def __init__(self, sModelName, sModelDir,
iBlockVisibility = None,
iLineVisibility = None,
sComment = None,
C=None, tol=None, njobs=None, max_iter=None,
inference_cache=None):
DU_ABPTableRCut.iBlockVisibility = iBlockVisibility
DU_ABPTableRCut.iLineVisibility = iLineVisibility
DU_CRF_Task.__init__(self
, sModelName, sModelDir
, dFeatureConfig = {'row_row':{} , 'row_hdr':{}, 'row_sepH':{},
'hdr_row':{} , 'hdr_hdr':{}, 'hdr_sepH':{},
'sepH_row':{},'sepH_hdr':{}, 'sepH_sepH':{},
'row':{} , 'hdr':{} , 'sepH':{}}
, dLearnerConfig = {
'C' : .1 if C is None else C
, 'njobs' : 4 if njobs is None else njobs
, 'inference_cache' : 50 if inference_cache is None else inference_cache
#, 'tol' : .1
, 'tol' : .05 if tol is None else tol
, 'save_every' : 50 #save every 50 iterations,for warm start
, 'max_iter' : 10 if max_iter is None else max_iter
}
, sComment=sComment
#,cFeatureDefinition=FeatureDefinition_PageXml_StandardOnes_noText
,cFeatureDefinition=My_FeatureDefinition_v2
)
def __init__(self, sModelName, sModelDir, sComment=None):
DU_CRF_Task.__init__(self
, sModelName, sModelDir
, dFeatureConfig = {
'n_tfidf_node' : 10
, 't_ngrams_node' : (2,2)
, 'b_tfidf_node_lc' : False
, 'n_tfidf_edge' : 10
, 't_ngrams_edge' : (2,2)
, 'b_tfidf_edge_lc' : False
}
, dLearnerConfig = {
'C' : .1
, 'njobs' : 2
, 'inference_cache' : 10
, 'tol' : .1
, 'save_every' : 5 #save every 50 iterations,for warm start
#, 'max_iter' : 1000
, 'max_iter' : 2
}
, sComment=sComment
)
self.addBaseline_LogisticRegression() #use a LR model as baseline
def __init__(self, sModelName, sModelDir, sComment=None, C=None, tol=None, njobs=None, max_iter=None, inference_cache=None):
#another way to specify the graph class
# defining a getConfiguredGraphClass is preferred
self.configureGraphClass(self.DU_GRAPH)
DU_CRF_Task.__init__(self
, sModelName, sModelDir
, dLearnerConfig = {
'C' : .1 if C is None else C
, 'njobs' : 8 if njobs is None else njobs
, 'inference_cache' : 50 if inference_cache is None else inference_cache
#, 'tol' : .1
, 'tol' : .05 if tol is None else tol
, 'save_every' : 50 #save every 50 iterations,for warm start
, 'max_iter' : 1000 if max_iter is None else max_iter
}
, sComment=sComment
, cFeatureDefinition=FeatureDefinition_T_PageXml_StandardOnes_noText_v3
, dFeatureConfig = {
#config for the extractor of nodes of each type
"text": None,
"sprtr": None,
#config for the extractor of edges of each type
"text_text": None,
"text_sprtr": None,
"sprtr_text": None,
"sprtr_sprtr": None
}
)
traceln("- classes: ", self.DU_GRAPH.getLabelNameList())
self.bsln_mdl = self.addBaseline_LogisticRegression() #use a LR model trained by GridSearch as baseline
def __init__(self,
sModelName,
sModelDir,
iBlockVisibility=None,
iLineVisibility=None,
fCutHeight=None,
bCutAbove=None,
lRadAngle=None,
bTxt=None,
sComment=None,
cFeatureDefinition=None,
dFeatureConfig={},
C=None,
tol=None,
njobs=None,
max_iter=None,
inference_cache=None):
DU_ABPTableSkewedRowCutLine.iBlockVisibility = iBlockVisibility
DU_ABPTableSkewedRowCutLine.iLineVisibility = iLineVisibility
DU_ABPTableSkewedRowCutLine.fCutHeight = fCutHeight
DU_ABPTableSkewedRowCutLine.bCutAbove = bCutAbove
