def test_BeagleEnvironment():
from inphosemantics import load_picklez, dump_matrix
root = 'test-data/iep/plato/'
corpus_filename =\
root + 'corpus/iep-plato.pickle.bz2'
matrix_filename =\
root + 'models/iep-plato-beagleenviroment-sentences.npy'
print 'Loading corpus\n'\
' ', corpus_filename
c = load_picklez(corpus_filename)
print 'Training model'
m = BeagleEnvironment()
m.train(c, n_columns=256)
print 'Row norms', np.sum(m.matrix**2, axis=1)**(1./2)
print 'Dumping matrix to\n'\
' ', matrix_filename
m.dump_matrix(matrix_filename)
return m
def test_TfModel():
from inphosemantics import load_picklez, dump_matrix
corpus_filename =\
'test-data/iep/selected/corpus/iep-plato.pickle.bz2'
matrix_filename =\
'test-data/iep/selected/models/iep-plato-tf-word-article.npy'
document_type = 'articles'
corpus = load_picklez(corpus_filename)
model = TfModel()
model.train(corpus, 'articles')
model.dump_matrix(matrix_filename)
model.load_matrix(matrix_filename)
return corpus, model, document_type
def test_BeagleComposite_2():
from inphosemantics import load_picklez, dump_matrix
root = 'test-data/iep/plato/'
corpus_filename =\
root + 'corpus/iep-plato.pickle.bz2'
env_filename =\
root + 'models/iep-plato-beagleenviroment-sentences.npy'
matrix_filename =\
root + 'models/iep-plato-beaglecomposite-sentences.npy'
print 'Loading corpus\n'\
' ', corpus_filename
c = load_picklez(corpus_filename)
print 'Loading environment model\n'\
' ', env_filename
e = BeagleEnvironment()
e.load_matrix(env_filename)
print e.matrix
print 'Training model'
m = BeagleComposite()
m.train(c, env_matrix=e.matrix)
print m.matrix
print 'Dumping matrix to\n'\
' ', matrix_filename
m.dump_matrix(matrix_filename)
return m
def __init__(self,
corpus=None,
corpus_filename=None,
model=None,
model_type=None,
matrix=None,
matrix_filename=None,
token_type=None,
stoplist=None):
if corpus:
if corpus_filename:
raise Exception("Both a corpus and a "
"corpus filename were given.")
self.corpus = corpus
elif corpus_filename:
print 'Loading corpus from\n'\
' ', corpus_filename
self.corpus = load_picklez(corpus_filename)
else:
raise Exception("Neither a corpus nor a "
"corpus filename were given.")
if model:
if matrix:
raise Exception("Both a model and a "
"matrix were given.")
elif matrix_filename:
raise Exception("Both a model and a "
"matrix filename were given.")
elif model_type:
raise Exception("Both a model and a "
"model type were given.")
else:
self.model = model
elif matrix:
if matrix_filename:
raise Exception("Both a matrix and a "
"matrix filename were given.")
else:
self.model = model_type(matrix)
elif matrix_filename:
self.model = model_type()
print 'Loading matrix from\n'\
' ', matrix_filename
self.model.load_matrix(matrix_filename)
else:
raise Exception("Neither a model, matrix nor "
"matrix filename were given.")
self.token_type = token_type
if stoplist:
self.stoplist = self.corpus.encode_tokens_str(stoplist)
print 'Applying stoplist to matrix'
self.model.filter_rows(self.stoplist)
