def der_error(w,l,sample,sampleSize):
d = std.sparse_mult(l, w)
sum = {}
for i in range(sampleSize):
label = sample[i].get(-1,0)
example = std.take_out_label(sample[i])
if (label*(std.sparse_dot(w,example)) < 1):
sum = std.sparse_vsum(sum,std.sparse_mult(-label,example))
#print("der_err summ part = " + str(sum))
dcost = std.sparse_vsum(d,sum)
return dcost
def guide_get_feature(stub):
# A variable to count the number of iteration of the client, which must coincide with the epoch in the server.
it = 1
# We make a first call to the server to get the data : after that call, vect is the data set. Then we store it.
vect = stub.GetFeature(route_guide_pb2.Vector(poids="pret"))
dataInfo = vect.poids.split("<depre>")
nbChunks = int(dataInfo[0])
computeInfo = dataInfo[1].split("<samples>")
# The depreciation of the SVM norm cost
l = float(computeInfo[0])
# Number of samples in each subtraining set
numSamples = float(computeInfo[1])
# Get the dataset from the server, by receiving all the chunks
k = 1
dataSampleSet = []
while (k <= nbChunks):
vect = stub.GetFeature(route_guide_pb2.Vector(poids="chunk<nb>" + str(k)))
dataSampleSet += std.str2datadict(vect.poids)
k +=1
# This second call serves to get the departure vector.
vect = stub.GetFeature(route_guide_pb2.Vector(poids="getw0"))
while (vect.poids != 'stop'):
print("iteration : " + str(it))
# We save the vector on which we base the computations
wt = std.str2dict(vect.poids)
# Gradient descent on the sample.
nw = sgd.descent(dataSampleSet, std.str2dict(vect.poids), numSamples, l)
# Normalization of the vector of parameters
normnW = math.sqrt(std.sparse_dot(nw, nw))
nw = std.sparse_mult(1/normnW, nw)
# The result is sent to the server.
vect.poids = std.dict2str(nw) + "<delay>" + std.dict2str(wt)
vect = stub.GetFeature(route_guide_pb2.Vector(poids=vect.poids))
it += 1
#time.sleep(1.7)
print(vect)
def guide_get_feature(stub):
# A variable to count the number of iteration of the client, which must coincide with the epoch in the server.
it = 1
# We make a first call to the server to get the data : after that call, vect is the data set. Then we store it.
vect = stub.GetFeature(route_guide_pb2.Vector(poids="pret"))
# We convert the set of data in the good format.
data = vect.poids.split("<samples>")
dataSampleSet = std.str2datadict(data[0])
data2 = data[1].split("<#compo>")
numSamples = int(data2[0])
nbCompo = int(data2[1])
# This second call serves to get the departure vector.
vect = stub.GetFeature(route_guide_pb2.Vector(poids="getw0"))
info = vect.poids.split("<<||>>")
vect.poids = info[0]
step = float(info[1])
# Vector of the rests
m = {}
while (vect.poids != 'stop'):
print("iteration : " + str(it))
# Gradient descent on the sample.
nw = sgd.descent(dataSampleSet, std.str2dict(vect.poids), numSamples, step)
# Updating of m
stepedGradient = std.sparse_mult(step,nw)
m = std.sparse_vsum(m,stepedGradient)
# Get the nbCompo biggest values in m, put it in g and remove them of m
g = std.infiniteNormInd(m,nbCompo)
# The result is sent to the server.
strVect = std.dict2str(g)
vect.poids = strVect + "<bytes>" + str(sys.getsizeof(strVect))
vect = stub.GetFeature(route_guide_pb2.Vector(poids=vect.poids))
if (vect.poids != 'stop'):
info = vect.poids.split("<<||>>")
vect.poids = info[0]
step = float(info[1])
it += 1
print(vect)
def GetFeature(self, request, context):
######################################################################
# Section 1 : wait for all the clients -> get their vectors and
# appoint one of them as the printer.
self.iterator += 1
if (request.poids == "pret" or request.poids == "getw0"):
self.vectors.append(request.poids)
else:
entry = request.poids.split("<bytes>")
b = int(entry[1])
if (self.epoch in self.bytesTab):
self.bytesTab[self.epoch] += b
else:
self.bytesTab[self.epoch] = b
v = std.str2dict(entry[0])
self.vectors.append(v)
self.enter_condition = (self.iterator == nbClients)
waiting.wait(lambda: self.enter_condition)
