def main():
my_format_string='%(asctime)s %(levelname)s %(module)s.' \
'%(funcName)s: %(message)s'
logging.basicConfig(level=logging.INFO, format=my_format_string)
chunkmap = chunkmap_factory(
pickle.load(bz2.BZ2File('test_data/5th.chunkmap.bz2')))
semrep_reader = SemrepOutput(bz2.BZ2File('test_data/5th.semrep.out.bz2'),
DEFAULT_LINES_TO_IGNORE, chunkmap)
tfidf = TF_IDF(file_mode="c")
tfidf.build_tf_from_file(semrep_reader)
semrep_reader.rewind()
semrep_grapher = SemrepCooccurrenceGraphBuilder(
node_weight_threshold=0.001,
link_weight_threshold=0.003,
tf_idf_provider=tfidf)
eval_params = EvaluationParameters()
eval_params.alpha = 0.65
work = myWorkflow(semrep_reader, semrep_grapher, TextRanker(), eval_params,
PAGERANK_CUTOFF, MESH_TREE_FILE, SAVCC_MATRIX_FILE,
lambda x: 1.0 / math.exp(x) if x >= 0 and x < 5 else 0.0,
UMLS_CONVERTER_DATA, UMLS_CONCEPT_DATA,
open(OUTPUT_FILE, 'w'))
work.run()
def main():
my_format_string='%(asctime)s %(levelname)s %(module)s.' \
'%(funcName)s: %(message)s'
logging.basicConfig(level=logging.INFO,
format=my_format_string)
chunkmap=chunkmap_factory(pickle.load(
bz2.BZ2File('test_data/5th.chunkmap.bz2')))
semrep_reader=SemrepOutput(bz2.BZ2File('test_data/5th.semrep.out.bz2'),
DEFAULT_LINES_TO_IGNORE,
chunkmap)
tfidf=TF_IDF(file_mode="c")
tfidf.build_tf_from_file(semrep_reader)
semrep_reader.rewind()
semrep_grapher=SemrepCooccurrenceGraphBuilder(node_weight_threshold=0.001,
link_weight_threshold=0.003,
tf_idf_provider=tfidf
)
eval_params=EvaluationParameters()
eval_params.alpha=0.65
work=myWorkflow(semrep_reader, semrep_grapher, TextRanker(), eval_params,
PAGERANK_CUTOFF, MESH_TREE_FILE, SAVCC_MATRIX_FILE,
lambda x: 1.0/math.exp(x) if x>=0 and x<5 else 0.0,
UMLS_CONVERTER_DATA, UMLS_CONCEPT_DATA,
open(OUTPUT_FILE, 'w'))
work.run()
def __init__(self, fileobject, lines_to_ignore, chunkmap, converter):
SemrepOutput.__init__(self,
fileobject,
lines_to_ignore=lines_to_ignore,
chunkmap=chunkmap)
self._my_converter = converter
self.line_type = self.line_factory
def setUp(self):
# Test setup borrowed from semrep.py
from MEDRank.file.semrep import (SemrepOutput)
from MEDRank.file.metamap import (MetamapOutput)
from MEDRank.file.chunkmap import chunkmap_factory
import StringIO
# logging.basicConfig(level=logging.DEBUG,
# format='%(asctime)s %(levelname)s %(message)s')
# This fakefile is NOT the same as semrep.py - this one has a
# relationship that should not be part of the graph, and one that
# should
sr_file = StringIO.StringIO("SE|0000000000||ti|2|entity|Affecting|"
"ftcn|C0392760|involved||||1000|319|326\n"
"SE|0000000000||ti|2|entity|Involvement"
"with|ftcn|C1314939|involved||"
"||1000|319|326\n"
"SE|0000000000||ti|2|relation|||Steroid"
"hormone|horm,strd|horm|C0301818|"
"||||||||901|115|130||INTERACTS_WITH"
"||379|385|||steroid hormone"
"receptor|gngm,aapp,rcpt|gngm|C0597519"
"||None|steroid hormone receptors|their"
" respective steroid hormone"
" receptors|||||890|390|431\n"
"SE|0000000000||ti|2|relation|||Affection"
"|horm,strd|horm|C0392760|"
"||||||||901|115|130||INTERACTS_WITH"
"||379|385|||Involvement"
"with|gngm,aapp,rcpt|gngm|C1314939"
"||None|steroid hormone receptors|their"
" respective steroid hormone"
" receptors|||||890|390|431\n"
"USELESS LINE!\n"
"SE|0000000000||ti|3|text|Coactivator and"
" corepressor proteins have recently been"
" identified that interact with steroid"
" hormone receptors and modulate"
" transcriptional activation\n")
fake_chunkmap = chunkmap_factory({'123.txt': [0]})
self.sro = SemrepOutput(sr_file, ["USELESS LINE!"], fake_chunkmap)
def __init__(self, fileobject, lines_to_ignore, chunkmap, converter):
SemrepOutput.__init__(self, fileobject,
lines_to_ignore=lines_to_ignore,
chunkmap=chunkmap)
self._my_converter=converter
self.line_type=self.line_factory
