def configure_command_line_arguments():
# Initialize the commandline argument parser.
parser = argparse.ArgumentParser(description='Naive Bayes Classifier')
# Configure the log level parser. Verbose shows some logs, veryVerbose
# shows more
logging_group = parser.add_mutually_exclusive_group(required=False)
logging_group.add_argument("-v",
"--verbose",
help="Set the log level verbose.",
action='store_true',
required=False)
logging_group.add_argument("-vv",
"--veryVerbose",
help="Set the log level verbose.",
action='store_true',
required=False)
# NLTK supports six built in plaintext corpora. This allows the user
# to choose between those six corpora or a seventh option - the
# corpus the user provided.
# The first is a corpus taken from ABC news.
parser.add_argument('-abc',
'--abc',
help="ABC news corpus",
required=False,
action='store_true')
# The second corpus is the book of Genesis
parser.add_argument('-gen',
'--genesis', help="The book of Genesis from the Bible.",
required=False,
action='store_true')
# Third is a collection of text from project Gutenberg
parser.add_argument('-gut',
'--gutenberg', help="Text from Project Gutenberg.",
required=False,
action='store_true')
# Fourth is text from presidential inaugural addresses
parser.add_argument('-in',
'--inaugural', help="Text from inaugural addresses.",
required=False,
action='store_true')
# Fifth is text from the State of the Union
parser.add_argument('-su',
'--stateUnion', help="Text from State of the Union Addresses.",
required=False,
action='store_true')
# The final NLTK provided corpus is text from the web
parser.add_argument('-web',
'--webtext', help="Text taken from the web.",
required=False,
action='store_true')
# Tell the parser that there is an optional corpus that can be pulled in.
# The directory can contain multiple files and directories (if the user
# also passes --recursive)
fs.add_filesystem_path_args(parser,
'-c',
'--custom',
help='Directory of files to include in a custom corpus.',
required=False)
parser.add_argument('-t',
'--train',
help="Train the classifier using the NLTK tokens",
required=False,
action='store_true')
parser.add_argument('-cl',
'--classify',
help="Classify the contents of classify.txt",
required=False)
# Third is a collection of text from project Gutenberg
parser.add_argument('-s',
'--stemming', help="Stem in the classifier or trainer.",
required=False,
action='store_true')
# Third is a collection of text from project Gutenberg
parser.add_argument('-lp',
'--printProbabilities', help="Print each word probability.",
required=False,
action='store_true')
# Parse the passed commandline args and turn them into a dictionary.
args = vars(parser.parse_args())
# Configure the log level based on passed in args to be one of DEBUG, INFO, WARN, ERROR, CRITICAL
log.set_log_level_from_args(args)
return args
def configure_command_line_arguments():
# Initialize the commandline argument parser.
parser = argparse.ArgumentParser(description="Play with words using NLTK.")
# Configure the log level parser. Verbose shows some logs, veryVerbose
# shows more
logging_group = parser.add_mutually_exclusive_group(required=False)
logging_group.add_argument(
"-v", "--verbose", help="Set the log level verbose.", action="store_true", required=False
)
logging_group.add_argument(
"-vv", "--veryVerbose", help="Set the log level verbose.", action="store_true", required=False
)
# In this app we allow the user to choose from a handful of built-in
# corpora and a user provided one
corpora_group = parser.add_mutually_exclusive_group(required=True)
# NLTK supports six built in plaintext corpora. This allows the user
# to choose between those six corpora or a seventh option - the
# corpus the user provided.
# The first option is a corpus taken from ABC news.
corpora_group.add_argument("-abc", "--abc", help="ABC news corpus", required=False, action="store_true")
# The second option is the book of Genesis
corpora_group.add_argument(
"-gen", "--genesis", help="The book of Genesis from the Bible.", required=False, action="store_true"
)
# Third option is a collection of text from project Gutenberg
corpora_group.add_argument(
"-gut", "--gutenberg", help="Text from Project Gutenberg.", required=False, action="store_true"
)
# Fourth is text from presidential inaugural addresses
corpora_group.add_argument(
"-in", "--inaugural", help="Text from inaugural addresses.", required=False, action="store_true"
)
# Fifth is text from the State of the Union
corpora_group.add_argument(
"-su", "--stateUnion", help="Text from State of the Union Addresses.", required=False, action="store_true"
)
# The final NLTK provided corpus is text from the web
corpora_group.add_argument(
"-web", "--webtext", help="Text taken from the web.", required=False, action="store_true"
)
corpora_group.add_argument(
"-svl",
"--stemVsLemma",
help="Generate chart of corpus length of original, stemmed and lemmatized word",
required=False,
action="store_true",
)
