def MiniBach_SparcePCA(self,N_component):
MiniPCA_calculator = skdecomp.MiniBatchSparsePCA(N_component,batch_size=15,normalize_components=True)
self.MiniPCs = MiniPCA_calculator.fit(self.vector_centered)
all_MiniPCs = self.MiniPCs.components_
pp.save_variable(all_MiniPCs,save_folder+r'\\MiniPCed_Data.pkl')
print('MiniBach Sparce PCA done, generating graphs')
self.cell_graph_plot('MINIPCA',all_MiniPCs)
def MiniBatchSparsePCA(self, source):
min_max_scaler = preprocessing.MinMaxScaler()
data_source = min_max_scaler.fit_transform(source)
pca = decomposition.MiniBatchSparsePCA(n_components=2)
#没有相关参数------------------------
result = {}
result['data'] = pca.fit_transform(data_source)
result['params'] = 0
return result
def gen_estimators():
'''
List of the different estimators, whether to center and transpose the problem, and whether the transformer uses the clustering API.
'''
rng = RandomState(0)
estimators = [
('Eigenfaces - RandomizedPCA',
decomposition.RandomizedPCA(n_components=n_components,
whiten=True), True),
('Non-negative components - NMF tol=1e-4',
decomposition.NMF(n_components=n_components,
init='nndsvda',
tol=1e-4,
solver='cd'), False),
('Non-negative components - NMF tol=1e-6',
decomposition.NMF(
n_components=n_components,
init='nndsvd',
), False),
('Independent components - FastICA',
decomposition.FastICA(n_components=n_components, whiten=True), True),
('Sparse comp. - MiniBatchSparsePCA',
decomposition.MiniBatchSparsePCA(n_components=n_components,
alpha=0.8,
n_iter=100,
batch_size=3,
random_state=rng), True),
('MiniBatchDictionaryLearning',
decomposition.MiniBatchDictionaryLearning(n_components=15,
alpha=0.1,
n_iter=50,
batch_size=3,
random_state=rng), True),
('Cluster centers - MiniBatchKMeans',
MiniBatchKMeans(n_clusters=n_components,
tol=1e-3,
batch_size=20,
max_iter=50,
random_state=rng), True),
('Factor Analysis components - FA',
decomposition.FactorAnalysis(n_components=n_components,
max_iter=2), True),
]
return estimators
# List of the different estimators, whether to center and transpose the
# problem, and whether the transformer uses the clustering API.
estimators = [
('Eigenfaces - PCA using randomized SVD',
decomposition.PCA(n_components=n_components,
svd_solver='randomized',
whiten=True), True),
('Non-negative components - NMF',
decomposition.NMF(n_components=n_components, init='nndsvda',
tol=5e-3), False),
('Independent components - FastICA',
decomposition.FastICA(n_components=n_components, whiten=True), True),
('Sparse comp. - MiniBatchSparsePCA',
decomposition.MiniBatchSparsePCA(n_components=n_components,
alpha=0.8,
n_iter=100,
batch_size=3,
random_state=rng), True),
('MiniBatchDictionaryLearning',
decomposition.MiniBatchDictionaryLearning(n_components=15,
alpha=0.1,
n_iter=50,
batch_size=3,
random_state=rng), True),
('Cluster centers - MiniBatchKMeans',
MiniBatchKMeans(n_clusters=n_components,
tol=1e-3,
batch_size=20,
max_iter=50,
random_state=rng), True),
('Factor Analysis components - FA',
from sklearn import decomposition
import numpy as np
import matplotlib.pyplot as plt
data = np.loadtxt("../Dataset/data.txt", delimiter=';')
target = np.loadtxt("../Dataset/target.txt", delimiter=';')
data_pre = np.loadtxt("../Dataset/data_pre.txt", delimiter=';')
#sentiment = svm.SVC(kernel="rbf", gamma=0.001, C=1000)
sentiment_bay_m = MultinomialNB()
sentiment_bay_g = GaussianNB()
sentiment_bay_b = BernoulliNB()
sentiment_dec = tree.DecisionTreeClassifier()
pca = decomposition.MiniBatchSparsePCA(n_components=20)
pca.fit_transform(data)
accuracy = np.mean(cross_validation.cross_val_score(sentiment, data, target))
print accuracy
'''
accuracy_pre = np.mean(cross_validation.cross_val_score(sentiment,data_pre,target))
