def __first_predict(self, data):
"""
Model::__first_predict()
Purpose: Predict IOB chunks on data
@param data. A list of split sentences (1 sent = 1 line from file)
@return A list of list of IOB labels (1:1 mapping with data)
"""
if globals_cliner.verbosity > 0:
print '\textracting features (pass one)'
# Seperate into
nested_prose_data = filter(lambda line: is_prose_sentence(line), data)
nested_nonprose_data = filter(lambda line: not is_prose_sentence(line),
data)
# Parition into prose v. nonprose
nested_prose_feats = feat_obj.IOB_prose_features(nested_prose_data)
nested_nonprose_feats = feat_obj.IOB_nonprose_features(
nested_nonprose_data)
# rename because code uses it
prose = nested_prose_feats
nonprose = nested_nonprose_feats
# Predict labels for IOB prose and nonprose text
nlist = self.__generic_first_predict('nonprose', nonprose,
self._first_nonprose_vec,
self._first_nonprose_clf)
plist = self.__generic_first_predict('prose', prose,
self._first_prose_vec,
self._first_prose_clf)
# Stitch prose and nonprose data back together
# translate IOB labels into a readable format
prose_iobs = []
nonprose_iobs = []
iobs = []
num2iob = lambda l: reverse_IOB_labels[int(l)]
for sentence in data:
if sentence == []:
iobs.append([])
elif is_prose_sentence(sentence):
prose_iobs.append(plist.pop(0))
prose_iobs[-1] = map(num2iob, prose_iobs[-1])
iobs.append(prose_iobs[-1])
else:
nonprose_iobs.append(nlist.pop(0))
nonprose_iobs[-1] = map(num2iob, nonprose_iobs[-1])
iobs.append(nonprose_iobs[-1])
# list of list of IOB labels
return iobs
def __first_train(self, tokenized_sentences, Y, do_grid=False):
"""
Model::__first_train()
Purpose: Train the first pass classifiers (for IOB chunking)
@param tokenized_sentences. <list> of tokenized sentences
@param Y. <list-of-lists> of IOB labels for words
@param do_grid. <boolean> whether to perform a grid search
@return None
"""
if globals_cliner.verbosity > 0: print 'first pass'
if globals_cliner.verbosity > 0:
print '\textracting features (pass one)'
# Seperate into prose v nonprose
nested_prose_data, nested_prose_Y = zip(
*filter(lambda line_iob_tup: is_prose_sentence(line_iob_tup[0]),
zip(tokenized_sentences, Y)))
nested_nonprose_data, nested_nonprose_Y = zip(*filter(
lambda line_iob_tup: not is_prose_sentence(line_iob_tup[0]),
zip(tokenized_sentences, Y)))
#extract features
nested_prose_feats = feat_obj.IOB_prose_features(nested_prose_data)
nested_nonprose_feats = feat_obj.IOB_nonprose_features(
nested_nonprose_data)
# Flatten lists (because classifier will expect flat)
prose_Y = flatten(nested_prose_Y)
nonprose_Y = flatten(nested_nonprose_Y)
# rename because code uses it
pchunks = prose_Y
nchunks = nonprose_Y
prose = nested_prose_feats
nonprose = nested_nonprose_feats
# Train classifiers for prose and nonprose
pvec, pclf = self.__generic_first_train('prose', prose, pchunks,
do_grid)
nvec, nclf = self.__generic_first_train('nonprose', nonprose, nchunks,
do_grid)
# Save vectorizers
self._first_prose_vec = pvec
self._first_nonprose_vec = nvec
# Save classifiers
self._first_prose_clf = pclf
self._first_nonprose_clf = nclf
def __init__(self, tagger, data):
"""
Constructor.
@param data. A list of split sentences
"""
# Filter out nonprose sentences
prose = [sent for sent in data if utilities.is_prose_sentence(sent)]
# Process prose sentences with GENIA tagger
self.GENIA_features = iter(interface_genia.genia(tagger, prose))
def __init__(self, tagger, data):
"""
Constructor.
