Some samples have been orphaned during '
'DAG construction, {} orphans detected'.format(
X.shape[0] - len(self.sample_idx)), RuntimeWarning)
return self
def cluster(clusterType, vectors, y):
if (clusterType == "KMeans"):
kclusterer = KMeansClusterer(
NUM_CLUSTERS,
distance=nltk.cluster.util.cosine_distance,
repeats=25)
assigned_clusters = kclusterer.cluster(vectors, assign_clusters=True)
elif (clusterType == "GMM"):
GMM = GaussianMixture(n_components=NUM_CLUSTERS)
assigned_clusters = GMM.fit_predict(vectors)
elif (clusterType == "SVM"):
classifier = SVC(kernel='rbf', gamma='auto', random_state=0)
#cross-validation
assigned_clusters = cross_validation(classifier, vectors, y)
elif (clusterType == "T2VH"):
ret = hierarchical.ward_tree(vectors, n_clusters=NUM_CLUSTERS)
children = ret[0]
n_leaves = ret[2]
assigned_clusters = hierarchical._hc_cut(NUM_CLUSTERS, children,
n_leaves)
elif (clusterType == "RandomForest"):
classifier = RandomForestClassifier()
#cross-validation
assigned_clusters = cross_validation(classifier, vectors, y)
# classifier.fit(vectors, y)
# assigned_clusters=classifier.predict(vectors)
elif (clusterType == "DecisionTree"):
classifier = DecisionTreeClassifier()
#cross-validation
assigned_clusters = cross_validation(classifier, vectors, y)
# classifier.fit(vectors, y)
# assigned_clusters=classifier.predict(vectors)
elif (clusterType == "LogisticRegression"):
classifier = sklearn.linear_model.LogisticRegression()
#cross-validation
assigned_clusters = cross_validation(classifier, vectors, y)
# classifier.fit(vectors, y)
# assigned_clusters=classifier.predict(vectors)
else:
print(clusterType, " is not a predefined cluster type.")
return
return assigned_clusters
def compute_stability_fold(samples, train, test, method='ward',
max_k=None, stack=False,
stability=True, cv_likelihood=False,
corr_score=None,
ground_truth=None, n_neighbors=1, **kwargs):
"""
General function to compute the stability on a cross-validation fold.
Parameters:
-----------
samples : list of arrays
List of arrays containing the samples to cluster, each
array has shape (n_samples, n_features) in PyMVPA terminology.
We are clustering the features, i.e., the nodes.
train : list or array
Indices for the training set.
test : list or array
Indices for the test set.
method : {'complete', 'gmm', 'kmeans', 'ward'}
Clustering method to use. Default is 'ward'.
max_k : int or None
Maximum k to compute the stability testing, starting from 2. By
default it will compute up to the maximum possible k, i.e.,
the number of points.
stack : bool
Whether to stack or average the datasets. Default is False,
meaning that the datasets are averaged by default.
stability : bool
Whether to compute the stability measure described in Lange et
al., 2004. Default is True.
cv_likelihood : bool
Whether to compute the cross-validated likelihood for mixture
model; only valid if 'gmm' method is used. Default is False.
corr_score : {'pearson','spearman'} or None
Whether to compute the specified type of correlation score.
Default is None.
ground_truth : array or None
Array containing the ground truth of the clustering of the data,
useful to compare stability against ground truth for simulations.
n_neighbors : int
Number of neighbors to use to predict clustering solution on
test set using K-nearest neighbors. Currently used only for
methods `complete` and `ward`. Default is 1.
kwargs : optional
Keyword arguments being passed to the clustering method (only for
'ward' and 'gmm').
