def exo67():
print("\n\n>>EXERCICE 6 et 7 : Calcul matriciel")
print(" --- K=1 ---")
#Xtrain, ytrain, Xvalid, yvalid, Xtest, ytest = utils.readMoonFile()
Xtrain = [[30, 20, 40, 50], [25, 15, 35, 45]]
ytrain = [0,0]
default_h = 2
nn = NeuralNetwork(len(Xtrain[0]), default_h, utils.getClassCount(ytrain), K=1, wd=0)
nne = NeuralNetworkEfficient(len(Xtrain[0]), default_h, utils.getClassCount(ytrain), K=1, wd=0)
nne._w1 = nn._w1 # trick pour que l'aleatoire soit egale
nne._w2 = nn._w2
nn.train(Xtrain,ytrain,1)
nne.train(Xtrain,ytrain,1)
utils.compareNN(nn,nne)
print(" --- K=10 ---")
Xtrain = [[30, 20, 40, 50], [25, 15, 35, 45],[30, 76, 45, 44],[89, 27, 42, 52],[30, 24, 44, 53],[89, 25, 45, 50],[30, 20, 40, 50],[30, 65, 47, 50],[30, 34, 40, 50],[39, 20, 29, 58]]
ytrain = [0,0,0,0,0,0,0,0,0,0]
default_h = 2
nn = NeuralNetwork(len(Xtrain[0]), default_h, utils.getClassCount(ytrain), K=10, wd=0)
nne = NeuralNetworkEfficient(len(Xtrain[0]), default_h, utils.getClassCount(ytrain), K=10, wd=0)
nne._w1 = nn._w1 # trick pour que l'aleatoire soit egale
nne._w2 = nn._w2
nn.train(Xtrain,ytrain,1)
nne.train(Xtrain,ytrain,1)
utils.compareNN(nn,nne,10)
def test():
Xtrain, ytrain, Xvalid, yvalid, Xtest, ytest = utils.readMoonFile()
h = 200
wd = 0.0001
K = 200
maxIter = 500
# neuralNetwork = NeuralNetwork(len(Xtrain[0]), h, utils.getClassCount(ytrain), K=10, wd=wd)
neuralNetworkEfficient = NeuralNetworkEfficient(len(Xtrain[0]), h, utils.getClassCount(ytrain), K, wd=wd)
# neuralNetworkEfficient._w1 = neuralNetwork._w1
# neuralNetworkEfficient._w2 = neuralNetwork._w2
# neuralNetwork.train(Xtrain, ytrain, maxIter)
# predTrain = neuralNetwork.computePredictions(Xtrain)
# predValid = neuralNetwork.computePredictions(Xvalid)
# predTest = neuralNetwork.computePredictions(Xtest)
# trainEfficiency = utils.calculatePredictionsEfficiency(predTrain, ytrain)
# validEfficiency = utils.calculatePredictionsEfficiency(predValid, yvalid)
# testEfficiency = utils.calculatePredictionsEfficiency(predTest, ytest)
# print( "Train Err: " + "{:.2f}".format(100 - trainEfficiency) + "%" \
# + " / Valid Err: " + "{:.2f}".format(100 - validEfficiency) + "%" \
# + " / Test Err: " + "{:.2f}".format(100 - testEfficiency) + "%")
neuralNetworkEfficient.train(Xtrain, ytrain, maxIter)
predTrain = neuralNetworkEfficient.computePredictions(Xtrain)
predValid = neuralNetworkEfficient.computePredictions(Xvalid)
predTest = neuralNetworkEfficient.computePredictions(Xtest)
trainEfficiency = utils.calculatePredictionsEfficiency(predTrain, ytrain)
validEfficiency = utils.calculatePredictionsEfficiency(predValid, yvalid)
testEfficiency = utils.calculatePredictionsEfficiency(predTest, ytest)
print( "Train Err: " + "{:.2f}".format(100 - trainEfficiency) + "%" \
+ " / Valid Err: " + "{:.2f}".format(100 - validEfficiency) + "%" \
+ " / Test Err: " + "{:.2f}".format(100 - testEfficiency) + "%")
def exo9_10():
print("\n\n>>EXERCICE 9-10")
