def test_from_dict_error(self):
d = dict(
literal="pneumonia",
category="CONDITION",
invalid="this is an invalid key",
)
with pytest.raises(ValueError):
TargetRule.from_dict(d)
def load():
import medspacy
nlp = medspacy.load(enable=["sentencizer", "tokenizer"])
# Add components
from medspacy.target_matcher import TargetMatcher, TargetRule
target_matcher = TargetMatcher(nlp)
target_filepath = path.join(RESOURCES_DIR, "target_rules.json")
target_rules = TargetRule.from_json(target_filepath)
target_matcher.add(target_rules)
nlp.add_pipe(target_matcher)
from medspacy.context import ConTextComponent, ConTextRule
context_filepath = path.join(RESOURCES_DIR, "context_rules.json")
context = ConTextComponent(nlp, rules=None, add_attrs=CONTEXT_ATTRS)
context_rules = ConTextRule.from_json(context_filepath)
context.add(context_rules)
nlp.add_pipe(context)
from medspacy.section_detection import Sectionizer
# TODO: Add radiology section rules
sectionizer = Sectionizer(nlp)
nlp.add_pipe(sectionizer)
clf = DocumentClassifier(nlp)
nlp.add_pipe(clf)
return nlp
def test_to_json(self):
import json, os
dname = os.path.join(tmpdirname.name, "test_target_rules.json")
literal = "pneumonia"
category = "CONDITION"
item = TargetRule(literal, category)
TargetRule.to_json([item], dname)
with open(dname) as f:
data = json.load(f)
assert "target_rules" in data
assert len(data["target_rules"]) == 1
rule_dict = data["target_rules"][0]
for key in ["literal", "category"]:
assert key in rule_dict
def test_add_rule_pattern(self):
matcher = TargetMatcher(nlp)
matcher.add([TargetRule("PE", "CONDITION", pattern=[{"LOWER": "pe"}])])
doc = nlp("Past Medical History: Pe")
matcher(doc)
assert len(doc.ents) == 1
assert (doc.ents[0].start, doc.ents[0].end) == (4, 5)
assert doc.ents[0].label_ == "CONDITION"
def test_basic_rule(self):
matcher = TargetMatcher(nlp)
matcher.add([TargetRule("PE", "CONDITION")])
doc = nlp("Past Medical History: PE")
matcher(doc)
assert len(doc.ents) == 1
assert (doc.ents[0].start, doc.ents[0].end) == (4, 5)
assert doc.ents[0].label_ == "CONDITION"
def test_add_rule_regex(self):
matcher = TargetMatcher(nlp)
matcher.add(
[TargetRule("PE", "CONDITION", pattern="pulmonary embolisms?")])
doc = nlp("Past Medical History: Pulmonary embolism")
matcher(doc)
assert len(doc.ents) == 1
assert (doc.ents[0].start, doc.ents[0].end) == (4, 6)
assert doc.ents[0].label_ == "CONDITION"
def test_add_ents_false(self):
matcher = TargetMatcher(nlp, add_ents=False)
matcher.add([TargetRule("PE", "CONDITION")])
doc = nlp("Past Medical History: PE")
spans = matcher(doc)
assert len(doc.ents) == 0
assert len(spans) == 1
assert isinstance(spans[0], spacy.tokens.Span)
import pytest
import os
import tempfile
from medspacy.io.db_connect import DbConnect
import sqlite3
import medspacy
from medspacy.target_matcher import TargetRule
from medspacy.io import DocConsumer
tmpdirname = tempfile.TemporaryDirectory()
db = os.path.join(tmpdirname.name, "test")
nlp = medspacy.load(enable=["sentencizer", "target_matcher", "context", "sectionizer"])
nlp.get_pipe("target_matcher").add(TargetRule("pneumonia", "CONDITION"))
doc = nlp("There is no evidence of pneumonia.")
doc_consumer = DocConsumer(nlp)
doc_consumer(doc)
class TestDbWriter:
def test_init_from_sqlite3_conn_defaults(self):
"""Test writing with default values for ent attributes."""
sq_conn = sqlite3.connect(db)
cursor = sq_conn.cursor()
db_conn = DbConnect(conn=sq_conn)
from medspacy.io.db_writer import DbWriter
import tempfile
from medspacy.io.db_connect import DbConnect
import sqlite3
import medspacy
from medspacy.target_matcher import TargetRule
from medspacy.io import DocConsumer
tmpdirname = tempfile.TemporaryDirectory()
db = os.path.join(tmpdirname.name, "test")
nlp = medspacy.load(
enable=["pyrush", "target_matcher", "context", "sectionizer"])
nlp.get_pipe("medspacy_target_matcher").add(
TargetRule("pneumonia", "CONDITION"))
doc = nlp("There is no evidence of pneumonia.")
doc_consumer = DocConsumer(nlp)
doc_consumer(doc)
class TestDbWriter:
def test_init_from_sqlite3_conn_defaults(self):
"""Test writing with default values for ent attributes."""
sq_conn = sqlite3.connect(db)
cursor = sq_conn.cursor()
db_conn = DbConnect(conn=sq_conn)
from medspacy.io.db_writer import DbWriter
writer = DbWriter(db_conn,
def test_from_json(self, from_json_file):
assert TargetRule.from_json(from_json_file)
def test_from_dict(self):
d = dict(literal="pneumonia", category="CONDITION")
assert TargetRule.from_dict(d)
def test_inherits_from_base_rule(self):
rule = TargetRule("pneumonia", "CONDITION")
assert isinstance(rule, BaseRule)
def test_initiate(self):
assert TargetRule("pneumonia", "CONDITION")
import pytest
import os
import tempfile
import medspacy
from medspacy.target_matcher import TargetRule
from medspacy.io import DocConsumer
tmpdirname = tempfile.TemporaryDirectory()
db = os.path.join(tmpdirname.name, "test.db")
# Set up a simple pipeline which will allow us to write results
nlp = medspacy.load(
enable=["pyrush", "target_matcher", "context", "sectionizer"])
nlp.get_pipe("medspacy_target_matcher").add([
TargetRule("pneumonia", "CONDITION"),
TargetRule("breast ca", "CONDITION")
])
doc = nlp("There is no evidence of pneumonia.")
doc_consumer = DocConsumer(
nlp,
dtype_attrs={"ent": ["text", "label_", "is_negated", "section_category"]})
nlp.add_pipe("medspacy_doc_consumer",
config={
"dtype_attrs": {
"ent":
["text", "label_", "is_negated", "section_category"]
}
})
def test_add(self):
matcher = TargetMatcher(nlp)
matcher.add([TargetRule("my direction", "RULE")])
assert matcher._rules
