def run_pca(data, pca_components, required_pcs):
model = PCA(k=pca_components).fit(data)
imgs = model.scores.pack()
if required_pcs == 0:
new_imgs = imgs[1:, :, :]
else:
new_imgs = imgs[required_pcs, :, :, :]
return model, imgs, new_imgs
def run_pca(self):
"""
Run PCA based on data and pca components given during function initialization
RETURN:
------
model : PCA model containing components. scores and latency
"""
model = PCA(k=self.pca_components_index).fit(self.data)
return model
def run_pca(self, required_pcs):
model = PCA(k=self.pca_components).fit(self.data)
imgs = model.scores.pack()
if required_pcs == 0:
new_imgs = imgs
else:
if len(imgs.shape) == 3:
new_imgs = imgs[required_pcs, :, :]
else:
new_imgs = imgs[required_pcs, :, :, :]
return model, new_imgs
"""
Example standalone app for principal component analysis
"""
import argparse
from thunder import ThunderContext, PCA, export
if __name__ == "__main__":
parser = argparse.ArgumentParser(description="do principal components analysis")
parser.add_argument("datafile", type=str)
parser.add_argument("outputdir", type=str)
parser.add_argument("k", type=int)
parser.add_argument("--svdmethod", choices=("direct", "em"), default="direct", required=False)
args = parser.parse_args()
tsc = ThunderContext.start(appName="pca")
data = tsc.loadSeries(args.datafile).cache()
model = PCA(args.k, args.svdmethod)
model.fit(data)
outputdir = args.outputdir + "-pca"
export(model.comps, outputdir, "comps", "matlab")
export(model.latent, outputdir, "latent", "matlab")
export(model.scores, outputdir, "scores", "matlab")
def run_pca(self):
model = PCA(k=self.pca_components).fit(self.data)
return model
if __name__ == "__main__":
parser = optparse.OptionParser(
description="fit a regression model",
usage="%prog datafile modelfile outputdir [options]")
parser.add_option("--regressmode",
choices=("mean", "linear", "bilinear"),
help="form of regression")
parser.add_option("--k", type=int, default=2)
opts, args = parser.parse_args()
try:
datafile = args[0]
modelfile = args[1]
outputdir = args[2]
except IndexError:
parser.print_usage()
raise Exception("too few arguments")
tsc = ThunderContext.start(appName="regresswithpca")
data = tsc.loadSeries(datafile)
model = RegressionModel.load(modelfile, opts.regressmode) # do regression
betas, stats, resid = model.fit(data)
pca = PCA(opts.k).fit(betas) # do PCA
traj = model.fit(data, pca.comps) # get trajectories
outputdir += "-regress"
export(pca.comps, outputdir, "comps", "matlab")
export(pca.latent, outputdir, "latent", "matlab")
export(pca.scores, outputdir, "scores", "matlab")
export(traj, outputdir, "traj", "matlab")
import optparse
from thunder import ThunderContext, PCA, export
if __name__ == "__main__":
parser = optparse.OptionParser(
description="do principal components analysis",
usage="%prog datafile outputdir k [options]")
parser.add_option("--svdmethod",
choices=("direct", "em"),
default="direct")
opts, args = parser.parse_args()
try:
datafile = args[0]
outputdir = args[1]
k = int(args[2])
except IndexError:
parser.print_usage()
raise Exception("too few arguments")
tsc = ThunderContext.start(appName="pca")
data = tsc.loadSeries(datafile).cache()
model = PCA(k, opts.svdmethod)
model.fit(data)
outputdir += "-pca"
export(model.comps, outputdir, "comps", "matlab")
export(model.latent, outputdir, "latent", "matlab")
export(model.scores, outputdir, "scores", "matlab")
"""
import argparse
from thunder import ThunderContext, RegressionModel, PCA, export
if __name__ == "__main__":
parser = argparse.ArgumentParser(description="fit a regression model")
parser.add_argument("datafile", type=str)
parser.add_argument("modelfile", type=str)
parser.add_argument("outputdir", type=str)
parser.add_argument("regressmode",
choices=("mean", "linear", "bilinear"),
help="form of regression")
parser.add_argument("--k", type=int, default=2)
args = parser.parse_args()
tsc = ThunderContext.start(appName="regresswithpca")
data = tsc.loadSeries(args.datafile)
model = RegressionModel.load(args.modelfile,
args.regressmode) # do regression
betas, stats, resid = model.fit(data)
pca = PCA(args.k).fit(betas) # do PCA
traj = model.fit(data, pca.comps) # get trajectories
outputdir = args.outputdir + "-regress"
export(pca.comps, outputdir, "comps", "matlab")
export(pca.latent, outputdir, "latent", "matlab")
export(pca.scores, outputdir, "scores", "matlab")
export(traj, outputdir, "traj", "matlab")