DU_ABPTableSkewedRowCutLine.lRadAngle = lRadAngle
DU_ABPTableSkewedRowCutLine.bTxt = bTxt
DU_CRF_Task.__init__(
self,
sModelName,
sModelDir,
dFeatureConfig={
'row_row': {},
'row_sepH': {},
'sepH_row': {},
'sepH_sepH': {},
'sepH': {},
'row': {}
},
dLearnerConfig={
'C':
.1 if C is None else C,
'njobs':
4 if njobs is None else njobs,
'inference_cache':
50 if inference_cache is None else inference_cache
#, 'tol' : .1
,
'tol':
.05 if tol is None else tol,
'save_every':
50 #save every 50 iterations,for warm start
,
'max_iter':
10 if max_iter is None else max_iter
},
sComment=sComment
#,cFeatureDefinition=FeatureDefinition_PageXml_StandardOnes_noText
,
cFeatureDefinition=My_FeatureDefinition_v3_txt
if self.bTxt else My_FeatureDefinition_v3)
def __init__(self,
sModelName,
sModelDir,
sComment=None,
C=None,
tol=None,
njobs=None,
max_iter=None,
inference_cache=None):
#NOTE: we might get a list in C tol max_iter inference_cache (in case of gridsearch)
DU_CRF_Task.__init__(
self,
sModelName,
sModelDir,
DU_GRAPH,
dFeatureConfig={
'nbClass': nbClass,
't_ngrams_node': (2, 4),
'b_node_lc': False,
't_ngrams_edge': (2, 4),
'b_edge_lc': False,
'n_jobs':
5 #n_jobs when fitting the internal Logit feat extractor model by grid search
},
dLearnerConfig={
'C':
.1 if C is None else C,
'njobs':
5 if njobs is None else njobs,
'inference_cache':
50 if inference_cache is None else inference_cache
#, 'tol' : .1
,
'tol':
.05 if tol is None else tol,
'save_every':
50 #save every 50 iterations,for warm start
,
'max_iter':
1000 if max_iter is None else max_iter
},
sComment=sComment,
cFeatureDefinition=FeatureDefinition_PageXml_LogitExtractorV2)
self.setNbClass(
nbClass
) #so that we check if all classes are represented in the training set
self.bsln_mdl = self.addBaseline_LogisticRegression(
) #use a LR model trained by GridSearch as baseline
def __init__(self,
sModelName,
sModelDir,
iGridVisibility=None,
iBlockVisibility=None,
sComment=None,
C=None,
tol=None,
njobs=None,
max_iter=None,
inference_cache=None):
DU_ABPTableRG.iGridVisibility = iGridVisibility
DU_ABPTableRG.iBlockVisibility = iBlockVisibility
DU_CRF_Task.__init__(
self,
sModelName,
sModelDir,
dFeatureConfig={
'row_row': {},
'row_gh': {},
'gh_row': {},
'gh_gh': {},
'gh': {},
'row': {}
},
dLearnerConfig={
'C':
.1 if C is None else C,
'njobs':
4 if njobs is None else njobs,
'inference_cache':
50 if inference_cache is None else inference_cache
#, 'tol' : .1
,
'tol':
.05 if tol is None else tol,
'save_every':
50 #save every 50 iterations,for warm start
,
'max_iter':
10 if max_iter is None else max_iter
},
sComment=sComment
#,cFeatureDefinition=FeatureDefinition_PageXml_StandardOnes_noText
,
cFeatureDefinition=My_FeatureDefinition)
self.cModelClass.setBalancedWeights(True)
def __init__(self, sModelName, sModelDir, sComment=None, C=None, tol=None, njobs=None, max_iter=None, inference_cache=None):
DU_CRF_Task.__init__(self
, sModelName, sModelDir
, dFeatureConfig = { }
, dLearnerConfig = {
'C' : .1 if C is None else C
, 'njobs' : 4 if njobs is None else njobs
, 'inference_cache' : 50 if inference_cache is None else inference_cache
#, 'tol' : .1
, 'tol' : .05 if tol is None else tol
, 'save_every' : 50 #save every 50 iterations,for warm start
