# Description: setting number of retained components and variance covered, using generalized eigenvectors
# Category: projection
# Uses: iris
# Referenced: orngPCA.htm
# Classes: orngPCA.PCA
import orange, orngPCA
data = orange.ExampleTable("iris.tab")
attributes = ['sepal length', 'sepal width', 'petal length', 'petal width']
pca = orngPCA.PCA(data,
standardize=True,
attributes=attributes,
maxNumberOfComponents=-1,
varianceCovered=1.0)
print "Retain all vectors and full variance:"
print pca
pca = orngPCA.PCA(data,
standardize=True,
maxNumberOfComponents=-1,
varianceCovered=1.0,
useGeneralizedVectors=1)
print "As above, only with generalized vectors:"
print pca
# Description: projecting data with trained PCA
# Category: projection
# Uses: iris
# Referenced: orngPCA.htm
# Classes: orngPCA.PCA
import orange, orngPCA
data = orange.ExampleTable("iris.tab")
attributes = ['sepal length', 'sepal width', 'petal length', 'petal width']
pca = orngPCA.PCA(data, attributes=attributes, standardize=True)
projected = pca(data)
print "Projection on first two components:"
for d in projected[:5]:
print d
# Description: PCA with attribute and row selection
# Category: projection
# Uses: iris
# Referenced: orngPCA.htm
# Classes: orngPCA.PCA
import orange, orngPCA
data = orange.ExampleTable("iris.tab")
pca = orngPCA.PCA(data, standardize=True)
print "PCA on all data:"
print pca
attributes = ['sepal length', 'sepal width', 'petal length', 'petal width']
pca = orngPCA.PCA(data, standardize=True, attributes=attributes)
print "PCA on attributes sepal.length, sepal.width, petal.length, petal.width:"
print pca
rows = [1, 0] * (len(data) / 2)
pca = orngPCA.PCA(data, standardize=True, rows=rows)
print "PCA on every second row:"
print pca
# Description: using your own imputer and continuizer in PCA
# Category: projection
# Uses: adult_sample
# Referenced: orngPCA.htm
# Classes: orngPCA.PCA
import orange, orngPCA
data = orange.ExampleTable("bridges.tab")
imputer = orange.ImputerConstructor_maximal
continuizer = orange.DomainContinuizer()
continuizer.multinomialTreatment = continuizer.AsNormalizedOrdinal
continuizer.classTreatment = continuizer.Ignore
continuizer.continuousTreatment = continuizer.Leave
pca = orngPCA.PCA(data,
standardize=True,
imputer=imputer,
continuizer=continuizer)
print pca