def Process(self, sourcex, sourcey, targetx, targety, subsize):
# fixed size windows for source stream and target stream
#kpca = KernelPCA(n_components=3, kernel = 'rbf',gamma = 15)
#print("sourcex.shape", sourcex.shape)
#x_kpca = kpca.fit_transform(sourcex)
#print("x_kpca.shape", x_kpca.shape)
#sourcex = np.matrix(x_kpca)
#y_kpca = kpca.fit_transform(targetx)
#targetx = np.matrix(y_kpca)
src_size, _ = sourcex.shape
tgt_size, _ = targetx.shape
#true_label = []
### get the initial model by using the first source and target windows
alpha = 0.5
b = targetx.T.shape[1]
fold = 5
sigma_list = Classification.sigma_list(np.array(targetx.T),
np.array(sourcex.T))
lambda_list = Classification.lambda_list()
srcx_array = np.array(sourcex.T)
trgx_array = np.array(targetx.T)
#(thetah_old, w, sce_old, sigma_old) = Classification.R_ULSIF(trgx_array, srcx_array, alpha, sigma_list, lambda_list, b, fold)
self.Ensemble.generateNewModelRULSIF(targetx, sourcex, sourcey, alpha,
sigma_list, lambda_list, b, fold,
subsize)
# print "update model", src_size, source.shape
truelablecount = 0.0
totalcount = 0.0
for i in range(0, len(targety)):
#print("targetx[i]", targetx[i])
instanceresult = self.Ensemble.evaluateEnsembleRULSIF(targetx[i])
#print("instanceresult", instanceresult)
#print("instanceresult[0]", instanceresult[0])
#print("truelabel[i]", targety[i])
if instanceresult[0] == targety[i]:
truelablecount += 1.0
totalcount += 1.0
if i % 100 == 0:
print("truelabelcount", truelablecount)
print("totalcount", totalcount)
print("tmp acc", truelablecount / totalcount)
with open('accuracynormgroup3datafilegame0726.csv', 'a+') as f:
writer = csv.writer(f)
writer.writerow([
len(targety), truelablecount, totalcount,
truelablecount / totalcount
])
def Process(self, sourcex: np.matrix, sourcey: List[int],
targetx: np.matrix, targety: List[int], subsize: int) -> None:
# fixed size windows for source stream and target stream
# kpca = KernelPCA(n_components=3, kernel = 'rbf',gamma = 15)
# x_kpca = kpca.fit_transform(sourcex)
# sourcex = np.matrix(x_kpca)
# y_kpca = kpca.fit_transform(targetx)
# targetx = np.matrix(y_kpca)
src_size, _ = sourcex.shape
tgt_size, _ = targetx.shape
# get the initial model by using the first source and target windows
alpha = 0.5
b = targetx.T.shape[1]
fold = 5
sigma_list = Classification.sigma_list(np.array(targetx.T),
np.array(sourcex.T))
lambda_list = Classification.lambda_list()
# srcx_array = np.array(sourcex.T)
# trgx_array = np.array(targetx.T)
# (thetah_old, w, sce_old, sigma_old) = Classification.R_ULSIF(trgx_array, srcx_array, alpha, sigma_list, lambda_list, b, fold)
# todo
self.Ensemble.generateNewModelRULSIF(targetx, sourcex, sourcey, alpha,
sigma_list, lambda_list, b, fold,
subsize)
# test model
trueLableCount = 0.0
totalCount = 0.0
for i in range(0, len(targety)):
instanceResult = self.Ensemble.evaluateEnsembleRULSIF(targetx[i])
if instanceResult[0] == targety[i]:
trueLableCount += 1.0
totalCount += 1.0
if i % 100 == 0:
print("test size", i)
print("true label count", trueLableCount)
print("total count", totalCount)
print("tmp acc", trueLableCount / totalCount)
# write result to file
with open('output/accuracy_norm15group1player.csv', 'a+') as f:
writer = csv.writer(f)
writer.writerow([
len(targety), trueLableCount, totalCount,
trueLableCount / totalCount
])
def readdata(
