def verifysettings(self):
super().verifysettings()
if 'class' not in self.settings:
self.settings['class'] = 'nonworderror'
if 'runonclass' not in self.settings:
self.settings['runonclass'] = 'runonerror'
if 'runon' not in self.settings:
self.settings['runon'] = True
if 'maxdistance' not in self.settings:
self.settings['maxdistance'] = 2
if 'maxdistance_short' not in self.settings:
self.settings['maxdistance_short'] = 1
if 'maxlength' not in self.settings:
self.settings['maxlength'] = 25 #longer words will be ignored
if 'minlength' not in self.settings:
self.settings['minlength'] = 5 #shorter word will be ignored
if 'shortlength' not in self.settings:
self.settings['shortlength'] = self.settings['minlength']
if 'maxnrclosest' not in self.settings:
self.settings['maxnrclosest'] = 5
if 'suffixes' not in self.settings:
self.settings['suffixes'] = []
if 'prefixes' not in self.settings:
self.settings['prefixes'] = []
self.cache = getcache(self.settings, 1000) #2nd arg is default cache size
def verifysettings(self):
if 'class' not in self.settings:
self.settings['class'] = 'confusion'
super().verifysettings()
if 'algorithm' not in self.settings:
self.settings['algorithm'] = 1
if 'leftcontext' not in self.settings:
self.settings['leftcontext'] = 3
if 'rightcontext' not in self.settings:
self.settings['rightcontext'] = 3
if 'threshold' not in self.settings:
self.threshold = 0.9
else:
self.threshold = self.settings['threshold']
if 'freqthreshold' not in self.settings:
self.freqthreshold = 2
else:
self.freqthreshold = self.settings['freqthreshold']
if 'minlength' not in self.settings:
self.minlength = 5
else:
self.minlength = self.settings['minlength']
if 'probfactor' not in self.settings:
self.probfactor = 10
else:
self.probfactor = self.settings['probfactor']
if 'maxdistance' not in self.settings:
self.settings['maxdistance'] = 2
if 'debug' in self.settings:
self.debug = bool(self.settings['debug'])
else:
self.debug = False
self.hapaxer = gethapaxer(self, self.settings)
self.cache = getcache(self.settings, 1000)
try:
modelfile = self.models[0]
if not modelfile.endswith(".ibase"):
raise Exception("First model must be a TIMBL instance base model, which must have the extension '.ibase', got " + modelfile + " instead")
if len(self.models) > 1:
lexiconfile = self.models[1]
if not lexiconfile.endswith("colibri.patternmodel"):
raise Exception("Second model must be a Colibri pattern model, which must have the extensions '.colibri.patternmodel', got " + modelfile + " instead")
except:
raise Exception("Expected one or two models, the first a TIMBL instance base, and the optional second a colibri patternmodel, got " + str(len(self.models)) )
def verifysettings(self):
if 'class' not in self.settings:
self.settings['class'] = 'confusion'
super().verifysettings()
if 'algorithm' not in self.settings:
self.settings['algorithm'] = 1
if 'leftcontext' not in self.settings:
self.settings['leftcontext'] = 3
if 'rightcontext' not in self.settings:
self.settings['rightcontext'] = 3
if 'threshold' not in self.settings:
self.threshold = 0.9
else:
self.threshold = self.settings['threshold']
if 'freqthreshold' not in self.settings:
self.freqthreshold = 2
else:
self.freqthreshold = self.settings['freqthreshold']
if 'minlength' not in self.settings:
self.minlength = 5
else:
self.minlength = self.settings['minlength']
if 'probfactor' not in self.settings:
self.probfactor = 10
else:
self.probfactor = self.settings['probfactor']
if 'maxdistance' not in self.settings:
self.settings['maxdistance'] = 2
if 'debug' in self.settings:
self.debug = bool(self.settings['debug'])
else:
self.debug = False
self.hapaxer = gethapaxer(self, self.settings)
self.cache = getcache(self.settings, 1000)
try:
modelfile = self.models[0]
if not modelfile.endswith(".ibase"):
