def feature_function():
from modshogun import RealFeatures
from modshogun import CSVFile
import numpy as np
#3x3 random matrix
feat_arr = np.random.rand(3, 3)
#initialize RealFeatures from numpy array
features = RealFeatures(feat_arr)
#get matrix value function
print features.get_feature_matrix(features)
#get selected column of matrix
print features.get_feature_vector(1)
#get number of columns
print features.get_num_features()
#get number of rows
print features.get_num_vectors()
feats_from_csv = RealFeatures(CSVFile("csv/feature.csv"))
print "csv is ", feats_from_csv.get_feature_matrix()
def features_dense_modular (A=matrixA,B=matrixB,C=matrixC):
a=RealFeatures(A)
b=LongIntFeatures(B)
c=ByteFeatures(C)
# or 16bit wide ...
#feat1 = f.ShortFeatures(N.zeros((10,5),N.short))
#feat2 = f.WordFeatures(N.zeros((10,5),N.uint16))
# print(some statistics about a)
# get first feature vector and set it
a.set_feature_vector(array([1,4,0,0,0,9], dtype=float64), 0)
# get matrices
a_out = a.get_feature_matrix()
b_out = b.get_feature_matrix()
c_out = c.get_feature_matrix()
assert(all(a_out==A))
assert(all(b_out==B))
assert(all(c_out==C))
return a_out,b_out,c_out,a,b,c
def features_dense_real_modular (A=matrix):
# ... of type Real, LongInt and Byte
a=RealFeatures(A)
# print(some statistics about a)
#print(a.get_num_vectors())
#print(a.get_num_features())
# get first feature vector and set it
#print(a.get_feature_vector(0))
a.set_feature_vector(array([1,4,0,0,0,9], dtype=float64), 0)
# get matrix
a_out = a.get_feature_matrix()
assert(all(a_out==A))
return a_out
def features_dense_real_modular(A=matrix):
# ... of type Real, LongInt and Byte
a = RealFeatures(A)
# print(some statistics about a)
#print(a.get_num_vectors())
#print(a.get_num_features())
# get first feature vector and set it
#print(a.get_feature_vector(0))
a.set_feature_vector(array([1, 4, 0, 0, 0, 9], dtype=float64), 0)
# get matrix
a_out = a.get_feature_matrix()
assert (all(a_out == A))
return a_out
# load wine features
features = RealFeatures(CSVFile('../data/fm_wine.dat'))
print('%d vectors with %d features.' % (features.get_num_vectors(), features.get_num_features()))
print('original features mean = ' + str(numpy.mean(features, axis=1)))
# rescale the features to [0,1]
feature_rescaling = RescaleFeatures()
feature_rescaling.init(features)
features.add_preprocessor(feature_rescaling)
features.apply_preprocessor()
print('mean after rescaling = ' + str(numpy.mean(features, axis=1)))
# remove mean from data
data = features.get_feature_matrix()
data = data.T
data-= numpy.mean(data, axis=0)
print numpy.mean(data, axis=0)
fig, axarr = pyplot.subplots(1,2)
axarr[0].matshow(numpy.cov(data.T))
#### whiten data
''' this method to whiten the data didn't really work out
L = cholesky(numpy.cov(data.T))
data = solve_triangular(L, data.T, lower=True).T
'''
# covariance matrix
evaluator = MulticlassAccuracy()
acc = evaluator.evaluate(predicted_labels, test_labels)
err = 1 - acc
return err
features_file = '../data/fm_ape_gut.txt'
labels_file = '../data/label_ape_gut.txt'
features = RealFeatures(CSVFile(features_file))
labels = MulticlassLabels(CSVFile(labels_file))
# reduce the number of features to use so that the training is faster but still
# the results of feature selection are significant
fm = features.get_feature_matrix()
features = RealFeatures(fm[:500, :])
assert (features.get_num_vectors() == labels.get_num_labels())
print('Number of examples = %d, number of features = %d.' %
(features.get_num_vectors(), features.get_num_features()))
visualize_tdsne(features, labels)
lmnn = diagonal_lmnn(features, labels, max_iter=1200)
diagonal_transform = lmnn.get_linear_transform()
diagonal = numpy.diag(diagonal_transform)
print('%d out of %d elements are non-zero' %
(numpy.sum(diagonal != 0), diagonal.shape[0]))
features = RealFeatures(CSVFile('../data/fm_wine.dat'))
print('%d vectors with %d features.' %
(features.get_num_vectors(), features.get_num_features()))
print('original features mean = ' + str(numpy.mean(features, axis=1)))
# rescale the features to [0,1]
feature_rescaling = RescaleFeatures()
feature_rescaling.init(features)
features.add_preprocessor(feature_rescaling)
features.apply_preprocessor()
print('mean after rescaling = ' + str(numpy.mean(features, axis=1)))
# remove mean from data
data = features.get_feature_matrix()
data = data.T
data -= numpy.mean(data, axis=0)
print numpy.mean(data, axis=0)
fig, axarr = pyplot.subplots(1, 2)
axarr[0].matshow(numpy.cov(data.T))
#### whiten data
''' this method to whiten the data didn't really work out
L = cholesky(numpy.cov(data.T))
data = solve_triangular(L, data.T, lower=True).T
'''
# covariance matrix
M = numpy.cov(data.T)
predicted_labels = knn.apply(test_features)
evaluator = MulticlassAccuracy()
acc = evaluator.evaluate(predicted_labels, test_labels)
err = 1-acc
return err
features_file = '../data/fm_ape_gut.txt'
labels_file = '../data/label_ape_gut.txt'
features = RealFeatures(CSVFile(features_file))
labels = MulticlassLabels(CSVFile(labels_file))
# reduce the number of features to use so that the training is faster but still
# the results of feature selection are significant
fm = features.get_feature_matrix()
features = RealFeatures(fm[:500, :])
assert(features.get_num_vectors() == labels.get_num_labels())
print('Number of examples = %d, number of features = %d.' % (features.get_num_vectors(), features.get_num_features()))
visualize_tdsne(features, labels)
lmnn = diagonal_lmnn(features, labels, max_iter=1200)
diagonal_transform = lmnn.get_linear_transform()
diagonal = numpy.diag(diagonal_transform)
print('%d out of %d elements are non-zero' % (numpy.sum(diagonal != 0), diagonal.shape[0]))
statistics = lmnn.get_statistics()
pyplot.plot(statistics.obj.get())