accuracy_bay_m = np.mean(cross_validation.cross_val_score(sentiment_bay_m,data,target))
accuracy_bay_pre_m = np.mean(cross_validation.cross_val_score(sentiment_bay_m,data_pre,target))
accuracy_bay_g = np.mean(cross_validation.cross_val_score(sentiment_bay_g,data,target))
accuracy_bay_pre_g = np.mean(cross_validation.cross_val_score(sentiment_bay_g,data_pre,target))
accuracy_bay_b = np.mean(cross_validation.cross_val_score(sentiment_bay_b,data,target))
accuracy_bay_pre_b = np.mean(cross_validation.cross_val_score(sentiment_bay_b,data_pre,target))
print accuracy,accuracy_pre,accuracy_bay_m,accuracy_bay_pre_m,accuracy_bay_g,accuracy_bay_pre_g,accuracy_bay_b,accuracy_bay_pre_b
'''
def _eval_search_params(params_builder):
search_params = {}
for p in params_builder['param_set']:
search_list = p['sp_list'].strip()
if search_list == '':
continue
param_name = p['sp_name']
if param_name.lower().endswith(NON_SEARCHABLE):
print("Warning: `%s` is not eligible for search and was "
"omitted!" % param_name)
continue
if not search_list.startswith(':'):
safe_eval = SafeEval(load_scipy=True, load_numpy=True)
ev = safe_eval(search_list)
search_params[param_name] = ev
else:
# Have `:` before search list, asks for estimator evaluatio
safe_eval_es = SafeEval(load_estimators=True)
search_list = search_list[1:].strip()
# TODO maybe add regular express check
ev = safe_eval_es(search_list)
preprocessings = (
preprocessing.StandardScaler(), preprocessing.Binarizer(),
preprocessing.MaxAbsScaler(), preprocessing.Normalizer(),
preprocessing.MinMaxScaler(),
preprocessing.PolynomialFeatures(),
preprocessing.RobustScaler(), feature_selection.SelectKBest(),
feature_selection.GenericUnivariateSelect(),
feature_selection.SelectPercentile(),
feature_selection.SelectFpr(), feature_selection.SelectFdr(),
feature_selection.SelectFwe(),
feature_selection.VarianceThreshold(),
decomposition.FactorAnalysis(random_state=0),
decomposition.FastICA(random_state=0),
decomposition.IncrementalPCA(),
decomposition.KernelPCA(random_state=0, n_jobs=N_JOBS),
decomposition.LatentDirichletAllocation(random_state=0,
n_jobs=N_JOBS),
decomposition.MiniBatchDictionaryLearning(random_state=0,
n_jobs=N_JOBS),
decomposition.MiniBatchSparsePCA(random_state=0,
n_jobs=N_JOBS),
decomposition.NMF(random_state=0),
decomposition.PCA(random_state=0),
decomposition.SparsePCA(random_state=0, n_jobs=N_JOBS),
decomposition.TruncatedSVD(random_state=0),
kernel_approximation.Nystroem(random_state=0),
kernel_approximation.RBFSampler(random_state=0),
kernel_approximation.AdditiveChi2Sampler(),
kernel_approximation.SkewedChi2Sampler(random_state=0),
cluster.FeatureAgglomeration(),
skrebate.ReliefF(n_jobs=N_JOBS), skrebate.SURF(n_jobs=N_JOBS),
skrebate.SURFstar(n_jobs=N_JOBS),
skrebate.MultiSURF(n_jobs=N_JOBS),
skrebate.MultiSURFstar(n_jobs=N_JOBS),
imblearn.under_sampling.ClusterCentroids(random_state=0,
n_jobs=N_JOBS),
imblearn.under_sampling.CondensedNearestNeighbour(
random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.EditedNearestNeighbours(random_state=0,
n_jobs=N_JOBS),
imblearn.under_sampling.RepeatedEditedNearestNeighbours(
random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.AllKNN(random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.InstanceHardnessThreshold(
random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.NearMiss(random_state=0,
n_jobs=N_JOBS),
imblearn.under_sampling.NeighbourhoodCleaningRule(
random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.OneSidedSelection(random_state=0,
n_jobs=N_JOBS),
imblearn.under_sampling.RandomUnderSampler(random_state=0),
imblearn.under_sampling.TomekLinks(random_state=0,
n_jobs=N_JOBS),
imblearn.over_sampling.ADASYN(random_state=0, n_jobs=N_JOBS),
