def main(args):
if args.cluster:
cluster(args.cluster, args.config_file)
return
config = topicexplorer.config.read(args.config_file)
corpus_filename = config.get("main", "corpus_file")
model_path = config.get("main", "path")
if config.getboolean("main", "sentences"):
from vsm.extensions.ldasentences import CorpusSent as Corpus
else:
from vsm.corpus import Corpus
if args.k is None:
try:
if config.get("main", "topics"):
default = ' '.join(map(str, eval(config.get("main", "topics"))))
if args.quiet:
args.k = [int(n) for n in default.split()]
else:
raise NoOptionError('main', 'topics')
except NoOptionError:
default = ' '.join(map(str, range(20, 100, 20)))
while args.k is None:
ks = input("Number of Topics [Default '{0}']: ".format(default))
try:
if ks:
args.k = [int(n) for n in ks.split()]
elif not ks.strip():
args.k = [int(n) for n in default.split()]
if args.k:
print("\nTIP: number of topics can be specified with argument '-k N N N ...':")
print(" topicexplorer train %s -k %s\n" %\
(args.config_file, ' '.join(map(str, args.k))))
except ValueError:
print("Enter valid integers, separated by spaces!")
if args.processes < 0:
import multiprocessing
args.processes = multiprocessing.cpu_count() + args.processes
print("Loading corpus... ")
corpus = Corpus.load(corpus_filename)
try:
model_pattern = config.get("main", "model_pattern")
except NoOptionError:
model_pattern = None
if (model_pattern is not None and not args.rebuild and (args.quiet or args.cont or
bool_prompt("""Existing topic models found. You can continue training or start a new model.
Do you want to continue training your existing models? """, default=True))):
from vsm.model.lda import LDA
m = LDA.load(model_pattern.format(args.k[0]),
multiprocessing=args.processes > 1,
n_proc=args.processes)
if args.iter is None and not args.quiet: # pragma: no cover
args.iter = int_prompt("Total number of training iterations:",
default=int(m.iteration * 1.5), min=m.iteration)
print("\nTIP: number of training iterations can be specified with argument '--iter N':")
print(" topicexplorer train --iter %d %s\n" % (args.iter, args.config_file))
elif args.iter is None and args.quiet: # pragma: no cover
args.iter = int(m.iteration * 1.5)
del m
# if the set changes, build some new models and continue some old ones
config_topics = eval(config.get("main", "topics"))
if args.k != config_topics:
new_models = set(args.k) - set(config_topics)
continuing_models = set(args.k) & set(config_topics)
build_models(corpus, corpus_filename, model_path,
config.get("main", "context_type"),
new_models, n_iterations=args.iter,
n_proc=args.processes, seed=args.seed,
dry_run=args.dry_run)
model_pattern = continue_training(model_pattern, continuing_models,
args.iter, n_proc=args.processes,
dry_run=args.dry_run)
else:
model_pattern = continue_training(model_pattern, args.k, args.iter,
n_proc=args.processes,
dry_run=args.dry_run)
else:
# build a new model
if args.iter is None and not args.quiet: # pragma: no cover
args.iter = int_prompt("Number of training iterations:", default=200)
print("\nTIP: number of training iterations can be specified with argument '--iter N':")
print(" topicexplorer train --iter %d %s\n" % (args.iter, args.config_file))
elif args.iter is None and args.quiet: # pragma: no cover
args.iter = 200
# TODO: if only one context_type, make it just the one context type.
ctxs = corpus.context_types
if len(ctxs) == 1:
args.context_type = ctxs[0]
else:
ctxs = sorted(ctxs, key=lambda ctx: len(corpus.view_contexts(ctx)))
if args.context_type not in ctxs:
while args.context_type not in ctxs:
contexts = ctxs[:]
contexts[0] = contexts[0].upper()
contexts = '/'.join(contexts)
args.context_type = input("Select a context type [%s] : " % contexts)
if args.context_type.strip() == '':
args.context_type = ctxs[0]
if args.context_type == ctxs[0].upper():
args.context_type = ctxs[0]
print("\nTIP: context type can be specified with argument '--context-type TYPE':")
print(" topicexplorer train --context-type %s %s\n" % (args.context_type, args.config_file))
print("\nTIP: This configuration can be automated as:")
print(" topicexplorer train %s --iter %d --context-type %s -k %s\n" %\
(args.config_file, args.iter, args.context_type,
' '.join(map(str, args.k))))
model_pattern = build_models(corpus, corpus_filename, model_path,
args.context_type, args.k,
n_iterations=args.iter,
n_proc=args.processes, seed=args.seed,
dry_run=args.dry_run)
config.set("main", "model_pattern", model_pattern)
if args.context_type:
# test for presence, since continuing doesn't require context_type
config.set("main", "context_type", args.context_type)
args.k.sort()
config.set("main", "topics", str(args.k))
if not args.dry_run:
if config.has_option("main", "cluster"):
cluster_path = config.get("main", "cluster", fallback=None)
config.remove_option("main", "cluster")
try:
if cluster_path:
os.remove(cluster_path)
except (OSError, IOError):
# fail silently on IOError
pass
with open(args.config_file, "w") as configfh:
config.write(configfh)
def main(args):
config = ConfigParser({"htrc": False, "sentences": "False"})
config.read(args.config_file)
if config.getboolean("main", "sentences"):
from vsm.extensions.ldasentences import CorpusSent as Corpus
else:
from vsm.corpus import Corpus
if args.lang is None:
args.lang = []
args.corpus_path = config.get("main", "corpus_file")
c = Corpus.load(args.corpus_path)
# check for htrc metadata
if args.htrc or config.get("main", "htrc"):