self.printerThreadName = threading.current_thread().name
######################################################################
######################################################################
# Section 2 : compute the new vector -> send the data, a merge of
# all the vectors we got from the clients or the message 'stop' the
# signal to the client that we converged.
normDiff = 0
normGradW = 0
normPrecW = 0
if (request.poids == 'pret'):
vector = std.datadict2Sstr(trainingSet) + "<samples>" + str(
numSamples) + "<#compo>" + str(nbCompo)
elif (request.poids == 'getw0'):
vector = std.dict2str(w0) + "<<||>>" + str(self.step)
else:
# Modification of the vector of parameters
gradParam = std.mergeSGD(self.vectors)
vector = std.sparse_vsous(self.oldParam, gradParam)
# Normalization of the vector of parameters
normW = math.sqrt(std.sparse_dot(vector, vector))
vector = std.sparse_mult(1 / normW, vector)
# Checking of the stoping criterion
diff = std.sparse_vsous(self.oldParam, vector)
normDiff = math.sqrt(std.sparse_dot(diff, diff))
normGradW = math.sqrt(std.sparse_dot(gradParam, gradParam))
normPrecW = math.sqrt(std.sparse_dot(self.oldParam, self.oldParam))
if ((normDiff <= c1 * normPrecW) or (self.epoch > nbMaxCall)
or (normGradW <= c2 * self.normGW0)):
self.paramVector = vector
vector = 'stop'
else:
vector = std.dict2str(vector) + "<<||>>" + str(self.step)
######################################################################
######################################################################
# Section 3 : wait that all the threads pass the computation area, and
# store the new computed vector.
realComputation = (request.poids != 'pret') and (
request.poids != 'getw0') and (vector != 'stop')
self.iterator -= 1
self.exit_condition = (self.iterator == 0)
waiting.wait(lambda: self.exit_condition)
if (realComputation):
self.oldParam = std.str2dict(vector.split("<<||>>")[0])
######################################################################
###################### PRINT OF THE CURRENT STATE ######################
##################### AND DO CRITICAL MODIFICATIONS ####################
if (threading.current_thread().name == self.printerThreadName):
std.printTraceRecData(self.epoch, vector, self.paramVector,
self.testingErrors, self.trainingErrors,
normDiff, normGradW, normPrecW, normGW0,
realComputation, self.oldParam, trainingSet,
testingSet, nbTestingData, nbExamples, c1,
c2, l, nbCompo, filePath)
self.merged.append(self.oldParam)
self.epoch += 1
self.step *= 0.9 #std.stepSize(nbExamples, self.epoch, nbDesc, nbCompo)
############################### END OF PRINT ###########################
dataTest = trainingSet[9]
label = dataTest.get(-1, 0)
example = std.take_out_label(dataTest)
print("label = " + str(label))
print("SVM says = " + str(std.sparse_dot(self.oldParam, example)))
######################################################################
# Section 4 : empty the storage list of the vectors, and wait for all
# the threads.
self.vectors = []
waiting.wait(lambda: (self.vectors == []))
######################################################################
#time.sleep(1)
return route_guide_pb2.Vector(poids=vector)
def GetFeature(self, request, context):
######################################################################
# Section 1 : wait for all the clients -> get their vectors and
# appoint one of them as the printer.
print(self.epoch)
self.printerThreadName = threading.current_thread().name
if (request.poids == "pret" or request.poids == "getw0"
or request.poids[:5] == "chunk"):
self.iterator += 1
self.vectors.append(request.poids)
self.enter_condition = (self.iterator == nbClients)
waiting.wait(lambda: self.enter_condition)
if ((way2work == "sync") and (request.poids != "pret")
and (request.poids != "getw0")
and (request.poids[:5] != "chunk")):
self.iterator += 1
self.vectors.append(std.str2dict(
request.poids.split("<delay>")[0]))
self.enter_condition = (self.iterator == nbClients)
waiting.wait(lambda: self.enter_condition)
if ((threading.current_thread().name == self.printerThreadName)
and (self.epoch == 1)):
############ Starting of the timer to time the run ############
self.startTime = time.time()