imblearn.over_sampling.RandomOverSampler(random_state=0),
imblearn.over_sampling.SMOTE(random_state=0, n_jobs=N_JOBS),
imblearn.over_sampling.SVMSMOTE(random_state=0, n_jobs=N_JOBS),
imblearn.over_sampling.BorderlineSMOTE(random_state=0,
n_jobs=N_JOBS),
imblearn.over_sampling.SMOTENC(categorical_features=[],
random_state=0,
n_jobs=N_JOBS),
imblearn.combine.SMOTEENN(random_state=0),
imblearn.combine.SMOTETomek(random_state=0))
newlist = []
for obj in ev:
if obj is None:
newlist.append(None)
elif obj == 'all_0':
newlist.extend(preprocessings[0:35])
elif obj == 'sk_prep_all': # no KernalCenter()
newlist.extend(preprocessings[0:7])
elif obj == 'fs_all':
newlist.extend(preprocessings[7:14])
elif obj == 'decomp_all':
newlist.extend(preprocessings[14:25])
elif obj == 'k_appr_all':
newlist.extend(preprocessings[25:29])
elif obj == 'reb_all':
newlist.extend(preprocessings[30:35])
elif obj == 'imb_all':
newlist.extend(preprocessings[35:54])
elif type(obj) is int and -1 < obj < len(preprocessings):
newlist.append(preprocessings[obj])
elif hasattr(obj, 'get_params'): # user uploaded object
if 'n_jobs' in obj.get_params():
newlist.append(obj.set_params(n_jobs=N_JOBS))
else:
newlist.append(obj)
else:
sys.exit("Unsupported estimator type: %r" % (obj))
search_params[param_name] = newlist
return search_params
def __init__(self, source):
min_max_scaler = preprocessing.MinMaxScaler()
data_source = min_max_scaler.fit_transform(source)
pca = decomposition.MiniBatchSparsePCA(n_components=2)
self.return_data = pca.fit_transform(data_source)
('Eigenfaces - RandomizedPCA',
decomposition.RandomizedPCA(n_components=n_components,
whiten=True), True, False),
('Non-negative components - NMF',
decomposition.NMF(n_components=n_components,
init='nndsvda',
beta=5.0,
tol=5e-3,
sparseness='components'), False, False),
('Independent components - FastICA',
decomposition.FastICA(n_components=n_components, whiten=True,
max_iter=10), True, True),
('Sparse comp. - MiniBatchSparsePCA',
decomposition.MiniBatchSparsePCA(n_components=n_components,
alpha=1e-3,
n_iter=100,
chunk_size=3,
random_state=rng), True, False),
('MiniBatchDictionaryLearning',
decomposition.MiniBatchDictionaryLearning(n_atoms=15,
alpha=5e-3,
n_iter=50,
chunk_size=3,
random_state=rng), True, False),
('Cluster centers - MiniBatchKMeans',
MiniBatchKMeans(k=n_components,
tol=1e-3,
chunk_size=20,
max_iter=50,
random_state=rng), True, False)
]
def get_search_params(params_builder):
search_params = {}
safe_eval = SafeEval(load_scipy=True, load_numpy=True)
safe_eval_es = SafeEval(load_estimators=True)
for p in params_builder['param_set']:
search_p = p['search_param_selector']['search_p']
if search_p.strip() == '':
continue
param_type = p['search_param_selector']['selected_param_type']
lst = search_p.split(':')
assert (
len(lst) == 2
), "Error, make sure there is one and only one colon in search parameter input."
literal = lst[1].strip()
param_name = lst[0].strip()
if param_name:
if param_name.lower() == 'n_jobs':
sys.exit("Parameter `%s` is invalid for search." % param_name)
elif not param_name.endswith('-'):
ev = safe_eval(literal)
if param_type == 'final_estimator_p':
search_params['estimator__' + param_name] = ev
else:
search_params['preprocessing_' + param_type[5:6] + '__' +
param_name] = ev
else:
# only for estimator eval, add `-` to the end of param
#TODO maybe add regular express check
ev = safe_eval_es(literal)
for obj in ev:
if 'n_jobs' in obj.get_params():
obj.set_params(n_jobs=N_JOBS)
if param_type == 'final_estimator_p':
search_params['estimator__' + param_name[:-1]] = ev
else:
search_params['preprocessing_' + param_type[5:6] + '__' +
param_name[:-1]] = ev
elif param_type != 'final_estimator_p':
#TODO regular express check ?
