def get_host_port(args):
"""
Returns the hostname and port number
"""
import topicexplorer.config
config = topicexplorer.config.read(args.config)
# automatic port assignment
def test_port(port):
try:
host = args.host or config.get("www", "host")
if host == '0.0.0.0':
host = 'localhost'
try:
s = socket.create_connection((host, port), 2)
s.close()
raise IOError("Socket connectable on port {0}".format(port))
except socket.error:
pass
return port
except IOError:
if not args.quiet:
port = int_prompt(
"Conflict on port {0}. Enter new port:".format(port))
return test_port(port)
else:
raise IOError(
"Conflict on port {0}. Try running with -p to manually set new port.".format(port))
port = args.port or int(config.get('www', 'port').format(0))
port = test_port(port)
# prompt to save
if (int(config.get("www", "port").format(0))) != port:
if not args.quiet and bool_prompt(
"Change default baseport to {0}?".format(port), default=True):
config.set("www", "port", text(port))
# create deep copy of configuration
# see http://stackoverflow.com/a/24343297
config_string = StringIO()
config.write(config_string)
# skip DEFAULT section
config_string.seek(0)
idx = config_string.getvalue().index("[main]")
config_string.seek(idx)
# read deep copy
new_config = ConfigParser()
config.read_file(config_string)
# write deep copy without DEFAULT section
# this preserves DEFAULT for rest of program
with open(args.config, 'w') as configfh:
new_config.write(configfh)
# hostname assignment
host = args.host or config.get('www', 'host')
return host, port
def cluster(n_clusters, config_file):
from .cluster import dimensionReduce
dimension_reduce_model = dimensionReduce(config_file)
dimension_reduce_model.fit_isomap()
dimension_reduce_model.fit_kmeans(int(n_clusters))
print("writing model files for Isomap and kmeans\n")
config = topicexplorer.config.read(config_file)
corpus_filename = config.get("main", "corpus_file")
filename = '.'.join(corpus_filename.split('.')[:-1]) + '-cluster.csv'
config.set("main", "cluster", filename)
with open(config_file, "w") as configfh:
config.write(configfh)
dimension_reduce_model.write(config.get("main", "cluster"))
return filename
def cluster(n_clusters, config_file):
from .cluster import dimensionReduce
dimension_reduce_model = dimensionReduce(config_file)
dimension_reduce_model.fit_isomap()
dimension_reduce_model.fit_kmeans(int(n_clusters))
print("writing model files for Isomap and kmeans\n")
config = topicexplorer.config.read(config_file)
corpus_filename = config.get("main", "corpus_file")
filename = '.'.join(corpus_filename.split('.')[:-1]) + '-cluster.csv'
config.set("main", "cluster", filename)
with open(config_file, "w") as configfh:
config.write(configfh)
dimension_reduce_model.write(config.get("main", "cluster"))
return filename
def main(args=None, launch=True):
download_and_extract()
pwd = os.getcwd()
init_parser = ArgumentParser()
init.populate_parser(init_parser)
args = init_parser.parse_args(
['ap', '--name', '"Associated Press 88-90 sample"', '--rebuild', '-q'])
init.main(args)
prep_parser = ArgumentParser()
prep.populate_parser(prep_parser)
args = prep_parser.parse_args(
'ap.ini --lang en --high 2000 --low 5 -q'.split())
prep.main(args)
train_parser = ArgumentParser()
train.populate_parser(train_parser)
args = train_parser.parse_args(
"ap.ini -k 20 40 60 --context-type article --iter 20".split())
train.main(args)
import topicexplorer.config
config = topicexplorer.config.read('ap.ini')
config.set("main", "label_module", "topicexplorer.extensions.ap")
config.set("main", "corpus_desc", "ap.md")
config.set("www", "icons", "ap,fingerprint,link")
config.set("www", "fulltext", "True")
shutil.copyfile(get_static_resource_path('demo/ap.md'), 'ap.md')
with open("ap.ini", "w") as configfh:
config.write(configfh)
if launch:
launch_parser = ArgumentParser()
server.populate_parser(launch_parser)
args = launch_parser.parse_args(['ap.ini'])
server.main(args)
def main(args=None, launch=True):
download_and_extract()
pwd = os.getcwd()
init_parser = ArgumentParser()
init.populate_parser(init_parser)
args = init_parser.parse_args(
['ap', '--name', '"Associated Press 88-90 sample"', '--rebuild', '-q'])
