def RepeatRealDatasetsDifferentRegressorsTest():
for name, func in dataset_list.iteritems():
print(name)
dataset = func()
make_ensemble(dataset,
"auto_repeat/auto_" + name + ".mat",
plotting=False)
def RealDatasetsDifferentRegressorsLargeTest():
for name, func in dataset_list.iteritems():
print(name)
dataset = func()
make_ensemble(dataset,
"auto_large/auto_" + name + ".mat",
plotting=False,
ensemble_type='auto_large',
scale_data=True)
def RealDatasetsManualEnsembleTest():
for name, func in dataset_list.iteritems():
print(name + ":", end="")
dataset = func()
print(" X.shape = " + str(dataset.data.shape))
ensemble = EnsembleRegressor(type='auto', verbose=True) #auto_large
if name is 'blog_feedback':
continue
# samples_per_regressor = 2810
# overlap = 2810
# train_size = 2810
else:
samples_per_regressor = 200
overlap = 0
train_size = samples_per_regressor * ensemble.regressor_count
if len(
dataset.target
) < train_size + 500: # ignore datasets with less than 6000 samples
continue
# if dataset.data.shape[1] < 5: # ignore datasets with less than 5 covariates
# continue
Xtrain, X, ytrain, y = model_selection.train_test_split(
dataset.data,
dataset.target,
random_state=0,
train_size=train_size)
ensemble.fit(Xtrain,
ytrain,
samples_per_regressor=samples_per_regressor,
regressor_overlap=overlap)
Ztrain = ensemble.predict(Xtrain)
Z = ensemble.predict(X)
sio.savemat(
path.join('ManualEnsembleDatasets', name + '.mat'), {
'names': ensemble.regressor_labels,
'Z': Z,
'y': y,
'Ztrain': Ztrain,
'ytrain': ytrain,
'samples_per_regressor': train_size,
'regressor_samples_overlap': train_size,
'Ey': np.mean(y),
'Ey2': np.mean(y**2),
'Description': ('Different Regressors (%s)' % name)
})
def RealDatasetsLargeMLPEnsembleTest():
for name, func in dataset_list.iteritems():
print(name)
dataset = func()
if len(dataset.target
) < 5500: # ignore datasets with less than 6000 samples
continue
if dataset.data.shape[
1] < 5: # ignore datasets with less than 5 covariates
continue
if name is 'blog_feedback':
train_size = 10000
else:
train_size = 500
Xtrain, X, ytrain, y = model_selection.train_test_split(
dataset.data,
dataset.target,
random_state=0,
train_size=train_size)
if name is 'affairs':
# ytrain, y = [np_utils.to_categorical(x) for x in (ytrain, y)]
continue
ensemble = EnsembleRegressor(type='mlp_large', verbose=True)
ensemble.fit(Xtrain,
ytrain,
samples_per_regressor=train_size,
regressor_overlap=train_size)
Ztrain = ensemble.predict(Xtrain)
Z = ensemble.predict(X)
sio.savemat(
path.join('ManualEnsembleDatasets', name + '_10mlp.mat'), {
'names': ensemble.regressor_labels,
'Z': Z,
'y': y,
'Ztrain': Ztrain,
'ytrain': ytrain,
'samples_per_regressor': train_size,
'regressor_samples_overlap': train_size,
'Ey': np.mean(y),
'Ey2': np.mean(y**2),
'Description': ('Different Regressors (%s)' % name)
})
def RealDatasetsManualEnsembleTest():
for name,func in dataset_list.iteritems():
print(name + ":", end="")
dataset = func()
print(" X.shape = " + str(dataset.data.shape))
ensemble = EnsembleRegressor(type='auto', verbose=True) #auto_large
if name is 'blog_feedback':
continue
# samples_per_regressor = 2810
# overlap = 2810
# train_size = 2810
else:
samples_per_regressor = 200
overlap = 0
train_size = samples_per_regressor * ensemble.regressor_count
if len(dataset.target) < train_size + 500: # ignore datasets with less than 6000 samples
continue
# if dataset.data.shape[1] < 5: # ignore datasets with less than 5 covariates
# continue
Xtrain, X, ytrain, y = cross_validation.train_test_split(
dataset.data, dataset.target, random_state=0, train_size=train_size)
ensemble.fit(Xtrain, ytrain, samples_per_regressor=samples_per_regressor, regressor_overlap=overlap)
Ztrain = ensemble.predict(Xtrain)
Z = ensemble.predict(X)
sio.savemat(path.join('ManualEnsembleDatasets',name + '.mat'), {
'names': ensemble.regressor_labels,
'Z': Z, 'y': y,
'Ztrain': Ztrain, 'ytrain': ytrain,
'samples_per_regressor': train_size,
'regressor_samples_overlap': train_size,
'Ey': np.mean(y),
'Ey2': np.mean(y ** 2),
'Description': ('Different Regressors (%s)' % name)
})
def RealDatasetsLargeMLPEnsembleTest():
for name,func in dataset_list.iteritems():
print(name)
dataset = func()
if len(dataset.target) < 5500: # ignore datasets with less than 6000 samples
continue
if dataset.data.shape[1] < 5: # ignore datasets with less than 5 covariates
continue
if name is 'blog_feedback':
train_size = 10000
else:
train_size = 500
Xtrain, X, ytrain, y = cross_validation.train_test_split(
dataset.data, dataset.target, random_state=0, train_size=train_size)
if name is 'affairs':
# ytrain, y = [np_utils.to_categorical(x) for x in (ytrain, y)]
continue
ensemble = EnsembleRegressor(type='mlp_large', verbose=True)
ensemble.fit(Xtrain, ytrain, samples_per_regressor=train_size, regressor_overlap=train_size)
Ztrain = ensemble.predict(Xtrain)
Z = ensemble.predict(X)
sio.savemat(path.join('ManualEnsembleDatasets',name + '_10mlp.mat'), {
'names': ensemble.regressor_labels,
'Z': Z, 'y': y,
'Ztrain': Ztrain, 'ytrain': ytrain,
'samples_per_regressor': train_size,
'regressor_samples_overlap': train_size,
'Ey': np.mean(y),
'Ey2': np.mean(y ** 2),
'Description': ('Different Regressors (%s)' % name)
})
def RealDatasetsDifferentRegressorsLargeTest():
for name,func in dataset_list.iteritems():
print(name)
dataset = func()
make_ensemble(dataset, "auto_large/auto_" + name + ".mat", plotting=False,
ensemble_type='auto_large', scale_data=True)
def RepeatRealDatasetsDifferentRegressorsTest():
for name,func in dataset_list.iteritems():
print(name)
dataset = func()
make_ensemble(dataset, "auto_repeat/auto_" + name + ".mat", plotting=False)