htrc_langs = get_htrc_langs(args)
if htrc_langs:
args.lang.extend(new_langs)
# auto-guess a language
"""
new_langs = [lang for lang in detect_langs(c) if lang in langs and lang not in args.lang]
if new_langs:
args.lang.extend(new_langs)
"""
# add default locale if no other languages are specified
# do not add if in quiet mode -- make everything explicit
if not args.lang and not args.quiet:
import locale
locale = locale.getdefaultlocale()[0].split('_')[0].lower()
if locale in langs.keys():
args.lang.append(locale)
# check for any new candidates
args.lang = [lang for lang in args.lang if stop_language(c, langs[lang])]
if args.lang and not args.quiet:
args.lang = lang_prompt(args.lang)
stoplist = set()
# Apply stop words
print(" ")
for lang in args.lang:
print("Applying", langs[lang], "stopwords")
candidates = stop_language(c, langs[lang])
if len(candidates):
stoplist.update(candidates)
# Apply custom stopwords file
if args.stopword_file:
with open(args.stopword_file, encoding='utf8') as swf:
#candidates = [unidecode(word.strip()) for word in swf]
candidates = [word.strip() for word in swf]
if len(candidates):
print("Applying custom stopword file to remove {} word{}.".
format(len(candidates),
's' if len(candidates) > 1 else ''))
stoplist.update(candidates)
if args.min_word_len:
candidates = get_small_words(c, args.min_word_len)
if len(candidates):
print("Filtering {} small word{} with less than {} characters.".
format(len(candidates), 's' if len(candidates) > 1 else '',
args.min_word_len))
stoplist.update(candidates)
if not args.special_chars:
candidates = get_special_chars(c)
if len(candidates):
print("Filtering {} word{} with special characters.".format(
len(candidates), 's' if len(candidates) > 1 else ''))
stoplist.update(candidates)
if args.high_filter is None and not args.quiet:
args.high_filter, candidates = get_high_filter(args, c, words=stoplist)
if len(candidates):
print("Filtering {} high frequency word{}.".format(
len(candidates), 's' if len(candidates) > 1 else ''))
stoplist.update(candidates)
elif args.high_filter > 0:
candidates = get_candidate_words(c, args.high_filter, sort=False)
if len(candidates):
print("Filtering {} high frequency word{}.".format(
len(candidates), 's' if len(candidates) > 1 else ''))
stoplist.update(candidates)
if args.low_filter is None and not args.quiet:
args.low_filter, candidates = get_low_filter(args, c, words=stoplist)
if len(candidates):
print("Filtering {} low frequency word{}.".format(
len(candidates), 's' if len(candidates) > 1 else ''))
stoplist.update(candidates)
elif args.low_filter > 0:
candidates = get_candidate_words(c, -1 * args.low_filter, sort=False)
if len(candidates):
print("Filtering {} low frequency words.".format(len(candidates)))
stoplist.update(candidates)
if not stoplist:
print("No stopwords applied.\n\n")
sys.exit(0)
else:
print("\n\nApplying {} stopword{}".format(
len(stoplist), 's' if len(stoplist) > 1 else ''))
c.in_place_stoplist(stoplist)
print("\n")
def name_corpus(dirname, languages, lowfreq=None, highfreq=None):
items, counts = get_items_counts(c.corpus)
corpus_name = [dirname]
if args.lang:
corpus_name.append('nltk')
corpus_name.append(''.join(args.lang))
if lowfreq > 0:
corpus_name.append('freq%s' % lowfreq)
else:
corpus_name.append('freq%s' % min(counts))
if highfreq > 0:
corpus_name.append('N%s' % highfreq)
else:
corpus_name.append('freq%s' % max(counts))
corpus_name = '-'.join(corpus_name)
corpus_name += '.npz'
return corpus_name
dirname = os.path.basename(args.corpus_path).split('-nltk-')[0].replace(
'.npz', '')
corpus_name = name_corpus(dirname, ['en'], args.low_filter,
args.high_filter)
model_path = os.path.dirname(args.corpus_path)
args.corpus_path = os.path.join(model_path, corpus_name)
c.save(args.corpus_path)
config.set("main", "corpus_file", args.corpus_path)
config.remove_option("main", "model_pattern")
with open(args.config_file, 'w') as configfh:
config.write(configfh)
import os.path
from collections import defaultdict
# load in the configuration file
from ConfigParser import ConfigParser as ConfigParser
config_file = r"$config_file"
config = ConfigParser({
'topic_range': None,
'topics': None,
'sentences' : 'false'})
config.read(config_file)
# load the corpus
if config.getboolean('main','sentences'):
from vsm.extensions.ldasentences import CorpusSent
c = CorpusSent.load(config.get('main', 'corpus_file'))
else:
c = Corpus.load(config.get('main', 'corpus_file'))
context_type = config.get('main', 'context_type')
ctx_metadata = c.view_metadata(context_type)
all_ids = ctx_metadata[doc_label_name(context_type)]
# create topic model patterns
pattern = config.get('main', 'model_pattern')
if config.get('main', 'topic_range'):
topic_range = map(int, config.get('main', 'topic_range').split(','))
topic_range = range(*topic_range)
if config.get('main', 'topics'):
topic_range = eval(config.get('main', 'topics'))
# load the topic models
def main(args):
config = topicexplorer.config.read(args.config_file)
if config.getboolean("main", "sentences"):
from vsm.extensions.ldasentences import CorpusSent as Corpus
else:
from vsm.corpus import Corpus
if args.lang is None:
args.lang = []
args.corpus_path = config.get("main", "corpus_file")
c = Corpus.load(args.corpus_path)
if c.original_length != len(c.corpus):
print("Corpus has already been prepared. Proceed to training or")
print("re-init the corpus to apply a different set of stopwords.")
