def process_documents(corpus_path):
corpus = Corpus(corpus_path)
final_text = []
corenlp_client = StanfordCoreNLP('http://localhost:9000')
lcount = 0
starts = set()
with codecs.open(corpus_path, 'r', 'utf-8') as docfile:
for l in docfile:
print lcount
if l[:10] in starts:
print "repeated abstract:", l[:10]
continue
lcount += 1
starts.add(l[:10])
values = l.strip().split("\t")
pmid = values[0]
abs_text = " ".join(values[1:])
newdoc = Document(abs_text, did="PMID" + pmid)
newdoc.process_document(corenlp_client)
#for sentence in newdoc.sentences:
# print [t.text for t in sentence.tokens]
newtext = ""
newdoc.did = "PMID" + pmid
corpus.documents["PMID" + pmid] = newdoc
"""for s in newdoc.sentences:
for t in s.tokens:
newtext += t.text + " "
final_text.append(newtext)"""
# if lcount > 10:
# break
if lcount % 1000 == 0:
corpus.save("{}_{}.pickle".format(corpus_path, str(lcount/1000)))
corpus = Corpus(corpus_path)
corpus.save("{}_{}.pickle".format(corpus_path, str(lcount / 1000)))
def process_documents():
corpus = Corpus("corpora/Thaliana/pubmed")
final_text = []
corenlp_client = StanfordCoreNLP('http://localhost:9000')
lcount = 0
starts = set()
with codecs.open("corpora/Thaliana/documents.txt", 'r',
'utf-8') as docfile:
for l in docfile:
print lcount
if l[:20] in starts:
continue
lcount += 1
starts.add(l[:20])
newdoc = Document(l.strip())
newdoc.process_document(corenlp_client)
for sentence in newdoc.sentences:
print[t.text for t in sentence.tokens]
newtext = ""
corpus.documents["d" + str(lcount)] = newdoc
"""for s in newdoc.sentences:
for t in s.tokens:
newtext += t.text + " "
final_text.append(newtext)"""
# if lcount > 10:
# break
if lcount % 1000 == 0:
corpus.save(
"corpora/Thaliana/thaliana-documents_{}.pickle".format(
str(lcount / 1000)))
def process_documents(corpus_path):
corpus = Corpus(corpus_path)
final_text = []
corenlp_client = StanfordCoreNLP('http://localhost:9000')
lcount = 0
starts = set()
with codecs.open(corpus_path, 'r', 'utf-8') as docfile:
for l in docfile:
print lcount
if l[:10] in starts:
print "repeated abstract:", l[:10]
continue
lcount += 1
starts.add(l[:10])
values = l.strip().split("\t")
pmid = values[0]
abs_text = " ".join(values[1:])
newdoc = Document(abs_text, did="PMID" + pmid)
newdoc.process_document(corenlp_client)
#for sentence in newdoc.sentences:
# print [t.text for t in sentence.tokens]
newtext = ""
newdoc.did = "PMID" + pmid
corpus.documents["PMID" + pmid] = newdoc
"""for s in newdoc.sentences:
for t in s.tokens:
newtext += t.text + " "
final_text.append(newtext)"""
# if lcount > 10:
# break
if lcount % 1000 == 0:
corpus.save("{}_{}.pickle".format(corpus_path,
str(lcount / 1000)))
corpus = Corpus(corpus_path)
corpus.save("{}_{}.pickle".format(corpus_path, str(lcount / 1000)))
def main():
start_time = time.time()
parser = argparse.ArgumentParser(description='')
parser.add_argument("actions", default="classify", help="Actions to be performed.",
choices=["load_corpus", "annotate", "classify", "write_results", "write_goldstandard",
"train", "test", "train_multiple", "test_multiple", "train_matcher", "test_matcher",
"crossvalidation", "train_relations", "test_relations", "load_genia", "load_biomodel",
"merge_corpus", "tuples", "generate_data"])
parser.add_argument("--goldstd", default="", dest="goldstd", nargs="+",
help="Gold standard to be used. Will override corpus, annotations",
choices=paths.keys())
parser.add_argument("--submodels", default="", nargs='+', help="sub types of classifiers"),
parser.add_argument("-i", "--input", dest="input", action="store",
default='''Administration of a higher dose of indinavir should be \\
considered when coadministering with megestrol acetate.''',
help="Text to classify.")
