1383 lines
50 KiB
Python
1383 lines
50 KiB
Python
"""This module contains bilinear models(Functions)
|
|
"""
|
|
import os
|
|
import copy
|
|
import pygtk
|
|
import gtk
|
|
import gtk.glade
|
|
from fluents import fluents
|
|
from fluents.workflow import Function, OptionsDialog, Options
|
|
from fluents.dataset import Dataset
|
|
from fluents import plots, dataset, workflow, logger
|
|
import scipy
|
|
from engines import pca, pls, nipals_lpls
|
|
from cx_stats import leverage, variances, hotelling
|
|
from cx_utils import mat_center
|
|
from validation import *
|
|
from packer import Packer
|
|
import blmplots
|
|
|
|
|
|
|
|
class NewStyleModel:
|
|
def __init__(self, id='johndoe', name='JohnDoe'):
|
|
self.id = id
|
|
self.name = name
|
|
self.name = name
|
|
self.options = Options
|
|
self.input_data = []
|
|
self.parts = {}
|
|
self.io_table = {}
|
|
self.datasets = []
|
|
self.plots = []
|
|
|
|
def create_dataset(self, param, Dataset=Dataset):
|
|
for ds in self.datasets:
|
|
if ds.get_name()==param: return ds
|
|
if not param in self.parts.keys():
|
|
logger.log('notice', 'Parameter: %s not present' %param)
|
|
return
|
|
if not param in self.io_table.keys():
|
|
logger.log('notice', 'Parameter: %s not in defined in io table' %param)
|
|
|
|
identifiers = self.io_table.get(param)
|
|
data = self.parts.get(param)
|
|
ds = Dataset(data, identifiers=identifiers, name=param)
|
|
self.datasets.append(dataset)
|
|
return ds
|
|
|
|
def create_plot(self, blmplot):
|
|
if blmplot.validate_model(self.parts):
|
|
plt = blmplot(self.parts)
|
|
self.plots.append(plt)
|
|
return plt
|
|
|
|
def save(self, stype=None):
|
|
pass
|
|
|
|
def load(self):
|
|
pass
|
|
|
|
|
|
|
|
class Model(Function):
|
|
"""Base class of bilinear models.
|
|
"""
|
|
def __init__(self, id='johndoe', name='JohnDoe'):
|
|
Function.__init__(self, id, name)
|
|
self.name = name
|
|
self._options = None
|
|
self._data = {}
|
|
self._dataset = {}
|
|
self._packers = {}
|
|
self.model = {}
|
|
|
|
def clear(self):
|
|
""" Clears model paramters
|
|
"""
|
|
self.model = {}
|
|
self._data = {}
|
|
self._packers = {}
|
|
|
|
|
|
class PCA(Model):
|
|
def __init__(self, id='pca', name='PCA'):
|
|
Model.__init__(self, id, name)
|
|
self._options = PcaOptions()
|
|
|
|
def validation(self, amax, cv_val_sets, pert_val_sets, cv_val_method, pert_val_method):
|
|
"""Model validation and estimate of optimal numer of components.
|
|
"""
|
|
if self._options['calc_cv']:
|
|
if cv_val_method == 'random':
|
|
sep, aopt = pca_cv_val(self.model['E0'], amax, cv_val_sets)
|
|
self.model['sep'] = sep
|
|
|
|
if self._options['calc_pert']:
|
|
if pert_val_method == 'random_diag':
|
|
sep, aopt = pca_alter_val(self.model['E0'], amax, pert_val_sets)
|
|
self.model['sep'] = sep
|
|
|
|
if self._options['calc_cv']==False and self._options['calc_pert']==False:
|
|
self.model['sep'] = None
|
|
aopt = self._options['amax']
|
|
|
|
if self._options['auto_aopt']:
|
|
logger.log("notice", "Auto aopt: " + str(aopt))
|
|
self._options['aopt'] = aopt
|
|
|
|
if aopt==1:
|
|
logger.log('notice', 'Aopt at first component!')
|
|
|
|
def confidence(self, aopt, n_sets, alpha, p_center,
|
|
crot, strict, cov_center):
|
|
"""Returns a confidence measure for model parameters.
|
|
Based on aopt.
|
|
|
|
Added model parts: p_tsq
|
|
"""
|
|
if aopt<2:
|
|
aopt = 2
|
|
logger.log('notice','Hotellings T2 needs more than 1 comp.\n switching to 2!!')
|
|
|
|
jk_segments = pca_jkP(self.model['E0'], aopt, n_sets)
|
|
Pcal = self.model['P'][:,:aopt]
|
|
# ensure scaled P
|
|
tnorm = scipy.apply_along_axis(norm, 0, self.model['T'][:,:aopt])
|
|
Pcal = Pcal*tnorm
|
|
tsq = hotelling(jk_segments, Pcal, p_center,
|
|
cov_center, alpha, crot, strict)
|
|
self.model['p_tsq'] = tsq
|
|
|
|
def make_model(self, amax, mode, scale):
|
|
"""Model on optimal number of components.
|
|
"""
|
|
dat = pca(self.model['E0'], amax, scale, mode)
|
|
self.model.update(dat)
|
|
|
|
def as_dataset(self, param, dtype='dataset'):
|
|
"""Return model parameter as Dataset.
|
|
"""
|
|
if not param in self.model.keys():
|
|
logger.log('notice', 'Parameter: %s not in model' %param)
|
|
return
|
|
DX = self._dataset['X'] #input dataset
|
|
dim_name_0, dim_name_1 = DX.get_dim_name()
|
|
# samples
|
|
ids_0 = [dim_name_0, DX.get_identifiers(dim_name_0, sorted=True)]
|
|
# vars
|
|
ids_1 = [dim_name_1, DX.get_identifiers(dim_name_1, sorted=True)]
|
|
# components (hidden)
|
|
pc_ids = ['_amax', map(str,range(self._options['amax'])) ]
|
|
pc_ids_opt = ['_aopt', map(str, range(self._options['aopt'])) ]
|
|
zero_dim = ['_doe', ['0']] # null dim, vector (hidden)
|
|
match_ids = {'E' : [ids_0, ids_1],
|
|
'E0' : [ids_0, ids_1],
|
|
'P' : [ids_1, pc_ids],
|
|
'T' : [ids_0, pc_ids],
|
|
'W' : [ids_1, pc_ids],
|
|
'p_tsq' : [ids_1, zero_dim],
|
|
'rmsep' : [pc_ids, zero_dim],
|
|
'var_leverages' : [ids_1, zero_dim],
|
|
'sample_leverages' : [pc_ids, zero_dim],
|
|
'exp_var_x' : [pc_ids, zero_dim],
|
|
'var_x' : [pc_ids, zero_dim],
|
|
'eigvals' : [pc_ids, zero_dim]
|
|
}
|
|
|
|
out = Dataset(self.model[param], match_ids[param], name=param)
|
|
return out
|
|
|
|
def get_out_plots(self, options):
|
|
out=[]
|
|
for plt in options['out_plots']:
|
|
#try:
|
|
out.append(plt(self))
|
|
#except:
|
|
# logger.log('debug', 'Plot: %s failed') %str(plt)
|
|
return out
|
|
|
|
def run_o(self, data):
|
|
"""Run pca with present options.
