def test_nbr_neuron(list_test):
color_list=['r','g','b','k','m','c','y']
color_list *= 3
k=0
for i in list_test :
my_layer1 = Layer.Linear(6,i)
my_layer2 = ActivationFunctions.Tanh()
my_layer5 = Layer.Linear(i,i)
my_layer6 = ActivationFunctions.Tanh()
my_layer3 = Layer.Linear(i,1)
my_layer4 = ActivationFunctions.Sigmoid()
my_NN = Neural_network.NeuralNet([my_layer1, my_layer2, my_layer5, my_layer6, my_layer3, my_layer4])
chi2_list, error_list = User.train(my_NN, data_train_input, data_train_target, num_epochs = num_epoch_max, optimizer = Optimizer.SGD(lr = my_lr), batch_size=my_batch_size)
data_test_prediction = User.prediction(my_NN,data_test_input)
error_final = Error_round.error_round(data_test_prediction, data_test_target)
plt.plot(range(num_epoch_max), error_list, label= str(i), c=color_list[k])
plt.plot([num_epoch_max],[error_final], marker='o', c=color_list[k])
plt.xlabel('Epoch')
plt.ylabel('Training round error')
k+=1
plt.legend(title='Neurons')
plt.title('Optimisation of the number of neurons')
plt.show()
def test_nbr_layer(list_test, n_neuron):
color_list=['r','g','b','k','m','c','y']
color_list *= 3
k=0
my_layerini1 = Layer.Linear(6,n_neuron)
my_layerini2 = ActivationFunctions.Tanh()
my_layerfini1 = Layer.Linear(n_neuron,1)
my_layerfini2 = ActivationFunctions.Sigmoid()
for i in list_test :
layers_new = [my_layerini1, my_layerini2]
for j in range(i) :
layers_new += [Layer.Linear(n_neuron,n_neuron),ActivationFunctions.Tanh()]
layers_new += [my_layerfini1, my_layerfini2]
my_NN = Neural_network.NeuralNet(layers_new)
chi2_list, error_list = User.train(my_NN, data_train_input, data_train_target, num_epochs = num_epoch_max,optimizer = Optimizer.SGD(lr = my_lr), batch_size=my_batch_size)
data_test_prediction = User.prediction(my_NN,data_test_input)
error_final = Error_round.error_round(data_test_prediction, data_test_target)
plt.plot(range(num_epoch_max), error_list, label= str(i),c=color_list[k])
plt.plot([num_epoch_max],[error_final], marker='o', c=color_list[k])
plt.xlabel('Epoch')
plt.ylabel('Training round error')
k+=1
plt.legend(title='Hidden layers')
plt.title('Optimisation of the number of hidden layers')
plt.show()
def test_NeuralNet() :
my_layer1 = Layer.Linear(3,2)
my_layer2 = ActivationFunctions.Tanh()
my_NN = Neural_network.NeuralNet([my_layer1,my_layer2])
input = np.array([[1,2,3],[4,5,6]])
grad = np.array([[0.5,0.2],[0.1,0.3]])
print('forward', my_NN.forward(input))
print('backward', my_NN.backward(grad))
'''OK'''
def test_train_prediction() :
my_layer1 = Layer.Linear(3,2)
my_layer2 = ActivationFunctions.Tanh()
my_NN = Neural_network.NeuralNet([my_layer1,my_layer2])
input = np.array([[1,2,3],[4,5,6]])
target = np.array([[0.5,0.2],[0.1,0.3]])
User.train(my_NN, input, target, batch_size = 1)
#By careful, we must have size_training = number of rows in our data
input_predict = np.array([[1,1,4],[0.5,2,4]])
print(User.prediction(my_NN,input_predict))
''' OK '''
def test_XOR() :
my_layer1 = Layer.Linear(2,3)
my_layer2 = ActivationFunctions.Tanh()
my_layer3 = Layer.Linear(3,1)
my_layer4 = ActivationFunctions.Sigmoid()
#my_layer3 = lib2.Arondi()
my_NN = Neural_network.NeuralNet([my_layer1,my_layer2,my_layer3,my_layer4])
input =np.array([[0, 0], [1, 0], [0, 1], [1, 1]])
target = np.array([[0], [1], [1], [0]])
User.train(my_NN, input, target, batch_size = 1,,num_epochs= 1000)
# By careful, we must have size_training = number of rows in our data
input_predict = np.array([[0, 0], [1, 0], [0, 1], [1, 1]])
print(User.prediction(my_NN,input_predict))
''' OK '''
def predict(symbImgs, topology):
# Flatten using knn first
knn = kNN.kNN()
flat_syms = knn.flatten_symbols(symbImgs)
binary_symbs = preprocessor.binarize(flat_syms)
flattened = logistic_regression.flatten(binary_symbs)
knn.load_MNIST()
m_data = logistic_regression.flatten(knn.mnist_data)
m_labels = knn.mnist_labels
nn = neural_network.NeuralNet(topology)
print("> Fitting NN")
m_labels = toArray(m_labels[:10000])
nn.fit(m_data[:10000], m_labels)
results = []
print("> Predicting NN")
for i in range(1, len(flattened) + 1):
if i % 1000 == 0:
print(i)
results.append(nn.predict(flattened[i - 1:i]))
return results
#script which generates prediction for the MNIST dataset
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import neural_network as nn
import sys
import os
sys.path.append(os.getcwd())
os.chdir("..")
