def train(self, ppc=1, uncovered_dupes=1):
"""
Keyword arguments:
ppc -- Limits the Proportion of Pairs Covered that we allow a
predicate to cover. If a predicate puts together a fraction
of possible pairs greater than the ppc, that predicate will
be removed from consideration.
As the size of the data increases, the user will generally
want to reduce ppc.
ppc should be a value between 0.0 and 1.0
uncovered_dupes -- The number of true dupes pairs in our training
data that we can accept will not be put into any
block. If true true duplicates are never in the
same block, we will never compare them, and may
never declare them to be duplicates.
However, requiring that we cover every single
true dupe pair may mean that we have to use
blocks that put together many, many distinct pairs
that we'll have to expensively, compare as well.
"""
n_folds = min(numpy.sum(self.training_data["label"] == "match") / 3, 20)
n_folds = max(n_folds, 2)
logger.info("%d folds", n_folds)
alpha = crossvalidation.gridSearch(self.training_data, core.trainModel, self.data_model, k=n_folds)
self._trainClassifier(alpha)
self._trainBlocker(ppc, uncovered_dupes)
def _regularizer(self):
n_folds = min(
numpy.sum(self.training_data['label'] == u'match') / 3, 20)
n_folds = max(n_folds, 2)
logger.info('%d folds', n_folds)
alpha = crossvalidation.gridSearch(self.training_data,
self.learner,
self.data_model,
self.num_cores,
k=n_folds)
return alpha
def _regularizer(self) :
n_folds = min(numpy.sum(self.training_data['label']==u'match')/3,
20)
n_folds = max(n_folds,
2)
logger.info('%d folds', n_folds)
alpha = crossvalidation.gridSearch(self.training_data,
self.learner,
self.data_model,
self.num_cores,
k=n_folds)
return alpha
def train(self,
ppc=.1,
uncovered_dupes=1,
index_predicates=True): # pragma : no cover
"""Keyword arguments:
ppc -- Limits the Proportion of Pairs Covered that we allow a
predicate to cover. If a predicate puts together a fraction
of possible pairs greater than the ppc, that predicate will
be removed from consideration.
As the size of the data increases, the user will generally
want to reduce ppc.
ppc should be a value between 0.0 and 1.0
uncovered_dupes -- The number of true dupes pairs in our training
data that we can accept will not be put into any
block. If true true duplicates are never in the
same block, we will never compare them, and may
never declare them to be duplicates.
However, requiring that we cover every single
true dupe pair may mean that we have to use
blocks that put together many, many distinct pairs
that we'll have to expensively, compare as well.
index_predicates -- Should dedupe consider predicates that
rely upon indexing the data. Index predicates can
be slower and take susbstantial memory.
Defaults to True.
"""
n_folds = min(
numpy.sum(self.training_data['label'] == u'match') / 3, 20)
n_folds = max(n_folds, 2)
logger.info('%d folds', n_folds)
alpha = crossvalidation.gridSearch(self.training_data,
core.trainModel,
self.data_model,
self.num_cores,
k=n_folds)
self._trainClassifier(alpha)
self._trainBlocker(ppc, uncovered_dupes, index_predicates)
def train(self, data_sample, training_source=None):
"""
Learn field weights from file of labeled examples or round of
interactive labeling
Keyword arguments:
data_sample -- a sample of record pairs
training_source -- either a path to a file of labeled examples or
a labeling function
In the sample of record_pairs, each element is a tuple of two
records. Each record is, in turn, a tuple of the record's key and
a record dictionary.
In in the record dictionary the keys are the names of the
record field and values are the record values.
For example, a data_sample with only one pair of records,
[
(
(854, {'city': 'san francisco',
'address': '300 de haro st.',
'name': "sally's cafe & bakery",
'cuisine': 'american'}),
(855, {'city': 'san francisco',
'address': '1328 18th st.',
'name': 'san francisco bbq',
'cuisine': 'thai'})
)
]
The labeling function will be used to do active learning. The
function will be supplied a list of examples that the learner
is the most 'curious' about, that is examples where we are most
uncertain about how they should be labeled. The labeling function
will label these, and based upon what we learn from these
examples, the labeling function will be supplied with new
examples that the learner is now most curious about. This will
continue until the labeling function sends a message that we
it is done labeling.
The labeling function must be a function that takes two
arguments. The first argument is a sequence of pairs of
records. The second argument is the data model.
The labeling function must return two outputs. The function
must return a dictionary of labeled pairs and a finished flag.