parser.add_argument("--corpus", dest="corpus", nargs=2,
default=["chemdner", "CHEMDNER/CHEMDNER_SAMPLE_JUNE25/chemdner_sample_abstracts.txt"],
help="format path")
parser.add_argument("--annotations", dest="annotations")
parser.add_argument("--tag", dest="tag", default="0", help="Tag to identify the experiment")
parser.add_argument("--models", dest="models", help="model destination path, without extension")
parser.add_argument("--entitytype", dest="etype", help="type of entities to be considered", default="all")
parser.add_argument("--entitysubtype", dest="subtype", help="subtype of entities to be considered", default="all")
parser.add_argument("--pairtype", dest="ptype", help="type of pairs to be considered", default="all")
parser.add_argument("--doctype", dest="doctype", help="type of document to be considered", default="all")
parser.add_argument("--annotated", action="store_true", default=False, dest="annotated",
help="True if the input has <entity> tags.")
parser.add_argument("-o", "--output", "--format", dest="output",
nargs=2, help="format path; output formats: xml, html, tsv, text, chemdner.")
parser.add_argument("--crf", dest="crf", help="CRF implementation", default="stanford",
choices=["stanford", "crfsuite", "banner", "ensemble"])
parser.add_argument("--log", action="store", dest="loglevel", default="WARNING", help="Log level")
parser.add_argument("--kernel", action="store", dest="kernel", default="svmtk", help="Kernel for relation extraction")
options = parser.parse_args()
# set logger
numeric_level = getattr(logging, options.loglevel.upper(), None)
if not isinstance(numeric_level, int):
raise ValueError('Invalid log level: %s' % options.loglevel)
while len(logging.root.handlers) > 0:
logging.root.removeHandler(logging.root.handlers[-1])
logging_format = '%(asctime)s %(levelname)s %(filename)s:%(lineno)s:%(funcName)s %(message)s'
logging.basicConfig(level=numeric_level, format=logging_format)
logging.getLogger().setLevel(numeric_level)
logging.getLogger("requests.packages").setLevel(30)
logging.info("Processing action {0} on {1}".format(options.actions, options.goldstd))
# set configuration variables based on the goldstd option if the corpus has a gold standard,
# or on corpus and annotation options
# pre-processing options
if options.actions == "load_corpus":
if len(options.goldstd) > 1:
print "load only one corpus each time"
sys.exit()
options.goldstd = options.goldstd[0]
corpus_format = paths[options.goldstd]["format"]
corpus_path = paths[options.goldstd]["text"]
corpus_ann = paths[options.goldstd]["annotations"]
corenlp_client = StanfordCoreNLP('http://localhost:9000')
corpus = load_corpus(options.goldstd, corpus_path, corpus_format, corenlp_client)
#corenlp_process.kill()
#corpus.load_genia() #TODO optional genia
corpus.save(paths[options.goldstd]["corpus"])
if corpus_ann: #add annotation if it is not a test set
corpus.load_annotations(corpus_ann, options.etype, options.ptype)
corpus.save(paths[options.goldstd]["corpus"])
elif options.actions == "load_genia":
options.goldstd = options.goldstd[0]
corpus_path = paths[options.goldstd]["corpus"]
corpus_ann = paths[options.goldstd]["annotations"]
logging.info("loading corpus %s" % corpus_path)
corpus = pickle.load(open(corpus_path, 'rb'))
corpus.load_genia()
corpus.save(paths[options.goldstd]["corpus"])
elif options.actions == "load_biomodel":
options.goldstd = options.goldstd[0]
corpus_path = paths[options.goldstd]["corpus"]
corpus_ann = paths[options.goldstd]["annotations"]
logging.info("loading corpus %s" % corpus_path)
corpus = pickle.load(open(corpus_path, 'rb'))
corpus.load_biomodel()
corpus.save(paths[options.goldstd]["corpus"])
elif options.actions == "tuples":
options.goldstd = options.goldstd[0]
corpus_path = paths[options.goldstd]["corpus"]
corpus_ann = paths[options.goldstd]["annotations"]
logging.info("loading corpus %s" % corpus_path)
corpus = pickle.load(open(corpus_path, 'rb'))
logging.info("converting to tuples...")
