Beispiel #1
0
def run_classifier_labels(hdfs_input_pos, hdfs_input_neg, hdfs_output, classifier_name, classifier_extra, local_labels, classifier, **kw):
    labels = {}
    try:
        labels = file_parse.load(local_labels)
    except IOError:
        pass
    hdfs_output_pos = hdfs_output + '/pos'
    hdfs_output_neg = hdfs_output + '/neg'
    hadoopy.launch_frozen(hdfs_input_pos, hdfs_output_pos, 'collect_keys.py')
    hadoopy.launch_frozen(hdfs_input_neg, hdfs_output_neg, 'collect_keys.py')
    pos_keys = sum((x[1] for x in hadoopy.readtb(hdfs_output_pos)), [])
    neg_keys = sum((x[1] for x in hadoopy.readtb(hdfs_output_neg)), [])
    labels[classifier_name] = {'labels': {'1': pos_keys, '-1': neg_keys},
                               'classifier': classifier,
                               'classifier_extra': classifier_extra}
    file_parse.dump(labels, local_labels)
Beispiel #2
0
 def __init__(self):
     self._labels = file_parse.load(os.environ['LOCAL_LABELS_FN'])
Beispiel #3
0
 def __init__(self):
     labels = file_parse.load(os.environ['LOCAL_LABELS_FN'])
     self._hash_class_labels = self._invert_labels(labels)
 def __init__(self):
     self._classifiers = [(x, classifiers.loads(y))
                          for x, y in file_parse.load(os.environ['CLASSIFIERS_FN'])]