from isanet.neural_network import MLPRegressor
from isanet.model import Mlp
from isanet.optimizer import SGD
from isanet.utils.model_utils import printMSE, printAcc, plotMse, save_data, load_data
from isanet.optimizer import EarlyStopping
from isanet.model_selection import Kfold, GridSearchCV
import numpy as np
dataset = np.genfromtxt('../dataset/cup10/ML-CUP19-TR_tr_vl_10.csv',
delimiter=',')
split = load_data("../dataset/cup10/4folds.index")
X_train = dataset[:, :-2]
Y_train = dataset[:, -2:]
es = EarlyStopping(0.009, 200)
mlp_r = MLPRegressor(X_train.shape[1], Y_train.shape[1])
grid = {
"n_layer_units": [[80], [100]],
"learning_rate": [0.03, 0.06, 0.08, 0.098],
"max_epoch": [30000],
"momentum": [0.2, 0.4, 0.6, 0.8, 0.9],
"nesterov": [True],
"kernel_regularizer": [0.0001, 0.0005, 0.0009, 0.0013],
"activation": ["sigmoid"],
"early_stop": [es],
}
gs = GridSearchCV(estimator=mlp_r, param_grid=grid, cv=split, verbose=1)
result = gs.fit(X_train, Y_train)
X_train, Y_train = load_monk("1", "train")
X_test, Y_test = load_monk("1", "test")
#create the model
model = Mlp()
# Specify the range for the weights and lambda for regularization
# Of course can be different for each layer
kernel_initializer = 0.003
kernel_regularizer = 0.001
# Add many layers with different number of units
model.add(4, input= 17, kernel_initializer, kernel_regularizer)
model.add(1, kernel_initializer, kernel_regularizer)
es = EarlyStopping(0.00009, 20) # eps_GL and s_UP
#fix which optimizer you want to use in the learning phase
model.setOptimizer(
SGD(lr = 0.83, # learning rate
momentum = 0.9, # alpha for the momentum
nesterov = True, # Specify if you want to use Nesterov
sigma = None # sigma for the Acc. Nesterov
))
#start the learning phase
model.fit(X_train,
Y_train,
epochs=600,
#batch_size=31,
validation_data = [X_test, Y_test],