def tokenize_extra(ds, store_path):
"""
Additional feature extraction for features that are not provided by the dataset
implementation.
@param ds dataset to read from
@param store_path path of store to write to
"""
class_space = 'ebmcat'
#print >>sys.stderr, "=== tokenize_extra for {0} ===".format(store_path)
with closing(Store(store_path, 'a', recursive_close=False)) as store:
proxy = DataProxy(ds, store=store)
proxy.tokenstream_name = 'treetaggerlemmapos'
proxy.tokenize(ext.bigram)
proxy.tokenstream_name = 'treetaggerpos'
proxy.tokenize(ext.trigram)
# Hackish workaround for store being unexpectedly closed
with closing(Store(store_path, 'a', recursive_close=False)) as store:
proxy = DataProxy(ds, store=store)
proxy.tokenstream_name = 'treetaggerpos'
proxy.tokenize(ext.bigram)
def tokenize(ds, features, store_path):
"""
Compute feature values and save them in a hydrat store.
@param ds dataset to read from
@param features names of features to read
@param store_path path of store to write to
"""
class_space = 'ebmcat'
#print >>sys.stderr, "=== opening store at {0} ===".format(store_path)
with closing(Store(store_path, 'a', recursive_close=False)) as store:
#print >>sys.stderr, "=== inducing features ({0}) ===".format(features)
# Induce all the features for the new test data
proxy = DataProxy(ds, store=store)
proxy.inducer.process(
proxy.dataset,
fms=features,
sqs=[
'abstract',
],
)
class_space = 'ebmcat'
try:
features = features.feature_sets[args.feats]
except KeyError:
parser.error("unknown feature group: {0}".format(args.feats))
l = repeat.RepeatLearner(
liblinear.liblinearL(svm_type=0, output_probability=True))
store = Store(args.feat_store, 'r') # TODO: Do we want this read-only?
for feature in features:
spaces[feature] = store.get_Space(feature)
spaces['ebmcat'] = store.get_Space('ebmcat')
proxy = DataProxy(ALTA2012Full(), store=store)
proxy.class_space = class_space
L0_cl = []
L1_fv = []
L1_gs = None
for feat in features:
proxy.feature_spaces = feat
proxy.split_name = 'crossvalidation'
with Timer() as L0_timer:
L0_cl.append(l(proxy.featuremap.raw, proxy.classmap.raw))
print >> sys.stderr, "== training L0 for {0} took {1:.2f}s ==".format(
feat, L0_timer.elapsed)
with Timer() as L1_cv_timer:
'core': core,
'dev': ('headingprev', 'headingvec', 'positionrel'),
}
datasets = [
ALTA2012Full(),
]
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument('output', help='write output to PATH', metavar='PATH')
args = parser.parse_args()
store = Store(args.output, 'a')
for ds in datasets:
proxy = DataProxy(ds, store=store)
proxy.inducer.process(proxy.dataset,
fms=feats_all,
cms=['ebmcat',],
sqs=['abstract',],
sps=['crossvalidation'],
)
proxy.tokenstream_name = 'treetaggerlemmapos'
proxy.tokenize(ext.bigram)
proxy.tokenstream_name = 'treetaggerpos'
proxy.tokenize(ext.bigram)
proxy.tokenize(ext.trigram)
