def preprocessor_pca_modular (data): from modshogun import RealFeatures from modshogun import PCA features = RealFeatures(data) preprocessor = PCA() preprocessor.init(features) preprocessor.apply_to_feature_matrix(features) return features
def RunPCAShogun(q):
totalTimer = Timer()
# Load input dataset.
Log.Info("Loading dataset", self.verbose)
try:
feat = RealFeatures(self.data.T)
with totalTimer:
# Get the options for running PCA.
if "new_dimensionality" in options:
k = int(options.pop("new_dimensionality"))
if (k > self.data.shape[1]):
Log.Fatal("New dimensionality (" + str(k) +
") cannot be greater than" +
"existing dimensionality (" +
str(self.data.shape[1]) + ")!")
q.put(-1)
return -1
else:
k = self.data.shape[1]
if "whiten" in options:
s = True
options.pop("whiten")
else:
s = False
if len(options) > 0:
Log.Fatal("Unknown parameters: " + str(options))
raise Exception("unknown parameters")
# Perform PCA.
prep = ShogunPCA(s)
prep.set_target_dim(k)
prep.init(feat)
prep.apply_to_feature_matrix(feat)
except Exception as e:
q.put(-1)
return -1
time = totalTimer.ElapsedTime()
q.put(time)
return time
def RunPCAShogun(q):
totalTimer = Timer()
# Load input dataset.
Log.Info("Loading dataset", self.verbose)
try:
feat = RealFeatures(self.data.T)
with totalTimer:
# Find out what dimension we want.
match = re.search('-d (\d+)', options)
if not match:
k = self.data.shape[1]
else:
k = int(match.group(1))
if (k > self.data.shape[1]):
Log.Fatal("New dimensionality (" + str(k) +
") cannot be greater than" +
"existing dimensionality (" +
str(self.data.shape[1]) + ")!")
q.put(-1)
return -1
# Get the options for running PCA.
s = True if options.find("-s") > -1 else False
# Perform PCA.
prep = ShogunPCA(s)
prep.set_target_dim(k)
prep.init(feat)
prep.apply_to_feature_matrix(feat)
except Exception as e:
q.put(-1)
return -1
time = totalTimer.ElapsedTime()
q.put(time)
return time
def RunPCAShogun():
totalTimer = Timer()
# Load input dataset.
Log.Info("Loading dataset", self.verbose)
try:
feat = RealFeatures(self.data.T)
with totalTimer:
# Get the options for running PCA.
if "new_dimensionality" in options:
k = int(options.pop("new_dimensionality"))
if (k > self.data.shape[1]):
Log.Fatal("New dimensionality (" + str(k) + ") cannot be greater than"
+ "existing dimensionality (" + str(self.data.shape[1]) + ")!")
return -1
else:
k = self.data.shape[1]
if "whiten" in options:
s = True
options.pop("whiten")
else:
s = False
if len(options) > 0:
Log.Fatal("Unknown parameters: " + str(options))
raise Exception("unknown parameters")
# Perform PCA.
prep = ShogunPCA(s)
prep.set_target_dim(k)
prep.init(feat)
prep.apply_to_feature_matrix(feat)
except Exception as e:
return -1
return totalTimer.ElapsedTime()
def RunPCAShogun(q):
totalTimer = Timer()
# Load input dataset.
Log.Info("Loading dataset", self.verbose)
try:
feat = RealFeatures(self.data.T)
with totalTimer:
# Find out what dimension we want.
match = re.search('-d (\d+)', options)
if not match:
k = self.data.shape[1]
else:
k = int(match.group(1))
if (k > self.data.shape[1]):
Log.Fatal("New dimensionality (" + str(k) + ") cannot be greater than"
+ "existing dimensionality (" + str(self.data.shape[1]) + ")!")
q.put(-1)
return -1
# Get the options for running PCA.
s = True if options.find("-s") > -1 else False
# Perform PCA.
prep = ShogunPCA(s)
prep.set_target_dim(k)
prep.init(feat)
prep.apply_to_feature_matrix(feat)
except Exception as e:
q.put(-1)
return -1
time = totalTimer.ElapsedTime()
q.put(time)
return time
