def predict(self, x):
# x is a list of data frames to feed into each submodel.
# This allows different normalizations to be used with each submodel
predictions = []
for i, k in enumerate(self.submodels):
xtemp = x[i].xs('wvl', axis=1, level=0, drop_level=False)
xtemp, mean_vect = meancenter(xtemp, 'wvl', previous_mean=self.mean_vects[i])
predictions.append(k.predict(xtemp['wvl']))
return predictions
def predict(self, x):
# x is a list of data frames to feed into each submodel.
# This allows different normalizations to be used with each submodel
predictions = []
for i, k in enumerate(self.submodels):
xtemp = x[i].xs('wvl', axis=1, level=0, drop_level=False)
xtemp, mean_vect = meancenter(xtemp, 'wvl', previous_mean=self.mean_vects[i])
predictions.append(k.predict(xtemp['wvl']))
return predictions
def fit(self, trainsets, ranges, ncs, ycol, figpath=None):
self.ranges = ranges
self.ncs = ncs
self.ycol = ycol
submodels = []
mean_vects = []
for i, rangei in enumerate(ranges):
data_tmp = within_range.within_range(trainsets[i], rangei, ycol)
x = data_tmp.xs('wvl', axis=1, level=0, drop_level=False)
y = data_tmp['meta'][ycol]
x_centered, x_mean_vect = meancenter(
x, 'wvl') # mean center training data
pls = PLSRegression(n_components=ncs[i], scale=False)
pls.fit(x, y)
submodels.append(pls)
mean_vects.append(x_mean_vect)
if figpath is not None:
# calculate spectral residuals
E = x_centered - np.dot(pls.x_scores_,
pls.x_loadings_.transpose())
Q_res = np.dot(E, E.transpose()).diagonal()
# calculate leverage
T = pls.x_scores_
leverage = np.diag(
T @ np.linalg.inv(T.transpose() @ T) @ T.transpose())
plot.figure()
plot.scatter(leverage, Q_res, color='r', edgecolor='k')
plot.title(ycol + ' (' + str(rangei[0]) + '-' +
str(rangei[1]) + ')')
plot.xlabel('Leverage')
plot.ylabel('Q')
plot.ylim([0, 1.1 * np.max(Q_res)])
plot.xlim([0, 1.1 * np.max(leverage)])
plot.savefig(figpath + '/' + ycol + '_' + str(rangei[0]) +
'-' + str(rangei[1]) + 'Qres_vs_Leverage.png',
dpi=600)
self.leverage = leverage
self.Q_res = Q_res
self.submodels = submodels
self.mean_vects = mean_vects
def fit(self, trainsets, ranges, ncs, ycol, figpath=None):
self.ranges = ranges
self.ncs = ncs
self.ycol = ycol
submodels = []
mean_vects = []
for i, rangei in enumerate(ranges):
data_tmp = within_range.within_range(trainsets[i], rangei, ycol)
x = data_tmp.xs('wvl', axis=1, level=0, drop_level=False)
y = data_tmp['meta'][ycol]
x_centered, x_mean_vect = meancenter(x, 'wvl') # mean center training data
pls = PLSRegression(n_components=ncs[i], scale=False)
pls.fit(x, y)
submodels.append(pls)
mean_vects.append(x_mean_vect)
if figpath is not None:
# calculate spectral residuals
E = x_centered - np.dot(pls.x_scores_, pls.x_loadings_.transpose())
Q_res = np.dot(E, E.transpose()).diagonal()
# calculate leverage
T = pls.x_scores_
leverage = np.diag(T @ np.linalg.inv(T.transpose() @ T) @ T.transpose())
plot.figure()
plot.scatter(leverage, Q_res, color='r', edgecolor='k')
plot.title(ycol + ' (' + str(rangei[0]) + '-' + str(rangei[1]) + ')')
plot.xlabel('Leverage')
plot.ylabel('Q')
plot.ylim([0, 1.1 * np.max(Q_res)])
plot.xlim([0, 1.1 * np.max(leverage)])
plot.savefig(
figpath + '/' + ycol + '_' + str(rangei[0]) + '-' + str(rangei[1]) + 'Qres_vs_Leverage.png',