print("\nTIP: Train the LDA models with:")
print(" topicexplorer train", args.config_file)
sys.exit(1)
# auto-guess a language
"""
new_langs = [lang for lang in detect_langs(c) if lang in langs and lang not in args.lang]
if new_langs:
args.lang.extend(new_langs)
"""
# add default locale if no other languages are specified
# do not add if in quiet mode -- make everything explicit
if not args.lang and not args.quiet:
import locale
locale = locale.getdefaultlocale()[0].split('_')[0].lower()
if locale in langs.keys():
args.lang.append(locale)
# check for any new candidates
args.lang = [lang for lang in args.lang if stop_language(c, langs[lang])]
if args.lang and not args.quiet:
args.lang = lang_prompt(args.lang)
stoplist = set()
# Apply stop words
print(" ")
for lang in args.lang:
print("Applying", langs[lang], "stopwords")
candidates = stop_language(c, langs[lang])
if len(candidates):
stoplist.update(candidates)
# Apply custom stopwords file
if args.stopword_file:
with open(args.stopword_file, encoding='utf8') as swf:
#candidates = [unidecode(word.strip()) for word in swf]
candidates = [word.strip() for word in swf]
if len(candidates):
print("Applying custom stopword file to remove {} word{}.".
format(len(candidates),
's' if len(candidates) > 1 else ''))
stoplist.update(candidates)
if args.min_word_len:
candidates = get_small_words(c, args.min_word_len)
if len(candidates):
print("Filtering {} small word{} with less than {} characters.".
format(len(candidates), 's' if len(candidates) > 1 else '',
args.min_word_len))
stoplist.update(candidates)
# cache item counts
items, counts = get_corpus_counts(c)
if args.high_filter is None and args.high_percent is None and not args.quiet:
args.high_filter, candidates = get_high_filter(c,
words=stoplist,
items=items,
counts=counts)
if len(candidates):
print("Filtering {} high frequency word{}.".format(
len(candidates), 's' if len(candidates) > 1 else ''))
stoplist.update(candidates)
elif args.high_filter is None and args.high_percent is None and args.quiet:
pass
elif args.high_filter:
candidates = get_candidate_words(c,
args.high_filter,
sort=False,
items=items,
counts=counts)
if len(candidates):
print("Filtering {} high frequency word{}.".format(
len(candidates), 's' if len(candidates) > 1 else ''))
stoplist.update(candidates)
elif args.high_percent:
args.high_filter = get_closest_bin(c,
1 - (args.high_percent / 100.),
counts=counts)
print(args.high_filter)
candidates = get_candidate_words(c,
args.high_filter,
sort=False,
items=items,
counts=counts)
if len(candidates):
print("Filtering {} high frequency word{}.".format(
len(candidates), 's' if len(candidates) > 1 else ''))
stoplist.update(candidates)
if args.low_filter is None and args.low_percent is None and not args.quiet:
args.low_filter, candidates = get_low_filter(c,
words=stoplist,
items=items,
counts=counts)
if len(candidates):
print("Filtering {} low frequency word{}.".format(
len(candidates), 's' if len(candidates) > 1 else ''))
stoplist.update(candidates)
elif args.low_filter is None and args.low_percent is None and args.quiet:
pass
elif args.low_filter:
candidates = get_candidate_words(c,
-1 * args.low_filter,
sort=False,
items=items,
counts=counts)
if len(candidates):
print("Filtering {} low frequency words.".format(len(candidates)))
stoplist.update(candidates)
elif args.low_percent:
args.low_filter = get_closest_bin(c,
1 - (args.low_percent / 100.),
reverse=True,
counts=counts)
print(args.low_filter)
candidates = get_candidate_words(c,
-1 * args.low_filter,
sort=False,
items=items,
counts=counts)
if len(candidates):
print("Filtering {} low frequency word{}.".format(
len(candidates), 's' if len(candidates) > 1 else ''))
stoplist.update(candidates)
if not stoplist:
print("No stopwords applied.\n\n")
sys.exit(0)
else:
print("\n\nApplying {} stopword{}".format(
len(stoplist), 's' if len(stoplist) > 1 else ''))
c.in_place_stoplist(stoplist)
print("\n")
def name_corpus(dirname, languages, lowfreq=None, highfreq=None):
corpus_name = [dirname]
