def makeArgParser(configfilename="config.json"):
language, \
corpus, \
datafolder, \
configtext = load_config_for_command_line_help(configfilename)
parser = argparse.ArgumentParser(
description="Extracting phone/letter ngrams from a wordlist; also other"
"phonology-related stuff\n\n{}"
.format(configtext),
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument("--config", help="configuration filename",
type=str, default=configfilename)
parser.add_argument("--language", help="Language name",
type=str, default=None)
parser.add_argument("--corpus", help="Corpus file to use",
type=str, default=None)
parser.add_argument("--datafolder", help="path of the data folder",
type=str, default=None)
parser.add_argument("--maxwordtokens", help="maximum number of word tokens;"
" if this is zero, then the program counts "
"all word tokens in the corpus",
type=int, default=0)
return parser
def makeArgParser(configfilename="config.json"):
language, \
corpus, \
datafolder, \
configtext = load_config_for_command_line_help(configfilename)
parser = argparse.ArgumentParser(
description="Word segmentation program.\n\n{}"
.format(configtext),
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument("--config", help="configuration filename",
type=str, default=configfilename)
parser.add_argument("--language", help="Language name",
type=str, default=None)
parser.add_argument("--corpus", help="Corpus file to use",
type=str, default=None)
parser.add_argument("--datafolder", help="path of the data folder",
type=str, default=None)
parser.add_argument("--cycles", help="number of cycles",
type=int, default=200)
parser.add_argument("--candidates", help="number of candidates"
"per iteration",
type=int, default=25)
parser.add_argument("--verbose", help="verbose output",
type=bool, default=False)
return parser
def makeArgParser(configfilename="config.json"):
language, corpus, datafolder, configtext = load_config_for_command_line_help(configfilename)
parser = argparse.ArgumentParser(
description="This program computes word neighbors.\n\n{}".format(configtext),
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
)
parser.add_argument("--config", help="configuration filename", type=str, default=configfilename)
parser.add_argument("--language", help="Language name", type=str, default=None)
parser.add_argument("--corpus", help="Corpus file to use", type=str, default=None)
parser.add_argument("--datafolder", help="path of the data folder", type=str, default=None)
parser.add_argument("--maxwordtypes", help="Number of word types to handle", type=int, default=1000)
parser.add_argument("--nNeighbors", help="Number of neighbors", type=int, default=9)
parser.add_argument("--nEigenvectors", help="Number of eigenvectors", type=int, default=11)
parser.add_argument(
"--mincontexts",
help="Minimum number of times that "
"a word occurs in a context; "
"also minimum number of neighbors for a word that share "
"a context (for WordToSharedContextsOfNeighbors)",
type=int,
default=3,
)
parser.add_argument("--wordtocontexts", help="create the WordToContexts dict?", type=bool, default=False)
parser.add_argument("--contexttowords", help="create the ContextToWords dict?", type=bool, default=False)
parser.add_argument("--usesigtransforms", help="use signature transforms?", type=bool, default=True)
return parser
def makeArgParser(configfilename="config.json"):
language, \
corpus, \
datafolder, \
configtext = load_config_for_command_line_help(configfilename)
parser = argparse.ArgumentParser(
description="This program creates word neighbor graphs.\n\n{}".format(
configtext),
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument("--config",
help="configuration filename",
type=str,
default=configfilename)
parser.add_argument("--language",
help="Language name",
type=str,
default=None)
parser.add_argument("--corpus",
help="Corpus file to use",
type=str,
default=None)
parser.add_argument("--datafolder",
help="path of the data folder",
type=str,
default=None)
return parser
def makeArgParser(configfilename="config.json"):
language, \
corpus, \
datafolder, \
configtext = load_config_for_command_line_help(configfilename)
parser = argparse.ArgumentParser(
description="This program computes morphological signatures.\n\n{}".
format(configtext),
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument("--config",
help="configuration filename",
type=str,
default=configfilename)
parser.add_argument("--language",
help="Language name",
type=str,
default=None)
parser.add_argument("--corpus",
help="Corpus file to use",
type=str,
default=None)
parser.add_argument("--datafolder",
help="path of the data folder",
type=str,
default=None)
parser.add_argument("--minstem",
help="Minimum stem length; "
"usually from 2 to 5, where a smaller number means "
"you can find shorter stems although the program "
"may run a lot slower",
type=int,
default=4)
parser.add_argument("--maxaffix",
help="Maximum affix length; "
"usually from 1 to 5, where a larger number means "
"you can find longer affixes",
type=int,
default=3)
parser.add_argument("--minsig",
help="Minimum number of signature use; "
"a small number like 5 is pretty much the smallest "
"to use in order to filter spurious signatures; may "
"try larger numbers like 10 or 20 and so forth",
type=int,
default=5)
parser.add_argument("--maxwordtokens",
help="maximum number of word tokens;"
" if this is zero, then the program counts "
"all word tokens in the corpus",
type=int,
default=0)
return parser
def makeArgParser(configfilename="config.json"):
language, \
corpus, \
datafolder, \
configtext = load_config_for_command_line_help(configfilename)
parser = argparse.ArgumentParser(
description="The program computes tries given corpus data.\n\n{}".
