def project_tags(tagstoproject, tagtargets):
targetstring = ','.join(tagtargets)
projectstring = ','.join(tagstoproject)
print('First we create a model of ' + targetstring)
sizecap = 400
modelname = targetstring + 'byitself'
paths = make_paths(modelname)
sourcefolder, extension, metadatapath, outputpath1, vocabpath = paths
exclusions = make_exclusions(0, 2000, sizecap, tagstoproject)
# Note that we exclude tagstoproject from the negative contrast set, so the
# contrast sets for the two models will be identical.
positive_tags = tagtargets
negative_tags = ['random', 'chirandom']
testconditions = set()
datetype = "firstpub"
numfeatures = 10000
regularization = .000075
classifyconditions = (positive_tags, negative_tags, datetype, numfeatures, regularization, testconditions)
rawaccuracy, allvolumes, coefficientuples = logisticpredict.create_model(paths, exclusions, classifyconditions)
print('If we divide the dataset with a horizontal line at 0.5, accuracy is: ', str(rawaccuracy))
print()
print('Then we create a model of ' + projectstring + ' and use it to predict ' + targetstring)
modelname = projectstring + 'predicts' + targetstring
paths = make_paths(modelname)
sourcefolder, extension, metadatapath, outputpath2, vocabpath = paths
exclusions = make_exclusions(0, 2000, sizecap, 'nonegatives')
positive_tags = list(tagtargets)
positive_tags.extend(tagstoproject)
testconditions = set(tagtargets)
# That's the line that actually excludes tagtarget from training.
classifyconditions = (positive_tags, negative_tags, datetype, numfeatures, regularization, testconditions)
rawaccuracy, allvolumes, coefficientuples = logisticpredict.create_model(paths, exclusions, classifyconditions)
print('If we divide the second dataset at 0.5, accuracy is: ', str(rawaccuracy))
print()
# Now we compare the predictions made by these two models, comparing only
# the volumes that are in both models but excluded from the training process
# in the second model.
comparemodels.compare_untrained(outputpath1, outputpath2)
def project_gothic_beyond_date(dividedate):
print('First we create a model of gothic fiction only after ' + str(dividedate))
sizecap = 300
modelname = 'gothicjustpost' + str(dividedate)
paths = make_paths(modelname)
sourcefolder, extension, metadatapath, outputpath1, vocabpath = paths
exclusions = make_exclusions(dividedate, 2000, sizecap, 'nonegatives')
positive_tags = ['lochorror', 'pbgothic', 'locghost', 'stangothic', 'chihorror']
negative_tags = ['random', 'chirandom']
testconditions = set()
datetype = "firstpub"
numfeatures = 10000
regularization = .000075
classifyconditions = (positive_tags, negative_tags, datetype, numfeatures, regularization, testconditions)
rawaccuracy, allvolumes, coefficientuples = logisticpredict.create_model(paths, exclusions, classifyconditions)
print('If we divide the dataset with a horizontal line at 0.5, accuracy is: ', str(rawaccuracy))
print()
print('Then we create a model of gothic fiction blindly predicting after ' + str(dividedate))
modelname = 'gothicpredictpost' + str(dividedate)
paths = make_paths(modelname)
sourcefolder, extension, metadatapath, outputpath2, vocabpath = paths
exclusions = make_exclusions(0, 2001, sizecap, 'nonegatives')
testconditions = {'1700', str(dividedate)}
classifyconditions = (positive_tags, negative_tags, datetype, numfeatures, regularization, testconditions)
rawaccuracy, allvolumes, coefficientuples = logisticpredict.create_model(paths, exclusions, classifyconditions)
print('If we divide the second dataset at 0.5, accuracy is: ', str(rawaccuracy))
print()
# Now we compare the predictions made by these two models, comparing only
# the volumes that are in both models but excluded from the training process
# in the second model.
comparemodels.compare_untrained(outputpath1, outputpath2)
def compare(dividedate):
print('First we create a model of gender only after ' + str(dividedate))
sizecap = 500
modelname = 'post' + str(dividedate)
sourcefolder = '/Volumes/TARDIS/work/characterdata/charpredict/'
extension = '.tsv'
metadatapath = '/Users/tunder/Dropbox/character/meta/predictmeta.csv'
vocabpath = '/Users/tunder/Dropbox/character/meta/predictALLvocab.csv'
outputpath1 = '/Users/tunder/Dropbox/character/results/' + modelname + str(
datetime.date.today()) + '.csv'
paths = (sourcefolder, extension, metadatapath, outputpath1, vocabpath)