if args.lang:
corpus_name.append('nltk')
corpus_name.append(''.join(args.lang))
if lowfreq is not None and lowfreq > 0:
corpus_name.append('freq%s' % lowfreq)
if highfreq is not None and highfreq > 0:
corpus_name.append('N%s' % highfreq)
corpus_name = '-'.join(corpus_name)
corpus_name += '.npz'
return corpus_name
dirname = os.path.basename(args.corpus_path).split('-nltk-')[0].replace(
'.npz', '')
corpus_name = name_corpus(dirname, ['en'], args.low_filter,
args.high_filter)
model_path = os.path.dirname(args.corpus_path)
args.corpus_path = os.path.join(model_path, corpus_name)
c.save(args.corpus_path)
config.set("main", "corpus_file", args.corpus_path)
config.remove_option("main", "model_pattern")
with open(args.config_file, 'w') as configfh:
config.write(configfh)
def main(args):
if args.cluster:
cluster(args.cluster, args.config_file)
return
config = topicexplorer.config.read(args.config_file)
corpus_filename = config.get("main", "corpus_file")
model_path = config.get("main", "path")
if config.getboolean("main", "sentences"):
from vsm.extensions.ldasentences import CorpusSent as Corpus
else:
from vsm.corpus import Corpus
if args.k is None:
try:
if config.get("main", "topics"):
default = ' '.join(map(str, eval(config.get("main",
"topics"))))
if args.quiet:
args.k = [int(n) for n in default.split()]
else:
raise NoOptionError('main', 'topics')
except NoOptionError:
default = ' '.join(map(str, range(20, 100, 20)))
while args.k is None:
ks = input("Number of Topics [Default '{0}']: ".format(default))
try:
if ks:
args.k = [int(n) for n in ks.split()]
elif not ks.strip():
args.k = [int(n) for n in default.split()]
if args.k:
print(
"\nTIP: number of topics can be specified with argument '-k N N N ...':"
)
print(" topicexplorer train %s -k %s\n" %\
(args.config_file, ' '.join(map(str, args.k))))
except ValueError:
print("Enter valid integers, separated by spaces!")
if args.processes < 0:
import multiprocessing
args.processes = multiprocessing.cpu_count() + args.processes
print("Loading corpus... ")
corpus = Corpus.load(corpus_filename)
try:
model_pattern = config.get("main", "model_pattern")
except NoOptionError:
model_pattern = None
if (model_pattern is not None and not args.rebuild and
(args.quiet or args.cont or bool_prompt(
"""Existing topic models found. You can continue training or start a new model.
Do you want to continue training your existing models? """,
default=True))):
from vsm.model.lda import LDA
m = LDA.load(model_pattern.format(args.k[0]),
multiprocessing=args.processes > 1,
n_proc=args.processes)
if args.iter is None and not args.quiet: # pragma: no cover
args.iter = int_prompt("Total number of training iterations:",
default=int(m.iteration * 1.5),
min=m.iteration)
print(
"\nTIP: number of training iterations can be specified with argument '--iter N':"
)
print(" topicexplorer train --iter %d %s\n" %
(args.iter, args.config_file))
elif args.iter is None and args.quiet: # pragma: no cover
args.iter = int(m.iteration * 1.5)
del m
# if the set changes, build some new models and continue some old ones
config_topics = eval(config.get("main", "topics"))
if args.k != config_topics:
new_models = set(args.k) - set(config_topics)
continuing_models = set(args.k) & set(config_topics)
build_models(corpus,
corpus_filename,
model_path,
config.get("main", "context_type"),
new_models,
n_iterations=args.iter,
n_proc=args.processes,
seed=args.seed,
dry_run=args.dry_run)
model_pattern = continue_training(model_pattern,
continuing_models,
args.iter,
n_proc=args.processes,
dry_run=args.dry_run)
else:
model_pattern = continue_training(model_pattern,
args.k,
args.iter,
n_proc=args.processes,
dry_run=args.dry_run)
else:
# build a new model
if args.iter is None and not args.quiet: # pragma: no cover
args.iter = int_prompt("Number of training iterations:",
default=200)
print(
"\nTIP: number of training iterations can be specified with argument '--iter N':"
)
print(" topicexplorer train --iter %d %s\n" %
(args.iter, args.config_file))