ev = safe_eval_es(literal)
preprocessors = [
preprocessing.StandardScaler(),
preprocessing.Binarizer(),
preprocessing.Imputer(),
preprocessing.MaxAbsScaler(),
preprocessing.Normalizer(),
preprocessing.MinMaxScaler(),
preprocessing.PolynomialFeatures(),
preprocessing.RobustScaler(),
feature_selection.SelectKBest(),
feature_selection.GenericUnivariateSelect(),
feature_selection.SelectPercentile(),
feature_selection.SelectFpr(),
feature_selection.SelectFdr(),
feature_selection.SelectFwe(),
feature_selection.VarianceThreshold(),
decomposition.FactorAnalysis(random_state=0),
decomposition.FastICA(random_state=0),
decomposition.IncrementalPCA(),
decomposition.KernelPCA(random_state=0, n_jobs=N_JOBS),
decomposition.LatentDirichletAllocation(random_state=0,
n_jobs=N_JOBS),
decomposition.MiniBatchDictionaryLearning(random_state=0,
n_jobs=N_JOBS),
decomposition.MiniBatchSparsePCA(random_state=0,
n_jobs=N_JOBS),
decomposition.NMF(random_state=0),
decomposition.PCA(random_state=0),
decomposition.SparsePCA(random_state=0, n_jobs=N_JOBS),
decomposition.TruncatedSVD(random_state=0),
kernel_approximation.Nystroem(random_state=0),
kernel_approximation.RBFSampler(random_state=0),
kernel_approximation.AdditiveChi2Sampler(),
kernel_approximation.SkewedChi2Sampler(random_state=0),
cluster.FeatureAgglomeration(),
skrebate.ReliefF(n_jobs=N_JOBS),
skrebate.SURF(n_jobs=N_JOBS),
skrebate.SURFstar(n_jobs=N_JOBS),
skrebate.MultiSURF(n_jobs=N_JOBS),
skrebate.MultiSURFstar(n_jobs=N_JOBS),
imblearn.under_sampling.ClusterCentroids(random_state=0,
n_jobs=N_JOBS),
imblearn.under_sampling.CondensedNearestNeighbour(
random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.EditedNearestNeighbours(random_state=0,
n_jobs=N_JOBS),
imblearn.under_sampling.RepeatedEditedNearestNeighbours(
random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.AllKNN(random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.InstanceHardnessThreshold(
random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.NearMiss(random_state=0,
n_jobs=N_JOBS),
imblearn.under_sampling.NeighbourhoodCleaningRule(
random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.OneSidedSelection(random_state=0,
n_jobs=N_JOBS),
imblearn.under_sampling.RandomUnderSampler(random_state=0),
imblearn.under_sampling.TomekLinks(random_state=0,
n_jobs=N_JOBS),
imblearn.over_sampling.ADASYN(random_state=0, n_jobs=N_JOBS),
imblearn.over_sampling.RandomOverSampler(random_state=0),
imblearn.over_sampling.SMOTE(random_state=0, n_jobs=N_JOBS),
imblearn.over_sampling.SVMSMOTE(random_state=0, n_jobs=N_JOBS),
imblearn.over_sampling.BorderlineSMOTE(random_state=0,
n_jobs=N_JOBS),
imblearn.over_sampling.SMOTENC(categorical_features=[],
random_state=0,
n_jobs=N_JOBS),
imblearn.combine.SMOTEENN(random_state=0),
imblearn.combine.SMOTETomek(random_state=0)
]
newlist = []
for obj in ev:
if obj is None:
newlist.append(None)
elif obj == 'all_0':
newlist.extend(preprocessors[0:36])
elif obj == 'sk_prep_all': # no KernalCenter()
newlist.extend(preprocessors[0:8])
elif obj == 'fs_all':
newlist.extend(preprocessors[8:15])
elif obj == 'decomp_all':
newlist.extend(preprocessors[15:26])
elif obj == 'k_appr_all':
newlist.extend(preprocessors[26:30])
elif obj == 'reb_all':
newlist.extend(preprocessors[31:36])
elif obj == 'imb_all':
newlist.extend(preprocessors[36:55])
elif type(obj) is int and -1 < obj < len(preprocessors):
newlist.append(preprocessors[obj])
elif hasattr(obj, 'get_params'): # user object
if 'n_jobs' in obj.get_params():
newlist.append(obj.set_params(n_jobs=N_JOBS))
else:
newlist.append(obj)
else:
sys.exit("Unsupported preprocessor type: %r" % (obj))
search_params['preprocessing_' + param_type[5:6]] = newlist
else:
sys.exit("Parameter name of the final estimator can't be skipped!")