sourcex_matrix=None,
sourcey_matrix=None,
targetx_matrix=None,
targety_matrix=None,
src_path=SRC_FILE_PATH,
tgt_path=TGT_FILE_PATH,
src_size=None,
tgt_size=None
) -> Tuple[np.matrix, List[int], np.matrix, List[int]]:
"""
input is: source dataset with y, here we assume it is a list of list, the name is source, target dataset with yhat,
here we assume it is a list of list, the name is target
"""
if sourcex_matrix is None:
sourcex_matrix_, sourcey_matrix = Classification.read_csv(
src_path) # matrix_ is source data
else:
sourcex_matrix_ = sourcex_matrix
sourcey_matrix_ = sourcey_matrix
if targetx_matrix is None:
targetx_matrix_, targety_matrix_ = Classification.read_csv(
tgt_path)
else:
targetx_matrix_ = targetx_matrix
targety_matrix_ = targety_matrix
# get list of all labels
labelList = []
for i in range(0, len(targety_matrix_)):
if targety_matrix_[i] not in labelList:
labelList.append(targety_matrix_[i])
print("label list len:", len(labelList))
# get list of indices of all source y labels
sourcey_label = []
for i in range(0, len(sourcey_matrix)):
sourcey_label.append(labelList.index(sourcey_matrix[i]))
# get list of indices of all target y labels
targety_label = []
for i in range(0, len(targety_matrix_)):
targety_label.append(labelList.index(targety_matrix_[i]))
return sourcex_matrix_, sourcey_label, targetx_matrix_, targety_label
def readdata(sourcex_matrix=None,
sourcey_matrix=None,
targetx_matrix=None,
targety_matrix=None,
src_path=SRC_FILE_PATH,
tgt_path=TGT_FILE_PATH,
src_size=None,
tgt_size=None):
"""
input is: source dataset with y, here we assume it is a list of list, the name is source, target dataset with yhat,
here we assume it is a list of list, the name is target
"""
if sourcex_matrix is None:
sourcex_matrix_, sourcey_matrix = Classification.read_csv(
src_path, None) # matrix_ is source data
else:
sourcex_matrix_ = sourcex_matrix
sourcey_matrix_ = sourcey_matrix
matrix_ = sourcex_matrix_[:src_size, :]
if targetx_matrix is None:
targetx_, targety_ = Classification.read_csv(tgt_path, size=None)
else:
targetx_ = targetx_matrix
targety_ = targety_matrix
labellist = []
for i in range(0, len(targety_)):
if targety_[i] not in labellist:
labellist.append(targety_[i])
print("labellistlen", len(labellist))
sourcey_label = []
for i in range(0, len(sourcey_matrix)):
sourcey_label.append(labellist.index(sourcey_matrix[i]))
for i in range(0, len(targety_)):
if targety_[i] not in labellist:
labellist.append(targety_[i])
targety_label = []
for i in range(0, len(targety_)):
targety_label.append(labellist.index(targety_[i]))
return sourcex_matrix_, sourcey_label, targetx_, targety_label
def generateNewModelRULSIF(self, trgx_matrix, srcx_matrix, srcy_matrix,
alpha, sigma_list, lambda_list, b, fold,
subsize):
model = Model()
if len(srcx_matrix) == 0 or len(trgx_matrix) == 0:
raise Exception(
'Source or Target stream should have some elements')
# Create new model
print('Target model creation')
model.model = Classification.get_model(trgx_matrix, srcx_matrix,
srcy_matrix, alpha, sigma_list,
lambda_list, b, fold, subsize)
# compute source and target weight
print('Computing model weights')
model.weight = model.computeModelWeightRULSIF(trgx_matrix)
# update ensemble
index = self.__addModelRULSIF(model, trgx_matrix)
if index != -1:
print('Ensemble updated at ' + str(index))