elif args.iter is None and args.quiet: # pragma: no cover
args.iter = 200
# TODO: if only one context_type, make it just the one context type.
ctxs = corpus.context_types
if len(ctxs) == 1:
args.context_type = ctxs[0]
else:
ctxs = sorted(ctxs, key=lambda ctx: len(corpus.view_contexts(ctx)))
if args.context_type not in ctxs:
while args.context_type not in ctxs:
contexts = ctxs[:]
contexts[0] = contexts[0].upper()
contexts = '/'.join(contexts)
args.context_type = input("Select a context type [%s] : " %
contexts)
if args.context_type.strip() == '':
args.context_type = ctxs[0]
if args.context_type == ctxs[0].upper():
args.context_type = ctxs[0]
print(
"\nTIP: context type can be specified with argument '--context-type TYPE':"
)
print(" topicexplorer train --context-type %s %s\n" %
(args.context_type, args.config_file))
print("\nTIP: This configuration can be automated as:")
print(" topicexplorer train %s --iter %d --context-type %s -k %s\n" %\
(args.config_file, args.iter, args.context_type,
' '.join(map(str, args.k))))
model_pattern = build_models(corpus,
corpus_filename,
model_path,
args.context_type,
args.k,
n_iterations=args.iter,
n_proc=args.processes,
seed=args.seed,
dry_run=args.dry_run)
config.set("main", "model_pattern", model_pattern)
if args.context_type:
# test for presence, since continuing doesn't require context_type
config.set("main", "context_type", args.context_type)
args.k.sort()
config.set("main", "topics", str(args.k))
if not args.dry_run:
if config.has_option("main", "cluster"):
cluster_path = config.get("main", "cluster", fallback=None)
config.remove_option("main", "cluster")
try:
if cluster_path:
os.remove(cluster_path)
except (OSError, IOError):
# fail silently on IOError
pass
with open(args.config_file, "w") as configfh:
config.write(configfh)
def main(args):
config = ConfigParser({"sentences": "False"})
config.read(args.config_file)
corpus_filename = config.get("main", "corpus_file")
model_path = config.get("main", "path")
if config.getboolean("main", "sentences"):
from vsm.extensions.ldasentences import CorpusSent as Corpus
else:
from vsm.corpus import Corpus
if args.k is None:
try:
if config.get("main", "topics"):
default = ' '.join(map(str, eval(config.get("main", "topics"))))
else:
raise NoOptionError
except NoOptionError:
default = ' '.join(map(str, range(20,100,20)))
while args.k is None:
ks = raw_input("Number of Topics [Default '{0}']: ".format(default))
try:
if ks:
args.k = [int(n) for n in ks.split()]
elif not ks.strip():
args.k = [int(n) for n in default.split()]
if args.k:
print "\nTIP: number of topics can be specified with argument '-k N N N ...':"
print " vsm train %s -k %s\n" %\
(args.config_file, ' '.join(map(str, args.k)))
except ValueError:
print "Enter valid integers, separated by spaces!"
if args.processes < 0:
import multiprocessing
args.processes = multiprocessing.cpu_count() + args.processes
print "Loading corpus... "
corpus = Corpus.load(corpus_filename)
try:
model_pattern = config.get("main", "model_pattern")
except NoOptionError:
model_pattern = None
if model_pattern is not None and\
bool_prompt("Existing models found. Continue training?", default=True):
from vsm.model.lda import LDA
m = LDA.load(model_pattern.format(args.k[0]),
multiprocessing=args.processes > 1,
n_proc=args.processes)
if args.iter is None:
args.iter = int_prompt("Total number of training iterations:",
default=int(m.iteration*1.5), min=m.iteration)
print "\nTIP: number of training iterations can be specified with argument '--iter N':"
print " vsm train --iter %d %s\n" % (args.iter, args.config_file)
del m
# if the set changes, build some new models and continue some old ones
config_topics = eval(config.get("main","topics"))
if args.k != config_topics :
new_models = set(args.k) - set(config_topics)
continuing_models = set(args.k) & set(config_topics)
build_models(corpus, corpus_filename, model_path,
config.get("main", "context_type"),
new_models, n_iterations=args.iter,
n_proc=args.processes, seed=args.seed)
model_pattern = continue_training(model_pattern, continuing_models,
args.iter, n_proc=args.processes)
else:
model_pattern = continue_training(model_pattern, args.k, args.iter,
n_proc=args.processes)
else:
# build a new model
if args.iter is None:
args.iter = int_prompt("Number of training iterations:", default=200)
print "\nTIP: number of training iterations can be specified with argument '--iter N':"
print " vsm train --iter %d %s\n" % (args.iter, args.config_file)
ctxs = corpus.context_types
ctxs = sorted(ctxs, key=lambda ctx: len(corpus.view_contexts(ctx)))
if args.context_type not in ctxs:
while args.context_type not in ctxs:
contexts = ctxs[:]
contexts[0] = contexts[0].upper()
contexts = '/'.join(contexts)
args.context_type = raw_input("Select a context type [%s] : " % contexts)
if args.context_type.strip() == '':
args.context_type = ctxs[0]
if args.context_type == ctxs[0].upper():
args.context_type = ctxs[0]
print "\nTIP: context type can be specified with argument '--context-type TYPE':"
print " vsm train --context-type %s %s\n" % (args.context_type, args.config_file)
print "\nTIP: This configuration can be automated as:"