return search_params
def main():
dataset = fetch_olivetti_faces(shuffle=True, random_state=rng)
faces = dataset.data
n_samples, n_features = faces.shape
# global centering
faces_centered = faces - faces.mean(axis=0)
# local centering
faces_centered -= faces_centered.mean(axis=1).reshape(n_samples, -1)
print("Dataset consists of %d faces" % n_samples)
estimators = [
('Eigenfaces - PCA using randomized SVD',
decomposition.PCA(n_components=n_components,
svd_solver='randomized',
whiten=True), True),
('Non-negative components - NMF',
decomposition.NMF(n_components=n_components, init='nndsvda',
tol=5e-3), False),
('Independent components - FastICA',
decomposition.FastICA(n_components=n_components, whiten=True), True),
('Sparse comp. - MiniBatchSparsePCA',
decomposition.MiniBatchSparsePCA(n_components=n_components,
alpha=0.8,
n_iter=100,
batch_size=3,
random_state=rng), True),
('MiniBatchDictionaryLearning',
decomposition.MiniBatchDictionaryLearning(n_components=15,
alpha=0.1,
n_iter=50,
batch_size=3,
random_state=rng), True),
('Cluster centers - MiniBatchKMeans',
MiniBatchKMeans(n_clusters=n_components,
tol=1e-3,
batch_size=20,
max_iter=50,
random_state=rng), True),
('Factor Analysis components - FA',
decomposition.FactorAnalysis(n_components=n_components,
max_iter=2), True),
]
plot_gallery("First centered Olivetti faces",
faces_centered[:n_components])
for name, estimator, center in estimators:
print("Extracting the top %d %s..." % (n_components, name))
t0 = time()
data = faces
if center:
data = faces_centered
estimator.fit(data)
train_time = (time() - t0)
print("done in %0.3fs" % train_time)
if hasattr(estimator, 'cluster_centers_'):
components_ = estimator.cluster_centers_
else:
components_ = estimator.components_
# so we skip it.
if (hasattr(estimator, 'noise_variance_')
and estimator.noise_variance_.ndim >
0): # Skip the Eigenfaces case
plot_gallery("Pixelwise variance",
estimator.noise_variance_.reshape(1, -1),
n_col=1,
n_row=1)
plot_gallery('%s - Train time %.1fs' % (name, train_time),
components_[:n_components])
plt.show()
def faces_decomposition():
import logging
from numpy.random import RandomState #随机数生成器种子，从高斯分布或者其他等分布产生
import matplotlib.pyplot as plt
from time import time
from sklearn.datasets import fetch_olivetti_faces
from sklearn.cluster import MiniBatchKMeans
from sklearn import decomposition
logging.basicConfig(level=logging.INFO,
format='%(asctime)s %(levelname)s %(message)s')
n_row, n_col = 2, 3
n_components = n_row * n_col
image_shape = (64, 64)
rng = RandomState(0)
#加载数据集
dataset = fetch_olivetti_faces(shuffle=True, random_state=rng)
faces = dataset.data
n_samples, n_features = faces.shape
faces_centered = faces - faces.mean(axis=0)
faces_centered -= faces_centered.mean(axis=1).reshape(n_samples, -1)
print("dataset consits of %d faces" % n_samples) #样本个数
def plot_gallery(title, images, n_col=n_col, n_row=n_row):
plt.figure(figsize=(2. * n_col, 2.26 * n_row))
plt.suptitle(title, size=16)
for i, comp in enumerate(images):
plt.subplot(n_row, n_col, i + 1)
vmax = max(comp.max(), -comp.min())
plt.imshow(comp.reshape(image_shape),
cmap=plt.cm.gray,
interpolation='nearest',
vmin=-vmax,
vmax=vmax)
plt.xticks(())
plt.yticks(())
plt.subplots_adjust(0.01, 0.05, 0.99, 0.93, 0.04, 0.)