corpus.to_tuple()
corpus.save(paths[options.goldstd]["corpus"])
elif options.actions == "annotate": # rext-add annotation to corpus
if len(options.goldstd) > 1:
print "load only one corpus each time"
sys.exit()
options.goldstd = options.goldstd[0]
corpus_path = paths[options.goldstd]["corpus"]
corpus_ann = paths[options.goldstd]["annotations"]
logging.info("loading corpus %s" % corpus_path)
corpus = pickle.load(open(corpus_path, 'rb'))
corpus.name = options.goldstd
logging.debug("loading annotations...")
corpus.clear_annotations(options.etype)
corpus.load_annotations(corpus_ann, options.etype, options.ptype)
# corpus.get_invalid_sentences()
corpus.save(paths[options.goldstd]["corpus"])
else:
corpus = Corpus("corpus/" + "&".join(options.goldstd))
for g in options.goldstd:
corpus_path = paths[g]["corpus"]
logging.info("loading corpus %s" % corpus_path)
this_corpus = pickle.load(open(corpus_path, 'rb'))
#logging.info("adding {} documents".format(len(documents)))
# docs = this_corpus.documents
docs = dict((k, this_corpus.documents[k]) for k in this_corpus.documents.keys()[:13000])
corpus.documents.update(docs)
if options.actions == "write_goldstandard":
model = BiasModel(options.output[1])
model.load_data(corpus, [])
results = model.test()
#results = ResultsNER(options.output[1])
#results.get_ner_results(corpus, model)
results.save(options.output[1] + ".pickle")
#logging.info("saved gold standard results to " + options.output[1] + ".txt")
elif options.actions == "merge_corpus":
corpus.save(paths[options.output[1]]["corpus"])
# training
elif options.actions == "generate_data":
corpus_path = paths[options.goldstd[0]]["corpus"]
print "writing to " + options.goldstd[0] + "_event_time_contains.txt"
with open(options.goldstd[0] + "_event_time_contains.txt", 'w') as datafile:
for sentence in corpus.get_sentences("goldstandard"):
sentence_entities = [entity for entity in sentence.entities.elist["goldstandard"]]
for pair in itertools.combinations(sentence_entities, 2):
if pair[0].type == "event" and pair[1].type == "time":
pair_label = (pair[1].eid, "temporal") in pair[0].targets
between_text = sentence.text[pair[0].start:pair[1].end]
datafile.write("{0}\t{1.original_id}\t{1.text}\t{2.original_id}\t{2.text}\t{3}\n".format(pair_label,
pair[0], pair[1], between_text))
elif options.actions == "train":
if options.crf == "stanford":
model = StanfordNERModel(options.models, options.etype)
elif options.crf == "crfsuite":
model = CrfSuiteModel(options.models, options.etype, subtype=options.subtype)
elif options.crf == "ensemble":
model = EnsembleModel(options.models, options.etype, goldstd=options.goldstd[0])
features = feature_extractors.keys()
if options.etype.startswith("time"):
features = time_features
elif options.etype.startswith("event"):
features = event_features
model.load_data(corpus, features, options.etype, subtype=options.subtype)
model.train()
elif options.actions == "train_matcher": # Train a simple classifier based on string matching
model = MatcherModel(options.models, options.etype)
model.train_list("temporal_list.txt")
# TODO: term list option
#model.train("TermList.txt")
elif options.actions == "train_multiple": # Train one classifier for each type of entity in this corpus
# logging.info(corpus.subtypes)
models = TaggerCollection(basepath=options.models, corpus=corpus, subtypes=corpus.subtypes)
models.train_types()
elif options.actions == "train_relations":
if options.kernel == "jsre":
model = JSREKernel(corpus, options.ptype, modelname=options.tag)
elif options.kernel == "svmtk":