, 'max_iter' : 10 if max_iter is None else max_iter
}
, sComment=sComment
#,cFeatureDefinition=FeatureDefinition_PageXml_StandardOnes_noText
,cFeatureDefinition=My_FeatureDefinition_v2
)
def __init__(self, sModelName, sModelDir, feat_select=None, sComment=None):
if feat_select == 'chi2':
DU_CRF_Task.__init__(self,
sModelName,
sModelDir,
DU_GRAPH,
dFeatureConfig=dFeatureConfig_FeatSelect,
dLearnerConfig=dLearnerConfig,
sComment=sComment)
else:
DU_CRF_Task.__init__(self,
sModelName,
sModelDir,
DU_GRAPH,
dFeatureConfig=dFeatureConfig_Baseline,
dLearnerConfig=dLearnerConfig,
sComment=sComment)
self.addBaseline_LogisticRegression() #use a LR model as baseline
def __init__(self,
sModelName,
sModelDir,
sComment=None,
C=None,
tol=None,
njobs=None,
max_iter=None,
inference_cache=None):
if sComment is None: sComment = sModelName
DU_CRF_Task.__init__(
self,
sModelName,
sModelDir,
dFeatureConfig={},
dLearnerConfig={
'C':
.1 if C is None else C,
'njobs':
2 if njobs is None else njobs,
'inference_cache':
50 if inference_cache is None else inference_cache
#, 'tol' : .1
,
'tol':
.05 if tol is None else tol,
'save_every':
50 #save every 50 iterations,for warm start
,
'max_iter':
200 if max_iter is None else max_iter
},
sComment=sComment
#,cFeatureDefinition=FeatureDefinition_PageXml_StandardOnes_noText
,
cFeatureDefinition=FeatureDefinition_PageXml_StandardOnes_noText_v3
)
#self.setNbClass(3) #so that we check if all classes are represented in the training set
if options.bBaseline:
self.bsln_mdl = self.addBaseline_LogisticRegression(
) #use a LR model trained by GridSearch as baseline
def __init__(self, sModelName, sModelDir, sComment=None, C=None, tol=None, njobs=None, max_iter=None, inference_cache=None):
if self.bHTR:
cFeatureDefinition = FeatureDefinition_PageXml_StandardOnes
dFeatureConfig = {
'n_tfidf_node':100, 't_ngrams_node':(1,2), 'b_tfidf_node_lc':False
, 'n_tfidf_edge':100, 't_ngrams_edge':(1,2), 'b_tfidf_edge_lc':False }
else:
cFeatureDefinition = FeatureDefinition_PageXml_StandardOnes_noText
dFeatureConfig = { }
#'n_tfidf_node':None, 't_ngrams_node':None, 'b_tfidf_node_lc':None
#, 'n_tfidf_edge':None, 't_ngrams_edge':None, 'b_tfidf_edge_lc':None }
DU_CRF_Task.__init__(self
, sModelName, sModelDir
, dFeatureConfig = dFeatureConfig
, dLearnerConfig = {
'C' : .1 if C is None else C
, 'njobs' : 16 if njobs is None else njobs
, 'inference_cache' : 50 if inference_cache is None else inference_cache
#, 'tol' : .1
, 'tol' : .05 if tol is None else tol
, 'save_every' : 50 #save every 50 iterations,for warm start
, 'max_iter' : 1000 if max_iter is None else max_iter
}
, sComment=sComment
, cFeatureDefinition=cFeatureDefinition
# , cFeatureDefinition=FeatureDefinition_T_PageXml_StandardOnes_noText
# , dFeatureConfig = {
# #config for the extractor of nodes of each type
# "text": None,
# "sprtr": None,
# #config for the extractor of edges of each type
# "text_text": None,
# "text_sprtr": None,
# "sprtr_text": None,
# "sprtr_sprtr": None
# }
)
traceln("- classes: ", self.getGraphClass().getLabelNameList())
self.bsln_mdl = self.addBaseline_LogisticRegression() #use a LR model trained by GridSearch as baseline