estimators = [
('Eigenfaces - PCA using randomized SVD',
decomposition.PCA(n_components=n_components,
svd_solver='randomized',
whiten=True), True),
('Non-negative components - NMF',
decomposition.NMF(n_components=n_components, init='nndsvda',
tol=5e-3), False),
('Independent components - FastICA',
decomposition.FastICA(n_components=n_components, whiten=True), True),
('Sparse comp. - MiniBatchSparsePCA',
decomposition.MiniBatchSparsePCA(n_components=n_components,
alpha=0.8,
n_iter=100,
batch_size=3,
random_state=rng), True),
('MiniBatchDictionaryLearning',
decomposition.MiniBatchDictionaryLearning(n_components=15,
alpha=0.1,
n_iter=50,
batch_size=3,
random_state=rng), True),
('Cluster centers - MiniBatchKMeans',
MiniBatchKMeans(n_clusters=n_components,
tol=1e-3,
batch_size=20,
max_iter=50,
random_state=rng), True),
('Factor Analysis components - FA',
decomposition.FactorAnalysis(n_components=n_components,
max_iter=2), True),
]
# #############################################################################
# Plot a sample of the input data
plot_gallery("First centered Olivetti faces",
faces_centered[:n_components])
# #############################################################################
# Do the estimation and plot it
for name, estimator, center in estimators:
print("Extracting the top %d %s..." % (n_components, name))
t0 = time()
data = faces
if center:
data = faces_centered
estimator.fit(data)
train_time = (time() - t0)
print("done in %0.3fs" % train_time)
if hasattr(estimator, 'cluster_centers_'):
components_ = estimator.cluster_centers_
else:
components_ = estimator.components_
# Plot an image representing the pixelwise variance provided by the
# estimator e.g its noise_variance_ attribute. The Eigenfaces estimator,
# via the PCA decomposition, also provides a scalar noise_variance_
# (the mean of pixelwise variance) that cannot be displayed as an image
# so we skip it.
if (hasattr(estimator, 'noise_variance_')
and estimator.noise_variance_.ndim >
0): # Skip the Eigenfaces case
plot_gallery("Pixelwise variance",
estimator.noise_variance_.reshape(1, -1),
n_col=1,
n_row=1)
plot_gallery('%s - Train time %.1fs' % (name, train_time),
components_[:n_components])
plt.show()
def plot_faces_decomposition():
# Display progress logs on stdout
logging.basicConfig(level=logging.INFO,
format='%(asctime)s %(levelname)s %(message)s')
n_row, n_col = 2, 3
n_components = n_row * n_col
image_shape = (64, 64)
rng = RandomState(0)
# #############################################################################
# Load faces data
faces, _ = fetch_olivetti_faces(return_X_y=True, shuffle=True,
random_state=rng)
n_samples, n_features = faces.shape
# global centering
faces_centered = faces - faces.mean(axis=0)
# local centering
faces_centered -= faces_centered.mean(axis=1).reshape(n_samples, -1)
print("Dataset consists of %d faces" % n_samples)
def plot_gallery(title, images, n_col=n_col, n_row=n_row, cmap=plt.cm.gray):
plt.figure(figsize=(2. * n_col, 2.26 * n_row))
plt.suptitle(title, size=16)
for i, comp in enumerate(images):
plt.subplot(n_row, n_col, i + 1)
vmax = max(comp.max(), -comp.min())
plt.imshow(comp.reshape(image_shape), cmap=cmap,
interpolation='nearest',
vmin=-vmax, vmax=vmax)
plt.xticks(())
plt.yticks(())
plt.subplots_adjust(0.01, 0.05, 0.99, 0.93, 0.04, 0.)