Returns:
--------
ks : array
A (max_k-1,) array, where ks[i] is the `k` of the clustering
solution for iteration `i`.
ari : array
A (max_k-1,) array, where ari[i] is the Adjusted Rand Index of the
predicted clustering solution on the test set and the actual
clustering solution of the test set for `k` of ks[i].
ami : array
A (max_k-1,) array, where ari[i] is the Adjusted Mutual
Information of the predicted clustering solution on the test set
and the actual clustering solution of the test set for
`k` of ks[i].
stab : array or None
A (max_k-1,) array, where stab[i] is the stability measure
described in Lange et al., 2004 for `k` of ks[i]. Note that this
measure is the un-normalized one. It will be normalized later in
the process.
likelihood : array or None
If method is 'gmm' and cv_likelihood is True, a
(max_k-1,) array, where likelihood[i] is the cross-validated
likelihood of the GMM clustering solution for `k` of ks[i].
Otherwise returns None.
ari_gt : array or None
If ground_truth is not None, a (max_k-1,) array, where ari_gt[i]
is the Adjusted Rand Index of the predicted clustering solution on
the test set for `k` of ks[i] and the ground truth clusters of the
data.
Otherwise returns None.
ami_gt : array or None
If ground_truth is not None, a (max_k-1,) array, where ami_gt[i]
is the Adjusted Mutual Information of the predicted clustering
solution on the test set for `k` of ks[i] and the ground truth
clusters of the data.
Otherwise returns None.
stab_gt : array or None
If ground_truth is not None, a (max_k-1,) array, where stab_gt[i]
is the stability measure of the predicted clustering
solution on the test set for `k` of ks[i] and the ground truth
clusters of the data.
Otherwise returns None.
corr : array or None
Average correlation for each fold. TODO
corr_gt : array or None
Avg correlation against GT. TODO
"""
if method not in AVAILABLE_METHODS:
raise ValueError('Method {0} not implemented'.format(method))
if cv_likelihood and method != 'gmm':
raise ValueError(
"Cross-validated likelihood is only available for 'gmm' method")
# if max_k is None, set max_k to maximum value
if not max_k:
max_k = samples[0].shape[1]
# preallocate arrays for results
ks = np.zeros(max_k-1, dtype=int)
ari = np.zeros(max_k-1)
ami = np.zeros(max_k-1)
if stability:
stab = np.zeros(max_k-1)
if cv_likelihood:
likelihood = np.zeros(max_k-1)
if corr_score is not None:
corr = np.zeros(max_k-1)
if ground_truth is not None:
ari_gt = np.zeros(max_k-1)
ami_gt = np.zeros(max_k-1)
if stability:
stab_gt = np.zeros(max_k-1)
if corr_score is not None:
corr_gt = np.zeros(max_k-1)
# get training and test
train_set = [samples[x] for x in train]
test_set = [samples[x] for x in test]
if stack:
train_ds = np.vstack(train_set)
test_ds = np.vstack(test_set)
else:
train_ds = np.mean(np.dstack(train_set), axis=2)
test_ds = np.mean(np.dstack(test_set), axis=2)
# compute clustering on training set
if method == 'complete':
train_ds_dist = pdist(train_ds.T, metric='correlation')
test_ds_dist = pdist(test_ds.T, metric='correlation')
# I'm computing the full tree and then cutting
# afterwards to speed computation
Y_train = complete(train_ds_dist)
# same on testing set
Y_test = complete(test_ds_dist)
elif method == 'ward':
(children_train, n_comp_train,
n_leaves_train, parents_train) = ward_tree(train_ds.T, **kwargs)
# same on testing set
(children_test, n_comp_test,
n_leaves_test, parents_test) = ward_tree(test_ds.T, **kwargs)
elif method == 'gmm' or method == 'kmeans':
pass # we'll have to run it for each k
else:
raise ValueError("We shouldn't get here")