print " vsm train %s --iter %d --context-type %s -k %s\n" %\
(args.config_file, args.iter, args.context_type,
' '.join(map(str, args.k)))
model_pattern = build_models(corpus, corpus_filename, model_path,
args.context_type, args.k,
n_iterations=args.iter,
n_proc=args.processes, seed=args.seed,
dry_run=args.dry_run)
config.set("main", "model_pattern", model_pattern)
if args.context_type:
# test for presence, since continuing doesn't require context_type
config.set("main", "context_type", args.context_type)
args.k.sort()
config.set("main", "topics", str(args.k))
if not args.dry_run:
with open(args.config_file, "wb") as configfh:
config.write(configfh)
def main(args):
config = ConfigParser({"sentences": "False"})
config.read(args.config_file)
corpus_filename = config.get("main", "corpus_file")
model_path = config.get("main", "path")
if config.getboolean("main", "sentences"):
from vsm.extensions.ldasentences import CorpusSent as Corpus
else:
from vsm.corpus import Corpus
if args.k is None:
try:
if config.get("main", "topics"):
default = ' '.join(map(str, eval(config.get("main",
"topics"))))
else:
raise NoOptionError
except NoOptionError:
default = ' '.join(map(str, range(20, 100, 20)))
while args.k is None:
ks = raw_input(
"Number of Topics [Default '{0}']: ".format(default))
try:
if ks:
args.k = [int(n) for n in ks.split()]
elif not ks.strip():
args.k = [int(n) for n in default.split()]
if args.k:
print "\nTIP: number of topics can be specified with argument '-k N N N ...':"
print " vsm train %s -k %s\n" %\
(args.config_file, ' '.join(map(str, args.k)))
except ValueError:
print "Enter valid integers, separated by spaces!"
if args.processes < 0:
import multiprocessing
args.processes = multiprocessing.cpu_count() + args.processes
print "Loading corpus... "
corpus = Corpus.load(corpus_filename)
try:
model_pattern = config.get("main", "model_pattern")
except NoOptionError:
model_pattern = None
if model_pattern is not None and\
bool_prompt("Existing models found. Continue training?", default=True):
from vsm.model.lda import LDA
m = LDA.load(model_pattern.format(args.k[0]),
multiprocessing=args.processes > 1,
n_proc=args.processes)
if args.iter is None:
args.iter = int_prompt("Total number of training iterations:",
default=int(m.iteration * 1.5),
min=m.iteration)
print "\nTIP: number of training iterations can be specified with argument '--iter N':"
print " vsm train --iter %d %s\n" % (args.iter,
args.config_file)
del m
# if the set changes, build some new models and continue some old ones
config_topics = eval(config.get("main", "topics"))
if args.k != config_topics:
new_models = set(args.k) - set(config_topics)
continuing_models = set(args.k) & set(config_topics)
build_models(corpus,
corpus_filename,
model_path,
config.get("main", "context_type"),
new_models,
n_iterations=args.iter,
n_proc=args.processes,
seed=args.seed)
model_pattern = continue_training(model_pattern,
continuing_models,
args.iter,
n_proc=args.processes)
else:
model_pattern = continue_training(model_pattern,
args.k,
args.iter,
n_proc=args.processes)
else:
# build a new model
if args.iter is None:
args.iter = int_prompt("Number of training iterations:",
default=200)
print "\nTIP: number of training iterations can be specified with argument '--iter N':"
print " vsm train --iter %d %s\n" % (args.iter,
args.config_file)
ctxs = corpus.context_types
ctxs = sorted(ctxs, key=lambda ctx: len(corpus.view_contexts(ctx)))
if args.context_type not in ctxs:
while args.context_type not in ctxs:
contexts = ctxs[:]
contexts[0] = contexts[0].upper()
contexts = '/'.join(contexts)
args.context_type = raw_input("Select a context type [%s] : " %
contexts)
if args.context_type.strip() == '':
args.context_type = ctxs[0]
if args.context_type == ctxs[0].upper():
args.context_type = ctxs[0]
print "\nTIP: context type can be specified with argument '--context-type TYPE':"
print " vsm train --context-type %s %s\n" % (
args.context_type, args.config_file)
print "\nTIP: This configuration can be automated as:"
print " vsm train %s --iter %d --context-type %s -k %s\n" %\
(args.config_file, args.iter, args.context_type,
' '.join(map(str, args.k)))
model_pattern = build_models(corpus,
corpus_filename,
model_path,
args.context_type,
args.k,
n_iterations=args.iter,
n_proc=args.processes,
seed=args.seed,
dry_run=args.dry_run)
config.set("main", "model_pattern", model_pattern)
if args.context_type:
# test for presence, since continuing doesn't require context_type
config.set("main", "context_type", args.context_type)
args.k.sort()
config.set("main", "topics", str(args.k))
if not args.dry_run:
with open(args.config_file, "wb") as configfh:
config.write(configfh)
def main(args):
config = topicexplorer.config.read(args.config_file)
if config.getboolean("main", "sentences"):
from vsm.extensions.ldasentences import CorpusSent as Corpus
else:
from vsm.corpus import Corpus
if args.lang is None:
args.lang = []
args.corpus_path = config.get("main", "corpus_file")
c = Corpus.load(args.corpus_path)
if c.original_length != len(c.corpus):
print("Corpus has already been prepared. Proceed to training or")
print("re-init the corpus to apply a different set of stopwords.")
