def bench_pymvpa(X, y, T, valid):
#
# .. PyMVPA ..
#
from mvpa.datasets import dataset_wizard
from mvpa.clfs import knn as mvpa_knn
start = datetime.now()
data = dataset_wizard(X, y)
mvpa_clf = mvpa_knn.kNN(k=n_neighbors)
mvpa_clf.train(data)
score = np.mean(mvpa_clf.predict(T) == valid)
return score, datetime.now() - start
def bench_pymvpa(X, y, T, valid):
#
# .. PyMVPA ..
#
from mvpa.datasets import dataset_wizard
from mvpa.clfs import knn as mvpa_knn
start = datetime.now()
data = dataset_wizard(X, y)
mvpa_clf = mvpa_knn.kNN(k=n_neighbors)
mvpa_clf.train(data)
score = np.mean(mvpa_clf.predict(T) == valid)
return score, datetime.now() - start
def testKNNState(self):
train = pureMultivariateSignal( 20, 3 )
test = pureMultivariateSignal( 20, 3 )
clf = kNN(k=10)
clf.train(train)
clf.states.enable('values')
clf.states.enable('predictions')
p = clf.predict(test.samples)
self.failUnless(p == clf.predictions)
self.failUnless(N.array(clf.values).shape == (80,2))
def test_knn_state(self):
train = pure_multivariate_signal( 40, 3 )
test = pure_multivariate_signal( 20, 3 )
clf = kNN(k=10)
clf.train(train)
clf.ca.enable(['estimates', 'predictions', 'distances'])
p = clf.predict(test.samples)
self.failUnless(p == clf.ca.predictions)
self.failUnless(np.array(clf.ca.estimates).shape == (80,2))
self.failUnless(clf.ca.distances.shape == (80,160))
self.failUnless(not clf.ca.distances.fa is train.sa)
# Those are deep-copied now by default so they should not be the same
self.failUnless(not (clf.ca.distances.fa['chunks'] is train.sa['chunks']))
self.failUnless(not (clf.ca.distances.fa.chunks is train.sa.chunks))
def test_knn_state(self):
train = pure_multivariate_signal( 40, 3 )
test = pure_multivariate_signal( 20, 3 )
clf = kNN(k=10)
clf.train(train)
clf.ca.enable(['estimates', 'predictions', 'distances'])
p = clf.predict(test.samples)
self.failUnless(p == clf.ca.predictions)
self.failUnless(np.array(clf.ca.estimates).shape == (80,2))
self.failUnless(clf.ca.distances.shape == (80,160))
self.failUnless(not clf.ca.distances.fa is train.sa)
# XXX if we revert to deepcopy for that state following test
# should fail
self.failUnless(clf.ca.distances.fa['chunks'] is train.sa['chunks'])
self.failUnless(clf.ca.distances.fa.chunks is train.sa.chunks)
def test_multivariate(self):
mv_perf = []
uv_perf = []
clf = kNN(k=10)
for i in xrange(20):
train = pure_multivariate_signal( 20, 3 )
test = pure_multivariate_signal( 20, 3 )
clf.train(train)
p_mv = clf.predict( test.samples )
mv_perf.append( np.mean(p_mv==test.targets) )
clf.train(train[:, 0])
p_uv = clf.predict(test[:, 0].samples)
uv_perf.append( np.mean(p_uv==test.targets) )
mean_mv_perf = np.mean(mv_perf)
mean_uv_perf = np.mean(uv_perf)
self.failUnless( mean_mv_perf > 0.9 )
self.failUnless( mean_uv_perf < mean_mv_perf )
def testMultivariate(self):
mv_perf = []
uv_perf = []
clf = kNN(k=10)
for i in xrange(20):
train = pureMultivariateSignal( 20, 3 )
test = pureMultivariateSignal( 20, 3 )
clf.train(train)
p_mv = clf.predict( test.samples )
mv_perf.append( N.mean(p_mv==test.labels) )
clf.train(train.selectFeatures([0]))
p_uv = clf.predict( test.selectFeatures([0]).samples )
uv_perf.append( N.mean(p_uv==test.labels) )
mean_mv_perf = N.mean(mv_perf)
mean_uv_perf = N.mean(uv_perf)
self.failUnless( mean_mv_perf > 0.9 )
self.failUnless( mean_uv_perf < mean_mv_perf )
def test_multivariate(self):