print("Train Err;Valid Err;Test Err;Avg Cost Train;Avg Cost Valid;Avg Cost Test")
h = 300
wd = 0.0001
maxIter = 500
K = 50
Xtrain, ytrain, Xvalid, yvalid, Xtest, ytest = utils.readMNISTfile()
neuralNetwork = NeuralNetworkEfficient(len(Xtrain[0]), h, utils.getClassCount(ytrain), K, wd)
neuralNetwork.setDataSets(Xtrain, Xvalid, Xtest, ytrain, yvalid, ytest)
neuralNetwork.train(Xtrain, ytrain, maxIter)
epochsData = ""
for d in neuralNetwork.epochData:
epochsData += d+"\n"
f = open('no9.txt', 'w')
f.write(epochsData)
f.close()
x = range(1, maxIter+1, 10)
title = "Taux d'erreur - "+str(maxIter)+" epoques"
name = str(h) + "_" + str(wd)+ "_" + str(h)+ "_" + "taux_erreur"
utils.plotCourbeApprentissage(neuralNetwork.trainError, neuralNetwork.validError, neuralNetwork.testError, x, title, name)
title = "Cout moyen - "+str(maxIter)+" epoques"
name = str(h) + "_" + str(wd)+ "_" + str(h)+ "_" +"cout_moyen"
utils.plotCourbeApprentissage(neuralNetwork.trainSumL, neuralNetwork.validSumL, neuralNetwork.testSumL, x, title, name)
def trainAndPrint(Xtrain, ytrain, Xvalid, yvalid, Xtest, ytest, h, wd, maxIter):
neuralNetwork = NeuralNetworkEfficient(len(Xtrain[0]), h, utils.getClassCount(ytrain), K=50, wd=wd)
neuralNetwork.train(Xtrain, ytrain, maxIter)
predTrain = neuralNetwork.computePredictions(Xtrain)
predValid = neuralNetwork.computePredictions(Xvalid)
predTest = neuralNetwork.computePredictions(Xtest)
trainEfficiency = utils.calculatePredictionsEfficiency(predTrain, ytrain)
validEfficiency = utils.calculatePredictionsEfficiency(predValid, yvalid)
testEfficiency = utils.calculatePredictionsEfficiency(predTest, ytest)
hparams = "[h: " + str(h) + " / wd: " + str(wd) + " / " + str(maxIter) + " epoques]"
title = "Train Err: " + "{:.2f}".format(100 - trainEfficiency) + "%" \
+ " / Valid Err: " + "{:.2f}".format(100 - validEfficiency) + "%" \
+ " / Test Err: " + "{:.2f}".format(100 - testEfficiency) + "%"
name = "regions_decision" + str(h) + "_" + str(wd) + "_" + str(maxIter)
utils.plotRegionsDescision(Xtrain, ytrain, Xvalid, yvalid, Xtest, ytest, neuralNetwork, title, name,hparams)
def exo8():
print("\n\n>>EXERCICE 8 MNIST")
Xtrain, ytrain, Xvalid, yvalid, Xtest, ytest = utils.readMNISTfile()
default_h = 30
maxIter = 1
neuralNetwork = NeuralNetwork(len(Xtrain[0]), default_h, utils.getClassCount(ytrain),K=100)
neuralNetworkEfficient = NeuralNetworkEfficient(len(Xtrain[0]), default_h, utils.getClassCount(ytrain),K=100)
neuralNetworkEfficient._w1 = neuralNetwork._w1
neuralNetworkEfficient._w2 = neuralNetwork._w2
print("--- Reseau de depart ---")
t1 = datetime.now()
neuralNetwork.train(Xtrain, ytrain, maxIter)
t2 = datetime.now()
delta = t2 - t1
print("Cela a mis : " + str(delta.total_seconds()) + " secondes")
print("--- Reseau optimise ---")
t1 = datetime.now()
neuralNetworkEfficient.train(Xtrain, ytrain, maxIter)
t2 = datetime.now()
delta = t2 - t1
print("Cela a mis : " + str(delta.total_seconds()) + " secondes")
def test():
