x = westdf.loc[:, :].values
x = StandardScaler(with_std=False).fit_transform(x) #centerlize the data
#SparsePCA transform
transformer = SparsePCA(n_components=3,\
alpha=0.1,\
normalize_components=True,\
random_state=0)
x_transformed = transformer.fit_transform(x)
# for data analysis
x_transformed.shape
transformer.alpha
egienvetors = transformer.components_
transformer.error_
transformer.get_params(deep=True)
np.mean(transformer.components_ == 0)
westspca = pd.DataFrame(data=egienvetors, columns=westdf.columns)
Spca1 = westspca.sort_values(by=[0], axis=1)
Spca2 = westspca.sort_values(by=[1], axis=1)
Spca3 = westspca.sort_values(by=[2], axis=1)
Spca4 = westspca.sort_values(by=[3], axis=1)
Spca5 = westspca.sort_values(by=[4], axis=1)
westtrans = pd.DataFrame(data=x_transformed)
westpcascore = pd.concat([chapter, westtrans], axis=1)
pcascore1 = westpcascore.sort_values(by=[0], axis=0)
pcascore2 = westpcascore.sort_values(by=[1], axis=0)
pcascore3 = westpcascore.sort_values(by=[2], axis=0)
pcascore4 = westpcascore.sort_values(by=[3], axis=0)
pcascore5 = westpcascore.sort_values(by=[4], axis=0)
class SPCA(object):
def __init__(self,
n_components=None,
alpha=1,
ridge_alpha=0.01,
max_iter=1000,
tol=1e-8,
method='lars',
n_jobs=None,
U_init=None,
V_init=None,
verbose=False,
random_state=None,
normalize_components='deprecated'):
"""
:param n_components:
:param alpha:
:param ridge_alpha:
:param max_iter:
:param tol:
:param method:
:param n_jobs:
:param U_init:
:param V_init:
:param verbose:
:param random_state:
:param normalize_components:
"""
self.model = SparsePCA(n_components=n_components,
alpha=alpha,
ridge_alpha=ridge_alpha,
max_iter=max_iter,
tol=tol,
method=method,
n_jobs=n_jobs,
U_init=U_init,
V_init=V_init,
verbose=verbose,
random_state=random_state,
normalize_components=normalize_components)
def fit(self, x, y):
self.model.fit(X=x, y=y)
def transform(self, x):
self.model.transform(X=x)
def fit_transform(self, x, y=None):
return self.model.fit_transform(X=x, y=y)
def get_params(self):
return self.model.get_params(deep=True)
def set_params(self, **params):
return self.model.set_params(**params)
def get_attributes(self):
components = self.model.components_
error = self.model.error_
n_iter = self.model.n_iter_
mean = self.model.mean_
return components, error, n_iter, mean
def btnConvert_click(self):
msgBox = QMessageBox()
# Alpha
try:
Alpha = np.float(ui.txtAlpha.text())
except:
msgBox.setText("Alpha is wrong!")
msgBox.setIcon(QMessageBox.Critical)
msgBox.setStandardButtons(QMessageBox.Ok)
msgBox.exec_()
return False
# Ridge
try:
Ridge = np.float(ui.txtRidge.text())
except:
msgBox.setText("Ridge Alpha is wrong!")
msgBox.setIcon(QMessageBox.Critical)
msgBox.setStandardButtons(QMessageBox.Ok)
msgBox.exec_()
return False
# Max Iter
try:
MaxIter = np.int32(ui.txtMaxIter.text())
except:
msgBox.setText("Maximum Iteration is wrong!")
msgBox.setIcon(QMessageBox.Critical)
msgBox.setStandardButtons(QMessageBox.Ok)
msgBox.exec_()
return False
# Tolerance
try:
Tol = np.float(ui.txtTole.text())
except:
msgBox.setText("Tolerance is wrong!")
msgBox.setIcon(QMessageBox.Critical)
msgBox.setStandardButtons(QMessageBox.Ok)
msgBox.exec_()
return False
#Method
if ui.rbLars.isChecked():
Method = "lars"
else:
Method = "cd"
# Number of Job
try:
njob = np.int32(ui.txtJobs.text())
except:
msgBox.setText("Number of jobs is wrong!")