raise Exception("First model must be a TIMBL instance base model, which must have the extension '.ibase', got " + modelfile + " instead")
if len(self.models) > 1:
lexiconfile = self.models[1]
if not lexiconfile.endswith("colibri.patternmodel"):
raise Exception("Second model must be a Colibri pattern model, which must have the extensions '.colibri.patternmodel', got " + modelfile + " instead")
except:
raise Exception("Expected one or two models, the first a TIMBL instance base, and the optional second a colibri patternmodel, got " + str(len(self.models)) )
def verifysettings(self):
super().verifysettings()
if 'class' not in self.settings:
self.settings['class'] = 'nonworderror'
if 'runonclass' not in self.settings:
self.settings['runonclass'] = 'runonerror'
if 'runon' not in self.settings:
self.settings['runon'] = True
if 'maxdistance' not in self.settings:
self.settings['maxdistance'] = 2
if 'maxdistance_short' not in self.settings:
self.settings['maxdistance_short'] = 1
if 'maxlength' not in self.settings:
self.settings['maxlength'] = 25 #longer words will be ignored
if 'minlength' not in self.settings:
self.settings['minlength'] = 5 #shorter word will be ignored
if 'shortlength' not in self.settings:
self.settings['shortlength'] = self.settings['minlength']
if 'maxnrclosest' not in self.settings:
self.settings['maxnrclosest'] = 5
if 'suffixes' not in self.settings:
self.settings['suffixes'] = []
if 'prefixes' not in self.settings:
self.settings['prefixes'] = []
self.cache = getcache(self.settings,
1000) #2nd arg is default cache size
def verifysettings(self):
if 'class' not in self.settings:
self.settings['class'] = 'nonworderror'
super().verifysettings()
if 'delimiter' not in self.settings:
self.settings['delimiter'] = "\t"
elif self.settings['delimiter'].lower() == 'space':
self.settings['delimiter'] = " "
elif self.settings['delimiter'].lower() == 'tab':
self.settings['delimiter'] = "\t"
elif self.settings['delimiter'].lower() == 'comma':
self.settings['delimiter'] = ","
if 'reversedformat' not in self.settings: #reverse format has (word,freq) pairs rather than (freq,word) pairs
self.settings['reversedformat'] = False
if 'ordered ' not in self.settings:
self.settings[
'ordered'] = True #Model file is ordered in descending frequency
if 'freqthreshold' not in self.settings:
self.settings['freqthreshold'] = 100
if 'maxdistance' not in self.settings:
self.settings['maxdistance'] = 2
if 'maxdistance_short' not in self.settings:
self.settings['maxdistance_short'] = 1
if 'maxlength' not in self.settings:
self.settings['maxlength'] = 25 #longer words will be ignored
if 'minlength' not in self.settings:
self.settings['minlength'] = 5 #shorter word will be ignored
if 'shortlength' not in self.settings:
self.settings['shortlength'] = self.settings['minlength']
if 'minfreqthreshold' not in self.settings:
self.settings['minfreqthreshold'] = 10000
if 'freqfactor' not in self.settings:
self.settings['freqfactor'] = 10000
if 'maxnrclosest' not in self.settings:
self.settings['maxnrclosest'] = 5
self.cache = getcache(self.settings,
1000) #2nd arg is default cache size
if 'suffixes' not in self.settings:
self.settings['suffixes'] = []
if 'prefixes' not in self.settings:
self.settings['prefixes'] = []
def verifysettings(self):
if 'class' not in self.settings:
self.settings['class'] = 'nonworderror'
super().verifysettings()
if 'delimiter' not in self.settings:
self.settings['delimiter'] = "\t"
elif self.settings['delimiter'].lower() == 'space':
self.settings['delimiter'] = " "
elif self.settings['delimiter'].lower() == 'tab':
self.settings['delimiter'] = "\t"
elif self.settings['delimiter'].lower() == 'comma':
self.settings['delimiter'] = ","
if 'reversedformat' not in self.settings: #reverse format has (word,freq) pairs rather than (freq,word) pairs