Xtrain, ytrain, Xvalid, yvalid, Xtest, ytest = utils.readMoonFile()
h = 200
wd = 0.0001
K = 200
maxIter = 500
# neuralNetwork = NeuralNetwork(len(Xtrain[0]), h, utils.getClassCount(ytrain), K=10, wd=wd)
neuralNetworkEfficient = NeuralNetworkEfficient(
len(Xtrain[0]), h, utils.getClassCount(ytrain), K, wd=wd)
# neuralNetworkEfficient._w1 = neuralNetwork._w1
# neuralNetworkEfficient._w2 = neuralNetwork._w2
# neuralNetwork.train(Xtrain, ytrain, maxIter)
# predTrain = neuralNetwork.computePredictions(Xtrain)
# predValid = neuralNetwork.computePredictions(Xvalid)
# predTest = neuralNetwork.computePredictions(Xtest)
# trainEfficiency = utils.calculatePredictionsEfficiency(predTrain, ytrain)
# validEfficiency = utils.calculatePredictionsEfficiency(predValid, yvalid)
# testEfficiency = utils.calculatePredictionsEfficiency(predTest, ytest)
# print( "Train Err: " + "{:.2f}".format(100 - trainEfficiency) + "%" \
# + " / Valid Err: " + "{:.2f}".format(100 - validEfficiency) + "%" \
# + " / Test Err: " + "{:.2f}".format(100 - testEfficiency) + "%")
neuralNetworkEfficient.train(Xtrain, ytrain, maxIter)
predTrain = neuralNetworkEfficient.computePredictions(Xtrain)
predValid = neuralNetworkEfficient.computePredictions(Xvalid)
predTest = neuralNetworkEfficient.computePredictions(Xtest)
trainEfficiency = utils.calculatePredictionsEfficiency(predTrain, ytrain)
validEfficiency = utils.calculatePredictionsEfficiency(predValid, yvalid)
testEfficiency = utils.calculatePredictionsEfficiency(predTest, ytest)
print( "Train Err: " + "{:.2f}".format(100 - trainEfficiency) + "%" \
+ " / Valid Err: " + "{:.2f}".format(100 - validEfficiency) + "%" \
+ " / Test Err: " + "{:.2f}".format(100 - testEfficiency) + "%")
def exo8():
print("\n\n>>EXERCICE 8 MNIST")
Xtrain, ytrain, Xvalid, yvalid, Xtest, ytest = utils.readMNISTfile()
default_h = 30
maxIter = 1
neuralNetwork = NeuralNetwork(len(Xtrain[0]),
default_h,
utils.getClassCount(ytrain),
K=100)
neuralNetworkEfficient = NeuralNetworkEfficient(
len(Xtrain[0]), default_h, utils.getClassCount(ytrain), K=100)
neuralNetworkEfficient._w1 = neuralNetwork._w1
neuralNetworkEfficient._w2 = neuralNetwork._w2
print("--- Reseau de depart ---")
t1 = datetime.now()
neuralNetwork.train(Xtrain, ytrain, maxIter)
t2 = datetime.now()
delta = t2 - t1
print("Cela a mis : " + str(delta.total_seconds()) + " secondes")
print("--- Reseau optimise ---")
t1 = datetime.now()
neuralNetworkEfficient.train(Xtrain, ytrain, maxIter)
t2 = datetime.now()
delta = t2 - t1
print("Cela a mis : " + str(delta.total_seconds()) + " secondes")
def trainAndPrint(Xtrain, ytrain, Xvalid, yvalid, Xtest, ytest, h, wd,
maxIter):
neuralNetwork = NeuralNetworkEfficient(len(Xtrain[0]),
h,
utils.getClassCount(ytrain),
K=50,
wd=wd)
neuralNetwork.train(Xtrain, ytrain, maxIter)
predTrain = neuralNetwork.computePredictions(Xtrain)
predValid = neuralNetwork.computePredictions(Xvalid)
predTest = neuralNetwork.computePredictions(Xtest)
