from os import path sys.path.insert(0, "../../ISANet") sys.path.insert(0, "./") from isanet.model_selection import Kfold from isanet.utils.model_utils import save_data import numpy as np np.random.seed(42) TS = np.genfromtxt('ML-CUP19-TR.csv', delimiter=',') np.random.shuffle(TS) np.savetxt('cup20/ML-CUP19-TR_tr_vl.csv', TS[:1500, 1:], delimiter=',') np.savetxt('cup20/ML-CUP19-TR_test.csv', TS[1500:, 1:], delimiter=',') kf = Kfold(n_splits=4, shuffle=True) split = kf.split(TS[:1500, 1:]) save_data(split, "cup20/4folds.index") ten_features = [1, 2, 3, 4, 5, 6, 7, 8, 12, 15, 21, 22] np.savetxt('cup10/ML-CUP19-TR_tr_vl_10.csv', TS[:1500, ten_features], delimiter=',') np.savetxt('cup10/ML-CUP19-TR_test_10.csv', TS[1500:, ten_features], delimiter=',') save_data(split, "cup10/4folds.index")
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) save_data(result, 'large_grid_2_result.data')
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": [[70], [80]], # "learning_rate": [0.03, 0.36, 0.042, 0.048, 0.54, 0.06], "learning_rate": [0.03, 0.034, 0.038, 0.042, 0.046, 0.050, 0.054, 0.058, 0.06], "max_epoch": [30000], "momentum": [0.6, 0.7, 0.8, 0.9], "nesterov": [True], "kernel_regularizer": [0.0001, 0.0002, 0.0003, 0.0004, 0.0005], "activation": ["sigmoid"], "early_stop": [es], } gs = GridSearchCV(estimator=mlp_r, param_grid=grid, cv=split, verbose=1) result = gs.fit(X_train, Y_train) save_data(result, 'finer_grid_2_result.data')