dpi=600)
self.leverage = leverage
self.Q_res = Q_res
self.submodels = submodels
self.mean_vects = mean_vects
def pls_cv(Train, Test=None, nc=20, nfolds=5, ycol='SiO2', doplot=True, outpath='.', plotfile='pls_cv.png'):
# create empty arrays for the RMSE values
pls_rmsecv = np.empty(nc)
pls_rmsec = np.empty(nc)
# If there is a test set provided, create the RMSEP array to hold test set errors
if Test is not None:
pls_rmsep = np.empty(nc)
# loop through each number of components
for i in range(1, nc + 1):
print('nc=' + str(i))
Train[('meta', ycol + '_cv_PLS_nc' + str(
i))] = 0 # create a column to hold the PLS cross validation results for this nc
Train[
('meta', ycol + '_PLS_nc' + str(i))] = 0 # create a column to hold the PLS training set results for this nc
if Test is not None:
Test[
('meta', ycol + '_PLS_nc' + str(i))] = 0 # create a column to hold the PLS test set results for this nc
# Do the cross validation
cv_iterator = LeaveOneLabelOut(
Train[('meta', 'Folds')]) # create the iterator for cross validation within the training data
for train, holdout in cv_iterator: # Iterate through each of the folds in the training set
cv_train = Train.iloc[train]
cv_holdout = Train.iloc[holdout]
# Do PLS for this number of components
cv_train_centered, cv_train_mean_vect = meancenter(cv_train) # mean center training data
cv_holdout_centered, cv_holdout_mean_vect = meancenter(cv_holdout,
previous_mean=cv_train_mean_vect) # apply same mean centering to holdout data
pls = PLSRegression(n_components=i, scale=False)
pls.fit(cv_train_centered['wvl'], cv_train_centered['meta'][ycol])
y_pred_holdout = pls.predict(cv_holdout_centered['wvl'])
Train.set_value(Train.index[holdout], ('meta', ycol + '_cv_PLS_nc' + str(i)), y_pred_holdout)
pls_rmsecv[i - 1] = np.sqrt(
np.mean(np.subtract(Train[('meta', ycol)], Train[('meta', ycol + '_cv_PLS_nc' + str(i))]) ** 2, axis=0))
# Do train and test set PLS predictions for this number of components
Train_centered, Train_mean_vect = meancenter(Train)
pls = PLSRegression(n_components=i, scale=False)
pls.fit(Train_centered['wvl'], Train_centered['meta'][ycol])
y_pred = pls.predict(Train_centered['wvl'])
Train.set_value(Train.index, ('meta', ycol + '_PLS_nc' + str(i)), y_pred)
pls_rmsec[i - 1] = np.sqrt(
np.mean(np.subtract(Train[('meta', ycol)], Train[('meta', ycol + '_PLS_nc' + str(i))]) ** 2, axis=0))
if Test is not None:
Test_centered, Train_mean_vect = meancenter(Test, previous_mean=Train_mean_vect)
y_pred = pls.predict(Test_centered['wvl'])
Test.set_value(Test.index, ('meta', ycol + '_PLS_nc' + str(i)), y_pred)
pls_rmsep[i - 1] = np.sqrt(
np.mean(np.subtract(Test[('meta', ycol)], Test[('meta', ycol + '_PLS_nc' + str(i))]) ** 2, axis=0))
if doplot == True:
plot.figure()
plot.title(ycol)
plot.xlabel('# of components')
plot.ylabel(ycol + ' RMSE (wt.%)')
plot.plot(range(1, nc + 1), pls_rmsecv, label='RMSECV', color='r')
plot.plot(range(1, nc + 1), pls_rmsec, label='RMSEC', color='b')
if Test is not None:
plot.plot(range(1, nc + 1), pls_rmsep, label='RMSEP', color='g')
plot.legend(loc=0, fontsize=6)
plot.savefig(outpath + '/' + plotfile, dpi=600)
rmses = {'RMSEC': pls_rmsec, 'RMSECV': pls_rmsecv}
if Test is not None:
rmses['RMSEP'] = pls_rmsep
return rmses