# Tell the parser that there is an optional corpus that can be pulled in.
# The directory can contain multiple files and directories (if the user
# also passes --recursive)
fs.add_filesystem_path_args(
parser,
"-c",
"--custom",
help="Directory of files to include in a custom corpus.",
required=False,
group=corpora_group,
)
# Optionally, the user is able to stem or lemmatize the input.
preprocessing_group = parser.add_mutually_exclusive_group(required=False)
# Select stemming
preprocessing_group.add_argument("-s", "--stem", help="Stem the input.", required=False, action="store_true")
# Select lemmatization
preprocessing_group.add_argument("-l", "--lemma", help="Lemmatize the input.", required=False, action="store_true")
# What do you want to know? These params allow one or more calculations to be run on
# the input data. In addition, you can ask the app to stem the data before running any
# of these calculations
# Calculate the vocabulary size of the selected corpus
parser.add_argument(
"-vs", "--vocabularySize", help="Calculate the vocabulary size.", required=False, action="store_true"
)
# List all terms found in the corpus
parser.add_argument(
"-tp", "--termPresence", help="List all words that are present.", required=False, action="store_true"
)
# List the frequency of terms in the corpus
parser.add_argument(
"-tf", "--termFrequency", help="Calculate the frequency of each word.", required=False, action="store_true"
)
# Log normalize the term frequencies
parser.add_argument(
"-ln", "--logNormalize", help="Calculate the log of the frequency.", required=False, action="store_true"
)
# Determine the frequency of each frequency of terms
parser.add_argument(
"-ff",
"--frequencyFrequency",
help="Calculate the frequency of each frequency. For example, 7 words appear once, 5 appear twice, etc.",
required=False,
action="store_true",
)
# Parse the passed commandline args and turn them into a dictionary.
args = vars(parser.parse_args())
# Configure the log level based on passed in args to be one of DEBUG, INFO, WARN, ERROR, CRITICAL
log.set_log_level_from_args(args)
return args
def configure_command_line_arguments():
# Initialize the commandline argument parser.
parser = argparse.ArgumentParser(description='Play with words using NLTK.')
# Configure the log level parser. Verbose shows some logs, veryVerbose
# shows more
logging_group = parser.add_mutually_exclusive_group(required=False)
logging_group.add_argument("-v",
"--verbose",
help="Set the log level verbose.",
action='store_true',
required=False)
logging_group.add_argument("-vv",
"--veryVerbose",
help="Set the log level verbose.",
action='store_true',
required=False)
# In this app we allow the user to choose from a handful of built-in
# corpora and a user provided one
corpora_group = parser.add_mutually_exclusive_group(required=True)
# NLTK supports six built in plaintext corpora. This allows the user
# to choose between those six corpora or a seventh option - the
# corpus the user provided.
# The first option is a corpus taken from ABC news.
corpora_group.add_argument('-abc',
'--abc',
help="ABC news corpus",
required=False,
action='store_true')
# The second option is the book of Genesis
corpora_group.add_argument('-gen',
'--genesis',
help="The book of Genesis from the Bible.",
required=False,
action='store_true')
# Third option is a collection of text from project Gutenberg
corpora_group.add_argument('-gut',
'--gutenberg',
help="Text from Project Gutenberg.",
required=False,
action='store_true')
# Fourth is text from presidential inaugural addresses
corpora_group.add_argument('-in',
'--inaugural',
help="Text from inaugural addresses.",
required=False,
action='store_true')
# Fifth is text from the State of the Union
corpora_group.add_argument('-su',
'--stateUnion',
help="Text from State of the Union Addresses.",
required=False,
action='store_true')
# The final NLTK provided corpus is text from the web
corpora_group.add_argument('-web',
'--webtext',
help="Text taken from the web.",
required=False,
action='store_true')
corpora_group.add_argument(
'-svl',
'--stemVsLemma',
help=
"Generate chart of corpus length of original, stemmed and lemmatized word",
required=False,
action='store_true')