######################################################################
######################################################################
# Section 2 : compute the new vector -> send the data, a merge of
# all the vectors we got from the clients or the message 'stop' the
# signal to the client that we converged.
normDiff = 0
normGradW = 0
normPrecW = 0
if (request.poids == 'pret'):
vector = str(nbChunks) + "<depre>" + str(l) + "<samples>" + str(
numSamples)
elif (request.poids[:5] == 'chunk'):
chunk = request.poids.split("<nb>")
chunk = int(chunk[1])
vector = std.datadict2Sstr(
trainingSet[(chunk - 1) * chunkSize:chunk * chunkSize])
elif (request.poids == 'getw0'):
vector = std.dict2str(w0)
else:
if (way2work == "sync"):
gradParam = std.mergeSGD(self.vectors)
if (self.epoch == 2):
self.normGradW0 = math.sqrt(
std.sparse_dot(gradParam, gradParam))
normGradW = math.sqrt(std.sparse_dot(gradParam, gradParam))
gradParam = std.sparse_mult(self.step, gradParam)
vector = std.sparse_vsous(self.oldParam, gradParam)
else:
info = request.poids.split("<delay>")
grad_vector = std.str2dict(info[0])
if (self.epoch == 2):
self.normGradW0 = math.sqrt(
std.sparse_dot(grad_vector, grad_vector))
normGradW = math.sqrt(std.sparse_dot(grad_vector, grad_vector))
wt = std.str2dict(info[1])
vector = std.asynchronousUpdate(self.oldParam, grad_vector, wt,
l, self.step)
######## NORMALIZATION OF THE VECTOR OF PARAMETERS #########
normW = math.sqrt(std.sparse_dot(vector, vector))
vector = std.sparse_mult(1. / normW, vector)
############################################################
diff = std.sparse_vsous(self.oldParam, vector)
normDiff = math.sqrt(std.sparse_dot(diff, diff))
normPrecW = math.sqrt(std.sparse_dot(self.oldParam, self.oldParam))
if ((normDiff <= c1 * normPrecW) or (self.epoch > nbMaxCall)
or (normGradW <= c2 * normGW0)):
self.paramVector = vector
print("1 : " + str((normDiff <= c1 * normPrecW)))
print("2 : " + str((self.epoch > nbMaxCall)))
print("3 : " + str((normGradW <= c2 * normGW0)))
vector = 'stop'
else:
vector = std.dict2str(vector)
######################################################################
######################################################################
# Section 3 : wait that all the threads pass the computation area, and
# store the new computed vector.
realComputation = (request.poids != 'pret') and (
request.poids !=
'getw0') and (vector != 'stop') and (request.poids[:5] != 'chunk')
if (realComputation):
self.oldParam = std.str2dict(vector)
######################################################################
###################### PRINT OF THE CURRENT STATE ######################
##################### AND DO CRITICAL MODIFICATIONS ####################
if (((threading.current_thread().name == self.printerThreadName) and
(way2work == "sync")) or (way2work == "async")):
print("oooooooo")
endTime = time.time()
duration = endTime - self.startTime
if (vector == 'stop'):
print("The server ran during : " + str(duration))
std.printTraceRecData(self.epoch, vector, self.testingErrors,
self.trainingErrors, normDiff, normGradW,
normPrecW, normGW0, realComputation,
self.oldParam, trainingSet, testingSet,
nbTestingData, nbExamples, c1, c2, l,
duration, filePath)
self.merged.append(self.oldParam)
if (realComputation):
self.epoch += 1
self.step *= 0.9
############################### END OF PRINT ###########################
######################################################################
# Section 4 : empty the storage list of the vectors, and wait for all
# the threads.
self.vectors = []
######################################################################
######################################################################
# Section 5 : synchronize all clients at the end of a server iteration
if (way2work == "sync"):
self.iterator -= 1
self.exit_condition = (self.iterator == 0)
waiting.wait(lambda: self.exit_condition)
#time.sleep(1)
return route_guide_pb2.Vector(poids=vector)
def GetFeature(self, request, context):