model = SVMTKernel(corpus, options.ptype, modelname=options.tag)
#elif options.kernel == "stanfordre":
# model = StanfordRE(corpus, options.ptype)
#elif options.kernel == "multir":
# model = MultiR(corpus, options.ptype)
#elif options.kernel == "scikit":
# model = ScikitRE(corpus, options.ptype)
#elif options.kernel == "crf":
# model = CrfSuiteRE(corpus, options.ptype)
elif options.kernel == "mil":
relations = set()
with open("corpora/transmir/transmir_relations.txt") as rfile:
for l in rfile:
relations.add(tuple(l.strip().split('\t')))
model = MILClassifier(corpus, options.ptype, relations, ner=options.models)
model.train()
# testing
elif options.actions == "test":
base_port = 9191
if len(options.submodels) > 1:
allresults = ResultSetNER(corpus, options.output[1])
for i, submodel in enumerate(options.submodels):
model = StanfordNERModel(options.models + "_" + submodel)
model.load_tagger(base_port + i)
# load data into the model format
model.load_data(corpus, feature_extractors.keys(), mode="test")
# run the classifier on the data
results = model.test(corpus, port=base_port + i)
allresults.add_results(results)
model.kill_process()
# save the results to an object that can be read again, and log files to debug
final_results = allresults.combine_results()
else:
if options.crf == "stanford":
model = StanfordNERModel(options.models + "_stanford", options.etype)
elif options.crf == "crfsuite":
model = CrfSuiteModel(options.models + "_crfsuite", options.etype, subtype=options.subtype)
elif options.crf == "banner":
model = BANNERModel(options.models, options.etype)
elif options.crf == "ensemble":
model = EnsembleModel(options.models, options.etype, goldstd=options.goldstd[0])
model.load_tagger()
features = feature_extractors.keys()
if options.etype.startswith("time"):
features = time_features
elif options.etype.startswith("event"):
features = event_features
model.load_data(corpus, features, options.etype, mode="test", subtype=options.subtype)
final_results = model.test(corpus)
#with codecs.open(options.output[1] + ".txt", 'w', 'utf-8') as outfile:
# lines = final_results.corpus.write_chemdner_results(options.models, outfile)
#final_results.lines = lines
final_results.save(options.output[1] + ".pickle")
elif options.actions == "test_matcher":
if "mirna" in options.models:
model = MirnaMatcher(options.models)
else:
model = MatcherModel(options.models, options.etype)
results = ResultsNER(options.models)
results.corpus, results.entities = model.test(corpus)
allentities = set()
for e in results.entities:
allentities.add(results.entities[e].text)
with codecs.open(options.output[1] + ".txt", 'w', 'utf-8') as outfile:
outfile.write('\n'.join(allentities))
results.save(options.output[1] + ".pickle")
elif options.actions == "test_multiple":
logging.info("testing with multiple classifiers... {}".format(' '.join(options.submodels)))
allresults = ResultSetNER(corpus, options.output[1])
if len(options.submodels) < 2:
models = TaggerCollection(basepath=options.models)
models.load_models()
results = models.test_types(corpus)
final_results = results.combine_results()
else:
base_port = 9191
for submodel in options.submodels:
models = TaggerCollection(basepath=options.models + "_" + submodel, baseport = base_port)
models.load_models()
results = models.test_types(corpus)
logging.info("combining results...")
submodel_results = results.combine_results()
allresults.add_results(submodel_results)
base_port += len(models.models)
final_results = allresults.combine_results()
logging.info("saving results...")
