def view_single_sentence_graph(sentence, modifiers, targets):
context = markup_context_document(sentence, modifiers, targets)
class_result = classrslts(context_document=context, exam_type="Chest X-Ray", report_text=sentence,
classification_result='N/A')
rview.markup_to_pydot(class_result)
display(Image("tmp.png"))
print(sentence)
def marking_false_negatives(current_false_negatives, modifiers, targets):
fn_report_results = []
print('Marking up False Negatives')
for anno_doc in current_false_negatives.values():
report_context = markup_context_document(anno_doc.text, modifiers, targets)
# package this up into a class that the RadNLP utilities can use
results = classrslts(context_document=report_context, exam_type="Chest X-Ray", report_text=anno_doc.text, classification_result='N/A')
fn_report_results.append(results)
return fn_report_results
def analyze_report(report, modifiers, targets, rules, schema):
"""
given an individual radiology report, creates a pyConTextGraph
object that contains the context markup
report: a text string containing the radiology reports
"""
markup = utils.mark_report(split.get_sentences(report),
modifiers,
targets)
clssfy = classifier.classify_document_targets(markup,
rules[0],
rules[1],
rules[2],
schema)
return classrslts(context_document=markup, exam_type="ctpa", report_text=report, classification_result=clssfy)