format(configtext),
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument("--config",
help="configuration filename",
type=str,
default=configfilename)
parser.add_argument("--language",
help="Language name",
type=str,
default=None)
parser.add_argument("--corpus",
help="Corpus file to use",
type=str,
default=None)
parser.add_argument("--datafolder",
help="relative path of the data folder",
type=str,
default=None)
parser.add_argument("--minstem",
help="Minimum stem length; "
"usually from 2 to 5, where a smaller number means "
"you can find shorter stems although the program "
"may run a lot slower",
type=int,
default=4)
parser.add_argument("--minaffix",
help="Minimum affix length",
type=int,
default=1)
parser.add_argument("--minsize",
help="Minimum size of "
"successors/predecessors for output",
type=int,
default=3)
parser.add_argument("--maxwordtokens",
help="maximum number of word tokens;"
" if this is zero, then the program counts "
"all word tokens in the corpus",
type=int,
default=0)
return parser
def makeArgParser(configfilename="config.json"):
language, \
corpus, \
datafolder, \
configtext = load_config_for_command_line_help(configfilename)
parser = argparse.ArgumentParser(
description="This program creates word neighbor graphs.\n\n{}"
.format(configtext),
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument("--config", help="configuration filename",
type=str, default=configfilename)
parser.add_argument("--language", help="Language name",
type=str, default=None)
parser.add_argument("--corpus", help="Corpus file to use",
type=str, default=None)
parser.add_argument("--datafolder", help="path of the data folder",
type=str, default=None)
return parser
def makeArgParser(configfilename="config.json"):
language, \
corpus, \
datafolder, \
configtext = load_config_for_command_line_help(configfilename)
parser = argparse.ArgumentParser(
description="Extracting phone/letter ngrams from a wordlist; also other"
"phonology-related stuff\n\n{}".format(configtext),
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument("--config",
help="configuration filename",
type=str,
default=configfilename)
parser.add_argument("--language",
help="Language name",
type=str,
default=None)
parser.add_argument("--corpus",
help="Corpus file to use",
type=str,
default=None)
parser.add_argument("--datafolder",
help="path of the data folder",
type=str,
default=None)
parser.add_argument("--maxwordtokens",
help="maximum number of word tokens;"
" if this is zero, then the program counts "
"all word tokens in the corpus",
type=int,
default=0)
return parser
def makeArgParser(configfilename="config.json"):
language, \
corpus, \
datafolder, \
configtext = load_config_for_command_line_help(configfilename)
parser = argparse.ArgumentParser(
description="The program computes tries given corpus data.\n\n{}"
.format(configtext),
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument("--config", help="configuration filename",
type=str, default=configfilename)
parser.add_argument("--language", help="Language name",
type=str, default=None)
parser.add_argument("--corpus", help="Corpus file to use",
type=str, default=None)
parser.add_argument("--datafolder", help="relative path of the data folder",
type=str, default=None)
parser.add_argument("--minstem", help="Minimum stem length; "
"usually from 2 to 5, where a smaller number means "
"you can find shorter stems although the program "
"may run a lot slower",
type=int, default=4)
parser.add_argument("--minaffix", help="Minimum affix length",
type=int, default=1)
parser.add_argument("--minsize", help="Minimum size of "
"successors/predecessors for output",
type=int, default=3)
parser.add_argument("--maxwordtokens", help="maximum number of word tokens;"
" if this is zero, then the program counts "
"all word tokens in the corpus",
type=int, default=0)
return parser
def makeArgParser(configfilename="config.json"):
language, \
corpus, \
datafolder, \
configtext = load_config_for_command_line_help(configfilename)
parser = argparse.ArgumentParser(
description="This program computes word neighbors.\n\n{}".format(
configtext),
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument("--config",
help="configuration filename",
type=str,
default=configfilename)
parser.add_argument("--language",
help="Language name",
type=str,
default=None)
parser.add_argument("--corpus",
help="Corpus file to use",
type=str,
default=None)
parser.add_argument("--datafolder",
help="path of the data folder",
type=str,
default=None)
parser.add_argument("--maxwordtypes",
help="Number of word types to handle",
type=int,
default=1000)
parser.add_argument("--nNeighbors",
help="Number of neighbors",
type=int,
default=9)
parser.add_argument("--nEigenvectors",
help="Number of eigenvectors",
type=int,
default=11)
parser.add_argument(
"--mincontexts",
help="Minimum number of times that "
"a word occurs in a context; "
"also minimum number of neighbors for a word that share "
"a context (for WordToSharedContextsOfNeighbors)",
type=int,
default=3)
parser.add_argument("--wordtocontexts",
help="create the WordToContexts dict?",
type=bool,
default=False)
parser.add_argument("--contexttowords",
help="create the ContextToWords dict?",
type=bool,
default=False)
parser.add_argument("--usesigtransforms",
help="use signature transforms?",
type=bool,
default=True)
return parser