final_results.save(options.output[1] + ".pickle")
elif options.actions == "test_relations":
if options.kernel == "jsre":
model = JSREKernel(corpus, options.ptype, train=False, modelname=options.tag, ner=options.models)
elif options.kernel == "svmtk":
model = SVMTKernel(corpus, options.ptype, modelname=options.tag, ner=options.models)
elif options.kernel == "rules":
model = RuleClassifier(corpus, options.ptype, ner=options.models)
elif options.kernel == "mirtex_rules":
model = MirtexClassifier(corpus, options.ptype)
elif options.kernel == "stanfordre":
model = StanfordRE(corpus, options.ptype)
elif options.kernel == "scikit":
model = ScikitRE(corpus, options.ptype)
elif options.kernel == "crf":
model = CrfSuiteRE(corpus, options.ptype, test=True)
elif options.kernel == "mil":
relations = set()
with open("corpora/transmir/transmir_relations.txt") as rfile:
for l in rfile:
relations.add(tuple(l.strip().split('\t')))
model = MILClassifier(corpus, options.ptype, relations, test=True, ner=options.models)
model.load_classifier()
model.test()
results = model.get_predictions(corpus)
results.save(options.output[1] + ".pickle")
total_time = time.time() - start_time
logging.info("Total time: %ss" % total_time)
def main():
start_time = time.time()
parser = argparse.ArgumentParser(description='')
parser.add_argument("actions", default="classify", help="Actions to be performed.",
choices=["load_corpus", "annotate", "classify", "write_results", "write_goldstandard",
"train", "test", "train_multiple", "test_multiple", "train_matcher", "test_matcher",
"crossvalidation", "train_relations", "test_relations", "load_genia", "load_biomodel",
"merge_corpus"])
parser.add_argument("--goldstd", default="", dest="goldstd", nargs="+",
help="Gold standard to be used. Will override corpus, annotations",
choices=paths.keys())
parser.add_argument("--submodels", default="", nargs='+', help="sub types of classifiers"),
parser.add_argument("-i", "--input", dest="input", action="store",
default='''Administration of a higher dose of indinavir should be \\
considered when coadministering with megestrol acetate.''',
help="Text to classify.")
parser.add_argument("--corpus", dest="corpus", nargs=2,
default=["chemdner", "CHEMDNER/CHEMDNER_SAMPLE_JUNE25/chemdner_sample_abstracts.txt"],
help="format path")
parser.add_argument("--annotations", dest="annotations")
parser.add_argument("--tag", dest="tag", default="0", help="Tag to identify the experiment")
parser.add_argument("--models", dest="models", help="model destination path, without extension")
parser.add_argument("--entitytype", dest="etype", help="type of entities to be considered", default="all")
parser.add_argument("--pairtype", dest="ptype", help="type of pairs to be considered", default="all")
parser.add_argument("--doctype", dest="doctype", help="type of document to be considered", default="all")
parser.add_argument("--annotated", action="store_true", default=False, dest="annotated",
help="True if the input has <entity> tags.")
parser.add_argument("-o", "--output", "--format", dest="output",
nargs=2, help="format path; output formats: xml, html, tsv, text, chemdner.")
parser.add_argument("--crf", dest="crf", help="CRF implementation", default="stanford",
choices=["stanford", "crfsuite", "banner"])
parser.add_argument("--log", action="store", dest="loglevel", default="WARNING", help="Log level")
parser.add_argument("--kernel", action="store", dest="kernel", default="svmtk", help="Kernel for relation extraction")
options = parser.parse_args()
# set logger
numeric_level = getattr(logging, options.loglevel.upper(), None)
if not isinstance(numeric_level, int):
raise ValueError('Invalid log level: %s' % options.loglevel)
while len(logging.root.handlers) > 0:
logging.root.removeHandler(logging.root.handlers[-1])
logging_format = '%(asctime)s %(levelname)s %(filename)s:%(lineno)s:%(funcName)s %(message)s'
logging.basicConfig(level=numeric_level, format=logging_format)
logging.getLogger().setLevel(numeric_level)
logging.getLogger("requests.packages").setLevel(30)