# Tell the parser that there is an optional corpus that can be pulled in.
# The directory can contain multiple files and directories (if the user
# also passes --recursive)
fs.add_filesystem_path_args(
parser,
'-c',
'--custom',
help='Directory of files to include in a custom corpus.',
required=False,
group=corpora_group)
# Optionally, the user is able to stem or lemmatize the input.
preprocessing_group = parser.add_mutually_exclusive_group(required=False)
# Select stemming
preprocessing_group.add_argument('-s',
'--stem',
help="Stem the input.",
required=False,
action='store_true')
# Select lemmatization
preprocessing_group.add_argument('-l',
'--lemma',
help="Lemmatize the input.",
required=False,
action='store_true')
# What do you want to know? These params allow one or more calculations to be run on
# the input data. In addition, you can ask the app to stem the data before running any
# of these calculations
# Calculate the vocabulary size of the selected corpus
parser.add_argument('-vs',
'--vocabularySize',
help="Calculate the vocabulary size.",
required=False,
action='store_true')
# List all terms found in the corpus
parser.add_argument('-tp',
'--termPresence',
help="List all words that are present.",
required=False,
action='store_true')
# List the frequency of terms in the corpus
parser.add_argument('-tf',
'--termFrequency',
help="Calculate the frequency of each word.",
required=False,
action='store_true')
# Log normalize the term frequencies
parser.add_argument('-ln',
'--logNormalize',
help="Calculate the log of the frequency.",
required=False,
action='store_true')
# Determine the frequency of each frequency of terms
parser.add_argument(
'-ff',
'--frequencyFrequency',
help=
"Calculate the frequency of each frequency. For example, 7 words appear once, 5 appear twice, etc.",
required=False,
action='store_true')
# Parse the passed commandline args and turn them into a dictionary.
args = vars(parser.parse_args())
# Configure the log level based on passed in args to be one of DEBUG, INFO, WARN, ERROR, CRITICAL
log.set_log_level_from_args(args)
return args
def configure_command_line_arguments():
# Initialize the commandline argument parser.
parser = argparse.ArgumentParser(description='Naive Bayes Classifier')
# Configure the log level parser. Verbose shows some logs, veryVerbose
# shows more
logging_group = parser.add_mutually_exclusive_group(required=False)
logging_group.add_argument("-v",
"--verbose",
help="Set the log level verbose.",
action='store_true',
required=False)
logging_group.add_argument("-vv",
"--veryVerbose",
help="Set the log level verbose.",
action='store_true',
required=False)
# NLTK supports six built in plaintext corpora. This allows the user
# to choose between those six corpora or a seventh option - the
# corpus the user provided.
# The first is a corpus taken from ABC news.
parser.add_argument('-abc',
'--abc',
help="ABC news corpus",
required=False,
action='store_true')
# The second corpus is the book of Genesis
parser.add_argument('-gen',
'--genesis',
help="The book of Genesis from the Bible.",
required=False,
action='store_true')
# Third is a collection of text from project Gutenberg
parser.add_argument('-gut',
'--gutenberg',
help="Text from Project Gutenberg.",
required=False,
action='store_true')
# Fourth is text from presidential inaugural addresses
parser.add_argument('-in',
'--inaugural',
help="Text from inaugural addresses.",
required=False,
action='store_true')
# Fifth is text from the State of the Union
parser.add_argument('-su',
'--stateUnion',
help="Text from State of the Union Addresses.",
required=False,
action='store_true')
# The final NLTK provided corpus is text from the web
parser.add_argument('-web',
'--webtext',
help="Text taken from the web.",
required=False,
action='store_true')
# Tell the parser that there is an optional corpus that can be pulled in.
# The directory can contain multiple files and directories (if the user
# also passes --recursive)
fs.add_filesystem_path_args(
parser,
'-c',
'--custom',
help='Directory of files to include in a custom corpus.',
required=False)
parser.add_argument('-t',
'--train',
help="Train the classifier using the NLTK tokens",
required=False,
action='store_true')
parser.add_argument('-cl',
'--classify',
help="Classify the contents of classify.txt",
required=False)
# Third is a collection of text from project Gutenberg
parser.add_argument('-s',
'--stemming',
help="Stem in the classifier or trainer.",
required=False,
action='store_true')
# Third is a collection of text from project Gutenberg
parser.add_argument('-lp',
'--printProbabilities',
help="Print each word probability.",
required=False,
action='store_true')
# Parse the passed commandline args and turn them into a dictionary.
args = vars(parser.parse_args())
# Configure the log level based on passed in args to be one of DEBUG, INFO, WARN, ERROR, CRITICAL
log.set_log_level_from_args(args)
return args
