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) #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:
E=x_centered-np.dot(pls.x_scores_,pls.x_loadings_.transpose())
Q_res=np.dot(E,E.transpose()).diagonal()
T=pls.x_scores_
leverage=np.diag([email protected](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.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, X, y=None):
self._sklearn_model = SKLModel(**self._hyperparams)
if (y is not None):
self._sklearn_model.fit(X, y)
else:
self._sklearn_model.fit(X)
return self
def __init__(self, n_components=2, scale=True, max_iter=500, tol=1e-06, copy=True):
self._hyperparams = {
'n_components': n_components,
'scale': scale,
'max_iter': max_iter,
'tol': tol,
'copy': copy}
self._wrapped_model = Op(**self._hyperparams)
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
class PLSRegressionImpl():
def __init__(self,
n_components=2,
scale=True,
max_iter=500,
tol=1e-06,
copy=True):
self._hyperparams = {
'n_components': n_components,
'scale': scale,
'max_iter': max_iter,
'tol': tol,
'copy': copy
}
def fit(self, X, y=None):
self._sklearn_model = SKLModel(**self._hyperparams)
if (y is not None):
self._sklearn_model.fit(X, y)
else:
self._sklearn_model.fit(X)
return self
def transform(self, X):
return self._sklearn_model.transform(X)
def predict(self, X):
return self._sklearn_model.predict(X)
def __init__(self, method, yrange, params, i=0, ransacparams={}):
self.method = method
self.outliers = None
self.inliers = None
self.ransac = False
self.yrange = yrange[i]
if self.method[i] == 'PLS':
self.model = PLSRegression(**params[i])
if self.method[i] == 'GP':
#get the method for dimensionality reduction and the number of components
self.reduce_dim = params[i]['reduce_dim']
self.n_components = params[i]['n_components']
#create a temporary set of parameters
params_temp = copy.copy(params[i])
#Remove parameters not accepted by Gaussian Process
params_temp.pop('reduce_dim')
params_temp.pop('n_components')
self.model = GaussianProcess(**params_temp)
def load_h5(file_name='blue.h5'):
try:
hf = h5py.File(os.path.join(get_resource_path(), file_name), 'r')
d1 = hf.get('coef')
d2 = hf.get('x_mean')
d3 = hf.get('y_mean')
d4 = hf.get('x_std')
model = PLSRegression(len(d1))
model.coef_ = np.array(d1)
model.x_mean_ = np.array(d2)
model.y_mean_ = np.array(d3)
model.x_std_ = np.array(d4)
hf.close()
except Exception as e:
print('Unable to load data ', file_name, ':', e)
return model
def __init__(
self,
method,
yrange,
params,
i=0
): #TODO: yrange doesn't currently do anything. Remove or do something with it!
self.algorithm_list = [
'PLS',
'GP',
'OLS',
'OMP',
'Lasso',
'Elastic Net',
'Ridge',
'Bayesian Ridge',
'ARD',
'LARS',
'LASSO LARS',
'SVR',
'KRR',
]
self.method = method
self.outliers = None
self.ransac = False
print(params)
if self.method[i] == 'PLS':
self.model = PLSRegression(**params[i])
if self.method[i] == 'OLS':
self.model = linear.LinearRegression(**params[i])
if self.method[i] == 'OMP':
# check whether to do CV or not
self.do_cv = params[i]['CV']
# create a temporary set of parameters
params_temp = copy.copy(params[i])
# Remove CV parameter
params_temp.pop('CV')
if self.do_cv is False:
self.model = linear.OrthogonalMatchingPursuit(**params_temp)
else:
params_temp.pop('precompute')
self.model = linear.OrthogonalMatchingPursuitCV(**params_temp)
if self.method[i] == 'LASSO':
# create a temporary set of parameters
params_temp = copy.copy(params[i])
# check whether to do CV or not
try:
self.do_cv = params[i]['CV']
# Remove CV parameter
params_temp.pop('CV')
except:
self.do_cv = False
if self.do_cv is False:
self.model = linear.Lasso(**params_temp)
else:
params_temp.pop('alpha')
self.model = linear.LassoCV(**params_temp)
if self.method[i] == 'Elastic Net':
params_temp = copy.copy(params[i])
try:
self.do_cv = params[i]['CV']
params_temp.pop('CV')
except:
self.do_cv = False
if self.do_cv is False:
self.model = linear.ElasticNet(**params_temp)
else:
params_temp['l1_ratio'] = [.1, .5, .7, .9, .95, .99, 1]
self.model = linear.ElasticNetCV(**params_temp)
if self.method[i] == 'Ridge':
# create a temporary set of parameters
params_temp = copy.copy(params[i])
try:
# check whether to do CV or not
self.do_cv = params[i]['CV']
# Remove CV parameter
params_temp.pop('CV')
except:
self.do_cv = False
if self.do_cv:
self.model = linear.RidgeCV(**params_temp)
else:
self.model = linear.Ridge(**params_temp)
if self.method[i] == 'BRR':
self.model = linear.BayesianRidge(**params[i])
if self.method[i] == 'ARD':
self.model = linear.ARDRegression(**params[i])
if self.method[i] == 'LARS':
# create a temporary set of parameters
params_temp = copy.copy(params[i])
try:
# check whether to do CV or not
self.do_cv = params[i]['CV']
# Remove CV parameter
params_temp.pop('CV')
except:
self.do_cv = False
if self.do_cv is False:
self.model = linear.Lars(**params_temp)
else:
self.model = linear.LarsCV(**params_temp)
if self.method[i] == 'LASSO LARS':
model = params[i]['model']
params_temp = copy.copy(params[i])
params_temp.pop('model')
if model == 0:
self.model = linear.LassoLars(**params_temp)
elif model == 1:
self.model = linear.LassoLarsCV(**params_temp)
elif model == 2:
self.model = linear.LassoLarsIC(**params_temp)
else:
print("Something went wrong, \'model\' should be 0, 1, or 2")
if self.method[i] == 'SVR':
self.model = svm.SVR(**params[i])
if self.method[i] == 'KRR':
self.model = kernel_ridge.KernelRidge(**params[i])
if self.method[i] == 'GP':
# get the method for dimensionality reduction and the number of components
self.reduce_dim = params[i]['reduce_dim']
self.n_components = params[i]['n_components']
# create a temporary set of parameters
params_temp = copy.copy(params[i])
# Remove parameters not accepted by Gaussian Process
params_temp.pop('reduce_dim')
params_temp.pop('n_components')
self.model = GaussianProcess(**params_temp)
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
'MultiTaskLassoCV':MultiTaskLassoCV(), 'MultinomialNB':MultinomialNB(), 'NMF':NMF(), 'NearestCentroid':NearestCentroid(), 'NearestNeighbors':NearestNeighbors(), 'Normalizer':Normalizer(), 'NuSVC':NuSVC(), 'NuSVR':NuSVR(), 'Nystroem':Nystroem(), 'OAS':OAS(), 'OneClassSVM':OneClassSVM(), 'OrthogonalMatchingPursuit':OrthogonalMatchingPursuit(), 'OrthogonalMatchingPursuitCV':OrthogonalMatchingPursuitCV(), 'PCA':PCA(), 'PLSCanonical':PLSCanonical(), 'PLSRegression':PLSRegression(), 'PLSSVD':PLSSVD(), 'PassiveAggressiveClassifier':PassiveAggressiveClassifier(), 'PassiveAggressiveRegressor':PassiveAggressiveRegressor(), 'Perceptron':Perceptron(), 'ProjectedGradientNMF':ProjectedGradientNMF(), 'QuadraticDiscriminantAnalysis':QuadraticDiscriminantAnalysis(), 'RANSACRegressor':RANSACRegressor(), 'RBFSampler':RBFSampler(), 'RadiusNeighborsClassifier':RadiusNeighborsClassifier(), 'RadiusNeighborsRegressor':RadiusNeighborsRegressor(), 'RandomForestClassifier':RandomForestClassifier(), 'RandomForestRegressor':RandomForestRegressor(), 'RandomizedLasso':RandomizedLasso(), 'RandomizedLogisticRegression':RandomizedLogisticRegression(), 'RandomizedPCA':RandomizedPCA(),
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
def __init__(self, method, yrange, params, i=0): #TODO: yrange doesn't currently do anything. Remove or do something with it!
self.algorithm_list = ['PLS',
'GP',
'OLS',
'OMP',
'Lasso',
'Elastic Net',
'Ridge',
'Bayesian Ridge',
'ARD',
'LARS',
'LASSO LARS',
'SVR',
'KRR',
]
self.method = method
self.outliers = None
self.ransac = False
print(params)
if self.method[i] == 'PLS':
self.model = PLSRegression(**params[i])
if self.method[i] == 'OLS':
self.model = linear.LinearRegression(**params[i])
if self.method[i] == 'OMP':
# create a temporary set of parameters
params_temp = copy.copy(params[i])
self.model = linear.OrthogonalMatchingPursuit(**params_temp)
if self.method[i] == 'LASSO':
# create a temporary set of parameters
params_temp = copy.copy(params[i])
self.model = linear.Lasso(**params_temp)
if self.method[i] == 'Elastic Net':
params_temp = copy.copy(params[i])
self.model = linear.ElasticNet(**params_temp)
if self.method[i] == 'Ridge':
# create a temporary set of parameters
params_temp = copy.copy(params[i])
self.model = linear.Ridge(**params_temp)
if self.method[i] == 'BRR':
self.model = linear.BayesianRidge(**params[i])
if self.method[i] == 'ARD':
self.model = linear.ARDRegression(**params[i])
if self.method[i] == 'LARS':
# create a temporary set of parameters
params_temp = copy.copy(params[i])
self.model = linear.Lars(**params_temp)
if self.method[i] == 'LASSO LARS':
self.model = linear.LassoLars(**params)
if self.method[i] == 'SVR':
self.model = svm.SVR(**params[i])
if self.method[i] == 'KRR':
self.model = kernel_ridge.KernelRidge(**params[i])
if self.method[i] == 'GP':
# get the method for dimensionality reduction and the number of components
self.reduce_dim = params[i]['reduce_dim']
self.n_components = params[i]['n_components']
# create a temporary set of parameters
params_temp = copy.copy(params[i])
# Remove parameters not accepted by Gaussian Process
params_temp.pop('reduce_dim')
params_temp.pop('n_components')
self.model = GaussianProcess(**params_temp)
def __init__(self, method, yrange, params, i=0, ransacparams={}):
self.method = method
self.outliers = None
self.inliers = None
self.ransac = False
self.yrange = yrange[i]
if self.method[i] == 'PLS':
self.model = PLSRegression(**params[i])
if self.method[i] == 'OLS':
self.model = linear.LinearRegression(**params[i])
if self.method[i] == 'OMP':
#check whether to do CV or not
self.do_cv = params[i]['CV']
# create a temporary set of parameters
params_temp = copy.copy(params[i])
# Remove CV parameter
params_temp.pop('CV')
if self.do_cv is False:
self.model = linear.OrthogonalMatchingPursuit(**params_temp)
else:
params_temp.pop('n_nonzero_coefs')
self.model = linear.OrthogonalMatchingPursuitCV(**params_temp)
if self.method[i] == 'Lasso':
# check whether to do CV or not
self.do_cv = params[i]['CV']
# create a temporary set of parameters
params_temp = copy.copy(params[i])
# Remove CV parameter
params_temp.pop('CV')
if self.do_cv is False:
self.model = linear.Lasso(**params_temp)
else:
params_temp.pop('alpha')
self.model = linear.LassoCV(**params_temp)
if self.method[i] == 'Elastic Net':
# check whether to do CV or not
self.do_cv = params[i]['CV']
# create a temporary set of parameters
params_temp = copy.copy(params[i])
# Remove CV parameter
params_temp.pop('CV')
if self.do_cv is False:
self.model = linear.ElasticNet(**params_temp)
else:
params_temp.pop('alpha')
self.model = linear.ElasticNetCV(**params_temp)
if self.method[i] == 'Ridge':
# check whether to do CV or not
self.do_cv = params[i]['CV']
# create a temporary set of parameters
params_temp = copy.copy(params[i])
# Remove CV parameter
params_temp.pop('CV')
if self.do_cv is False:
self.model = linear.Ridge(**params_temp)
else:
#Ridge requires a specific set of alphas to be provided... this needs more work to be implemented correctly
self.model = linear.RidgeCV(**params_temp)
if self.method[i] == 'Bayesian Ridge':
self.model = linear.BayesianRidge(**params[i])
if self.method[i] == 'ARD':
self.model = linear.ARDRegression(**params[i])
if self.method[i] == 'LARS':
# check whether to do CV or not
self.do_cv = params[i]['CV']
# create a temporary set of parameters
params_temp = copy.copy(params[i])
# Remove CV parameter
params_temp.pop('CV')
if self.do_cv is False:
self.model = linear.Lars(**params_temp)
else:
self.model = linear.LarsCV(**params_temp)
if self.method[i] == 'Lasso LARS':
# check whether to do CV or not
self.do_cv = params[i]['CV']
# check whether to do IC or not
self.do_ic = params[i]['IC']
# create a temporary set of parameters
params_temp = copy.copy(params[i])
# Remove CV and IC parameter
params_temp.pop('CV')
params_temp.pop('IC')
if self.do_cv is False and self.do_ic is False:
self.model = linear.LassoLars(**params[i])
if self.do_cv is True and self.do_ic is False:
self.model = linear.LassoLarsCV(**params[i])
if self.do_cv is False and self.do_ic is True:
self.model = linear.LassoLarsIC(**params[i])
if self.do_cv is True and self.do_ic is True:
print(
"Can't use both cross validation AND information criterion to optimize!"
)
if self.method[i] == 'SVR':
self.model = svm.SVR(**params[i])
if self.method[i] == 'KRR':
self.model = kernel_ridge.KernelRidge(**params[i])
if self.method[i] == 'GP':
#get the method for dimensionality reduction and the number of components
self.reduce_dim = params[i]['reduce_dim']
self.n_components = params[i]['n_components']
#create a temporary set of parameters
params_temp = copy.copy(params[i])
#Remove parameters not accepted by Gaussian Process
params_temp.pop('reduce_dim')
params_temp.pop('n_components')
self.model = GaussianProcess(**params_temp)