mv_perf = []
uv_perf = []
clf = kNN(k=10)
for i in xrange(20):
train = pure_multivariate_signal( 20, 3 )
test = pure_multivariate_signal( 20, 3 )
clf.train(train)
p_mv = clf.predict( test.samples )
mv_perf.append( np.mean(p_mv==test.targets) )
clf.train(train[:, 0])
p_uv = clf.predict(test[:, 0].samples)
uv_perf.append( np.mean(p_uv==test.targets) )
mean_mv_perf = np.mean(mv_perf)
mean_uv_perf = np.mean(uv_perf)
self.failUnless( mean_mv_perf > 0.9 )
self.failUnless( mean_uv_perf < mean_mv_perf )
_lars_tags = ['lars', 'linear', 'regression', 'does_feature_selection']
_lars = SKLLearnerAdapter(sklLARS(),
tags=_lars_tags,
descr='skl.LARS()')
_lasso_lars = SKLLearnerAdapter(sklLassoLARS(),
tags=_lars_tags,
descr='skl.LassoLARS()')
regrswh += [_lars, _lasso_lars]
clfswh += [RegressionAsClassifier(_lars, descr="skl.LARS_C()"),
RegressionAsClassifier(_lasso_lars, descr="skl.LassoLARS_C()")]
# kNN
clfswh += kNN(k=5, descr="kNN(k=5)")
clfswh += kNN(k=5, voting='majority', descr="kNN(k=5, voting='majority')")
clfswh += \
FeatureSelectionClassifier(
kNN(),
SensitivityBasedFeatureSelection(
SMLRWeights(SMLR(lm=1.0, implementation="C"),
postproc=maxofabs_sample()),
RangeElementSelector(mode='select')),
descr="kNN on SMLR(lm=1) non-0")
clfswh += \
FeatureSelectionClassifier(
kNN(),
SensitivityBasedFeatureSelection(
#pymvpa stuff
f_handle = open("classdatafile.txt", 'r')
f_handle2 = open("classidfile.txt", 'r')
f_handle3 = open("predictdata.txt", 'r')
features = genfromtxt(f_handle, dtype = float)
classes = genfromtxt(f_handle2, dtype = int)
predictdata = genfromtxt(f_handle3, dtype = float)
predictdata = np.expand_dims(predictdata, axis=0)
print predictdata
print np.shape(features), features.ndim, features.dtype
print np.shape(classes), classes.ndim, classes.dtype
print np.shape(predictdata), predictdata.ndim, predictdata.dtype
f_handle.close()
f_handle2.close()
f_handle3.close()
training = Dataset(samples=features,labels=classes)
clf = kNN(k=2)
print "clf = ", clf
clf.train(training)
#print np.mean(clf.predict(training.samples) == training.labels)
classID = clf.predict(predictdata)
print "classID = ", classID
#print clf.trained_labels
if classID[0] == 1: print "Image is of class: GRASS"
if classID[0] == 2: print "Image is of class: DIRT/GRAVEL"
if classID[0] == 3: print "Image is of class: CEMENT/ASPHALT"
from mvpa.datasets import Dataset
#pymvpa stuff
f_handle = open("classdatafile.txt", 'r')
f_handle2 = open("classidfile.txt", 'r')
f_handle3 = open("predictdata.txt", 'r')
features = genfromtxt(f_handle, dtype=float)
classes = genfromtxt(f_handle2, dtype=int)
predictdata = genfromtxt(f_handle3, dtype=float)
predictdata = np.expand_dims(predictdata, axis=0)
print predictdata
print np.shape(features), features.ndim, features.dtype
print np.shape(classes), classes.ndim, classes.dtype
print np.shape(predictdata), predictdata.ndim, predictdata.dtype
f_handle.close()
f_handle2.close()
f_handle3.close()
training = Dataset(samples=features, labels=classes)
clf = kNN(k=2)
print "clf = ", clf
clf.train(training)
#print np.mean(clf.predict(training.samples) == training.labels)
classID = clf.predict(predictdata)
print "classID = ", classID
#print clf.trained_labels
if classID[0] == 1: print "Image is of class: GRASS"
if classID[0] == 2: print "Image is of class: DIRT/GRAVEL"
if classID[0] == 3:
print "Image is of class: CEMENT/ASPHALT"