msgBox.setIcon(QMessageBox.Critical)
msgBox.setStandardButtons(QMessageBox.Ok)
msgBox.exec_()
return False
# OutFile
OutFile = ui.txtOutFile.text()
if not len(OutFile):
msgBox.setText("Please enter out file!")
msgBox.setIcon(QMessageBox.Critical)
msgBox.setStandardButtons(QMessageBox.Ok)
msgBox.exec_()
return False
# InFile
InFile = ui.txtInFile.text()
if not len(InFile):
msgBox.setText("Please enter input file!")
msgBox.setIcon(QMessageBox.Critical)
msgBox.setStandardButtons(QMessageBox.Ok)
msgBox.exec_()
return False
if not os.path.isfile(InFile):
msgBox.setText("Input file not found!")
msgBox.setIcon(QMessageBox.Critical)
msgBox.setStandardButtons(QMessageBox.Ok)
msgBox.exec_()
return False
if ui.rbScale.isChecked() == True and ui.rbALScale.isChecked(
) == False:
msgBox.setText(
"Subject Level Normalization is just available for Subject Level Analysis!"
)
msgBox.setIcon(QMessageBox.Critical)
msgBox.setStandardButtons(QMessageBox.Ok)
msgBox.exec_()
return False
InData = io.loadmat(InFile)
OutData = dict()
OutData["imgShape"] = InData["imgShape"]
if not len(ui.txtData.currentText()):
msgBox.setText("Please enter Data variable name!")
msgBox.setIcon(QMessageBox.Critical)
msgBox.setStandardButtons(QMessageBox.Ok)
msgBox.exec_()
return False
try:
X = InData[ui.txtData.currentText()]
if ui.cbScale.isChecked() and (not ui.rbScale.isChecked()):
X = preprocessing.scale(X)
print("Whole of data is scaled X~N(0,1).")
except:
print("Cannot load data")
return
try:
NumFea = np.int32(ui.txtNumFea.text())
except:
msgBox.setText("Number of features is wrong!")
msgBox.setIcon(QMessageBox.Critical)
msgBox.setStandardButtons(QMessageBox.Ok)
msgBox.exec_()
return False
if NumFea < 1:
msgBox.setText("Number of features must be greater than zero!")
msgBox.setIcon(QMessageBox.Critical)
msgBox.setStandardButtons(QMessageBox.Ok)
msgBox.exec_()
return False
if NumFea > np.shape(X)[1]:
msgBox.setText("Number of features is wrong!")
msgBox.setIcon(QMessageBox.Critical)
msgBox.setStandardButtons(QMessageBox.Ok)
msgBox.exec_()
return False
# Subject
if not len(ui.txtSubject.currentText()):
msgBox.setText("Please enter Subject variable name!")
msgBox.setIcon(QMessageBox.Critical)
msgBox.setStandardButtons(QMessageBox.Ok)
msgBox.exec_()
return False
try:
Subject = InData[ui.txtSubject.currentText()]
OutData[ui.txtOSubject.text()] = Subject
except:
print("Cannot load Subject ID")
return
# Label
if not len(ui.txtLabel.currentText()):
msgBox.setText("Please enter Label variable name!")
msgBox.setIcon(QMessageBox.Critical)
msgBox.setStandardButtons(QMessageBox.Ok)
msgBox.exec_()
return False
OutData[ui.txtOLabel.text()] = InData[ui.txtLabel.currentText()]
# Task
if ui.cbTask.isChecked():
if not len(ui.txtTask.currentText()):
msgBox.setText("Please enter Task variable name!")
msgBox.setIcon(QMessageBox.Critical)
msgBox.setStandardButtons(QMessageBox.Ok)
msgBox.exec_()
return False
OutData[ui.txtOTask.text()] = InData[ui.txtTask.currentText()]
# Run
if ui.cbRun.isChecked():
if not len(ui.txtRun.currentText()):
msgBox.setText("Please enter Run variable name!")
msgBox.setIcon(QMessageBox.Critical)
msgBox.setStandardButtons(QMessageBox.Ok)
msgBox.exec_()
return False
OutData[ui.txtORun.text()] = InData[ui.txtRun.currentText()]
# Counter
if ui.cbCounter.isChecked():
if not len(ui.txtCounter.currentText()):
msgBox.setText("Please enter Counter variable name!")