print("\nTIP: Train the LDA models with:")
print(" topicexplorer train", args.config_file)
sys.exit(1)
# auto-guess a language
"""
new_langs = [lang for lang in detect_langs(c) if lang in langs and lang not in args.lang]
if new_langs:
args.lang.extend(new_langs)
"""
# add default locale if no other languages are specified
# do not add if in quiet mode -- make everything explicit
if not args.lang and not args.quiet:
import locale
locale = locale.getdefaultlocale()[0].split('_')[0].lower()
if locale in langs.keys():
args.lang.append(locale)
# check for any new candidates
args.lang = [lang for lang in args.lang if stop_language(c, langs[lang])]
if args.lang and not args.quiet:
args.lang = lang_prompt(args.lang)
stoplist = set()
# Apply stop words
print(" ")
for lang in args.lang:
print("Applying", langs[lang], "stopwords")
candidates = stop_language(c, langs[lang])
if len(candidates):
stoplist.update(candidates)
# Apply custom stopwords file
if args.stopword_file:
with open(args.stopword_file, encoding='utf8') as swf:
#candidates = [unidecode(word.strip()) for word in swf]
candidates = [word.strip() for word in swf]
if len(candidates):
print("Applying custom stopword file to remove {} word{}.".format(
len(candidates), 's' if len(candidates) > 1 else ''))
stoplist.update(candidates)
if args.min_word_len:
candidates = get_small_words(c, args.min_word_len)
if len(candidates):
print("Filtering {} small word{} with less than {} characters.".format(
len(candidates), 's' if len(candidates) > 1 else '', args.min_word_len))
stoplist.update(candidates)
# cache item counts
items, counts = get_corpus_counts(c)
if args.high_filter is None and args.high_percent is None and not args.quiet:
args.high_filter, candidates = get_high_filter(c, words=stoplist, items=items, counts=counts)
if len(candidates):
print("Filtering {} high frequency word{}.".format(len(candidates),
's' if len(candidates) > 1 else ''))
stoplist.update(candidates)
elif args.high_filter is None and args.high_percent is None and args.quiet:
pass
elif args.high_filter:
candidates = get_candidate_words(c, args.high_filter, sort=False, items=items, counts=counts)
if len(candidates):
print("Filtering {} high frequency word{}.".format(len(candidates),
's' if len(candidates) > 1 else ''))
stoplist.update(candidates)
elif args.high_percent:
args.high_filter = get_closest_bin(c, 1 - (args.high_percent / 100.), counts=counts)
print(args.high_filter)
candidates = get_candidate_words(c, args.high_filter, sort=False, items=items, counts=counts)
if len(candidates):
print("Filtering {} high frequency word{}.".format(len(candidates),
's' if len(candidates) > 1 else ''))
stoplist.update(candidates)
if args.low_filter is None and args.low_percent is None and not args.quiet:
args.low_filter, candidates = get_low_filter(c, words=stoplist, items=items, counts=counts)
if len(candidates):
print("Filtering {} low frequency word{}.".format(len(candidates),
's' if len(candidates) > 1 else ''))
stoplist.update(candidates)
elif args.low_filter is None and args.low_percent is None and args.quiet:
pass
elif args.low_filter:
candidates = get_candidate_words(c, -1 * args.low_filter, sort=False, items=items, counts=counts)
if len(candidates):
print("Filtering {} low frequency words.".format(len(candidates)))
stoplist.update(candidates)
elif args.low_percent:
args.low_filter = get_closest_bin(c, 1 - (args.low_percent / 100.), reverse=True, counts=counts)
print(args.low_filter)
candidates = get_candidate_words(c, -1 * args.low_filter, sort=False, items=items, counts=counts)
if len(candidates):
print("Filtering {} low frequency word{}.".format(len(candidates),
's' if len(candidates) > 1 else ''))
stoplist.update(candidates)
if not stoplist:
print("No stopwords applied.\n\n")
sys.exit(0)
else:
print("\n\nApplying {} stopword{}".format(len(stoplist),
's' if len(stoplist) > 1 else ''))
c.in_place_stoplist(stoplist)
print("\n")
def name_corpus(dirname, languages, lowfreq=None, highfreq=None):
corpus_name = [dirname]
if args.lang:
corpus_name.append('nltk')
corpus_name.append(''.join(args.lang))
if lowfreq is not None and lowfreq > 0:
corpus_name.append('freq%s' % lowfreq)
if highfreq is not None and highfreq > 0:
corpus_name.append('N%s' % highfreq)
corpus_name = '-'.join(corpus_name)
corpus_name += '.npz'
return corpus_name
dirname = os.path.basename(args.corpus_path).split('-nltk-')[0].replace('.npz', '')
corpus_name = name_corpus(dirname, ['en'], args.low_filter, args.high_filter)
model_path = os.path.dirname(args.corpus_path)
args.corpus_path = os.path.join(model_path, corpus_name)