## Still fails unittests battery although overhauled otherwise.
## # enet from R via RPy2
## if externals.exists('elasticnet'):
## from mvpa.clfs.enet import ENET
## clfswh += RegressionAsClassifier(ENET(),
## descr="RegressionAsClassifier(ENET())")
## regrswh += ENET(descr="ENET()")
# glmnet from R via RPy
if externals.exists('glmnet'):
from mvpa.clfs.glmnet import GLMNET_C, GLMNET_R
clfswh += GLMNET_C(descr="GLMNET_C()")
regrswh += GLMNET_R(descr="GLMNET_R()")
# kNN
clfswh += kNN(k=5, descr="kNN(k=5)")
clfswh += kNN(k=5, voting='majority', descr="kNN(k=5, voting='majority')")
clfswh += \
FeatureSelectionClassifier(
kNN(),
SensitivityBasedFeatureSelection(
SMLRWeights(SMLR(lm=1.0, implementation="C"),
postproc=maxofabs_sample()),
RangeElementSelector(mode='select')),
descr="kNN on SMLR(lm=1) non-0")
clfswh += \
FeatureSelectionClassifier(
kNN(),
SensitivityBasedFeatureSelection(
from mvpa.clfs.knn import kNN
from mvpa.misc.plot import *
mvpa.seed(0) # to reproduce the plot
dataset_kwargs = dict(nfeatures=2, nchunks=10, snr=2, nlabels=4, means=[[0, 1], [1, 0], [1, 1], [0, 0]])
dataset_train = normal_feature_dataset(**dataset_kwargs)
dataset_plot = normal_feature_dataset(**dataset_kwargs)
# make a new figure
pl.figure(figsize=(9, 9))
for i, k in enumerate((1, 3, 9, 20)):
knn = kNN(k)
print "Processing kNN(%i) problem..." % k
pl.subplot(2, 2, i + 1)
"""
"""
knn.train(dataset_train)
plot_decision_boundary_2d(dataset_plot, clf=knn, maps="targets")
if cfg.getboolean("examples", "interactive", True):
# show all the cool figures
pl.show()
rgb_histo = np.asarray(rgb_histo) id_index = 15 lbp_predictdata = lbp[[id_index]] i3_histo_predictdata = lbp[[id_index]] print #print predictdata print classID[id_index] #print "len lbp:", len(lbp) #print "shape:", lbp.shape #mvpa lbp_training = Dataset(samples=lbp,labels=classID) i3_histo_training = Dataset(samples=lbp,labels=classID) clf = kNN(k=1, voting='majority') print "clf = ", clf clf.train(lbp_training) lbp_predicted_classID = clf.predict(lbp_predictdata) clf.train(i3_histo_training) i3_histo_predicted_classID = clf.predict(i3_histo_predictdata) print "lbp_predicted_classID: ", lbp_predicted_classID print "i3_histo__predicted_classID :", i3_histo_predicted_classID #if predicted_classID[0] == 1.0: print "Image is of class: GRASS" #if predicted_classID[0] == 2.0: print "Image is of class: DIRT/GRAVEL" #if predicted_classID[0] == 3.0: print "Image is of class: CEMENT/ASPHALT" #mlpy
mvpa.seed(0) # to reproduce the plot
dataset_kwargs = dict(nfeatures=2,
nchunks=10,
snr=2,
nlabels=4,
means=[[0, 1], [1, 0], [1, 1], [0, 0]])
dataset_train = normal_feature_dataset(**dataset_kwargs)
dataset_plot = normal_feature_dataset(**dataset_kwargs)
# make a new figure
pl.figure(figsize=(9, 9))
for i, k in enumerate((1, 3, 9, 20)):
knn = kNN(k)
print "Processing kNN(%i) problem..." % k
pl.subplot(2, 2, i + 1)
"""
"""
knn.train(dataset_train)
plot_decision_boundary_2d(dataset_plot, clf=knn, maps='targets')
if cfg.getboolean('examples', 'interactive', True):
# show all the cool figures
pl.show()