def test_elmr_boston():
# load dataset
data = elm.read("tests/data/boston.data")
# create a regressor
elmr = elm.ELMRandom()
try:
# search for best parameter for this dataset
# elmr.search_param(data, cv="kfold", of="rmse")
# split data in training and testing sets
tr_set, te_set = elm.split_sets(data, training_percent=.8, perm=True)
#train and test
tr_result = elmr.train(tr_set)
te_result = elmr.test(te_set)
except:
ERROR = 1
else:
ERROR = 0
assert (ERROR == 0)
def test_elmr_boston():
# load dataset
data = elm.read("elmTestData/boston.data")
# create a regressor
elmr = elm.ELMRandom()
try:
# search for best parameter for this dataset
# elmr.search_param(data, cv="kfold", of="rmse")
# split data in training and testing sets
tr_set, te_set = elm.split_sets(data, training_percent=.8, perm=True)
#train and test
tr_result = elmr.train(tr_set)
te_result = elmr.test(te_set)
except:
ERROR = 1
else:
ERROR = 0
assert (ERROR == 0)
def main():
# Load in 2D velocity data
velocity = data.load_data()
# data.example_of_data(velocity)
# form testing and training sets for velocity data
X_train, y_train, X_test, y_test = data.form_train_test_sets(velocity)
# Data transformation
#print(X_test[0]['u'].shape)
print("len of y", len(y_test))
# print("shape of y", y_test.shape)
#print(y_train)
#print(X_train['u'].shape)
import elm as standard_elm
# create a classifier
elmk = standard_elm.ELMKernel()
nn_structure = [9, 100, 1]
x, y = utils.transform_dict_for_nn(X_train, y_train, nn_structure[0])
x = np.transpose(x)
y = np.transpose([y])
tr_set = np.concatenate(
(y, x), 1) #standard format for elm function - y_train + x_train
x_test, y_test = utils.transform_dict_for_nn(X_test[0], y_test[0],
nn_structure[0])
#x_test = np.transpose(x_test)
#y_test = np.transpose([y_test])
#te_set = np.concatenate((y_test, x_test), 1)
# load dataset
dataa = standard_elm.read("boston.data")
# create a classifier
elmk = standard_elm.elmk.ELMKernel()
# split data in training and testing sets
# use 80% of dataset to training and shuffle data before splitting
tr_set, te_set = standard_elm.split_sets(dataa,
training_percent=.8,
perm=True)
#train and test
# results are Error objects
tr_result = elmk.train(tr_set)
te_result = elmk.test(te_set)
print(te_result.get_accuracy())
te_result.predicted_targets
def test_elmk_iris():
# load dataset
data = elm.read("tests/data/iris.data")
# create a regressor
elmk = elm.ELMKernel()
try:
# search for best parameter for this dataset
elmk.search_param(data, cv="kfold", of="accuracy", eval=10)
# split data in training and testing sets
tr_set, te_set = elm.split_sets(data, training_percent=.8, perm=True)
#train and test
tr_result = elmk.train(tr_set)
te_result = elmk.test(te_set)
except:
ERROR = 1
else:
ERROR = 0
assert (ERROR == 0)
def test_elmr_iris():
# load dataset
data = elm.read("tests/data/iris.data")
# create a regressor
elmr = elm.ELMRandom()
try:
# search for best parameter for this dataset
elmr.search_param(data, cv="kfold", of="accuracy", eval=10)
# split data in training and testing sets
tr_set, te_set = elm.split_sets(data, training_percent=.8, perm=True)
#train and test
tr_result = elmr.train(tr_set)
te_result = elmr.test(te_set)
except:
ERROR = 1
else:
ERROR = 0
assert (ERROR == 0)
# split data in training and testing sets
tr_set, te_set = elm.split_sets(data, training_percent=.8, perm=True)
#train and test
tr_result = elmr.train(tr_set)
te_result = elmr.test(te_set)
print(tr_result.get_accuracy)
print(te_result.get_accuracy)
except:
ERROR = 1
else:
ERROR = 0
assert (ERROR == 0)
# assert (te_result.get_rmse() <= 70)
if __name__ == '__main__':
# load dataset
data = elm.read("elmTestData/diabetes.data")