c.save(args.corpus_path)
config.set("main", "corpus_file", args.corpus_path)
config.remove_option("main", "model_pattern")
with open(args.config_file, 'w') as configfh:
config.write(configfh)
def main(args):
config = ConfigParser({"htrc": False,
"sentences": "False"})
config.read(args.config_file)
if config.getboolean("main", "sentences"):
from vsm.extensions.ldasentences import CorpusSent as Corpus
else:
from vsm.corpus import Corpus
if args.lang is None:
args.lang = []
args.corpus_path = config.get("main", "corpus_file")
c = Corpus.load(args.corpus_path)
# check for htrc metadata
if args.htrc or config.get("main", "htrc"):
htrc_langs = get_htrc_langs(args)
if htrc_langs:
args.lang.extend(new_langs)
# auto-guess a language
"""
new_langs = [lang for lang in detect_langs(c) if lang in langs and lang not in args.lang]
if new_langs:
args.lang.extend(new_langs)
"""
# add default locale if no other languages are specified
# do not add if in quiet mode -- make everything explicit
if not args.lang and not args.quiet:
import locale
locale = locale.getdefaultlocale()[0].split('_')[0].lower()
if locale in langs.keys():
args.lang.append(locale)
# check for any new candidates
args.lang = [lang for lang in args.lang if stop_language(c, langs[lang])]
if args.lang and not args.quiet:
args.lang = lang_prompt(args.lang)
stoplist = set()
# Apply stop words
print(" ")
for lang in args.lang:
print("Applying", langs[lang], "stopwords")
candidates = stop_language(c, langs[lang])
if len(candidates):
stoplist.update(candidates)
# Apply custom stopwords file
if args.stopword_file:
with open(args.stopword_file, encoding='utf8') as swf:
#candidates = [unidecode(word.strip()) for word in swf]
candidates = [word.strip() for word in swf]
if len(candidates):
print("Applying custom stopword file to remove {} word{}.".format(
len(candidates), 's' if len(candidates) > 1 else ''))
stoplist.update(candidates)
if args.min_word_len:
candidates = get_small_words(c, args.min_word_len)
if len(candidates):
print("Filtering {} small word{} with less than {} characters.".format(
len(candidates), 's' if len(candidates) > 1 else '', args.min_word_len))
stoplist.update(candidates)
if not args.special_chars:
candidates = get_special_chars(c)
if len(candidates):
print("Filtering {} word{} with special characters.".format(
len(candidates), 's' if len(candidates) > 1 else ''))
stoplist.update(candidates)
if args.high_filter is None and not args.quiet:
args.high_filter, candidates = get_high_filter(args, c, words=stoplist)
if len(candidates):
print("Filtering {} high frequency word{}.".format(len(candidates),
's' if len(candidates) > 1 else ''))
stoplist.update(candidates)
elif args.high_filter > 0:
candidates = get_candidate_words(c, args.high_filter, sort=False)
if len(candidates):
print("Filtering {} high frequency word{}.".format(len(candidates),
's' if len(candidates) > 1 else ''))
stoplist.update(candidates)
if args.low_filter is None and not args.quiet:
args.low_filter, candidates = get_low_filter(args, c, words=stoplist)
if len(candidates):
print("Filtering {} low frequency word{}.".format(len(candidates),
's' if len(candidates) > 1 else ''))
stoplist.update(candidates)
elif args.low_filter > 0:
candidates = get_candidate_words(c, -1 * args.low_filter, sort=False)
if len(candidates):
print("Filtering {} low frequency words.".format(len(candidates)))
stoplist.update(candidates)
if not stoplist:
print("No stopwords applied.\n\n")
sys.exit(0)
else:
print("\n\nApplying {} stopword{}".format(len(stoplist),
's' if len(stoplist) > 1 else ''))
c.in_place_stoplist(stoplist)
print("\n")
def name_corpus(dirname, languages, lowfreq=None, highfreq=None):
items, counts = get_items_counts(c.corpus)
corpus_name = [dirname]
if args.lang:
corpus_name.append('nltk')
corpus_name.append(''.join(args.lang))
if lowfreq > 0:
corpus_name.append('freq%s' % lowfreq)
else:
corpus_name.append('freq%s' % min(counts))
if highfreq > 0:
corpus_name.append('N%s' % highfreq)
else:
corpus_name.append('freq%s' % max(counts))
corpus_name = '-'.join(corpus_name)
corpus_name += '.npz'
return corpus_name
dirname = os.path.basename(args.corpus_path).split('-nltk-')[0].replace('.npz', '')
corpus_name = name_corpus(dirname, ['en'], args.low_filter, args.high_filter)
model_path = os.path.dirname(args.corpus_path)
args.corpus_path = os.path.join(model_path, corpus_name)
c.save(args.corpus_path)
config.set("main", "corpus_file", args.corpus_path)
config.remove_option("main", "model_pattern")
with open(args.config_file, 'w') as configfh:
config.write(configfh)