|
|
"""
|
|
self.clear()
|
|
options = self._options
|
|
self._dataset['X'] = data
|
|
self._data['X'] = data.asarray().astype('<f8')
|
|
if options['center']:
|
|
center = options['center_mth']
|
|
self.model['E0'] = center(self._data['X'])
|
|
else:
|
|
self.model['E0'] = data.asarray()
|
|
|
|
self.validation(**options.validation_options())
|
|
self.model['aopt'] = self._options['aopt']
|
|
self.make_model(**options.make_model_options())
|
|
if options['calc_conf']:
|
|
self.confidence(**options.confidence_options())
|
|
|
|
out = [self.as_dataset(p) for p in options['out_data']]
|
|
for plt in self.get_out_plots(options):
|
|
out.append(plt)
|
|
return out
|
|
|
|
def run(self, data):
|
|
"""Run Pca with option gui.
|
|
"""
|
|
dialog = PcaOptionsDialog([data], self._options)
|
|
dialog.show_all()
|
|
response = dialog.run()
|
|
dialog.hide()
|
|
|
|
if response == gtk.RESPONSE_OK:
|
|
# set output data and plots
|
|
dialog.set_output()
|
|
#run with current data and options
|
|
return self.run_o(data)
|
|
|
|
|
|
class PLS(Model):
|
|
def __init__(self, id='pls', name='PLS'):
|
|
Model.__init__(self, id, name)
|
|
self._options = PlsOptions()
|
|
|
|
def validation(self):
|
|
"""Returns rmsep for pls model.
|
|
"""
|
|
m, n = self.model['E0'].shape
|
|
if m>n:
|
|
val_engine = w_pls_cv_val
|
|
else:
|
|
val_engine = pls_val
|
|
if self._options['calc_cv']==True:
|
|
print "Doing RMSEP calc ..."
|
|
rmsep, aopt = val_engine(self.model['E0'], self.model['F0'],
|
|
self._options['amax'], self._options['n_sets'])
|
|
self.model['rmsep'] = rmsep[:,:-1]
|
|
self.model['aopt'] = aopt
|
|
else:
|
|
self.model['rmsep'] = None
|
|
self.model['aopt'] = self._options['aopt']
|
|
|
|
def confidence(self, aopt, n_sets, alpha, p_center,
|
|
crot, strict, cov_center ):
|
|
"""Returns a confidence measure for model parameters
|
|
Supported parameters: W
|
|
"""
|
|
aopt = self.model['aopt']
|
|
if self._options['calc_conf']:
|
|
print "Doing Tsq"
|
|
jk_segments = pls_jkW(self.model['E0'], self.model['F0'],
|
|
aopt, n_sets)
|
|
Wcal = self.model['W'][:,:aopt]
|
|
# ensure that Wcal is scaled
|
|
tnorm = scipy.apply_along_axis(norm, 0, self.model['T'][:,:aopt])
|
|
Wcal = Wcal*tnorm
|
|
tsq = hotelling(jk_segments, Wcal, p_center,
|
|
alpha, crot, strict, cov_center)
|
|
self.model['w_tsq'] = tsq
|
|
else:
|
|
self.model['w_tsq'] = None
|
|
|
|
def permutation_confidence(self, a, b, aopt, reg,
|
|
n_iter, algo, sim_method):
|
|
"""Estimates cut off on significant vars by controlling fdr."""
|
|
|
|
if self._options['calc_qvals']==True:
|
|
print "Doing Qvals"
|
|
qvals = pls_qvals(a, b,
|
|
aopt=None,
|
|
alpha=reg,
|
|
n_iter=n_iter,
|
|
algo='pls',
|
|
sim_method=sim_method)
|
|
self.model['qval'] = qvals
|
|
#self.model['qval_sorted'] = qvals_sorted
|
|
else:
|
|
self.model['qval'] = None
|
|
self.model['qval_sorted'] = None
|
|
|
|
def make_model(self, a, b, amax, scale, mode, engine):
|
|
"""Make model on amax components.
|
|
"""
|
|
print "Making model"
|
|
dat = engine(a, b, amax, scale, mode)
|
|
self.model.update(dat)
|
|
|
|
def as_dataset(self, name, dtype='Dataset'):
|
|
"""Return any model parameter as Dataset
|
|
No ids matching
|
|
"""
|
|
if name not in self.model.keys():
|
|
return
|
|
DX, DY = self._dataset['X'], self._dataset['Y']
|
|
dim_name_0, dim_name_1 = DX.get_dim_name()
|
|
dim_name_2, dim_name_3 = DY.get_dim_name()
|
|
#samples
|
|
ids_0 = [dim_name_0, DX.get_identifiers(dim_name_0, sorted=True)]
|
|
# x vars
|
|
ids_1 = [dim_name_1, DX.get_identifiers(dim_name_1, sorted=True)]
|
|
# y vars
|
|
ids_3 = [dim_name_3, DY.get_identifiers(dim_name_3, sorted=True)]
|
|
# components (hidden)
|
|
pc_ids = ['_comp', map(str, range(self._options['amax']))]
|
|
pc_ids_opt = ['_comp', map(str, range(self.model['aopt']))]
|
|
zero_dim = ['_doe',['0']] # null dim, vector (hidden)
|
|
|
|
match_ids = {'E' : [ids_0, ids_1],
|
|
'P' : [ids_1, pc_ids],
|
|
'T' : [ids_0, pc_ids],
|
|
'W' : [ids_1, pc_ids],
|
|
'R' : [ids_1, pc_ids],
|
|
'Q' : [ids_3, pc_ids],
|
|
'F' : [ids_0, ids_3],
|
|
'B' : [ids_1, ids_3],
|
|
'qval' : [ids_1, zero_dim],
|
|
'qval_sorted':[ids_1, zero_dim],
|
|
'w_tsq' : [ids_1, zero_dim],
|
|
'rmsep' : [ids_3, pc_ids],
|
|
'CP': [ids_1, pc_ids]
|
|
}
|
|
|
|
array = self.model[name]
|
|
M = Dataset(array, identifiers=match_ids[name], name=name)
|
|
return M
|
|
|
|
def get_out_plots(self, options):
|
|
out=[]
|
|
for plt in options['out_plots']:
|
|
#try:
|
|
out.append(plt(self))
|
|
#except:
|
|
# logger.log('debug', 'Plot: %s failed' %plt)
|
|
return out
|
|
|
|
def run_o(self, a, b):
|
|
"""Run PLS with present options."""
|
|
options = self._options
|
|
self._dataset['X'] = a
|
|
self._dataset['Y'] = b
|
|
self._data['X'] = a.asarray()
|
|
self._data['Y'] = b.asarray()
|
|
|
|
if options['center']:
|
|
self.model['E0'] = options['center_mth'](self._data['X'])
|
|
self.model['F0'] = options['center_mth'](self._data['Y'])
|
|
else:
|
|
self.model['E0'] = self._data['X']
|
|
self.model['F0'] = self._data['Y']
|
|
|
|
self.validation()
|
|
self.make_model(self.model['E0'], self.model['F0'],
|
|
**options.make_model_options())
|
|
# variance captured
|
|
var_x, exp_var_x = variances(self.model['E0'], self.model['T'], self.model['P'])
|
|
self.model['evx'] = var_x
|
|
self.model['exp_var_x'] = exp_var_x
|
|
|
|
var_y, exp_var_y = variances(self.model['F0'], self.model['T'], self.model['Q'])
|
|
self.model['evy'] = var_y
|
|
self.model['exp_var_y'] = exp_var_y
|
|
|
|
if options['calc_conf']:
|
|
self.confidence(**options.confidence_options())
|
|
|
|
out = [self.as_dataset(p) for p in options['out_data']]
|
|
for plt in self.get_out_plots(options):
|
|
out.append(plt)
|
|
return out
|
|
|
|
def run(self, a, b):
|
|
"""Run PLS with option gui.