init.main(args)
prep_parser = ArgumentParser()
prep.populate_parser(prep_parser)
args = prep_parser.parse_args('ap.ini --lang en --high 2000 --low 5 -q'.split())
prep.main(args)
train_parser = ArgumentParser()
train.populate_parser(train_parser)
args = train_parser.parse_args("ap.ini -k 20 40 60 --context-type article --iter 20".split())
train.main(args)
import topicexplorer.config
config = topicexplorer.config.read('ap.ini')
config.set("main", "label_module", "topicexplorer.extensions.ap")
config.set("main", "corpus_desc", "ap.md")
config.set("www", "icons", "ap,fingerprint,link")
config.set("www", "fulltext", "True")
shutil.copyfile(get_static_resource_path('demo/ap.md'), 'ap.md')
with open("ap.ini", "w") as configfh:
config.write(configfh)
if launch:
launch_parser = ArgumentParser()
server.populate_parser(launch_parser)
args = launch_parser.parse_args(['ap.ini'])
server.main(args)
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 = 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 add_htrc_metadata(config, corpus=None, corpus_filename=None):
import htrc.metadata
config.set("main", "label_module", "topicexplorer.extensions.htrc")
config.set("www", "doc_title_format", '<a href="{1}">{0}</a>')
config.set("www", "doc_url_format", 'http://hdl.handle.net/2027/{0}')
config.set("www", "icons", "htrcbook,link")
config.set("main", "htrc", True)
if corpus_filename:
corpus = Corpus.load(corpus_filename)
config.set("main", "context_type", corpus.context_types[0])
if corpus:
ctx_type = config.get("main", "context_type")
label_name = doc_label_name(ctx_type)
ids = corpus.view_metadata(ctx_type)[label_name]
htrc_metapath = os.path.abspath(config.get("main", "corpus_file"))
htrc_metapath = os.path.join(
os.path.dirname(htrc_metapath),
os.path.basename(htrc_metapath) + '.metadata.json')
print("Downloading metadata to ", htrc_metapath)
htrc.metadata.get_metadata(ids, output_file=htrc_metapath)
config.set("www", "htrc_metadata", htrc_metapath)
return config
def add_htrc_metadata(config, corpus=None, corpus_filename=None):
import htrc.metadata
config.set("main", "label_module", "topicexplorer.extensions.htrc")
config.set("www", "doc_title_format", '<a href="{1}">{0}</a>')
config.set("www", "doc_url_format", 'http://hdl.handle.net/2027/{0}')
config.set("www", "icons", "htrcbook,link")
config.set("main", "htrc", "True")
if corpus_filename:
corpus = Corpus.load(corpus_filename)
config.set("main", "context_type", corpus.context_types[0])
if corpus:
ctx_type = config.get("main", "context_type")
label_name = doc_label_name(ctx_type)
ids = corpus.view_metadata(ctx_type)[label_name]
htrc_metapath = os.path.abspath(config.get("main", "corpus_file"))
htrc_metapath = os.path.join(
os.path.dirname(htrc_metapath),
os.path.basename(htrc_metapath) + '.metadata.json')
print("Downloading metadata to ", htrc_metapath)
htrc.metadata.get_metadata(ids, output_file=htrc_metapath)
config.set("www", "htrc_metadata", htrc_metapath)
return config
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 absolutize_config_file(config_file, output_dir):
config_file = os.path.join(output_dir, config_file)
config = topicexplorer.config.read(config_file)
# path variables
corpus_file = config.get('main', 'corpus_file')
corpus_file = os.path.join(output_dir, corpus_file)
corpus_file = os.path.abspath(corpus_file)
config.set('main', 'corpus_file', corpus_file)
model_pattern = config.get('main', 'model_pattern')
model_pattern = os.path.join(output_dir, model_pattern)
model_pattern = os.path.abspath(model_pattern)
config.set('main', 'model_pattern', model_pattern)
cluster_path = config.get('main', 'cluster')
if cluster_path is not None and cluster_path != 'None':
cluster_path = os.path.join(output_dir, cluster_path)
cluster_path = os.path.abspath(cluster_path)
config.set('main', 'cluster', cluster_path)
path = config.get('main', 'path')
if path is not None and path != 'None':
path = os.path.join(output_dir, path)
path = os.path.abspath(path)
config.set('main', 'path', path)
raw_corpus = config.get('main', 'raw_corpus')
if raw_corpus is not None and raw_corpus != 'None':