@param data. A list of split sentences
"""
# Filter out nonprose sentences
prose = [ sent for sent in data if utilities.is_prose_sentence(sent) ]
# Process prose sentences with GENIA tagger
self.GENIA_features = iter(interface_genia.genia(tagger, prose))
def first_predict(self, data):
"""
Model::first_predict()
Purpose: Predict IOB chunks on data
@param data. A list of split sentences (1 sent = 1 line from file)
@return A list of list of IOB labels (1:1 mapping with data)
"""
print '\textracting features (pass one)'
# Create object that is a wrapper for the features
feat_obj = FeatureWrapper(data)
# separate prose and nonprose data
prose = []
nonprose = []
plinenos = []
nlinenos = []
for i, line in enumerate(data):
isProse, feats = feat_obj.extract_IOB_features(line)
if isProse:
prose.append(feats)
plinenos.append(i)
else:
nonprose.append(feats)
nlinenos.append(i)
# Classify both prose & nonprose
flabels = ['prose', 'nonprose']
fsets = [prose, nonprose]
dvects = [self.first_prose_vec, self.first_nonprose_vec]
clfs = [self.first_prose_clf, self.first_nonprose_clf]
preds = []
for flabel, fset, dvect, clf in zip(flabels, fsets, dvects, clfs):
# If nothing to predict, skip actual prediction
if len(fset) == 0:
preds.append([])
continue
print '\tvectorizing features (pass one) ' + flabel
# Save list structure to reconstruct after vectorization
offsets = [len(sublist) for sublist in fset]
for i in range(1, len(offsets)):
offsets[i] += offsets[i - 1]
# Vectorize features
flattened = [item for sublist in fset for item in sublist]
X = dvect.transform(flattened)
print '\tpredicting labels (pass one) ' + flabel
# CRF requires reconstruct lists
if self.crf_enabled:
X = list(X)
X = [X[i:j] for i, j in zip([0] + offsets, offsets)]
lib = crf
else:
lib = sci
# Predict IOB labels
out = lib.predict(clf, X)
# Format labels from output
pred = [out[i:j] for i, j in zip([0] + offsets, offsets)]
preds.append(pred)
# Recover predictions
plist = preds[0]
nlist = preds[1]
# Stitch prose and nonprose data back together
# translate IOB labels into a readable format
prose_iobs = []
nonprose_iobs = []
iobs = []
trans = lambda l: reverse_IOB_labels[int(l)]
for sentence in data:
if is_prose_sentence(sentence):
prose_iobs.append(plist.pop(0))
prose_iobs[-1] = map(trans, prose_iobs[-1])
iobs.append(prose_iobs[-1])
else:
nonprose_iobs.append(nlist.pop(0))
nonprose_iobs[-1] = map(trans, nonprose_iobs[-1])
iobs.append(nonprose_iobs[-1])
# list of list of IOB labels
return iobs, prose_iobs, nonprose_iobs
def first_predict(self, data):
"""
Model::first_predict()
Purpose: Predict IOB chunks on data
@param data. A list of split sentences (1 sent = 1 line from file)
@return A list of list of IOB labels (1:1 mapping with data)
"""
print '\textracting features (pass one)'
# Create object that is a wrapper for the features
feat_obj = FeatureWrapper(data)
# separate prose and nonprose data
prose = []
nonprose = []
plinenos = []
nlinenos = []
for i,line in enumerate(data):
isProse,feats = feat_obj.extract_IOB_features(line)
if isProse:
prose.append(feats)
plinenos.append(i)
else:
nonprose.append(feats)
nlinenos.append(i)
# Classify both prose & nonprose
flabels = ['prose' , 'nonprose' ]
fsets = [prose , nonprose ]
dvects = [self.first_prose_vec, self.first_nonprose_vec]
clfs = [self.first_prose_clf, self.first_nonprose_clf]
preds = []
for flabel,fset,dvect,clf in zip(flabels, fsets, dvects, clfs):
# If nothing to predict, skip actual prediction
if len(fset) == 0:
preds.append([])
continue
print '\tvectorizing features (pass one) ' + flabel
# Save list structure to reconstruct after vectorization
offsets = [ len(sublist) for sublist in fset ]
for i in range(1, len(offsets)):
offsets[i] += offsets[i-1]
# Vectorize features
flattened = [item for sublist in fset for item in sublist]
X = dvect.transform(flattened)
print '\tpredicting labels (pass one) ' + flabel
# CRF requires reconstruct lists
if self.crf_enabled:
X = list(X)
X = [ X[i:j] for i, j in zip([0] + offsets, offsets)]
lib = crf
else:
lib = sci
# Predict IOB labels
out = lib.predict(clf, X)
# Format labels from output
pred = [out[i:j] for i, j in zip([0] + offsets, offsets)]
preds.append(pred)
# Recover predictions
plist = preds[0]
nlist = preds[1]
# Stitch prose and nonprose data back together
# translate IOB labels into a readable format
prose_iobs = []
nonprose_iobs = []
iobs = []
trans = lambda l: reverse_IOB_labels[int(l)]
for sentence in data:
if is_prose_sentence(sentence):
prose_iobs.append( plist.pop(0) )
prose_iobs[-1] = map(trans, prose_iobs[-1])
iobs.append( prose_iobs[-1] )
else:
nonprose_iobs.append( nlist.pop(0) )
nonprose_iobs[-1] = map(trans, nonprose_iobs[-1])
iobs.append( nonprose_iobs[-1] )
# list of list of IOB labels
return iobs, prose_iobs, nonprose_iobs