logging.info("Processing action {0} on {1}".format(options.actions, options.goldstd))
# set configuration variables based on the goldstd option if the corpus has a gold standard,
# or on corpus and annotation options
# pre-processing options
if options.actions == "load_corpus":
if len(options.goldstd) > 1:
print "load only one corpus each time"
sys.exit()
options.goldstd = options.goldstd[0]
corpus_format = paths[options.goldstd]["format"]
corpus_path = paths[options.goldstd]["text"]
corpus_ann = paths[options.goldstd]["annotations"]
corenlp_client = StanfordCoreNLP('http://localhost:9000')
corpus = load_corpus(options.goldstd, corpus_path, corpus_format, corenlp_client)
#corpus.load_genia() #TODO optional genia
corpus.save(paths[options.goldstd]["corpus"])
if corpus_ann: #add annotation if it is not a test set
corpus.load_annotations(corpus_ann, options.etype, options.ptype)
corpus.save(paths[options.goldstd]["corpus"])
elif options.actions == "load_genia":
options.goldstd = options.goldstd[0]
corpus_path = paths[options.goldstd]["corpus"]
corpus_ann = paths[options.goldstd]["annotations"]
logging.info("loading corpus %s" % corpus_path)
corpus = pickle.load(open(corpus_path, 'rb'))
corpus.load_genia()
corpus.save(paths[options.goldstd]["corpus"])
elif options.actions == "load_biomodel":
options.goldstd = options.goldstd[0]
corpus_path = paths[options.goldstd]["corpus"]
corpus_ann = paths[options.goldstd]["annotations"]
logging.info("loading corpus %s" % corpus_path)
corpus = pickle.load(open(corpus_path, 'rb'))
corpus.load_biomodel()
corpus.save(paths[options.goldstd]["corpus"])
elif options.actions == "annotate": # rext-add annotation to corpus
if len(options.goldstd) > 1:
print "load only one corpus each time"
sys.exit()
options.goldstd = options.goldstd[0]
corpus_path = paths[options.goldstd]["corpus"]
corpus_ann = paths[options.goldstd]["annotations"]
logging.info("loading corpus %s" % corpus_path)
corpus = pickle.load(open(corpus_path, 'rb'))
logging.debug("loading annotations...")
corpus.clear_annotations(options.etype)
corpus.load_annotations(corpus_ann, options.etype, options.ptype)
# corpus.get_invalid_sentences()
corpus.save(paths[options.goldstd]["corpus"])
else:
corpus = Corpus("corpus/" + "&".join(options.goldstd))
for g in options.goldstd:
corpus_path = paths[g]["corpus"]
logging.info("loading corpus %s" % corpus_path)
this_corpus = pickle.load(open(corpus_path, 'rb'))
corpus.documents.update(this_corpus.documents)
if options.actions == "write_goldstandard":
model = BiasModel(options.output[1])
model.load_data(corpus, [])
results = model.test()
#results = ResultsNER(options.output[1])
#results.get_ner_results(corpus, model)
results.save(options.output[1] + ".pickle")
#logging.info("saved gold standard results to " + options.output[1] + ".txt")
elif options.actions == "merge_corpus":
corpus.save(paths[options.output[1]]["corpus"])
# training
elif options.actions == "train":
if options.crf == "stanford":
model = StanfordNERModel(options.models, options.etype)
elif options.crf == "crfsuite":
model = CrfSuiteModel(options.models, options.etype)
model.load_data(corpus, feature_extractors.keys(), options.etype)
model.train()
elif options.actions == "train_matcher": # Train a simple classifier based on string matching
model = MatcherModel(options.models)
model.train(corpus)
# TODO: term list option
#model.train("TermList.txt")
elif options.actions == "train_multiple": # Train one classifier for each type of entity in this corpus
# logging.info(corpus.subtypes)
models = TaggerCollection(basepath=options.models, corpus=corpus, subtypes=corpus.subtypes)
models.train_types()
elif options.actions == "train_relations":
if options.kernel == "jsre":
model = JSREKernel(corpus, options.ptype, modelname=options.tag)
elif options.kernel == "svmtk":
model = SVMTKernel(corpus, options.ptype, modelname=options.tag)
#elif options.kernel == "stanfordre":
# model = StanfordRE(corpus, options.ptype)
#elif options.kernel == "multir":
# model = MultiR(corpus, options.ptype)
#elif options.kernel == "scikit":
# model = ScikitRE(corpus, options.ptype)
#elif options.kernel == "crf":