|
|
"""
|
|
dialog = PlsOptionsDialog([a, b], self._options)
|
|
dialog.show_all()
|
|
response = dialog.run()
|
|
dialog.hide()
|
|
|
|
if response == gtk.RESPONSE_OK:
|
|
# set output data and plots
|
|
dialog.set_output()
|
|
|
|
#run with current data and options
|
|
return self.run_o(a, b)
|
|
|
|
class LPLS(Model):
|
|
def __init__(self, id='lpls', name='LPLS'):
|
|
Model.__init__(self, id, name)
|
|
self._options = LplsOptions()
|
|
|
|
def validation(self, opt):
|
|
"""Returns rmsep for lpls model.
|
|
"""
|
|
|
|
if opt['calc_cv']==True:
|
|
val_engine = opt['val_engine']
|
|
rmsep, aopt = val_engine(self.model['X'], self.model['Y'],
|
|
self.model['Z'], opt['amax'], opt['n_sets'], opt['xz_alpha'])
|
|
self.model['rmsep'] = rmsep
|
|
self.model['aopt'] = aopt
|
|
else:
|
|
self.model['rmsep'] = None
|
|
self.model['aopt'] = opt['aopt']
|
|
|
|
def confidence(self, opt):
|
|
"""Returns a confidence measure for model parameters
|
|
Supported parameters: W
|
|
"""
|
|
aopt = self.model['aopt']
|
|
if opt['calc_conf']:
|
|
Wx, Wz = lpls_jk(self._data['X'], self._data['Y'], self._data['Z'], aopt, opt['n_sets'], opt['xz_alpha'])
|
|
Wcal = self.model['W'][:,:aopt]
|
|
Lcal = self.model['L'][:,:aopt]
|
|
# ensure that Wcal is scaled
|
|
tnorm = scipy.apply_along_axis(norm, 0, self.model['T'][:,:aopt])
|
|
Wcal = Wcal*tnorm
|
|
a,b,c,d,e = opt['p_center'], opt['crot'], opt['alpha'], opt['strict'], opt['cov_center']
|
|
tsqx = hotelling(Wx, Wcal, a,b,c,d,e)
|
|
tsqz = hotelling(Wz, Lcal, a,b,c,d,e)
|
|
self.model['tsqx'] = tsqx
|
|
self.model['tsqz'] = tsqz
|
|
else:
|
|
self.model['tsqx'] = None
|
|
self.model['tsqz'] = None
|
|
|
|
def permutation_confidence(self, opt):
|
|
"""Estimates cut off on significant vars by controlling fdr.
|
|
|
|
"""
|
|
self.model['qval'] = None
|
|
self.model['qval_sorted'] = None
|
|
|
|
def make_model(self, opt):
|
|
"""Make model on amax components.
|
|
"""
|
|
engine = opt['engine']
|
|
dat = engine(self._data['X'], self._data['Y'], self._data['Z'],
|
|
opt['amax'], opt['xz_alpha'], opt['center_mth'],
|
|
opt['mode'], opt['scale'], False)
|
|
self.model.update(dat)
|
|
|
|
def as_dataset(self, name, dtype='Dataset'):
|
|
"""Return any model parameter as Dataset
|
|
No ids matching
|
|
"""
|
|
if name not in self.model.keys():
|
|
raise ValueError("There is no key named: %s in model" %name)
|
|
DX, DY, DZ = self._dataset['X'], self._dataset['Y'], self._dataset['Z']
|
|
dim_name_0, dim_name_1 = DX.get_dim_name()
|
|
dim_name_2, dim_name_3 = DY.get_dim_name()
|
|
dim_name_4, dim_name_5 = DZ.get_dim_name()
|
|
#samples
|
|
ids_0 = [dim_name_0, DX.get_identifiers(dim_name_0, sorted=True)]
|
|
# x vars (genes)
|
|
ids_1 = [dim_name_1, DX.get_identifiers(dim_name_1, sorted=True)]
|
|
# y vars (sample descriptors)
|
|
ids_3 = [dim_name_3, DY.get_identifiers(dim_name_3, sorted=True)]
|
|
#z-vars (variable descriptors)
|
|
ids_4 = [dim_name_4, DZ.get_identifiers(dim_name_4, sorted=True)]
|
|
# components (hidden)
|
|
pc_ids = ['_comp', map(str, range(self._options['amax']))]
|
|
pc_ids_opt = ['_comp', map(str, range(self.model['aopt']))]
|
|
zero_dim = ['_doe',['0']] # null dim, vector (hidden)
|
|
|
|
match_ids = {'E' : [ids_0, ids_1],
|
|
'P' : [ids_1, pc_ids],
|
|
'T' : [ids_0, pc_ids],
|
|
'W' : [ids_1, pc_ids],
|
|
'L' : [ids_4, pc_ids],
|
|
'Q' : [ids_3, pc_ids],
|
|
'F' : [ids_0, ids_3],
|
|
'B' : [ids_1, ids_3],
|
|
'tsqx' : [ids_1, zero_dim],
|
|
'tsqz' : [ids_4, zero_dim],
|
|
'K' : [ids_1, pc_ids],
|
|
'rmsep' : [ids_3, pc_ids],
|
|
'Rx' : [ids_1, pc_ids],
|
|
'Rz' : [ids_4, pc_ids]
|
|
}
|
|
|
|
try:
|
|
array = self.model[name]
|
|
ids = match_ids[name]
|
|
except:
|
|
raise ValueError("There are no identifers stored for: %s in model" %name)
|
|
M = Dataset(array, identifiers=ids, name=name)
|
|
return M
|
|
|
|
def get_out_plots(self, options):
|
|
out=[]
|
|
for plt in options['out_plots']:
|
|
out.append(plt(self))
|
|
return out
|
|
|
|
def run(self, a, b, c):
|
|
"""Run L-PLS with present options."""
|
|
options = self._options
|
|
self._dataset['X'] = a
|
|
self._dataset['Y'] = b
|
|
self._dataset['Z'] = c
|
|
self._data['X'] = a.asarray()
|
|
self._data['Y'] = b.asarray()
|
|
self._data['Z'] = c.asarray()
|
|
self.validation(options)
|
|
self.make_model(options)
|
|
|
|
if options['calc_conf']:
|
|
self.confidence(options)
|
|
|
|
out = [self.as_dataset(p) for p in options['out_data']]
|
|
for plt in self.get_out_plots(options):
|
|
out.append(plt)
|
|
return out
|
|
|
|
def run_gui(self, a, b, c):
|
|
"""Run LPLS with option gui.
|
|
"""
|
|
dialog = LPlsOptionsDialog([a, b, c], self._options)
|
|
dialog.show_all()
|
|
response = dialog.run()
|
|
dialog.hide()
|
|
|
|
if response == gtk.RESPONSE_OK:
|
|
# set output data and plots
|
|
dialog.set_output()
|
|
#run with current data and options
|
|
return self.run(a, b, c)
|
|
|
|
class PcaOptions(Options):
|
|
"""Options for Principal Component Analysis.
