class PCA(Model):
"""Given a set of input vectors, find their principle components"""
def __init__(self, fn=None, n_comp=None, batch_size=None):
self.model = IncrementalPCA()
self.fn = fn
self.params = {"n_components": n_comp, "batch_size": batch_size}
self.set_params()
def load(self, fn):
"""Set parameters after loading from filename"""
super().load(fn)
self.params = self.model.get_params()
return
def fit(self, reps):
"""Fit a list of representations"""
X = [r.to_vector() for r in reps]
self.model.fit(X)
def err(self, to_transform, to_check_against):
"""Mesh error between reconstructed to_transform representation and
mesh conversion of to_check_against
"""
vec = to_transform.to_vector()
vec_trans = self.model.transform(vec)
vec_recon = self.model.inverse_transform(vec_trans)
transformed = to_transform.from_vector(vec_recon)
mesh1 = transformed.mesh()
mesh2 = to_check_against.mesh()
error = representation.mesh_error(mesh1, mesh2)
return error
class IPCA(object):
def __init__(self,
n_components=None,
whiten=False,
copy=True,
batch_size=None):
"""
:param n_components: default为None ，int 或None， 想要保留的分量数，None 时，
min(n_samples, n_features)
:param whiten: bool型，可选项， 默认为False, 当true（默认情况下为false）时，components_ 向量除以
n_samples*components_以确保具有单位组件级方差的不相关输出。
:param copy: 默认为True, False时，x 将被覆盖，将节约能存，但存在不安全
:param batch_size: default None， 批量样本数， 只在fit 中使用，设为None,系统自动设成5*n_features,
以保持经度与内存开销的平衡
"""
self.model = IncrementalPCA(n_components=n_components,
whiten=whiten,
copy=copy,
batch_size=batch_size)
def fit(self, x, y=None):
self.model.fit(X=x, y=y)
def transform(self, x):
return 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, deep=True): # 获取评估器的参数
return self.model.get_params(deep=deep)
def set_params(self, **params): # 设置评估器的参数
self.model.set_params(**params)
def inverse_transform(self, x): # 与 fit_tansform 刚好相反的两个操作
return self.model.inverse_transform(X=x)
def get_precision(self): # 根据生成模型计算精度矩阵
return self.model.get_precision()
def get_covariance(self): # 根据生成模型获取协方差
return self.model.get_covariance()
def partial_fit(self, x, y=None, check_input=True): # 增量训练
self.model.partial_fit(X=x, y=y, check_input=check_input)
def get_attributes(self):
component = self.model.components_
explained_variance = self.model.explained_variance_
explained_variance_ratio = self.model.explained_variance_ratio_
singular_values = self.model.singular_values_
means = self.model.mean_ # 每个特征的均值
var = self.model.var_ # 每个特征的方差
noise_variance = self.model.noise_variance_ # 评估的噪声协方差
n_component = self.model.n_components_
n_samples_seen = self.model.n_samples_seen_
return component, explained_variance, explained_variance_ratio, singular_values, means, var, noise_variance, \
n_component, n_samples_seen
def btnConvert_click(self):
msgBox = QMessageBox()
# 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
# Batch
try:
Batch = np.int32(ui.txtBatch.text())
except:
msgBox.setText("Size of batch is wrong!")
msgBox.setIcon(QMessageBox.Critical)
msgBox.setStandardButtons(QMessageBox.Ok)
msgBox.exec_()
return False
if Batch == 0:
Batch = None
# 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"] = "IPCA"
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 IPCA in subject level ...")
X_Sub_PCA = list()
lenPCA = len(X_Sub)
for xsubindx, xsub in enumerate(X_Sub):
model = IncrementalPCA(n_components=NumFea, batch_size=Batch)
model.fit(xsub)
X_Sub_PCA.append(model.transform(xsub))
Models["Model" + str(xsubindx + 1)] = str(
model.get_params(deep=True))
print("IPCA: ", 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 IPCA ...")
model = IncrementalPCA(n_components=NumFea, batch_size=Batch)
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("Incremental PCA is done.")
msgBox.setIcon(QMessageBox.Information)
msgBox.setStandardButtons(QMessageBox.Ok)
msgBox.exec_()
print('#================================================================#')
print('\nshape of Training Matrix = ', Train_matrix.shape)
print('shape of Test Matrix = ', Test_matrix.shape,'\n')
print('#================================================================#')
#========================= Principal Component Analysis ==========================#
print ('\nRunning Incrmental PCA with 200 Componenets and 5000 batch size')
pca = IncrementalPCA(n_components=200, batch_size = 5000)
pca.fit(Train_matrix)
Train_matrix = pca.transform(Train_matrix)
Test_matrix = pca.transform(Test_matrix)
parameters = pca.get_params()
variance = pca.explained_variance_ratio_
cumvariance = pca.explained_variance_ratio_.cumsum()
#np.savetxt("pca_result_variance_200.csv", variance, delimiter=",")
#np.savetxt("pca_result_cum_variance_200.csv", variance, delimiter=",")
print ('\nPCA complete!\n')
print ('#================================================================#')
print('\nWriting transformed Train and Test matrices to CSV\n')
print('#================================================================#')
with open(csv_pca_train_out_path, 'w', newline='') as csvtrainoutfile:
csv_matrix_writer(csvtrainoutfile , Train_matrix)
with open(csv_pca_test_out_path, 'w', newline='') as csvtestoutfile:
csv_matrix_writer(csvtestoutfile , Test_matrix)
# In[ ]:
# In[16]:
# IncrementalPCA
ipca = IncrementalPCA(n_components=3)
print(ipca)
ipca.fit(feature)
x = ipca.transform(feature)
print(ipca.explained_variance_ratio_)
# In[17]:
# ipca.get_covariance()
ipca.get_precision()
ipca.get_params(deep=True)
# ## Gaussian random projection
# In[27]:
from sklearn import random_projection
transform = random_projection.GaussianRandomProjection(n_components=5)
feature_new = transform.fit_transform(feature)
classifier_f = open('n_GaussianRandomProjection.pickle', 'wb')
pickle.dump(feature_new, classifier_f)
classifier_f.close()
print(feature_new)
# In[52]:
