示例#1
0
文件: api.py 项目: lazymike/dedupe
    def _trainClassifier(self, alpha=.1) : # pragma : no cover

        self.data_model = core.trainModel(self.training_data,
                                          self.data_model, 
                                          alpha)

        self._logLearnedWeights()
示例#2
0
文件: api.py 项目: jtbates/dedupe
    def _trainClassifier(self, alpha=.1) : # pragma : no cover

        self.data_model = core.trainModel(self.training_data,
                                          self.data_model, 
                                          alpha)

        self._logLearnedWeights()
示例#3
0
    def _trainClassifier(self, alpha=None):  # pragma : no cover

        if alpha is None:
            alpha = self._regularizer()

        self.data_model = core.trainModel(self.training_data, self.data_model,
                                          self.learner, alpha)

        self._logLearnedWeights()
示例#4
0
    def _trainClassifier(self, alpha=None) : # pragma : no cover

        if alpha is None :
            alpha = self._regularizer()

        self.data_model = core.trainModel(self.training_data,
                                          self.data_model, 
                                          self.learner,
                                          alpha)

        self._logLearnedWeights()
示例#5
0
文件: api.py 项目: nilesh-c/dedupe
    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()
示例#6
0
    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()