|
|
"""
|
|
def __init__(self):
|
|
Options.__init__(self)
|
|
self._set_default()
|
|
|
|
def _set_default(self):
|
|
opt = {}
|
|
opt['algo'] = 'pca'
|
|
opt['engine'] = pca
|
|
opt['mode'] = 'normal' # how much info to calculate
|
|
opt['amax'] = 10
|
|
opt['aopt'] = 5
|
|
opt['auto_aopt'] = False
|
|
opt['center'] = True
|
|
opt['center_mth'] = mat_center
|
|
opt['scale'] = 'scores'
|
|
|
|
opt['calc_conf'] = False
|
|
opt['n_sets'] = 7
|
|
opt['strict'] = True
|
|
opt['p_center'] = 'med'
|
|
opt['alpha'] = .2
|
|
opt['cov_center'] = 'med'
|
|
opt['crot'] = True
|
|
|
|
opt['calc_cv'] = False
|
|
opt['calc_pert'] = False
|
|
opt['pert_val_method'] = 'random_diag'
|
|
opt['cv_val_method'] = 'random'
|
|
opt['cv_val_sets'] = 10
|
|
opt['pert_val_sets'] = 10
|
|
|
|
opt['all_data'] = [('T', 'scores', True),
|
|
('P', 'loadings', True),
|
|
('E','residuals', False),
|
|
('p_tsq', 't2', False),
|
|
('rmsep', 'RMSEP', False)
|
|
]
|
|
|
|
# (class, name, sensitive, ticked)
|
|
opt['all_plots'] = [(blmplots.PcaScorePlot, 'Scores', True),
|
|
(blmplots.PcaLoadingPlot, 'Loadings', True),
|
|
(blmplots.LineViewXc, 'Line view', True),
|
|
(blmplots.PredictionErrorPlot, 'Residual Error', False),
|
|
(blmplots.PcaScreePlot, 'Scree', True)
|
|
]
|
|
|
|
opt['out_data'] = ['T','P', 'p_tsq']
|
|
opt['out_plots'] = [blmplots.PcaScorePlot,
|
|
blmplots.PcaLoadingPlot,
|
|
blmplots.LineViewXc,
|
|
blmplots.PcaScreePlot]
|
|
|
|
self.update(opt)
|
|
|
|
def make_model_options(self):
|
|
"""Options for make_model method."""
|
|
opt_list = ['scale', 'mode', 'amax']
|
|
return self._copy_from_list(opt_list)
|
|
|
|
def confidence_options(self):
|
|
"""Options for confidence method."""
|
|
opt_list = ['n_sets', 'aopt', 'alpha', 'p_center',
|
|
'strict', 'crot', 'cov_center']
|
|
return self._copy_from_list(opt_list)
|
|
|
|
def validation_options(self):
|
|
"""Options for pre_validation method."""
|
|
opt_list = ['amax', 'cv_val_sets', 'pert_val_sets',
|
|
'cv_val_method', 'pert_val_method']
|
|
return self._copy_from_list(opt_list)
|
|
|
|
|
|
class PlsOptions(Options):
|
|
"""Options for Partial Least Squares Regression.
|
|
"""
|
|
def __init__(self):
|
|
Options.__init__(self)
|
|
self._set_default()
|
|
|
|
def _set_default(self):
|
|
opt = {}
|
|
opt['algo'] = 'pls'
|
|
opt['engine'] = pls
|
|
opt['mode'] = 'normal' # how much info to calculate
|
|
opt['amax'] = 10
|
|
opt['aopt'] = 10
|
|
opt['auto_aopt'] = False
|
|
opt['center'] = True
|
|
opt['center_mth'] = mat_center
|
|
opt['scale'] = 'scores'
|
|
|
|
opt['calc_conf'] = True
|
|
opt['n_sets'] = 7
|
|
opt['strict'] = True
|
|
opt['p_center'] = 'med'
|
|
opt['alpha'] = .2
|
|
opt['cov_center'] = 'med'
|
|
opt['crot'] = True
|
|
|
|
opt['calc_cv'] = False
|
|
opt['cv_val_method'] = 'random'
|
|
opt['cv_val_sets'] = opt['n_sets']
|
|
|
|
opt['all_data'] = [('T', 'scores', True),
|
|
('P', 'loadings', True),
|
|
('E','residuals', False),
|
|
('w_tsq', 't2', True),
|
|
('rmsep', 'RMSEP', False)
|
|
]
|
|
|
|
# (class, name, sensitive, ticked)
|
|
opt['all_plots'] = [(blmplots.PlsScorePlot, 'Scores', True),
|
|
(blmplots.PlsXLoadingPlot, 'X-Loadings', True),
|
|
(blmplots.PlsYLoadingPlot, 'Y-Loadings', True),
|
|
(blmplots.LineViewXc, 'Line view', True),
|
|
(blmplots.PredictionErrorPlot, 'Residual Error', False),
|
|
(blmplots.RMSEPPlot, 'RMSEP', False),
|
|
(blmplots.PlsCorrelationLoadingPlot, 'Corr. loadings', False)
|
|
]
|
|
|
|
opt['out_data'] = ['T','P', 'w_tsq']
|
|
opt['out_plots'] = [blmplots.PlsScorePlot,blmplots.PlsXLoadingPlot,blmplots.PlsYLoadingPlot,blmplots.LineViewXc]
|
|
|
|
#opt['out_data'] = None
|
|
|
|
opt['pack'] = True
|
|
opt['calc_qvals'] = False
|
|
opt['q_pert_method'] = 'shuffle_rows'
|
|
opt['q_iter'] = 20
|
|
|
|
self.update(opt)
|
|
|
|
def make_model_options(self):
|
|
"""Options for make_model method."""
|
|
opt_list = ['scale','mode', 'amax', 'engine']
|
|
return self._copy_from_list(opt_list)
|
|
|
|
def confidence_options(self):
|
|
"""Options for confidence method."""
|
|
opt_list = ['n_sets', 'aopt', 'alpha', 'p_center',
|
|
'strict', 'crot', 'cov_center']
|
|
return self._copy_from_list(opt_list)
|
|
|
|
def validation_options(self):
|
|
opt_list = ['amax', 'n_sets', 'cv_val_method']
|
|
return self._copy_from_list(opt_list)
|
|
|
|
def permutation_confidence(self):
|
|
opt_list = ['q_pert_method', 'q_iter']
|
|
return self._copy_from_list(opt_list)
|
|
|
|
|
|
class LplsOptions(Options):
|
|
"""Options for L-shaped Partial Least Squares Regression.
