def run(self):
blendranges = []
submodel_blend_names = []
submodel_predictions = []
datakey = self.ChooseDataComboBox.currentText()
refcol = ('comp', self.optimizeSubRangesComboBox.currentText())
# start with the low model
blendranges.append(
[-9999, float(self.lowPredictionMaxSpinBox.value())])
submodel_blend_names.append(self.lowPredictionComboBox.currentText())
submodel_predictions.append(
self.data[datakey].df[('predict',
self.lowPredictionComboBox.currentText())])
# append the intermediate submodels
for i in range(0, self.index_spin.value()):
temp_vals = self.subwidgets[i].getValues()
blendranges.append(temp_vals[1])
submodel_blend_names.append(temp_vals[0])
submodel_predictions.append(self.data[datakey].df[('predict',
temp_vals[0])])
# append the high model
blendranges.append(
[float(self.highPredictionMinSpinBox.value()), 9999])
submodel_blend_names.append(self.highPredictionComboBox.currentText())
submodel_predictions.append(
self.data[datakey].df[('predict',
self.highPredictionComboBox.currentText())])
# append the reference model as a catch-all
submodel_blend_names.append(
self.referencePredictionComboBox.currentText())
submodel_predictions.append(self.data[datakey].df[(
'predict', self.referencePredictionComboBox.currentText())])
if self.optimizeSubRangesCheckBox.isChecked():
truevals = self.data[datakey].df[refcol]
else:
truevals = None
sm_obj = sm.sm(blendranges)
# optimize blending if reference data is provided
if truevals is not None:
predictions_blended = sm_obj.do_blend(
np.array(submodel_predictions), truevals=truevals)
else:
# otherwise just blend the predictions together
predictions_blended = sm_obj.do_blend(
np.array(submodel_predictions))
# save the blended predictions
self.data[datakey].df[('predict', 'Blended-Predict ' +
str(sm_obj.blendranges))] = predictions_blended
def test_sm_blend():
df = pd.read_csv(get_path('test_data.csv'), header=[0, 1])
x = df['wvl']
y = df[('comp', 'SiO2')]
model1 = reg.regression(method=['PLS'],
params=[{
'n_components': 3,
'scale': False
}])
model1.fit(x, y)
df[('predict', 'model1')] = model1.predict(x)
model2 = reg.regression(method=['PLS'],
params=[{
'n_components': 5,
'scale': False
}])
model2.fit(x, y)
df[('predict', 'model2')] = model2.predict(x)
model3 = reg.regression(method=['PLS'],
params=[{
'n_components': 4,
'scale': False
}])
model3.fit(x, y)
df[('predict', 'model3')] = model3.predict(x)
predictions = [
df[('predict', 'model2')], df[('predict', 'model1')],
df[('predict', 'model3')], df[('predict', 'model1')]
]
blendranges = [[-9999, 30], [20, 60], [50, 9999]]
sm_obj = sm.sm(blendranges)
blended_predictions = sm_obj.do_blend(
np.array(predictions)) #without optimization
rmse = np.sqrt(np.average((blended_predictions - df[('comp', 'SiO2')])**2))
np.testing.assert_almost_equal(rmse, 12.703434300128926, decimal=5)
blended_predictions = sm_obj.do_blend(
np.array(predictions),
truevals=np.array(df[('comp', 'SiO2')])) #with optimization
rmse = np.sqrt(np.average((blended_predictions - df[('comp', 'SiO2')])**2))
expected_blendranges = [
-9999., 36.5198746, 47.98157746, 56.2537253, 118.94036468, 9999.
]
np.testing.assert_almost_equal(rmse, 9.954065920454982, decimal=5)
np.testing.assert_allclose(expected_blendranges,
sm_obj.blendranges,
rtol=1e-5)
def setup(self):
blendranges = []
datakey = self.ChooseDataComboBox.currentText()
# start with the low model
blendranges.append(
[-9999, float(self.lowPredictionMaxSpinBox.value())])
# append the intermediate submodels
for i in range(0, self.index_spin.value()):
temp_vals = self.subwidgets[i].getValues()
blendranges.append(temp_vals[1])
# append the high model
blendranges.append(
[float(self.highPredictionMinSpinBox.value()), 9999])
sm_obj = sm.sm(blendranges)
# save the blended predictions
try:
self.data[datakey].df[('predict', 'Blended-Predict ' +
str(sm_obj.blendranges))] = 99999
except:
pass