msgBox.setIcon(QMessageBox.Critical)
msgBox.setStandardButtons(QMessageBox.Ok)
msgBox.exec_()
return False
OutData[ui.txtOCounter.text()] = InData[
ui.txtCounter.currentText()]
# Matrix Label
if ui.cbmLabel.isChecked():
if not len(ui.txtmLabel.currentText()):
msgBox.setText("Please enter Matrix Label variable name!")
msgBox.setIcon(QMessageBox.Critical)
msgBox.setStandardButtons(QMessageBox.Ok)
msgBox.exec_()
return False
OutData[ui.txtOmLabel.text()] = InData[ui.txtmLabel.currentText()]
# Design
if ui.cbDM.isChecked():
if not len(ui.txtDM.currentText()):
msgBox.setText("Please enter Design Matrix variable name!")
msgBox.setIcon(QMessageBox.Critical)
msgBox.setStandardButtons(QMessageBox.Ok)
msgBox.exec_()
return False
OutData[ui.txtODM.text()] = InData[ui.txtDM.currentText()]
# Coordinate
if ui.cbCol.isChecked():
if not len(ui.txtCol.currentText()):
msgBox.setText("Please enter Coordinator variable name!")
msgBox.setIcon(QMessageBox.Critical)
msgBox.setStandardButtons(QMessageBox.Ok)
msgBox.exec_()
return False
OutData[ui.txtOCol.text()] = InData[ui.txtCol.currentText()]
# Condition
if ui.cbCond.isChecked():
if not len(ui.txtCond.currentText()):
msgBox.setText("Please enter Condition variable name!")
msgBox.setIcon(QMessageBox.Critical)
msgBox.setStandardButtons(QMessageBox.Ok)
msgBox.exec_()
return False
OutData[ui.txtOCond.text()] = InData[ui.txtCond.currentText()]
# Number of Scan
if ui.cbNScan.isChecked():
if not len(ui.txtScan.currentText()):
msgBox.setText("Please enter Number of Scan variable name!")
msgBox.setIcon(QMessageBox.Critical)
msgBox.setStandardButtons(QMessageBox.Ok)
msgBox.exec_()
return False
OutData[ui.txtOScan.text()] = InData[ui.txtScan.currentText()]
Models = dict()
Models["Name"] = "SPCA"
if ui.rbALScale.isChecked():
print("Partition data to subject level ...")
SubjectUniq = np.unique(Subject)
X_Sub = list()
for subj in SubjectUniq:
if ui.cbScale.isChecked() and ui.rbScale.isChecked():
X_Sub.append(
preprocessing.scale(
X[np.where(Subject == subj)[1], :]))
print("Data in subject level is scaled, X_" + str(subj) +
"~N(0,1).")
else:
X_Sub.append(X[np.where(Subject == subj)[1], :])
print("Subject ", subj, " is extracted from data.")
print("Running SPCA in subject level ...")
X_Sub_PCA = list()
lenPCA = len(X_Sub)
for xsubindx, xsub in enumerate(X_Sub):
model = SparsePCA(n_components=NumFea,alpha=Alpha,ridge_alpha=Ridge,max_iter=MaxIter,\
tol=Tol, method=Method, n_jobs=njob)
X_Sub_PCA.append(model.fit_transform(xsub))
Models["Model" + str(xsubindx + 1)] = str(
model.get_params(deep=True))
print("SPCA: ", xsubindx + 1, " of ", lenPCA, " is done.")
print("Data integration ... ")
X_new = None
for xsubindx, xsub in enumerate(X_Sub_PCA):
X_new = np.concatenate(
(X_new, xsub)) if X_new is not None else xsub
print("Integration: ", xsubindx + 1, " of ", lenPCA,
" is done.")
OutData[ui.txtOData.text()] = X_new
else:
print("Running SPCA ...")
model = SparsePCA(n_components=NumFea, alpha=Alpha, ridge_alpha=Ridge, max_iter=MaxIter, \
tol=Tol, method=Method, n_jobs=njob)
OutData[ui.txtOData.text()] = model.fit_transform(X)
Models["Model"] = str(model.get_params(deep=True))
OutData["ModelParameter"] = Models
print("Saving ...")
io.savemat(ui.txtOutFile.text(), mdict=OutData)
print("DONE.")
msgBox.setText("Sparse PCA is done.")
msgBox.setIcon(QMessageBox.Information)
msgBox.setStandardButtons(QMessageBox.Ok)
msgBox.exec_()
class SPCA(object):
"""
Wrapper for sklearn package. Performs sparse PCA
SPCA has 5 methods:
- fit(waveforms)
update class instance with ICA fit
- fit_transform()
do what fit() does, but additionally return the projection onto ICA space
- inverse_transform(A)
inverses the decomposition, returns waveforms for an input A, using Z
- get_basis()
returns the basis vectors Z^\dagger
- get_params()
returns metadata used for fits.