|
|
"""
|
|
def __init__(self):
|
|
Options.__init__(self)
|
|
self._set_default()
|
|
|
|
def _set_default(self):
|
|
opt = {}
|
|
opt['engine'] = nipals_lpls
|
|
opt['mode'] = 'normal' # how much info to calculate
|
|
opt['amax'] = 10
|
|
opt['aopt'] = 3
|
|
opt['xz_alpha'] = 0.6
|
|
opt['auto_aopt'] = False
|
|
opt['center'] = True
|
|
opt['center_mth'] = [2, 0, 2]
|
|
opt['scale'] = 'scores'
|
|
opt['calc_conf'] = False
|
|
opt['n_sets'] = 7
|
|
opt['strict'] = False
|
|
opt['p_center'] = 'med'
|
|
opt['alpha'] = .3
|
|
opt['cov_center'] = 'med'
|
|
opt['crot'] = True
|
|
|
|
opt['calc_cv'] = False
|
|
opt['cv_val_method'] = 'random'
|
|
opt['cv_val_sets'] = opt['n_sets']
|
|
|
|
opt['all_data'] = [('T', 'scores', True),
|
|
('Wx', 'X-weights', True),
|
|
('Wz', 'Z-weights', True),
|
|
('E','residuals', False),
|
|
('tsq_x', 't2X', False),
|
|
('rmsep', 'RMSEP', False)
|
|
]
|
|
|
|
# (class, name, sensitive, ticked)
|
|
opt['all_plots'] = [(blmplots.LplsScorePlot, 'Scores', True),
|
|
(blmplots.LplsXLoadingPlot, 'Loadings', True),
|
|
(blmplots.LineViewXc, 'Line view', True),
|
|
(blmplots.LplsHypoidCorrelationPlot, 'Hypoid corr.', False),
|
|
(blmplots.LplsXCorrelationPlot, 'X corr.', True),
|
|
(blmplots.LplsZCorrelationPlot, 'Z corr.', True)
|
|
]
|
|
|
|
opt['out_data'] = ['T','P','L','K', 'tsqx', 'tsqz']
|
|
opt['out_plots'] = [blmplots.LplsScorePlot,
|
|
blmplots.LplsXLoadingPlot,
|
|
blmplots.LplsZLoadingPlot,
|
|
blmplots.LplsXCorrelationPlot,
|
|
blmplots.LplsZCorrelationPlot,
|
|
blmplots.LineViewXc,
|
|
blmplots.LplsExplainedVariancePlot]
|
|
|
|
#opt['out_data'] = None
|
|
|
|
opt['pack'] = False
|
|
opt['calc_qvals'] = False
|
|
opt['q_pert_method'] = 'shuffle_rows'
|
|
opt['q_iter'] = 20
|
|
|
|
self.update(opt)
|
|
|
|
def make_model_options(self):
|
|
"""Options for make_model method."""
|
|
opt_list = ['scale','mode', 'amax', 'engine']
|
|
return self._copy_from_list(opt_list)
|
|
|
|
def confidence_options(self):
|
|
"""Options for confidence method."""
|
|
opt_list = ['n_sets', 'aopt', 'alpha', 'p_center',
|
|
'strict', 'crot', 'cov_center']
|
|
return self._copy_from_list(opt_list)
|
|
|
|
def validation_options(self):
|
|
"""Options for pre_validation method."""
|
|
opt_list = ['amax', 'n_sets', 'cv_val_method']
|
|
return self._copy_from_list(opt_list)
|
|
|
|
|
|
class PcaOptionsDialog(OptionsDialog):
|
|
"""Options dialog for Principal Component Analysis.
|
|
"""
|
|
def __init__(self, data, options, input_names=['X']):
|
|
OptionsDialog.__init__(self, data, options, input_names)
|
|
glade_file = os.path.join(fluents.DATADIR, 'pca_options.glade')
|
|
|
|
notebook_name = "vbox1"
|
|
page_name = "Options"
|
|
self.add_page_from_glade(glade_file, notebook_name, page_name)
|
|
# connect signals to handlers
|
|
dic = {"on_amax_value_changed" : self.on_amax_changed,
|
|
"on_aopt_value_changed" : self.on_aopt_changed,
|
|
"auto_aopt_toggled" : self.auto_aopt_toggled,
|
|
"center_toggled" : self.center_toggled,
|
|
#"on_scale_changed" : self.on_scale_changed,
|
|
"on_val_none" : self.val_toggled,
|
|
"on_val_cv" : self.cv_toggled,
|
|
"on_val_pert" : self.pert_toggled,
|
|
"on_cv_method_changed" : self.on_cv_method_changed,
|
|
"on_cv_sets_changed" : self.on_cv_sets_changed,
|
|
"on_pert_sets_changed" : self.on_pert_sets_changed,
|
|
"on_conf_toggled" : self.on_conf_toggled,
|
|
"on_subset_loc_changed" : self.on_subset_loc_changed,
|
|
"on_cov_loc_changed" : self.on_cov_loc_changed,
|
|
"on_alpha_changed" : self.on_alpha_changed,
|
|
"on_rot_changed" : self.on_rot_changed
|
|
}
|
|
|
|
self.wTree.signal_autoconnect(dic)
|
|
|
|
# set/ensure valid default values/ranges
|
|
#
|
|
amax_sb = self.wTree.get_widget("amax_spinbutton")
|
|
max_comp = min(data[0].shape) # max num of components
|
|
if self._options['amax']>max_comp:
|
|
logger.log('debug', 'amax default too large ... adjusting')
|
|
self._options['amax'] = max_comp
|
|
amax_sb.get_adjustment().set_all(self._options['amax'], 1, max_comp, 1, 0, 0)
|
|
# aopt spin button
|
|
aopt_sb = self.wTree.get_widget("aopt_spinbutton")
|
|
if self._options['aopt']>self._options['amax']:
|
|
self._options['aopt'] = self._options['amax'] + 1 - 1
|
|
aopt_sb.get_adjustment().set_all(self._options['aopt'], 1, self._options['amax'], 1, 0, 0)
|
|
|
|
# scale
|
|
# scale_cb = self.wTree.get_widget("scale_combobox")
|
|
# scale_cb.set_active(0)
|
|
|
|
# validation frames
|
|
if self._options['calc_cv']==False:
|
|
cv_frame = self.wTree.get_widget("cv_frame")
|
|
cv_frame.set_sensitive(False)
|
|
if self._options['calc_pert']==False:
|
|
pert_frame = self.wTree.get_widget("pert_frame")
|
|
pert_frame.set_sensitive(False)
|
|
|
|
cv = self.wTree.get_widget("cv_method").set_active(0)
|
|
pm = self.wTree.get_widget("pert_method").set_active(0)
|
|
|
|
# confidence
|
|
if self._options['calc_conf']==True:
|
|
self.wTree.get_widget("subset_expander").set_sensitive(True)
|
|
else:
|
|
self.wTree.get_widget("subset_expander").set_sensitive(False)
|
|
|
|
cb = self.wTree.get_widget("subset_loc")
|
|
_m = {'med': 0, 'mean': 1, 'full_model': 2}
|
|
cb.set_active(_m.get(self._options['p_center']))
|
|
|
|
cb = self.wTree.get_widget("cov_loc")
|
|
_m = {'med': 0, 'mean': 1}
|
|
cb.set_active(_m.get(self._options['cov_center']))
|
|
|
|
hs = self.wTree.get_widget("alpha_scale")
|
|
hs.set_value(self._options['alpha'])
|
|
|
|
|
|
def on_amax_changed(self, sb):
|
|
logger.log("debug", "amax changed: new value: %s" %sb.get_value_as_int())
|
|
amax = sb.get_value_as_int()