# create a regressor
elmr = elm.ELMRandom()
tr_set, te_set = elm.split_sets(data, training_percent=.8, perm=True)
# train and test
tr_result = elmr.train(tr_set)
te_result = elmr.test(te_set)
print(tr_result.get_rmse())
print(te_result.get_rmse())
def buildELM(data, iterNum, isNormal, isRegression, isPCA, n_components,normalMethod):
rfList = []
elmr = elm.ELMKernel()
# elmr = elm.ELMRandom()
elmr.search_param(data, eval=100, cv='kfold')
# print("This is X_norm: ", X_norm)
for j in range(iterNum):
# X_train, X_test, y_train, y_test = train_test_split(X_norm, y, test_size=0.2)
# param_test1 = {'n_hidden': range(10, 21, 10)}
# model = GridSearchCV(estimator=elm.ELMRegressor(),
# param_grid=param_test1, cv=5, n_jobs=1)
# model = elm.ELMRegressor(n_hidden=tempDim,activation_func='sine')
# model = elm.ELMRegressor(activation_func='tanh')
# model = elm.GenELMRegressor()
# temp = model.fit(X_train, y_train)
# print("The best parameters are %s with a score of %0.2f"
# % (model.best_params_, model.best_score_))
# Predict on new data
# y_pred = temp.predict(X_test).tolist()
# y_test_list = y_test.tolist()
# create a classifier
# elmr = elm.ELMRandom()
# search for best parameter for this dataset
# define "kfold" cross-validation method, "accuracy" as a objective function
# to be optimized and perform 10 searching steps.
# best parameters will be saved inside 'elmk' object
# split data in training and testing sets
# use 80% of dataset to training and shuffle data before splitting
tr_set, te_set = elm.split_sets(data, training_percent=.9, perm=True)
# print("This is tr_set: ", tr_set)
X_train = tr_set[:, 1:].copy()
# print("This is X_train", X_train)
X_test = te_set[:, 1:].copy()
# print("This is X_test: ", X_test)
if normalMethod == 1:
print("Normalizer() is using..." )
sc = preprocessing.Normalizer()
elif normalMethod == 2:
print("StandardScalar() is using...")
sc = preprocessing.StandardScaler()
elif normalMethod == 3:
print("MinMaxScalar() is using...")
sc = preprocessing.MinMaxScaler()
sc.fit(X_train)
X_train_std = sc.transform(X_train)
X_test_std = sc.transform(X_test)
if isPCA:
X_train, X_test = reduceDim.featureExtraction(X_train_std, X_test_std, n_components)
else:
X_train = X_train_std
X_test = X_test_std
tr_set = np.c_[tr_set[:, 0], X_train]
te_set = np.c_[te_set[:, 0], X_test]
# print("This is new tr_set: ", tr_set)
# print("This is new te_set: ", te_set)
# train and test
# results are Error objects
tr_result = elmr.train(tr_set)
te_result = elmr.test(te_set)
y_test_list = te_result.expected_targets
y_pred = te_result.predicted_targets
# print("This is tr_result: ", tr_result.expected_targets)
# print("This is tr_result pre: ",tr_result.predicted_targets )
# print("This is te_result: ", te_result.expected_targets) # expected is the real value
# print("This is te_result predict: ", te_result.predicted_targets)
# print(te_result.get_accuracy)
if isRegression:
return y_pred
else:
sum_mean = 0
for i in range(len(y_pred)):
# print(
# "This is REAL value %.4f, ======ELM=====> PRED value: %.4f" % (y_test_list[i], y_pred[i]))
# sum_mean += (y_pred[i] - y_test[i]) ** 2 # if the target is np array
sum_mean += (float("{0:.4f}".format(float(y_pred[i]))) - y_test_list[i]) ** 2
# else:
# print("This is REAL value %.4f, ======Random Forest=====> PRED value: %.4f" % (
# y_test.values[i], y_pred[i]))
# # sum_mean += (y_pred[i] - y_test.values[i]) ** 2
# sum_mean += (float("{0:.4f}".format(float(y_pred[i]))) - y_test.values[i]) ** 2
sum_erro = np.sqrt(sum_mean / len(y_pred))
rfList.append(sum_erro)
print("This is RMSE for ELM: ", sum_erro)
print("This is iteration num: ", j + 1)
return rfList