def spca(data, num_components=None, alpha=1):
# creates a matrix with sparse principal component analysis
# build matrix with all data
data = [d.flatten() for d in data if not any(isnan(d))]
datamatrix = row_stack(data)
# center data
cdata = datamatrix - mean(datamatrix, axis=0)
if num_components is None:
num_components = cdata.shape[0]
# do spca on matrix
spca = SparsePCA(n_components=num_components, alpha=alpha)
spca.fit(cdata)
# normalize components
components = spca.components_.T
for r in range(0, components.shape[1]):
compnorm = numpy.apply_along_axis(numpy.linalg.norm, 0, components[:,
r])
if not compnorm == 0:
components[:, r] /= compnorm
components = components.T
# calc adjusted explained variance from "Sparse Principal Component Analysis" by Zou, Hastie, Tibshirani
spca.components_ = components
#nuz = spca.transform(cdata).T
nuz = ridge_regression(spca.components_.T,
cdata.T,
0.01,
solver='dense_cholesky').T
#nuz = dot(components, cdata.T)
q, r = qr(nuz.T)
cumulative_var = []
for i in range(1, num_components + 1):
cumulative_var.append(trace(r[0:i, ] * r[0:i, ]))
explained_var = [math.sqrt(cumulative_var[0])]
for i in range(1, num_components):
explained_var.append(
math.sqrt(cumulative_var[i]) - math.sqrt(cumulative_var[i - 1]))
order = numpy.argsort(explained_var)[::-1]
components = numpy.take(components, order, axis=0)
evars = numpy.take(explained_var, order).tolist()
#evars = numpy.take(explained_var,order)
#order2 = [0,1,2,4,5,7,12,19]
#components = numpy.take(components,order2,axis=0)
#evars = numpy.take(evars,order2).tolist()
return components, evars
def spca(data, num_components=None, alpha=1): # creates a matrix with sparse principal component analysis # build matrix with all data data = [d.flatten() for d in data if not any(isnan(d))] datamatrix = row_stack(data) # center data cdata = datamatrix - mean(datamatrix, axis=0) if num_components is None: num_components = cdata.shape[0] # do spca on matrix spca = SparsePCA(n_components=num_components, alpha=alpha) spca.fit(cdata) # normalize components components = spca.components_.T for r in xrange(0,components.shape[1]): compnorm = numpy.apply_along_axis(numpy.linalg.norm, 0, components[:,r]) if not compnorm == 0: components[:,r] /= compnorm components = components.T # calc adjusted explained variance from "Sparse Principal Component Analysis" by Zou, Hastie, Tibshirani spca.components_ = components #nuz = spca.transform(cdata).T nuz = ridge_regression(spca.components_.T, cdata.T, 0.01, solver='dense_cholesky').T #nuz = dot(components, cdata.T) q,r = qr(nuz.T) cumulative_var = [] for i in range(1,num_components+1): cumulative_var.append(trace(r[0:i,]*r[0:i,])) explained_var = [math.sqrt(cumulative_var[0])] for i in range(1,num_components): explained_var.append(math.sqrt(cumulative_var[i])-math.sqrt(cumulative_var[i-1])) order = numpy.argsort(explained_var)[::-1] components = numpy.take(components,order,axis=0) evars = numpy.take(explained_var,order).tolist() #evars = numpy.take(explained_var,order) #order2 = [0,1,2,4,5,7,12,19] #components = numpy.take(components,order2,axis=0) #evars = numpy.take(evars,order2).tolist() return components, evars
def test_fit_transform_variance():
alpha = 1
rng = np.random.RandomState(0)
Y, _, _ = generate_toy_data(3, 10, (8, 8), random_state=rng) # wide array
spca_lars = SparsePCA(n_components=3, method='lars', alpha=alpha,
random_state=0, variance=True)
pca = PCA(n_components=3, random_state=0)
pca.fit(Y)
# no need to fit spca for this
spca_lars.fit(Y)
components = pca.components_
explained_variance = pca.explained_variance_
spca_lars.components_ = components
explained_variance_sparse = spca_lars.explained_variance_
assert_array_almost_equal(explained_variance, explained_variance_sparse)