|
|
# update aopt if needed
|
|
if amax<self._options['aopt']:
|
|
self._options['aopt'] = amax
|
|
aopt_sb = self.wTree.get_widget("aopt_spinbutton")
|
|
aopt_sb.get_adjustment().set_all(self._options['aopt'], 1, amax, 1, 0, 0)
|
|
self._options['amax'] = sb.get_value_as_int()
|
|
|
|
def on_aopt_changed(self, sb):
|
|
aopt = sb.get_value_as_int()
|
|
self._options['aopt'] = aopt
|
|
|
|
def auto_aopt_toggled(self, tb):
|
|
aopt_sb = self.wTree.get_widget("aopt_spinbutton")
|
|
if tb.get_active():
|
|
self._options['auto_aopt'] = True
|
|
aopt_sb.set_sensitive(False)
|
|
else:
|
|
self._options['auto_aopt'] = False
|
|
aopt_sb.set_sensitive(True)
|
|
|
|
def center_toggled(self, tb):
|
|
if tb.get_active():
|
|
self._options['center'] = True
|
|
else:
|
|
logger.log("debug", "centering set to False")
|
|
self._options['center'] = False
|
|
|
|
#def on_scale_changed(self, cb):
|
|
# scale = cb.get_active_text()
|
|
# if scale=='Scores':
|
|
# self._options['scale'] = 'scores'
|
|
# elif scale=='Loadings':
|
|
# self._options['scale'] = 'loads'
|
|
# else:
|
|
# raise IOError
|
|
|
|
def val_toggled(self, tb):
|
|
"""Callback for validation: None. """
|
|
cv_frame = self.wTree.get_widget("cv_frame")
|
|
pert_frame = self.wTree.get_widget("pert_frame")
|
|
cv_tb = self.wTree.get_widget("cv_toggle")
|
|
p_tb = self.wTree.get_widget("pert_toggle")
|
|
if tb.get_active():
|
|
self._options['calc_cv'] = False
|
|
self._options['calc_pert'] = False
|
|
cv_frame.set_sensitive(False)
|
|
pert_frame.set_sensitive(False)
|
|
cv_tb.set_sensitive(False)
|
|
p_tb.set_sensitive(False)
|
|
else:
|
|
p_tb.set_sensitive(True)
|
|
cv_tb.set_sensitive(True)
|
|
if p_tb.get_active():
|
|
pert_frame.set_sensitive(True)
|
|
self._options['calc_pert'] = True
|
|
if cv_tb.get_active():
|
|
cv_frame.set_sensitive(True)
|
|
self._options['calc_cv'] = True
|
|
|
|
def cv_toggled(self, tb):
|
|
cv_frame = self.wTree.get_widget("cv_frame")
|
|
if tb.get_active():
|
|
cv_frame.set_sensitive(True)
|
|
self._options['calc_cv'] = True
|
|
else:
|
|
cv_frame.set_sensitive(False)
|
|
self._options['calc_cv'] = False
|
|
|
|
def pert_toggled(self, tb):
|
|
pert_frame = self.wTree.get_widget("pert_frame")
|
|
if tb.get_active():
|
|
pert_frame.set_sensitive(True)
|
|
self._options['calc_pert'] = True
|
|
else:
|
|
pert_frame.set_sensitive(False)
|
|
self._options['calc_pert'] = False
|
|
|
|
|
|
def on_cv_method_changed(self, cb):
|
|
method = cb.get_active_text()
|
|
if method == 'Random':
|
|
self._options['cv_val_method'] = 'random'
|
|
|
|
def on_pert_method_changed(self, cb):
|
|
method = cb.get_active_text()
|
|
if method == 'Random diags':
|
|
self._options['pert_val_method'] = 'random_diag'
|
|
|
|
def on_cv_sets_changed(self, sb):
|
|
val = sb.get_value_as_int()
|
|
self._options['cv_val_sets'] = val
|
|
|
|
def on_pert_sets_changed(self, sb):
|
|
val = sb.get_value_as_int()
|
|
self._options['pert_val_sets'] = val
|
|
|
|
def on_conf_toggled(self, tb):
|
|
if tb.get_active():
|
|
self._options['calc_conf'] = False
|
|
self.wTree.get_widget("subset_expander").set_sensitive(False)
|
|
else:
|
|
self._options['calc_conf'] = True
|
|
self.wTree.get_widget("subset_expander").set_sensitive(True)
|
|
|
|
def on_subset_loc_changed(self, cb):
|
|
method = cb.get_active_text()
|
|
if method=='Full model':
|
|
self._options['p_center'] = 'full_model'
|
|
elif method=='Median':
|
|
self._options['p_center'] = 'med'
|
|
elif method=='Mean':
|
|
self._options['p_center'] = 'mean'
|
|
|
|
def on_cov_loc_changed(self, cb):
|
|
method = cb.get_active_text()
|
|
if method=='Median':
|
|
self._options['cov_center'] = 'med'
|
|
elif method=='Mean':
|
|
self._options['cov_center'] = 'mean'
|
|
|
|
def on_alpha_changed(self, hs):
|
|
self._options['alpha'] = hs.get_value()
|
|
|
|
def on_rot_changed(self, rg):
|
|
proc, strict = rg
|
|
if proc.get_active():
|
|
self._options['crot'] = True
|
|
else:
|
|
self._options['crot'] = True
|
|
self._options['strict'] = True
|
|
|
|
class LplsOptionsDialog(OptionsDialog):
|
|
"""Options dialog for L-shaped Partial Least squares regression.
|
|
"""
|
|
def __init__(self, data, options, input_names=['X', 'Y', 'Z']):
|
|
OptionsDialog.__init__(self, data, options, input_names)
|
|
glade_file = os.path.join(fluents.DATADIR, 'lpls_options.glade')
|
|
|
|
notebook_name = "vbox1"
|
|
page_name = "Options"
|
|
self.add_page_from_glade(glade_file, notebook_name, page_name)
|
|
# connect signals to handlers
|
|
dic = {"on_amax_value_changed" : self.on_amax_changed,
|
|
"on_aopt_value_changed" : self.on_aopt_changed,
|
|
"auto_aopt_toggled" : self.auto_aopt_toggled,
|
|
"center_toggled" : self.center_toggled,
|
|
#"on_scale_changed" : self.on_scale_changed,
|
|
"on_val_none" : self.val_toggled,
|
|
"on_val_cv" : self.cv_toggled,
|
|
"on_cv_method_changed" : self.on_cv_method_changed,
|
|
"on_cv_sets_changed" : self.on_cv_sets_changed,
|
|
"on_conf_toggled" : self.conf_toggled,
|
|
"on_subset_loc_changed" : self.on_subset_loc_changed,
|
|
"on_cov_loc_changed" : self.on_cov_loc_changed,
|
|
"on_alpha_changed" : self.on_alpha_changed,
|
|
"on_rot_changed" : self.on_rot_changed,
|
|
"on__toggled" : self.conf_toggled,
|
|
"on_qval_changed" : self.on_qval_changed,
|
|
"on_iter_changed" : self.on_iter_changed
|
|
}
|
|
|
|
self.wTree.signal_autoconnect(dic)
|
|
|
|
# set/ensure valid default values/ranges
|
|
#
|
|
amax_sb = self.wTree.get_widget("amax_spinbutton")
|
|
max_comp = min(data[0].shape) # max num of components