trainEfficiency = utils.calculatePredictionsEfficiency(predTrain, ytrain)
validEfficiency = utils.calculatePredictionsEfficiency(predValid, yvalid)
testEfficiency = utils.calculatePredictionsEfficiency(predTest, ytest)
hparams = "[h: " + str(h) + " / wd: " + str(wd) + " / " + str(
maxIter) + " epoques]"
title = "Train Err: " + "{:.2f}".format(100 - trainEfficiency) + "%" \
+ " / Valid Err: " + "{:.2f}".format(100 - validEfficiency) + "%" \
+ " / Test Err: " + "{:.2f}".format(100 - testEfficiency) + "%"
name = "regions_decision" + str(h) + "_" + str(wd) + "_" + str(maxIter)
utils.plotRegionsDescision(Xtrain, ytrain, Xvalid, yvalid, Xtest, ytest,
neuralNetwork, title, name, hparams)
def exo9_10():
print("\n\n>>EXERCICE 9-10")
print(
"Train Err;Valid Err;Test Err;Avg Cost Train;Avg Cost Valid;Avg Cost Test"
)
h = 300
wd = 0.0001
maxIter = 500
K = 50
Xtrain, ytrain, Xvalid, yvalid, Xtest, ytest = utils.readMNISTfile()
neuralNetwork = NeuralNetworkEfficient(len(Xtrain[0]), h,
utils.getClassCount(ytrain), K, wd)
neuralNetwork.setDataSets(Xtrain, Xvalid, Xtest, ytrain, yvalid, ytest)
neuralNetwork.train(Xtrain, ytrain, maxIter)
epochsData = ""
for d in neuralNetwork.epochData:
epochsData += d + "\n"
f = open('no9.txt', 'w')
f.write(epochsData)
f.close()
x = range(1, maxIter + 1, 10)
title = "Taux d'erreur - " + str(maxIter) + " epoques"
name = str(h) + "_" + str(wd) + "_" + str(h) + "_" + "taux_erreur"
utils.plotCourbeApprentissage(neuralNetwork.trainError,
neuralNetwork.validError,
neuralNetwork.testError, x, title, name)
title = "Cout moyen - " + str(maxIter) + " epoques"
name = str(h) + "_" + str(wd) + "_" + str(h) + "_" + "cout_moyen"
utils.plotCourbeApprentissage(neuralNetwork.trainSumL,
neuralNetwork.validSumL,
neuralNetwork.testSumL, x, title, name)
def exo67():
print("\n\n>>EXERCICE 6 et 7 : Calcul matriciel")
print(" --- K=1 ---")
#Xtrain, ytrain, Xvalid, yvalid, Xtest, ytest = utils.readMoonFile()
Xtrain = [[30, 20, 40, 50], [25, 15, 35, 45]]
ytrain = [0, 0]
default_h = 2
nn = NeuralNetwork(len(Xtrain[0]),
default_h,
utils.getClassCount(ytrain),
K=1,
wd=0)
nne = NeuralNetworkEfficient(len(Xtrain[0]),
default_h,
utils.getClassCount(ytrain),
K=1,
wd=0)
nne._w1 = nn._w1 # trick pour que l'aleatoire soit egale
nne._w2 = nn._w2
nn.train(Xtrain, ytrain, 1)
nne.train(Xtrain, ytrain, 1)
utils.compareNN(nn, nne)
print(" --- K=10 ---")
Xtrain = [[30, 20, 40, 50], [25, 15, 35, 45], [30, 76, 45, 44],
[89, 27, 42, 52], [30, 24, 44, 53], [89, 25, 45, 50],
[30, 20, 40, 50], [30, 65, 47, 50], [30, 34, 40, 50],
[39, 20, 29, 58]]
ytrain = [0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
default_h = 2
nn = NeuralNetwork(len(Xtrain[0]),
default_h,
utils.getClassCount(ytrain),
K=10,
wd=0)
nne = NeuralNetworkEfficient(len(Xtrain[0]),
default_h,
utils.getClassCount(ytrain),
K=10,
wd=0)
nne._w1 = nn._w1 # trick pour que l'aleatoire soit egale
nne._w2 = nn._w2
nn.train(Xtrain, ytrain, 1)
nne.train(Xtrain, ytrain, 1)
utils.compareNN(nn, nne, 10)