# #############################################################################
# List of the different estimators, whether to center and transpose the
# problem, and whether the transformer uses the clustering API.
estimators = [
('Eigenfaces - PCA using randomized SVD',
decomposition.PCA(n_components=n_components, svd_solver='randomized',
whiten=True),
True),
('Non-negative components - NMF',
decomposition.NMF(n_components=n_components, init='nndsvda', tol=5e-3),
False),
('Independent components - FastICA',
decomposition.FastICA(n_components=n_components, whiten=True),
True),
('Sparse comp. - MiniBatchSparsePCA',
decomposition.MiniBatchSparsePCA(n_components=n_components, alpha=0.8,
n_iter=100, batch_size=3,
random_state=rng),
True),
('MiniBatchDictionaryLearning',
decomposition.MiniBatchDictionaryLearning(n_components=15, alpha=0.1,
n_iter=50, batch_size=3,
random_state=rng),
True),
('Cluster centers - MiniBatchKMeans',
MiniBatchKMeans(n_clusters=n_components, tol=1e-3, batch_size=20,
max_iter=50, random_state=rng),
True),
('Factor Analysis components - FA',
decomposition.FactorAnalysis(n_components=n_components, max_iter=20),
True),
]
# #############################################################################
# Plot a sample of the input data
plot_gallery("First centered Olivetti faces", faces_centered[:n_components])
# #############################################################################
# Do the estimation and plot it
for name, estimator, center in estimators:
print("Extracting the top %d %s..." % (n_components, name))
t0 = time()
data = faces
if center:
data = faces_centered
estimator.fit(data)
train_time = (time() - t0)
print("done in %0.3fs" % train_time)
if hasattr(estimator, 'cluster_centers_'):
components_ = estimator.cluster_centers_
else:
components_ = estimator.components_
# Plot an image representing the pixelwise variance provided by the
# estimator e.g its noise_variance_ attribute. The Eigenfaces estimator,
# via the PCA decomposition, also provides a scalar noise_variance_
# (the mean of pixelwise variance) that cannot be displayed as an image
# so we skip it.
if (hasattr(estimator, 'noise_variance_') and
estimator.noise_variance_.ndim > 0): # Skip the Eigenfaces case
plot_gallery("Pixelwise variance",
estimator.noise_variance_.reshape(1, -1), n_col=1,
n_row=1)
plot_gallery('%s - Train time %.1fs' % (name, train_time),
components_[:n_components])
plt.show()
# #############################################################################
# Various positivity constraints applied to dictionary learning.
estimators = [
('Dictionary learning',
decomposition.MiniBatchDictionaryLearning(n_components=15, alpha=0.1,
n_iter=50, batch_size=3,
random_state=rng),
True),
('Dictionary learning - positive dictionary',
decomposition.MiniBatchDictionaryLearning(n_components=15, alpha=0.1,
n_iter=50, batch_size=3,
random_state=rng,
positive_dict=True),
True),
('Dictionary learning - positive code',
decomposition.MiniBatchDictionaryLearning(n_components=15, alpha=0.1,
n_iter=50, batch_size=3,
fit_algorithm='cd',
random_state=rng,
positive_code=True),
True),
('Dictionary learning - positive dictionary & code',
decomposition.MiniBatchDictionaryLearning(n_components=15, alpha=0.1,
n_iter=50, batch_size=3,
fit_algorithm='cd',
random_state=rng,
positive_dict=True,
positive_code=True),
True),
]
# #############################################################################
# Plot a sample of the input data
plot_gallery("First centered Olivetti faces", faces_centered[:n_components],
cmap=plt.cm.RdBu)
# #############################################################################
# Do the estimation and plot it
for name, estimator, center in estimators:
print("Extracting the top %d %s..." % (n_components, name))
t0 = time()
data = faces
if center:
data = faces_centered
estimator.fit(data)
train_time = (time() - t0)
print("done in %0.3fs" % train_time)
components_ = estimator.components_
plot_gallery(name, components_[:n_components], cmap=plt.cm.RdBu)
plt.show()
ica_estimator.fit(faces_centered)
plot_gallery("Independent components - FastICA",
ica_estimator.components_[:n_components])
# %%
# Sparse components - MiniBatchSparsePCA
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
#
# Mini-batch sparse PCA (`MiniBatchSparsePCA`) extracts the set of sparse
# components that best reconstruct the data. This variant is faster but
# less accurate than the similar :py:mod:`sklearn.decomposition.SparsePCA`.
# %%
batch_pca_estimator = decomposition.MiniBatchSparsePCA(
n_components=n_components,
alpha=0.1,
n_iter=100,
batch_size=3,
random_state=rng)
batch_pca_estimator.fit(faces_centered)
plot_gallery(
"Sparse components - MiniBatchSparsePCA",
batch_pca_estimator.components_[:n_components],
)
# %%
# Dictionary learning
# ^^^^^^^^^^^^^^^^^^^
#
# By default, :class:`MiniBatchDictionaryLearning` divides the data into
# mini-batches and optimizes in an online manner by cycling over the
# mini-batches for the specified number of iterations.
