def _readTraining(self, file_name, training_pairs):
with open(file_name, "r") as f:
training_pairs_raw = json.load(f)
training_pairs = {0: [], 1: []}
for (label, examples) in training_pairs_raw.iteritems():
for pair in examples:
training_pairs[int(label)].append((core.frozendict(pair[0]), core.frozendict(pair[1])))
training_data = training.addTrainingData(training_pairs, self.data_model, self.training_data)
return training_pairs, training_data
def train(self, data_d, training_source=None, key_groups=[]) :
"""
Learn field weights and blocking predicate from file of
labeled examples or round of interactive labeling
Keyword arguments:
data_d -- a dictionary of records
training_source -- either a path to a file of labeled examples or
a labeling function
In the dictionary of records, the keys are unique identifiers
for each record, the values are a dictionary where the keys
are the names of the record field and values are the record
values.
For Example,
{
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_sample
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.
"""
if (training_source.__class__ is not str
and not isinstance(training_source, types.FunctionType)):
raise ValueError
# data_d = core.sampleDict(data_d, 700) #we should consider changing this
print "data_d length: ", len(data_d)
self.data_d = dict([(key, core.frozendict(value)) for key, value in data_d.iteritems()])
if training_source.__class__ is str:
print 'reading training from file'
if not hasattr(self, 'training_data'):
self.initializeTraining(training_source)
self.training_pairs, self.training_data = self._readTraining(training_source,
self.training_data)
elif isinstance(training_source, types.FunctionType) :
if not hasattr(self, 'training_data'):
self.initializeTraining()
(self.training_data,
self.training_pairs,
self.data_model) = training_sample.activeLearning(self.data_d,
self.data_model,
training_source,
self.training_data,
self.training_pairs,
key_groups)
self.alpha = crossvalidation.gridSearch(self.training_data,
core.trainModel,
self.data_model,
k=20)
self.data_model = core.trainModel(self.training_data,
self.data_model,
self.alpha)
self._printLearnedWeights()