|
|
if self._options['amax']>max_comp:
|
|
logger.log('debug', 'amax default too large ... adjusting')
|
|
self._options['amax'] = max_comp
|
|
amax_sb.get_adjustment().set_all(self._options['amax'], 1, max_comp, 1, 0, 0)
|
|
# aopt spin button
|
|
aopt_sb = self.wTree.get_widget("aopt_spinbutton")
|
|
if self._options['aopt']>self._options['amax']:
|
|
self._options['aopt'] = self._options['amax'] + 1 - 1
|
|
aopt_sb.get_adjustment().set_all(self._options['aopt'], 1, self._options['amax'], 1, 0, 0)
|
|
|
|
# scale
|
|
# scale_cb = self.wTree.get_widget("scale_combobox")
|
|
# scale_cb.set_active(0)
|
|
|
|
# validation frames
|
|
if self._options['calc_cv']==False:
|
|
cv_frame = self.wTree.get_widget("cv_frame")
|
|
cv_frame.set_sensitive(False)
|
|
|
|
cv = self.wTree.get_widget("cv_method").set_active(0)
|
|
|
|
# confidence
|
|
if self._options['calc_conf']==True:
|
|
self.wTree.get_widget("subset_expander").set_sensitive(True)
|
|
else:
|
|
self.wTree.get_widget("subset_expander").set_sensitive(False)
|
|
|
|
cb = self.wTree.get_widget("subset_loc")
|
|
_m = {'med': 0, 'mean': 1, 'full_model': 2}
|
|
cb.set_active(_m.get(self._options['p_center']))
|
|
|
|
cb = self.wTree.get_widget("cov_loc")
|
|
_m = {'med': 0, 'mean': 1}
|
|
cb.set_active(_m.get(self._options['cov_center']))
|
|
|
|
hs = self.wTree.get_widget("alpha_scale")
|
|
hs.set_value(self._options['alpha'])
|
|
|
|
tb = self.wTree.get_widget("qvals")
|
|
tb.set_sensitive(True)
|
|
|
|
|
|
def on_amax_changed(self, sb):
|
|
logger.log("debug", "amax changed: new value: %s" %sb.get_value_as_int())
|
|
amax = sb.get_value_as_int()
|
|
# update aopt if needed
|
|
if amax<self._options['aopt']:
|
|
self._options['aopt'] = amax
|
|
aopt_sb = self.wTree.get_widget("aopt_spinbutton")
|
|
aopt_sb.get_adjustment().set_all(self._options['aopt'], 1, amax, 1, 0, 0)
|
|
self._options['amax'] = sb.get_value_as_int()
|
|
|
|
def on_aopt_changed(self, sb):
|
|
aopt = sb.get_value_as_int()
|
|
self._options['aopt'] = aopt
|
|
|
|
def auto_aopt_toggled(self, tb):
|
|
aopt_sb = self.wTree.get_widget("aopt_spinbutton")
|
|
if tb.get_active():
|
|
self._options['auto_aopt'] = True
|
|
aopt_sb.set_sensitive(False)
|
|
else:
|
|
self._options['auto_aopt'] = False
|
|
aopt_sb.set_sensitive(True)
|
|
|
|
def center_toggled(self, tb):
|
|
if tb.get_active():
|
|
self._options['center'] = True
|
|
else:
|
|
logger.log("debug", "centering set to False")
|
|
self._options['center'] = False
|
|
|
|
#def on_scale_changed(self, cb):
|
|
# scale = cb.get_active_text()
|
|
# if scale=='Scores':
|
|
# self._options['scale'] = 'scores'
|
|
# elif scale=='Loadings':
|
|
# self._options['scale'] = 'loads'
|
|
# else:
|
|
# raise IOError
|
|
|
|
def val_toggled(self, tb):
|
|
"""Callback for validation: None. """
|
|
cv_frame = self.wTree.get_widget("cv_frame")
|
|
cv_tb = self.wTree.get_widget("cv_toggle")
|
|
if tb.get_active():
|
|
self._options['calc_cv'] = False
|
|
cv_frame.set_sensitive(False)
|
|
cv_tb.set_sensitive(False)
|
|
else:
|
|
cv_tb.set_sensitive(True)
|
|
if cv_tb.get_active():
|
|
cv_frame.set_sensitive(True)
|
|
self._options['calc_cv'] = True
|
|
|
|
def cv_toggled(self, tb):
|
|
cv_frame = self.wTree.get_widget("cv_frame")
|
|
val_tb = self.wTree.get_widget("val_none_toggle")
|
|
if tb.get_active():
|
|
cv_frame.set_sensitive(True)
|
|
self._options['calc_cv'] = True
|
|
else:
|
|
cv_frame.set_sensitive(False)
|
|
self._options['calc_cv'] = False
|
|
|
|
def on_cv_method_changed(self, cb):
|
|
method = cb.get_active_text()
|
|
if method == 'Random':
|
|
self._options['cv_val_method'] = 'random'
|
|
|
|
def on_cv_sets_changed(self, sb):
|
|
val = sb.get_value_as_int()
|
|
self._options['cv_val_sets'] = val
|
|
|
|
def conf_toggled(self, tb):
|
|
if tb.get_active():
|
|
self._options['calc_conf'] = False
|
|
self.wTree.get_widget("subset_expander").set_sensitive(False)
|
|
else:
|
|
self._options['calc_conf'] = True
|
|
self.wTree.get_widget("subset_expander").set_sensitive(True)
|
|
|
|
def on_subset_loc_changed(self, cb):
|
|
method = cb.get_active_text()
|
|
if method=='Full model':
|
|
self._options['p_center'] = 'full_model'
|
|
elif method=='Median':
|
|
self._options['p_center'] = 'med'
|
|
elif method=='Mean':
|
|
self._options['p_center'] = 'mean'
|
|
|
|
def on_cov_loc_changed(self, cb):
|
|
method = cb.get_active_text()
|
|
if method=='Median':
|
|
self._options['cov_center'] = 'med'
|
|
elif method=='Mean':
|
|
self._options['cov_center'] = 'mean'
|
|
|
|
def on_alpha_changed(self, hs):
|
|
self._options['alpha'] = hs.get_value()
|
|
|
|
def on_rot_changed(self, rg):
|
|
proc, strict = rg
|
|
if proc.get_active():
|
|
self._options['crot'] = True
|
|
else:
|
|
self._options['crot'] = True
|
|
self._options['strict'] = True
|
|
|
|
def qval_toggled(self, tb):
|
|
if tb.get_active():
|
|
self._options['calc_qval'] = False
|
|
self.wTree.get_widget("qval_method").set_sensitive(False)
|
|
self.wTree.get_widget("q_iter").set_sensitive(False)
|
|
else:
|
|
self._options['calc_qval'] = True
|
|
self.wTree.get_widget("qval_method").set_sensitive(True)
|
|
self.wTree.get_widget("q_iter").set_sensitive(True)
|
|
|
|
def on_iter_changed(self, sb):
|
|
self._options['q_iter'] = sb.get_value()
|
|
|
|
def on_qval_changed(self, cb):
|
|
q_method = cb.get_active_text()
|
|
if method=='Shuffle rows':
|
|
self._options['q_pert_method'] = 'shuffle'
|
|
|
|
|
|
class PlsOptionsDialog(OptionsDialog):
|
|
"""Options dialog for Partial Least squares regression.