######################################################################
# Section 1 : wait for all the clients -> get their vectors and
# appoint one of them as the printer.
if (way2work == "sync"):
self.iterator += 1
if (request.poids == "pret" or request.poids == "getw0"):
self.vectors.append(request.poids)
else:
self.vectors.append(
std.str2dict(request.poids.split("<delay>")[0]))
self.enter_condition = (self.iterator == nbClients)
waiting.wait(lambda: self.enter_condition)
self.printerThreadName = threading.current_thread().name
######################################################################
######################################################################
# Section 2 : compute the new vector -> send the data, a merge of
# all the vectors we got from the clients or the message 'stop' the
# signal to the client that we converged.
normDiff = 0
normGradW = 0
normPrecW = 0
if (request.poids == 'pret'):
vector = std.datadict2Sstr(trainingSet) + "<depre>" + str(
l) + "<samples>" + str(numSamples)
elif (request.poids == 'getw0'):
vector = std.dict2str(w0)
else:
if (way2work == "sync"):
gradParam = std.mergeSGD(self.vectors)
gradParam = std.sparse_mult(self.step, gradParam)
vector = std.sparse_vsous(self.oldParam, gradParam)
else:
info = request.poids.split("<delay>")
grad_vector = std.str2dict(info[0])
wt = std.str2dict(info[1])
vector = std.asynchronousUpdate(self.oldParam, grad_vector, wt,
l, self.step)
######## NORMALIZATION OF THE VECTOR OF PARAMETERS #########
normW = math.sqrt(std.sparse_dot(vector, vector))
vector = std.sparse_mult(1. / normW, vector)
############################################################
diff = std.sparse_vsous(self.oldParam, vector)
normDiff = math.sqrt(std.sparse_dot(diff, diff))
normGradW = math.sqrt(std.sparse_dot(vector, vector))
normPrecW = math.sqrt(std.sparse_dot(self.oldParam, self.oldParam))
if ((normDiff <= c1 * normPrecW) or (self.epoch > nbMaxCall)
or (normGradW <= c2 * self.normgW0)):
self.paramVector = vector
vector = 'stop'
else:
vector = std.dict2str(vector)
######################################################################
######################################################################
# Section 3 : wait that all the threads pass the computation area, and
# store the new computed vector.
realComputation = (request.poids != 'pret') and (
request.poids != 'getw0') and (vector != 'stop')
if (way2work == "sync"):
self.iterator -= 1
self.exit_condition = (self.iterator == 0)
waiting.wait(lambda: self.exit_condition)
if (realComputation):
self.oldParam = std.str2dict(vector)
######################################################################
###################### PRINT OF THE CURRENT STATE ######################
##################### AND DO CRITICAL MODIFICATIONS ####################
if ((threading.current_thread().name == self.printerThreadName) &
(way2work == "sync") or (way2work == "async")):
std.printTraceGenData(self.epoch, vector, self.paramVector,
self.testingErrors, self.trainingErrors,
trainaA, trainaB, trainoA, trainoB, hypPlace,
normDiff, normGradW, normPrecW, self.normgW0,
w0, realComputation, self.oldParam,
trainingSet, testingSet, nbTestingData,
nbExamples, nbMaxCall, self.merged, "", c1,
c2, l)
self.merged.append(self.oldParam)
self.epoch += 1
self.step *= 0.9
dataTest = trainingSet[9]
label = dataTest.get(-1, 0)
example = std.take_out_label(dataTest)
print("label = " + str(label))
print("SVM says = " + str(std.sparse_dot(self.oldParam, example)))
############################### END OF PRINT ###########################
######################################################################
# Section 4 : empty the storage list of the vectors, and wait for all
# the threads.
self.vectors = []
waiting.wait(lambda: (self.vectors == []))
######################################################################
#time.sleep(1)
return route_guide_pb2.Vector(poids=vector)
spdsous = std.sparse_vsous(spV1, spV2)
print("spdsous = " + str(spdsous))
print('')
print("############ Test of the sparse division. ############")
print('')
spddiv = std.sparse_vdiv(spV1, spV2)
print("spddiv = " + str(spddiv))
print('')
print("############ Test of the elementwise multiplication. ############")
print('')
spdmult = std.sparse_mult(2, spV1)
print("spdmult = " + str(spdmult))
print('')
print("######### Test of the conversion dict -> str. ##########")
print('')
spddict2str = std.dict2str(spV1)
print("spV1 under string is : " + spddict2str)
print('')
print("######### Test of the conversion str -> dict. ##########")
print('')
spdstr2dict = std.str2dict(spddict2str)
print("spV1 under dict is : " + str(spdstr2dict))