# model = CrfSuiteRE(corpus, options.ptype)
elif options.kernel == "mil":
relations = set()
with open("corpora/transmir/transmir_relations.txt") as rfile:
for l in rfile:
relations.add(tuple(l.strip().split('\t')))
model = MILClassifier(corpus, options.ptype, relations, ner=options.models)
model.train()
# testing
elif options.actions == "test":
base_port = 9191
if len(options.submodels) > 1:
allresults = ResultSetNER(corpus, options.output[1])
for i, submodel in enumerate(options.submodels):
model = StanfordNERModel(options.models + "_" + submodel)
model.load_tagger(base_port + i)
# load data into the model format
model.load_data(corpus, feature_extractors.keys(), mode="test")
# run the classifier on the data
results = model.test(corpus, port=base_port + i)
allresults.add_results(results)
model.kill_process()
# save the results to an object that can be read again, and log files to debug
final_results = allresults.combine_results()
else:
if options.crf == "stanford":
model = StanfordNERModel(options.models, options.etype)
elif options.crf == "crfsuite":
model = CrfSuiteModel(options.models, options.etype)
elif options.crf == "banner":
model = BANNERModel(options.models, options.etype)
model.load_tagger()
model.load_data(corpus, feature_extractors.keys(), mode="test")
final_results = model.test(corpus)
#with codecs.open(options.output[1] + ".txt", 'w', 'utf-8') as outfile:
# lines = final_results.corpus.write_chemdner_results(options.models, outfile)
#final_results.lines = lines
final_results.save(options.output[1] + ".pickle")
elif options.actions == "test_matcher":
if "mirna" in options.models:
model = MirnaMatcher(options.models)
else:
model = MatcherModel(options.models)
results = ResultsNER(options.models)
results.corpus, results.entities = model.test(corpus)
allentities = set()
for e in results.entities:
allentities.add(results.entities[e].text)
with codecs.open(options.output[1] + ".txt", 'w', 'utf-8') as outfile:
outfile.write('\n'.join(allentities))
results.save(options.output[1] + ".pickle")
elif options.actions == "test_multiple":
logging.info("testing with multiple classifiers... {}".format(' '.join(options.submodels)))
allresults = ResultSetNER(corpus, options.output[1])
if len(options.submodels) < 2:
models = TaggerCollection(basepath=options.models)
models.load_models()
results = models.test_types(corpus)
final_results = results.combine_results()
else:
base_port = 9191
for submodel in options.submodels:
models = TaggerCollection(basepath=options.models + "_" + submodel, baseport = base_port)
models.load_models()
results = models.test_types(corpus)
logging.info("combining results...")
submodel_results = results.combine_results()
allresults.add_results(submodel_results)
base_port += len(models.models)
final_results = allresults.combine_results()
logging.info("saving results...")
final_results.save(options.output[1] + ".pickle")
elif options.actions == "test_relations":
if options.kernel == "jsre":
model = JSREKernel(corpus, options.ptype, train=False, modelname=options.tag, ner=options.models)
elif options.kernel == "svmtk":
model = SVMTKernel(corpus, options.ptype, modelname=options.tag, ner=options.models)
elif options.kernel == "rules":
model = RuleClassifier(corpus, options.ptype, ner=options.models)
elif options.kernel == "mirtex_rules":
model = MirtexClassifier(corpus, options.ptype)
elif options.kernel == "stanfordre":
model = StanfordRE(corpus, options.ptype)
elif options.kernel == "scikit":
model = ScikitRE(corpus, options.ptype)
elif options.kernel == "crf":
model = CrfSuiteRE(corpus, options.ptype, test=True)
elif options.kernel == "mil":
relations = set()
with open("corpora/transmir/transmir_relations.txt") as rfile:
for l in rfile:
relations.add(tuple(l.strip().split('\t')))
model = MILClassifier(corpus, options.ptype, relations, test=True, ner=options.models)
model.load_classifier()
model.test()
results = model.get_predictions(corpus)
results.save(options.output[1] + ".pickle")
total_time = time.time() - start_time
logging.info("Total time: %ss" % total_time)