|
|
"""
|
|
def __init__(self, data, options, input_names=['X', 'Y']):
|
|
OptionsDialog.__init__(self, data, options, input_names)
|
|
glade_file = os.path.join(fluents.DATADIR, 'pls_options.glade')
|
|
|
|
notebook_name = "vbox1"
|
|
page_name = "Options"
|
|
self.add_page_from_glade(glade_file, notebook_name, page_name)
|
|
# connect signals to handlers
|
|
dic = {"on_amax_value_changed" : self.on_amax_changed,
|
|
"on_aopt_value_changed" : self.on_aopt_changed,
|
|
"auto_aopt_toggled" : self.auto_aopt_toggled,
|
|
"center_toggled" : self.center_toggled,
|
|
#"on_scale_changed" : self.on_scale_changed,
|
|
"on_val_none" : self.val_toggled,
|
|
"on_val_cv" : self.cv_toggled,
|
|
"on_cv_method_changed" : self.on_cv_method_changed,
|
|
"on_cv_sets_changed" : self.on_cv_sets_changed,
|
|
"on_conf_toggled" : self.conf_toggled,
|
|
"on_subset_loc_changed" : self.on_subset_loc_changed,
|
|
"on_cov_loc_changed" : self.on_cov_loc_changed,
|
|
"on_alpha_changed" : self.on_alpha_changed,
|
|
"on_rot_changed" : self.on_rot_changed,
|
|
"on__toggled" : self.conf_toggled,
|
|
"on_qval_changed" : self.on_qval_changed,
|
|
"on_iter_changed" : self.on_iter_changed
|
|
}
|
|
|
|
self.wTree.signal_autoconnect(dic)
|
|
|
|
# set/ensure valid default values/ranges
|
|
#
|
|
amax_sb = self.wTree.get_widget("amax_spinbutton")
|
|
max_comp = min(data[0].shape) # max num of components
|
|
if self._options['amax']>max_comp:
|
|
logger.log('debug', 'amax default too large ... adjusting')
|
|
self._options['amax'] = max_comp
|
|
amax_sb.get_adjustment().set_all(self._options['amax'], 1, max_comp, 1, 0, 0)
|
|
# aopt spin button
|
|
aopt_sb = self.wTree.get_widget("aopt_spinbutton")
|
|
if self._options['aopt']>self._options['amax']:
|
|
self._options['aopt'] = self._options['amax'] + 1 - 1
|
|
aopt_sb.get_adjustment().set_all(self._options['aopt'], 1, self._options['amax'], 1, 0, 0)
|
|
|
|
# scale
|
|
# scale_cb = self.wTree.get_widget("scale_combobox")
|
|
# scale_cb.set_active(0)
|
|
|
|
# validation frames
|
|
if self._options['calc_cv']==False:
|
|
cv_frame = self.wTree.get_widget("cv_frame")
|
|
cv_frame.set_sensitive(False)
|
|
|
|
cv = self.wTree.get_widget("cv_method").set_active(0)
|
|
|
|
# confidence
|
|
if self._options['calc_conf']==True:
|
|
self.wTree.get_widget("subset_expander").set_sensitive(True)
|
|
else:
|
|
self.wTree.get_widget("subset_expander").set_sensitive(False)
|
|
|
|
cb = self.wTree.get_widget("subset_loc")
|
|
_m = {'med': 0, 'mean': 1, 'full_model': 2}
|
|
cb.set_active(_m.get(self._options['p_center']))
|
|
|
|
cb = self.wTree.get_widget("cov_loc")
|
|
_m = {'med': 0, 'mean': 1}
|
|
cb.set_active(_m.get(self._options['cov_center']))
|
|
|
|
hs = self.wTree.get_widget("alpha_scale")
|
|
hs.set_value(self._options['alpha'])
|
|
|
|
tb = self.wTree.get_widget("qvals")
|
|
tb.set_sensitive(True)
|
|
|
|
|
|
def on_amax_changed(self, sb):
|
|
logger.log("debug", "amax changed: new value: %s" %sb.get_value_as_int())
|
|
amax = sb.get_value_as_int()
|
|
# update aopt if needed
|
|
if amax<self._options['aopt']:
|
|
self._options['aopt'] = amax
|
|
aopt_sb = self.wTree.get_widget("aopt_spinbutton")
|
|
aopt_sb.get_adjustment().set_all(self._options['aopt'], 1, amax, 1, 0, 0)
|
|
self._options['amax'] = sb.get_value_as_int()
|
|
|
|
def on_aopt_changed(self, sb):
|
|
aopt = sb.get_value_as_int()
|
|
self._options['aopt'] = aopt
|
|
|
|
def auto_aopt_toggled(self, tb):
|
|
aopt_sb = self.wTree.get_widget("aopt_spinbutton")
|
|
if tb.get_active():
|
|
self._options['auto_aopt'] = True
|
|
aopt_sb.set_sensitive(False)
|
|
else:
|
|
self._options['auto_aopt'] = False
|
|
aopt_sb.set_sensitive(True)
|
|
|
|
def center_toggled(self, tb):
|
|
if tb.get_active():
|
|
self._options['center'] = True
|
|
else:
|
|
logger.log("debug", "centering set to False")
|
|
self._options['center'] = False
|
|
|
|
#def on_scale_changed(self, cb):
|
|
# scale = cb.get_active_text()
|
|
# if scale=='Scores':
|
|
# self._options['scale'] = 'scores'
|
|
# elif scale=='Loadings':
|
|
# self._options['scale'] = 'loads'
|
|
# else:
|
|
# raise IOError
|
|
|
|
def val_toggled(self, tb):
|
|
"""Callback for validation: None. """
|
|
cv_frame = self.wTree.get_widget("cv_frame")
|
|
cv_tb = self.wTree.get_widget("cv_toggle")
|
|
if tb.get_active():
|
|
self._options['calc_cv'] = False
|
|
cv_frame.set_sensitive(False)
|
|
cv_tb.set_sensitive(False)
|
|
else:
|
|
cv_tb.set_sensitive(True)
|
|
if cv_tb.get_active():
|
|
cv_frame.set_sensitive(True)
|
|
self._options['calc_cv'] = True
|
|
|
|
def cv_toggled(self, tb):
|
|
cv_frame = self.wTree.get_widget("cv_frame")
|
|
val_tb = self.wTree.get_widget("val_none_toggle")
|
|
if tb.get_active():
|
|
cv_frame.set_sensitive(True)
|
|
self._options['calc_cv'] = True
|
|
else:
|
|
cv_frame.set_sensitive(False)
|
|
self._options['calc_cv'] = False
|
|
|
|
def on_cv_method_changed(self, cb):
|
|
method = cb.get_active_text()
|
|
if method == 'Random':
|
|
self._options['cv_val_method'] = 'random'
|
|
|
|
def on_cv_sets_changed(self, sb):
|
|
val = sb.get_value_as_int()
|
|
self._options['cv_val_sets'] = val
|
|
|
|
def conf_toggled(self, tb):
|
|
if tb.get_active():
|
|
self._options['calc_conf'] = False
|
|
self.wTree.get_widget("subset_expander").set_sensitive(False)
|
|
else:
|
|
self._options['calc_conf'] = True
|
|
self.wTree.get_widget("subset_expander").set_sensitive(True)
|
|
|
|
def on_subset_loc_changed(self, cb):
|
|
method = cb.get_active_text()
|
|
if method=='Full model':
|
|
self._options['p_center'] = 'full_model'
|
|
elif method=='Median':
|
|
self._options['p_center'] = 'med'
|
|
elif method=='Mean':
|
|
self._options['p_center'] = 'mean'
|
|
|
|
def on_cov_loc_changed(self, cb):
|
|
method = cb.get_active_text()
|
|
if method=='Median':
|
|
self._options['cov_center'] = 'med'
|
|
elif method=='Mean':
|
|
self._options['cov_center'] = 'mean'
|
|
|
|
def on_alpha_changed(self, hs):
|
|
self._options['alpha'] = hs.get_value()
|
|
|
|
def on_rot_changed(self, rg):
|
|
proc, strict = rg
|
|
if proc.get_active():
|
|
self._options['crot'] = True
|
|
else:
|
|
self._options['crot'] = True
|
|
self._options['strict'] = True
|
|
|
|
def qval_toggled(self, tb):
|
|
if tb.get_active():
|
|
self._options['calc_qval'] = False
|
|
self.wTree.get_widget("qval_method").set_sensitive(False)
|
|
self.wTree.get_widget("q_iter").set_sensitive(False)
|
|
else:
|
|
self._options['calc_qval'] = True
|
|
self.wTree.get_widget("qval_method").set_sensitive(True)
|
|
self.wTree.get_widget("q_iter").set_sensitive(True)
|
|
|
|
def on_iter_changed(self, sb):
|
|
self._options['q_iter'] = sb.get_value()
|
|
|
|
def on_qval_changed(self, cb):
|
|
q_method = cb.get_active_text()
|
|
if method=='Shuffle rows':
|
|
self._options['q_pert_method'] = 'shuffle'
|