"""
def __init__(self, num_components=10,
catalog_name='unknown',
alpha = 0.1,
ridge_alpha = 0.01,
max_iter = 2000,
tol = 1e-9,
n_jobs = 1,
random_state = None):
self._decomposition = 'Sparse PCA'
self._num_components = num_components
self._catalog_name = catalog_name
self._alpha = alpha
self._ridge_alpha = ridge_alpha
self._n_jobs = n_jobs
self._max_iter = max_iter
self._tol = tol
self._random_state = random_state
self._SPCA = SparsePCA(n_components=self._num_components,
alpha = self._alpha,
ridge_alpha = self._ridge_alpha,
n_jobs = self._n_jobs,
max_iter = self._max_iter,
tol = self._tol,
random_state = self._random_state)
def fit(self,waveforms):
# TODO make sure there are more columns than rows (transpose if not)
# normalize waveforms
self._waveforms = waveforms
self._SPCA.fit(self._waveforms)
def fit_transform(self,waveforms):
# TODO make sure there are more columns than rows (transpose if not)
# normalize waveforms
self._waveforms = waveforms
self._A = self._SPCA.fit_transform(self._waveforms)
return self._A
def inverse_transform(self,A):
# convert basis back to waveforms using fit
new_waveforms = self._SPCA.inverse_transform(A)
return new_waveforms
def get_params(self):
# TODO know what catalog was used! (include waveform metadata)
params = self._SPCA.get_params()
params['num_components'] = params.pop('n_components')
params['Decompositon'] = self._decomposition
return params
def get_basis(self):
""" Return the SPCA basis vectors (Z^\dagger)"""
Zt = self._SPCA.components_
return Zt
class SPCA(object):
"""
Wrapper for sklearn package. Performs sparse PCA
SPCA has 5 methods:
- fit(waveforms)
update class instance with ICA fit
- fit_transform()
do what fit() does, but additionally return the projection onto ICA space
- inverse_transform(A)
inverses the decomposition, returns waveforms for an input A, using Z
- get_basis()
returns the basis vectors Z^\dagger
- get_params()
returns metadata used for fits.
"""
def __init__(self,
num_components=10,
catalog_name='unknown',
alpha=0.1,
ridge_alpha=0.01,
max_iter=2000,
tol=1e-9,
n_jobs=1,
random_state=None):
self._decomposition = 'Sparse PCA'
self._num_components = num_components
self._catalog_name = catalog_name
self._alpha = alpha
self._ridge_alpha = ridge_alpha
self._n_jobs = n_jobs
self._max_iter = max_iter
self._tol = tol
self._random_state = random_state
self._SPCA = SparsePCA(n_components=self._num_components,
alpha=self._alpha,
ridge_alpha=self._ridge_alpha,
n_jobs=self._n_jobs,
max_iter=self._max_iter,
tol=self._tol,
random_state=self._random_state)
def fit(self, waveforms):
# TODO make sure there are more columns than rows (transpose if not)
# normalize waveforms
self._waveforms = waveforms
self._SPCA.fit(self._waveforms)
def fit_transform(self, waveforms):
# TODO make sure there are more columns than rows (transpose if not)
# normalize waveforms
self._waveforms = waveforms
self._A = self._SPCA.fit_transform(self._waveforms)
return self._A
def inverse_transform(self, A):
# convert basis back to waveforms using fit
new_waveforms = self._SPCA.inverse_transform(A)
return new_waveforms
def get_params(self):
# TODO know what catalog was used! (include waveform metadata)
params = self._SPCA.get_params()
params['num_components'] = params.pop('n_components')
params['Decompositon'] = self._decomposition
return params
def get_basis(self):
""" Return the SPCA basis vectors (Z^\dagger)"""
Zt = self._SPCA.components_
return Zt
