def main(argv=None):
'''this is called if run from command line'''
parser = argparse.ArgumentParser()
parser.add_argument('-i','--input_dir', required=True)
parser.add_argument('--file_format', default='sequence', choices=('text', 'sequence'))
parser.add_argument('-o','--output_dir', required=True)
parser.add_argument('--output_file_format', default='sequence', choices=('text', 'sequence'))
parser.add_argument('--config', default=None)
parser.add_argument('-l','--limit', required=False, default=None, type=int)
parser.add_argument('-e','--emptylines',required=False,default=True)
args=parser.parse_args()
# Default configuration to empty config
# (avoid mutable container as default)
args.config = args.config or {}
sparkName = "testTokenizer"
sc = SparkContext(appName=sparkName)
# remove positional args, everything else passed verbatim
kwargs = dict_minus(as_dict(args), "input_dir", "output_dir", "config")
print 'Got Options : ',kwargs
testTokenizer(sc, args.input_dir, args.output_dir, args.config, **kwargs)
def main(argv=None):
'''this is called if run from command line'''
parser = argparse.ArgumentParser()
parser.add_argument('-i', '--input_dir', required=True)
parser.add_argument('--file_format',
default='sequence',
choices=('text', 'sequence'))
parser.add_argument('-o', '--output_dir', required=True)
parser.add_argument('--output_file_format',
default='sequence',
choices=('text', 'sequence'))
parser.add_argument('--config', default=None)
parser.add_argument('-l',
'--limit',
required=False,
default=None,
type=int)
parser.add_argument('-e', '--emptylines', required=False, default=True)
args = parser.parse_args()
# Default configuration to empty config
# (avoid mutable container as default)
args.config = args.config or {}
sparkName = "testTokenizer"
sc = SparkContext(appName=sparkName)
# remove positional args, everything else passed verbatim
kwargs = dict_minus(as_dict(args), "input_dir", "output_dir", "config")
print 'Got Options : ', kwargs
testTokenizer(sc, args.input_dir, args.output_dir, args.config, **kwargs)
dest="threshold", default=0.0, help="similarity threshold")
parser.add_option("-e", "--base", dest="base", type="string",
help="base file", default="")
parser.add_option("-o", "--outputformat", dest="outputformat", type="string",
help="output file format: text/sequence", default="text")
parser.add_option("-y", "--outputtype", dest="outputtype", type="string",
help="output type: csv/json", default="json")
parser.add_option("-k", "--topk", dest="topk", type="int",
help="top n matches", default=3)
parser.add_option("-x", "--numPartitions", dest="numPartitions", type="int",
help="number of partitions", default=10)
parser.add_option("-z", "--candidatesName", dest="candidates_name", type="string",
help="name for json element for matching candidates", default="candidates")
(c_options, args) = parser.parse_args()
print "Got options:", c_options
inputFilename = args[0]
outputFilename = args[1]
print "Save to:", outputFilename
kwargs = as_dict(c_options)
clusterer = Clusterer(**kwargs)
fileUtil = FileUtil(sc)
rdd = fileUtil.load_file(inputFilename,file_format='text')
cluster_rdd = clusterer.compute_clusters(rdd)
fileUtil.save_file(cluster_rdd,outputFilename,file_format='text')
def __init__(self, config_filename, **p_options):
self.options = as_dict(p_options)
self.config = FileUtil.get_json_config(config_filename)
print('In tokenizer')
def __init__(self, config_filename, **p_options):
self.options = as_dict(p_options)
self.config = FileUtil.get_json_config(config_filename)
print('In tokenizer')