raw_corpus = os.path.join(output_dir, raw_corpus)
raw_corpus = os.path.abspath(raw_corpus)
config.set('main', 'raw_corpus', raw_corpus)
corpus_desc = config.get('main', 'corpus_desc')
if corpus_desc is not None and corpus_desc != 'None':
corpus_desc = os.path.join(output_dir, corpus_desc)
corpus_desc = os.path.abspath(corpus_desc)
config.set('main', 'corpus_desc', corpus_desc)
htrc_metadata = config.get('www', 'htrc_metadata')
if htrc_metadata is not None and htrc_metadata != 'None':
htrc_metadata = os.path.join(output_dir, htrc_metadata)
htrc_metadata = os.path.abspath(htrc_metadata)
config.set('www', 'htrc_metadata', htrc_metadata)
with open(config_file, 'w', encoding='utf8') as configfile:
config.write(configfile)
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 create_relative_config_file(config_file, manifest, include_corpus=False):
if sys.version_info[0] == 3:
root = os.path.commonpath(map(os.path.abspath, manifest)) + '/'
else:
root = os.path.commonprefix(map(os.path.abspath, manifest))
config = topicexplorer.config.read(config_file)
# path variables
corpus_file = config.get('main', 'corpus_file')
model_pattern = config.get('main', 'model_pattern')
cluster_path = config.get('main', 'cluster')
path = config.get('main', 'path')
raw_corpus = config.get('main', 'raw_corpus')
corpus_desc = config.get('main', 'corpus_desc')
config.set('main', 'corpus_file', corpus_file.replace(root, ''))
config.set('main', 'model_pattern', model_pattern.replace(root, ''))
if cluster_path is not None:
config.set('main', 'cluster', cluster_path.replace(root, ''))
if path is not None:
config.set('main', 'path', path.replace(root, ''))
if raw_corpus is not None and include_corpus:
config.set('main', 'raw_corpus', raw_corpus.replace(root, ''))
else:
config.set('main', 'raw_corpus', None)
if corpus_desc is not None:
config.set('main', 'corpus_desc', corpus_desc.replace(root, ''))
try:
if config.getboolean('main', 'htrc'):
htrc_metapath = config.get('www', 'htrc_metadata')
if htrc_metapath is not None:
config.set('www', 'htrc_metadata', htrc_metapath.replace(root, ''))
except:
pass
tempfh = NamedTemporaryFile(prefix='tez.'+config_file, delete=False)
temp_config_file = tempfh.name
tempfh.close()
with open(temp_config_file, 'w', encoding='utf-8') as tempfile:
config.write(tempfile)
return temp_config_file
def absolutize_config_file(config_file, output_dir):
config_file = os.path.join(output_dir, config_file)
config = topicexplorer.config.read(config_file)
# path variables
corpus_file = config.get('main', 'corpus_file')
corpus_file = os.path.join(output_dir, corpus_file)
corpus_file = os.path.abspath(corpus_file)
config.set('main', 'corpus_file', corpus_file)
model_pattern = config.get('main', 'model_pattern')
model_pattern = os.path.join(output_dir, model_pattern)
model_pattern = os.path.abspath(model_pattern)
config.set('main', 'model_pattern', model_pattern)
cluster_path = config.get('main', 'cluster')
if cluster_path is not None and cluster_path != 'None':
cluster_path = os.path.join(output_dir, cluster_path)
cluster_path = os.path.abspath(cluster_path)
config.set('main', 'cluster', cluster_path)
path = config.get('main', 'path')
if path is not None and path != 'None':
path = os.path.join(output_dir, path)
path = os.path.abspath(path)
config.set('main', 'path', path)
raw_corpus = config.get('main', 'raw_corpus')
if raw_corpus is not None and raw_corpus != 'None':
raw_corpus = os.path.join(output_dir, raw_corpus)
raw_corpus = os.path.abspath(raw_corpus)
config.set('main', 'raw_corpus', raw_corpus)
corpus_desc = config.get('main', 'corpus_desc')
if corpus_desc is not None and corpus_desc != 'None':
corpus_desc = os.path.join(output_dir, corpus_desc)
corpus_desc = os.path.abspath(corpus_desc)
config.set('main', 'corpus_desc', corpus_desc)
htrc_metadata = config.get('www', 'htrc_metadata')
if htrc_metadata is not None and htrc_metadata != 'None':
htrc_metadata = os.path.join(output_dir, htrc_metadata)
htrc_metadata = os.path.abspath(htrc_metadata)
config.set('www', 'htrc_metadata', htrc_metadata)
with open(config_file, 'w', encoding='utf8') as configfile:
config.write(configfile)