class FeaturesPerceptronRanker(BasePerceptronRanker):
"""Base class for global ranker for whole trees, based on features."""
def __init__(self, cfg):
super(FeaturesPerceptronRanker, self).__init__(cfg)
if not cfg:
cfg = {}
self.feats = ['bias: bias']
self.vectorizer = None
self.normalizer = None
self.binarize = cfg.get('binarize', False)
# initialize feature functions
if 'features' in cfg:
self.feats.extend(cfg['features'])
self.feats = Features(self.feats, cfg.get('intermediate_features', []))
def _extract_feats(self, tree, da):
feats = self.vectorizer.transform(
[self.feats.get_features(tree, {'da': da})])
if self.normalizer:
feats = self.normalizer.transform(feats)
return feats[0]
def _init_training(self, das_file, ttree_file, data_portion):
super(FeaturesPerceptronRanker,
self)._init_training(das_file, ttree_file, data_portion)
# precompute training data features
X = []
for da, tree in zip(self.train_das, self.train_trees):
X.append(self.feats.get_features(tree, {'da': da}))
if self.prune_feats > 1:
self._prune_features(X)
# vectorize and binarize or normalize (+train vectorizer/normalizer)
if self.binarize:
self.vectorizer = DictVectorizer(sparse=False,
binarize_numeric=True)
self.train_feats = self.vectorizer.fit_transform(X)
else:
self.vectorizer = DictVectorizer(sparse=False)
self.normalizer = StandardScaler(copy=False)
self.train_feats = self.normalizer.fit_transform(
self.vectorizer.fit_transform(X))
log_info('Features matrix shape: %s' % str(self.train_feats.shape))
def _prune_features(self, X):
"""Prune features – remove all entries from X that involve features not having a
specified minimum occurrence count.
"""
counts = defaultdict(int)
for inst in X:
for key in inst.iterkeys():
counts[key] += 1
for inst in X:
for key in inst.keys():
if counts[key] < self.prune_feats:
del inst[key]
class FeaturesPerceptronRanker(BasePerceptronRanker):
"""Base class for global ranker for whole trees, based on features."""
def __init__(self, cfg):
super(FeaturesPerceptronRanker, self).__init__(cfg)
if not cfg:
cfg = {}
self.feats = ['bias: bias']
self.vectorizer = None
self.normalizer = None
self.binarize = cfg.get('binarize', False)
# initialize feature functions
if 'features' in cfg:
self.feats.extend(cfg['features'])
self.feats = Features(self.feats, cfg.get('intermediate_features', []))
def _extract_feats(self, tree, da):
feats = self.vectorizer.transform([self.feats.get_features(tree, {'da': da})])
if self.normalizer:
feats = self.normalizer.transform(feats)
return feats[0]
def _init_training(self, das_file, ttree_file, data_portion):
super(FeaturesPerceptronRanker, self)._init_training(das_file, ttree_file, data_portion)
# precompute training data features
X = []
for da, tree in zip(self.train_das, self.train_trees):
X.append(self.feats.get_features(tree, {'da': da}))
if self.prune_feats > 1:
self._prune_features(X)
# vectorize and binarize or normalize (+train vectorizer/normalizer)
if self.binarize:
self.vectorizer = DictVectorizer(sparse=False, binarize_numeric=True)
self.train_feats = self.vectorizer.fit_transform(X)
else:
self.vectorizer = DictVectorizer(sparse=False)
self.normalizer = StandardScaler(copy=False)
self.train_feats = self.normalizer.fit_transform(self.vectorizer.fit_transform(X))
log_info('Features matrix shape: %s' % str(self.train_feats.shape))
def _prune_features(self, X):
"""Prune features – remove all entries from X that involve features not having a
specified minimum occurrence count.
"""
counts = defaultdict(int)
for inst in X:
for key in inst.iterkeys():
counts[key] += 1
for inst in X:
for key in inst.keys():
if counts[key] < self.prune_feats:
del inst[key]
def _init_training(self, das_file, ttree_file, data_portion):
super(FeaturesPerceptronRanker, self)._init_training(das_file, ttree_file, data_portion)
# precompute training data features
X = []
for da, tree in zip(self.train_das, self.train_trees):
X.append(self.feats.get_features(tree, {'da': da}))
if self.prune_feats > 1:
self._prune_features(X)
# vectorize and binarize or normalize (+train vectorizer/normalizer)
if self.binarize:
self.vectorizer = DictVectorizer(sparse=False, binarize_numeric=True)
self.train_feats = self.vectorizer.fit_transform(X)
else:
self.vectorizer = DictVectorizer(sparse=False)
self.normalizer = StandardScaler(copy=False)
self.train_feats = self.normalizer.fit_transform(self.vectorizer.fit_transform(X))
log_info('Features matrix shape: %s' % str(self.train_feats.shape))
def _init_training(self, das_file, ttree_file, data_portion):
super(FeaturesPerceptronRanker,
self)._init_training(das_file, ttree_file, data_portion)
# precompute training data features
X = []
for da, tree in zip(self.train_das, self.train_trees):
X.append(self.feats.get_features(tree, {'da': da}))
if self.prune_feats > 1:
self._prune_features(X)
# vectorize and binarize or normalize (+train vectorizer/normalizer)
if self.binarize:
self.vectorizer = DictVectorizer(sparse=False,
binarize_numeric=True)
self.train_feats = self.vectorizer.fit_transform(X)
else:
self.vectorizer = DictVectorizer(sparse=False)
self.normalizer = StandardScaler(copy=False)
self.train_feats = self.normalizer.fit_transform(
self.vectorizer.fit_transform(X))
log_info('Features matrix shape: %s' % str(self.train_feats.shape))