for i_k, k in enumerate(range(2, max_k+1)):
if method == 'complete':
# cut the tree with right K for both train and test
train_label = cut_tree_scipy(Y_train, k)
test_label = cut_tree_scipy(Y_test, k)
# train a classifier on this clustering
knn = KNeighborsClassifier(#algorithm='brute',
# metric='correlation',
n_neighbors=n_neighbors)
knn.fit(train_ds.T, train_label)
# predict the clusters in the test set
prediction_label = knn.predict(test_ds.T)
elif method == 'ward':
# cut the tree with right K for both train and test
train_label = _hc_cut(k, children_train, n_leaves_train)
test_label = _hc_cut(k, children_test, n_leaves_test)
# train a classifier on this clustering
knn = KNeighborsClassifier(n_neighbors=n_neighbors)
knn.fit(train_ds.T, train_label)
# predict the clusters in the test set
prediction_label = knn.predict(test_ds.T)
elif method == 'gmm':
gmm = GMM(n_components=k, **kwargs)
# fit on train and predict test
gmm.fit(train_ds.T)
prediction_label = gmm.predict(test_ds.T)
if cv_likelihood:
log_prob = np.sum(gmm.score(test_ds.T))
# fit on test and get labels
gmm.fit(test_ds.T)
test_label = gmm.predict(test_ds.T)
elif method == 'kmeans':
kmeans = KMeans(n_clusters=k)
# fit on train and predict test
kmeans.fit(train_ds.T)
prediction_label = kmeans.predict(test_ds.T)
# fit on test and get labels
kmeans.fit(test_ds.T)
test_label = kmeans.predict(test_ds.T)
else:
raise ValueError("We shouldn't get here")
# append results
ks[i_k] = k
ari[i_k] = adjusted_rand_score(prediction_label, test_label)
ami[i_k] = adjusted_mutual_info_score(prediction_label, test_label)
if stability:
stab[i_k] = stability_score(prediction_label, test_label, k)
if cv_likelihood:
likelihood[i_k] = log_prob
if corr_score is not None:
corr[i_k] = correlation_score(prediction_label, test_label,
test_ds, corr_score)
if ground_truth is not None:
ari_gt[i_k] = adjusted_rand_score(prediction_label, ground_truth)
ami_gt[i_k] = adjusted_mutual_info_score(prediction_label,
ground_truth)
if stability:
stab_gt[i_k] = stability_score(prediction_label,
ground_truth, k)
if corr_score is not None:
corr_gt[i_k] = correlation_score(prediction_label,
ground_truth,
test_ds, corr_score)
results = [ks, ari, ami]
if stability:
results.append(stab)
else:
results.append(None)
if cv_likelihood:
results.append(likelihood)
else:
results.append(None)
if ground_truth is not None:
results += [ari_gt, ami_gt]
else:
results += [None, None]
if stability and ground_truth is not None:
results.append(stab_gt)
else:
results.append(None)
if corr_score is not None:
results.append(corr)
else:
results.append(None)
if corr_score is not None and ground_truth is not None:
results.append(corr_gt)
else:
results.append(None)
return results
#a = a[order]
#b = b[order]
#height = height[order]
if 1:
import pylab as pl
children = np.c_[a, b].astype(np.int)
from sklearn.cluster.hierarchical import _hc_cut, ward_tree
labels = _hc_cut(n_clusters=4, children=children, n_leaves=N)
pl.figure(1)
pl.clf()
pl.scatter(X[:, 0], X[:, 1], c=labels, cmap=pl.cm.spectral)
pl.title('Complete linkage')
if 1:
from scipy.cluster import hierarchy
children_s = hierarchy.complete(X)[:, :2].astype(np.int)
labels_s = _hc_cut(n_clusters=4, children=children_s, n_leaves=N)
import pylab as pl
pl.figure(0)
pl.clf()
pl.scatter(X[:, 0], X[:, 1], c=labels_s, cmap=pl.cm.spectral)
pl.title('Complete linkage (scipy)')
if 0:
pl.figure(2)
pl.clf()
children_w, _, _ = ward_tree(X)
labels_w = _hc_cut(n_clusters=4, children=children_w, n_leaves=N)
pl.scatter(X[:, 0], X[:, 1], c=labels_w, cmap=pl.cm.spectral)
pl.title('Ward')
pl.show()
