Diff of
/tests/pipeline/test_deduce.py
[000000]
..
[79668b]
Switch to unified view
| a | b/tests/pipeline/test_deduce.py | ||
|---|---|---|---|
| 1 | import docdeid as dd |
||
| 2 | |||
| 3 | from deduce.person import Person |
||
| 4 | |||
| 5 | text = ( |
||
| 6 | "betreft: Jan Jansen, bsn 111222333, patnr 000334433. De patient J. Jansen is 64 " |
||
| 7 | "jaar oud en woonachtig in Utrecht. Hij werd op 10 oktober 2018 door arts " |
||
| 8 | "Peter de Visser ontslagen van de kliniek van het UMCU. Voor nazorg kan hij " |
||
| 9 | "worden bereikt via j.JNSEN.123@gmail.com of (06)12345678." |
||
| 10 | ) |
||
| 11 | |||
| 12 | |||
| 13 | class TestDeduce: |
||
| 14 | def test_annotate(self, model): |
||
| 15 | metadata = {"patient": Person(first_names=["Jan"], surname="Jansen")} |
||
| 16 | doc = model.deidentify(text, metadata=metadata) |
||
| 17 | |||
| 18 | expected_annotations = dd.AnnotationSet( |
||
| 19 | [ |
||
| 20 | dd.Annotation( |
||
| 21 | text="(06)12345678", |
||
| 22 | start_char=272, |
||
| 23 | end_char=284, |
||
| 24 | tag="telefoonnummer", |
||
| 25 | ), |
||
| 26 | dd.Annotation(text="111222333", start_char=25, end_char=34, tag="bsn"), |
||
| 27 | dd.Annotation( |
||
| 28 | text="Peter de Visser", start_char=153, end_char=168, tag="persoon" |
||
| 29 | ), |
||
| 30 | dd.Annotation( |
||
| 31 | text="j.JNSEN.123@gmail.com", |
||
| 32 | start_char=247, |
||
| 33 | end_char=268, |
||
| 34 | tag="emailadres", |
||
| 35 | ), |
||
| 36 | dd.Annotation( |
||
| 37 | text="J. Jansen", start_char=64, end_char=73, tag="patient" |
||
| 38 | ), |
||
| 39 | dd.Annotation( |
||
| 40 | text="Jan Jansen", start_char=9, end_char=19, tag="patient" |
||
| 41 | ), |
||
| 42 | dd.Annotation( |
||
| 43 | text="10 oktober 2018", start_char=127, end_char=142, tag="datum" |
||
| 44 | ), |
||
| 45 | dd.Annotation(text="64", start_char=77, end_char=79, tag="leeftijd"), |
||
| 46 | dd.Annotation(text="000334433", start_char=42, end_char=51, tag="id"), |
||
| 47 | dd.Annotation( |
||
| 48 | text="Utrecht", start_char=106, end_char=113, tag="locatie" |
||
| 49 | ), |
||
| 50 | dd.Annotation( |
||
| 51 | text="UMCU", start_char=202, end_char=206, tag="ziekenhuis" |
||
| 52 | ), |
||
| 53 | ] |
||
| 54 | ) |
||
| 55 | |||
| 56 | assert doc.annotations == set(expected_annotations) |
||
| 57 | |||
| 58 | def test_deidentify(self, model): |
||
| 59 | metadata = {"patient": Person(first_names=["Jan"], surname="Jansen")} |
||
| 60 | doc = model.deidentify(text, metadata=metadata) |
||
| 61 | |||
| 62 | expected_deidentified = ( |
||
| 63 | "betreft: [PATIENT], bsn [BSN-1], patnr [ID-1]. De patient [PATIENT] is " |
||
| 64 | "[LEEFTIJD-1] jaar oud en woonachtig in [LOCATIE-1]. Hij werd op " |
||
| 65 | "[DATUM-1] door arts [PERSOON-1] ontslagen van de kliniek van het " |
||
| 66 | "[ZIEKENHUIS-1]. Voor nazorg kan hij worden bereikt via [EMAILADRES-1] " |
||
| 67 | "of [TELEFOONNUMMER-1]." |
||
| 68 | ) |
||
| 69 | |||
| 70 | assert doc.deidentified_text == expected_deidentified |
||
| 71 | |||
| 72 | def test_annotate_intext(self, model): |
||
| 73 | metadata = {"patient": Person(first_names=["Jan"], surname="Jansen")} |
||
| 74 | doc = model.deidentify(text, metadata=metadata) |
||
| 75 | |||
| 76 | expected_intext_annotated = ( |
||
| 77 | "betreft: <PATIENT>Jan Jansen</PATIENT>, bsn <BSN>111222333</BSN>, " |
||
| 78 | "patnr <ID>000334433</ID>. De patient <PATIENT>J. Jansen</PATIENT> is " |
||
| 79 | "<LEEFTIJD>64</LEEFTIJD> jaar oud en woonachtig in <LOCATIE>Utrecht" |
||
| 80 | "</LOCATIE>. Hij werd op <DATUM>10 oktober 2018</DATUM> door arts " |
||
| 81 | "<PERSOON>Peter de Visser</PERSOON> ontslagen van de kliniek van het " |
||
| 82 | "<ZIEKENHUIS>UMCU</ZIEKENHUIS>. Voor nazorg kan hij worden bereikt " |
||
| 83 | "via <EMAILADRES>j.JNSEN.123@gmail.com</EMAILADRES> of " |
||
| 84 | "<TELEFOONNUMMER>(06)12345678</TELEFOONNUMMER>." |
||
| 85 | ) |
||
| 86 | |||
| 87 | assert dd.utils.annotate_intext(doc) == expected_intext_annotated |