data = np.array(pd.read_csv("mnist_train.csv"))
X = data[:, 1:]
Y = data[:, 0][:, np.newaxis]
os.chdir("neural-network")
model = nn.NeuralNet(hidden_size=60, n_labels=10, lamb=1, alpha=0.4)
theta1, theta2 = model.import_theta("weights_digits2.csv", X)
prediction, accuracy = model.predict(theta1, theta2, X, Y)
def show_pred():
a = np.random.randint(60000)
print("The predicted number is", prediction[a])
fig, ax = plt.subplots()
ax.imshow(X[a, :].reshape((28, 28)), cmap="Greys")
plt.show()
#quitar la columna diagnosis y qrs
X = arch.drop(columns=['diagnosis'])
# reemplazaremos el diagnostico con 0 y 1 (0 no esta enfermo, 1 esta enfermo)
arch['diagnosis'] = arch['diagnosis'].replace(1, 0)
arch['diagnosis'] = arch['diagnosis'].replace(2, 1)
y_label = arch['diagnosis'].values.reshape(X.shape[0], 1)
# estandarizar el dataset
sc = StandardScaler()
sc.fit(X)
X = sc.transform(X)
nn = neural_network.NeuralNet()
nn.entrenar(X, y_label)
#predecir
result = nn.predecir(X)
print(result)
precistion = nn.exactitud(y_label, result)
# verificar que se paresca
print("procentaje de precision", float(precistion), "%")
result = nn.predecir(X)
print(
"-----------------------------------------------------------------------------------------------------------:"
)
def train_simultaneousNN(
inputs_train: Tensor,
targets_train: Tensor,
loss: Loss.Loss = Loss.MeanSquareError(),
optimizer: OptimizerClass.Optimizer = OptimizerClass.SGD(),
num_epochs: int = 5000,
batch_size: int = 32) -> tuple:
size_training = inputs_train.shape[0]
Result_chi2 = [[], [], [], [], [], [], [], [], []]
list_epoch = np.array(range(10, 50, 5)) / 100 * num_epochs
'''initialisation des 9 NN''' #verifier question seed()
list_net = []
for i in range(9):
layers = []
layers.append(Layer.Linear(6, 4))
layers.append(ActivationFunctions.Tanh())
layers.append(Layer.Linear(4, 2))
layers.append(ActivationFunctions.Tanh())
layers.append(Layer.Linear(2, 1))
layers.append(ActivationFunctions.Sigmoid())
list_net.append(Neural_network.NeuralNet(layers))
destroyed_NN = []
nbr_batch = size_training // batch_size
''' training des 9 NN'''
for epoch in range(num_epochs):
for k in range(9):
if k not in destroyed_NN:
Chi2_train = 0
for i in range(0, size_training, batch_size):
# 1) feed forward
y_actual = list_net[k].forward(inputs_train[i:i +
batch_size])
# 2) compute the loss and the gradients
Chi2_train += loss.loss(targets_train[i:i + batch_size],
y_actual)
grad_ini = loss.grad(targets_train[i:i + batch_size],
y_actual)
# 3)feed backwards
grad_fini = list_net[k].backward(grad_ini)
# 4) update the net
optimizer.step(list_net[k], n_epoch=epoch)
Chi2_train = Chi2_train / nbr_batch
Result_chi2[k].append(Chi2_train)
'''Supression du NN le moins efficace '''
if epoch in list_epoch:
Comparaison = [[], []]
for k in range(9):
if k not in destroyed_NN:
ErrorSlope = np.polyfit(np.array(range(epoch - 49, epoch)),
Result_chi2[k][-50:-1], 1)[0]
MixedError = Result_chi2[k][-1] * (1 -
np.arctan(ErrorSlope) /
(np.pi / 2))
Comparaison[0].append(k)
Comparaison[1].append(MixedError)
