def addTrainingData(labeled_pairs, data_model, training_data=[]): fields = data_model['fields'] field_dtype = training_data.dtype[1] distances = numpy.zeros(1, dtype=field_dtype) num_training_pairs = len(labeled_pairs[0]) + len(labeled_pairs[1]) new_training_data = numpy.zeros(num_training_pairs, dtype=training_data.dtype) i = 0 for (label, examples) in labeled_pairs.items(): for pair in examples: c_distances = core.calculateDistance(pair[0], pair[1], fields, distances) example = (label, c_distances) new_training_data[i] = example i += 1 training_data = numpy.append(training_data, new_training_data) return training_data
def addTrainingData(labeled_pairs, training_data, data_model) : fields = data_model['fields'] field_dtype = [('names', 'a10', (len(fields)),), ('values', 'f4', (len(fields)),) ] distances = numpy.zeros(1, dtype=field_dtype) for label, examples in labeled_pairs.items() : for pair in examples : c_distances = core.calculateDistance(pair[0], pair[1], fields, distances) c_distances = dict(zip(fields.keys(), c_distances[0]['values'])) training_data.append((label, c_distances)) return training_data
def trainingDistances(training_pairs, data_model): fields = data_model['fields'] field_dtype = [('names', 'a10', len(fields)), ('values', 'f4', len(fields))] distances = numpy.zeros(1, dtype=field_dtype) training_data = [] for (label, examples) in training_pairs.items(): for (i, pair) in enumerate(examples): c_distances = core.calculateDistance(pair[0], pair[1], fields, distances) c_distances = dict(zip(fields.keys(), c_distances[0]['values'])) training_data.append((label, c_distances)) return training_data