The dictionary of labeled pairs must have two keys, 1 and 0,
corresponding to record pairs that are duplicates or
nonduplicates respectively. The values of the dictionary must
be a sequence of records pairs, like the sequence that was
passed in.
The 'finished' flag should take the value False for active
learning to continue, and the value True to stop active learning.
i.e.
labelFunction(record_pairs, data_model) :
...
return (labeled_pairs, finished)
For a working example, see consoleLabel in training
Labeled example files are typically generated by saving the
examples labeled in a previous session. If you need details
for this file see the method writeTraining.
"""
self.data_sample = data_sample
if training_source.__class__ is not str and not isinstance(training_source, types.FunctionType):
raise ValueError
if training_source.__class__ is str:
logging.info("reading training from file")
if self.training_data is None:
self._initializeTraining(training_source)
(self.training_pairs, self.training_data) = self._readTraining(training_source, self.training_data)
elif isinstance(training_source, types.FunctionType):
if self.training_data is None:
self._initializeTraining()
(self.training_data, self.training_pairs, self.data_model) = training.activeLearning(
self.data_sample, self.data_model, training_source, self.training_data, self.training_pairs
)
n_folds = min(max(2, numpy.sum(self.training_data["label"]) / 3), 20)
print n_folds
alpha = crossvalidation.gridSearch(self.training_data, core.trainModel, self.data_model, k=n_folds)
self.data_model = core.trainModel(self.training_data, self.data_model, alpha)
self._logLearnedWeights()
def train(self, data_sample, training_source=None):
"""
Learn field weights from file of labeled examples or round of
interactive labeling
Keyword arguments:
data_sample -- a sample of record pairs
training_source -- either a path to a file of labeled examples or
a labeling function
In the sample of record_pairs, each element is a tuple of two
records. Each record is, in turn, a tuple of the record's key and
a record dictionary.
In in the record dictionary the keys are the names of the
record field and values are the record values.
For example, a data_sample with only one pair of records,
[
(
(854, {'city': 'san francisco',
'address': '300 de haro st.',
'name': "sally's cafe & bakery",
'cuisine': 'american'}),
(855, {'city': 'san francisco',
'address': '1328 18th st.',
'name': 'san francisco bbq',
'cuisine': 'thai'})
)
]
The labeling function will be used to do active learning. The
function will be supplied a list of examples that the learner
is the most 'curious' about, that is examples where we are most
uncertain about how they should be labeled. The labeling function
will label these, and based upon what we learn from these
examples, the labeling function will be supplied with new
examples that the learner is now most curious about. This will
continue until the labeling function sends a message that we
it is done labeling.
The labeling function must be a function that takes two
arguments. The first argument is a sequence of pairs of
records. The second argument is the data model.
The labeling function must return two outputs. The function
must return a dictionary of labeled pairs and a finished flag.
The dictionary of labeled pairs must have two keys, 1 and 0,
corresponding to record pairs that are duplicates or
nonduplicates respectively. The values of the dictionary must
be a sequence of records pairs, like the sequence that was
passed in.
The 'finished' flag should take the value False for active
learning to continue, and the value True to stop active learning.
i.e.
labelFunction(record_pairs, data_model) :
...
return (labeled_pairs, finished)
For a working example, see consoleLabel in training
Labeled example files are typically generated by saving the
examples labeled in a previous session. If you need details
for this file see the method writeTraining.
"""
self.data_sample = data_sample
if training_source.__class__ is not str and not isinstance(
training_source, types.FunctionType):
raise ValueError
if training_source.__class__ is str:
logging.info('reading training from file')
if self.training_data is None:
self._initializeTraining(training_source)
(self.training_pairs,
self.training_data) = self._readTraining(training_source,
self.training_data)
elif isinstance(training_source, types.FunctionType):
if self.training_data is None:
self._initializeTraining()
(self.training_data, self.training_pairs,
self.data_model) = training.activeLearning(
self.data_sample, self.data_model, training_source,
self.training_data, self.training_pairs)
n_folds = min(numpy.sum(self.training_data['label']) / 3, 20)
n_folds = min(max(2, numpy.sum(self.training_data['label']) / 3), 20)
logging.info('%d folds', n_folds)
alpha = crossvalidation.gridSearch(self.training_data,
core.trainModel,
self.data_model,
k=n_folds)
self.data_model = core.trainModel(self.training_data, self.data_model,
alpha)
self._logLearnedWeights()