self.settings['reversedformat'] = False
if 'ordered ' not in self.settings:
self.settings['ordered'] = True #Model file is ordered in descending frequency
if 'freqthreshold' not in self.settings:
self.settings['freqthreshold'] = 100
if 'maxdistance' not in self.settings:
self.settings['maxdistance'] = 2
if 'maxdistance_short' not in self.settings:
self.settings['maxdistance_short'] = 1
if 'maxlength' not in self.settings:
self.settings['maxlength'] = 25 #longer words will be ignored
if 'minlength' not in self.settings:
self.settings['minlength'] = 5 #shorter word will be ignored
if 'shortlength' not in self.settings:
self.settings['shortlength'] = self.settings['minlength']
if 'minfreqthreshold' not in self.settings:
self.settings['minfreqthreshold'] = 10000
if 'freqfactor' not in self.settings:
self.settings['freqfactor'] = 10000
if 'maxnrclosest' not in self.settings:
self.settings['maxnrclosest'] = 5
self.cache = getcache(self.settings, 1000) #2nd arg is default cache size
if 'suffixes' not in self.settings:
self.settings['suffixes'] = []
if 'prefixes' not in self.settings:
self.settings['prefixes'] = []
def verifysettings(self):
if 'class' not in self.settings:
self.settings['class'] = 'contexterror'
super().verifysettings()
if 'algorithm' not in self.settings:
self.settings['algorithm'] = 1
if 'leftcontext' not in self.settings:
self.settings['leftcontext'] = 3
if 'rightcontext' not in self.settings:
self.settings['rightcontext'] = 3
if 'threshold' not in self.settings:
self.threshold = self.settings['threshold']
else:
self.threshold = 0.9
if 'maxdistance' not in self.settings:
self.settings['maxdistance'] = 2
if 'debug' in self.settings:
self.debug = bool(self.settings['debug'])
else:
self.debug = False
self.hapaxer = gethapaxer(self.settings)
self.cache = getcache(self.settings, 1000)
try:
modelfile = self.models[0]
if not modelfile.endswith(".ibase"):
raise Exception("TIMBL models must have the extension ibase, got " + modelfile + " instead")
except:
raise Exception("Expected one model, got 0 or more")
def verifysettings(self):
if 'class' not in self.settings:
self.settings['class'] = 'contexterror'
super().verifysettings()
if 'leftcontext' not in self.settings:
self.settings['leftcontext'] = 3
if 'rightcontext' not in self.settings:
self.settings['rightcontext'] = 3
self.maxcontext = max(self.settings['leftcontext'], self.settings['rightcontext'])
if 'freqthreshold' not in self.settings:
self.threshold = 25
if 'threshold' not in self.settings:
self.threshold = self.settings['threshold']
else:
self.threshold = 0.9
if 'maxdistance' not in self.settings:
self.settings['maxdistance'] = 2
if 'debug' in self.settings:
self.debug = bool(self.settings['debug'])
else:
self.debug = False
self.hapaxer = gethapaxer(self.settings)
self.cache = getcache(self.settings, 1000)
try:
modelfile = self.models[0]
except:
raise Exception("Expected one model, got 0 or more")
def verifysettings(self):
if 'class' not in self.settings:
self.settings['class'] = 'confusion'
super().verifysettings()
if 'leftcontext' not in self.settings:
self.settings['leftcontext'] = 3
if 'rightcontext' not in self.settings:
self.settings['rightcontext'] = 3
self.maxcontext = max(self.settings['leftcontext'], self.settings['rightcontext'])
if 'freqthreshold' not in self.settings:
self.freqthreshold = 25
if 'threshold' not in self.settings:
self.threshold = self.settings['threshold']
else:
self.threshold = 0.9
if 'maxdistance' not in self.settings:
self.settings['maxdistance'] = 2
if 'debug' in self.settings:
self.debug = bool(self.settings['debug'])
else:
self.debug = False
self.hapaxer = gethapaxer(self, self.settings)
self.cache = getcache(self.settings, 1000)
try:
self.models[0]
except:
raise Exception("Expected one model, got 0 or more")