## EXCLUSIONS.
excludeif = dict()
excludeifnot = dict()
excludeabove = dict()
excludebelow = dict()
excludebelow['firstpub'] = 1900
excludeabove['firstpub'] = 1950
exclusions = (excludeif, excludeifnot, excludebelow, excludeabove, sizecap)
positive_tags = ['f']
negative_tags = ['m']
testconditions = set()
datetype = "firstpub"
numfeatures = 2000
regularization = .00009
classifyconditions = (positive_tags, negative_tags, datetype, numfeatures,
regularization, testconditions)
rawaccuracy, allvolumes, coefficientuples = logisticpredict.create_model(
paths, exclusions, classifyconditions)
print(
'If we divide the dataset with a horizontal line at 0.5, accuracy is: ',
str(rawaccuracy))
print()
print(
'Then we create a model of detective fiction blindly predicting after '
+ str(dividedate))
modelname = 'predictpost' + str(dividedate)
outputpath2 = '/Users/tunder/Dropbox/character/results/' + modelname + str(
datetime.date.today()) + '.csv'
paths = (sourcefolder, extension, metadatapath, outputpath2, vocabpath)
excludebelow['firstpub'] = 1780
excludeabove['firstpub'] = 2000
sizecap = 1000
exclusions = (excludeif, excludeifnot, excludebelow, excludeabove, sizecap)
testconditions = {'1700', 1880}
classifyconditions = (positive_tags, negative_tags, datetype, numfeatures,
regularization, testconditions)
rawaccuracy, allvolumes, coefficientuples = logisticpredict.create_model(
paths, exclusions, classifyconditions)
print('If we divide the second dataset at 0.5, accuracy is: ',
str(rawaccuracy))
print()
# Now we compare the predictions made by these two models, comparing only
# the volumes that are in both models but excluded from the training process
# in the second model.
comparemodels.compare_untrained(outputpath1, outputpath2)
def compare(dividedate):
print('First we create a model of gender only after ' + str(dividedate))
sizecap = 500
modelname = 'post' + str(dividedate)
sourcefolder = '/Volumes/TARDIS/work/characterdata/charpredict/'
extension = '.tsv'
metadatapath = '/Users/tunder/Dropbox/character/meta/predictmeta.csv'
vocabpath = '/Users/tunder/Dropbox/character/meta/predictALLvocab.csv'
outputpath1 = '/Users/tunder/Dropbox/character/results/' + modelname + str(datetime.date.today()) + '.csv'
paths = (sourcefolder, extension, metadatapath, outputpath1, vocabpath)
## EXCLUSIONS.
excludeif = dict()
excludeifnot = dict()
excludeabove = dict()
excludebelow = dict()
excludebelow['firstpub'] = 1900
excludeabove['firstpub'] = 1950
exclusions = (excludeif, excludeifnot, excludebelow, excludeabove, sizecap)
positive_tags = ['f']
negative_tags = ['m']
testconditions = set()
datetype = "firstpub"
numfeatures = 2000
regularization = .00009
classifyconditions = (positive_tags, negative_tags, datetype, numfeatures, regularization, testconditions)
rawaccuracy, allvolumes, coefficientuples = logisticpredict.create_model(paths, exclusions, classifyconditions)
print('If we divide the dataset with a horizontal line at 0.5, accuracy is: ', str(rawaccuracy))
print()
print('Then we create a model of detective fiction blindly predicting after ' + str(dividedate))
modelname = 'predictpost' + str(dividedate)
outputpath2 = '/Users/tunder/Dropbox/character/results/' + modelname + str(datetime.date.today()) + '.csv'
paths = (sourcefolder, extension, metadatapath, outputpath2, vocabpath)
excludebelow['firstpub'] = 1780
excludeabove['firstpub'] = 2000
sizecap = 1000
exclusions = (excludeif, excludeifnot, excludebelow, excludeabove, sizecap)
testconditions = {'1700', 1880}
classifyconditions = (positive_tags, negative_tags, datetype, numfeatures, regularization, testconditions)
rawaccuracy, allvolumes, coefficientuples = logisticpredict.create_model(paths, exclusions, classifyconditions)
print('If we divide the second dataset at 0.5, accuracy is: ', str(rawaccuracy))
print()
# Now we compare the predictions made by these two models, comparing only
# the volumes that are in both models but excluded from the training process
# in the second model.
comparemodels.compare_untrained(outputpath1, outputpath2)