k = Comparaison[0][Comparaison[1].index(max(Comparaison[1]))]
destroyed_NN.append(k)
if epoch % 100 == 0:
print('epoch : ' + str(epoch) + "/" + str(num_epochs) + "\r",
end="")
for k in range(9):
if k not in destroyed_NN:
my_NN = list_net[k]
return my_NN, Result_chi2
x = x.astype(float)
means, sd = NN.get_moments(x)
x = NN.standardize(x, means, sd)
#x = x/255
x_test = np.delete(x_test, np.s_[:1], 1)
x_test = np.transpose(x_test)
x_dim = x.shape
t = np.zeros((10, x_dim[1]))
arange = np.arange(x_dim[1])
t[truth, arange] = 1
print(t)
nn = NN.NeuralNet(nHidUnits, nInputs, nOutputU)
# weights = initWeights(nHidUnits,nInputs,nOutputU)
# w_trained = train(x,weights,nHidLay,t,sigmoid_,softmax_,600,0.1)
# predict(x_test, w_trained, nHidLay, sigmoid_pos, softmax_, truth_test)
#print(weights[0])
for seg in range(1, 9):
startI = int((seg - 1) * 0.2 * x_dim[1])
endI = int(seg * 0.2 * x_dim[1])
trainX = np.concatenate((x[:, :startI], x[:, endI:]), axis=1)
trainTruth = np.concatenate((t[:, :startI], t[:, endI:]), axis=1)
nn.train(trainX, trainTruth, NN.sigmoid_, NN.softmax_, 400, 0.1)
#print(w_trained[0])
my_initial_lr = 0.1
my_decay_coeff = 1 / 200
'''Construction of the neural network '''
my_layer1 = Layer.Linear(6, 5)
my_layer2 = ActivationFunctions.Tanh()
my_layer3 = Layer.Linear(5, 4)
my_layer4 = ActivationFunctions.Tanh()
my_layer5 = Layer.Linear(4, 3)
my_layer6 = ActivationFunctions.Tanh()
my_layer7 = Layer.Linear(3, 2)
my_layer8 = ActivationFunctions.Tanh()
my_layer9 = Layer.Linear(2, 1)
my_layer10 = ActivationFunctions.Sigmoid()
my_NN = Neural_network.NeuralNet([
my_layer1, my_layer2, my_layer3, my_layer4, my_layer5, my_layer6,
my_layer7, my_layer8, my_layer9, my_layer10
])
## Importation of the training and testing data
os.chdir(path_ini[:-4])
data_training_path = 'Data/data_train.csv'
data_test_path = 'Data/data_test.csv'
Data_train = pd.read_csv(data_training_path)
Data_test = pd.read_csv(data_test_path)
param = ['cosTBz', 'R2', 'chiProb', 'Ks_distChi', 'm_KSpipi_norm', 'Mbc_norm']
'''training set'''
data_train_input = np.array(Data_train[param][:train_size])
data_train_target = np.array(Data_train[['isSignal']][:train_size])
import Neural_Network_Library.user as User
'''
plt.close()
# Parameters' choice
'''seed '''
np.random.seed(1)
'''Construction of the neural network '''
my_layer1 = Layer.Linear(6, 4)
my_layer2 = ActivationFunctions.Tanh()
my_layer5 = Layer.Linear(4, 2)
my_layer6 = ActivationFunctions.Tanh()
my_layer3 = Layer.Linear(2, 1)
my_layer4 = ActivationFunctions.Sigmoid()
my_NN = Neural_network.NeuralNet(
[my_layer1, my_layer2, my_layer5, my_layer6, my_layer3, my_layer4])
'''Maximal number of epochs '''
Nmax = 50000
'''size of the training set and the testing set '''
train_size = 3000
test_size = 1500
'''size of the batch'''
my_batch_size = 100
''' learning rate'''
my_lr = 0.0005
'''importation of the training and testing data'''
os.chdir(path_ini[:-12]) #changement ici
Data_train = pd.read_csv('Data/data_train.csv')
Data_test = pd.read_csv('Data/data_test.csv')