Add function to insert LOINC related names (#73)

## Description

This PR add a function to randomly insert a number of LOINC related
names (according to the min and max inserts) into a given string.

## Related Issues
Closes #65 

## Additional Notes
I didn't add any of the functionality to parse the appropriate related
names for a given LOINC `text`, figuring that would be a separate
function.

Also made some small changes to the script to pull down LOINCs that I
needed to get it running.

<--------------------- REMOVE THE LINES BELOW BEFORE MERGING
--------------------->

## Checklist

Please review and complete the following checklist before submitting
your pull request:

- [ ] I have ensured that the pull request is of a manageable size,
allowing it to be reviewed within a single session.
- [ ] I have reviewed my changes to ensure they are clear, concise, and
well-documented.
- [ ] I have updated the documentation, if applicable.
- [ ] I have added or updated test cases to cover my changes, if
applicable.
- [ ] I have minimized the number of reviewers to include only those
essential for the review.

## Checklist for Reviewers

Please review and complete the following checklist during the review
process:

- [ ] The code follows best practices and conventions.
- [ ] The changes implement the desired functionality or fix the
reported issue.
- [ ] The tests cover the new changes and pass successfully.
- [ ] Any potential edge cases or error scenarios have been considered.

Author: m-goggins

scripts/terminology_valueset_sync.py

@@ -30,6 +30,7 @@
 
 load_dotenv()
 
+
 # Set Terminology URLS
 LOINC_BASE_URL = "https://loinc.regenstrief.org/searchapi/loincs?"
 LOINC_LAB_ORDER_SUFFIX = "query=orderobs:Order+OR+orderobs:Both&rows=500"

src/dibbs_text_to_code/augmentation.py

@@ -31,3 +31,35 @@ def scramble_word_order(
         words.insert(new_pos, word)
 
     return " ".join(words)
+
+
+def insert_loinc_related_names(
+    text: str, loinc_names: list[str], max_inserts: int, min_inserts: int = 1
+) -> str:
+    """
+    Inserts 1 or more LOINC related names into the input text at random positions.
+
+    :param text: The input text to modify.
+    :param loinc_names: A list of LOINC related names to insert.
+    :param num_inserts: The number of LOINC names to insert.
+    :return: The text with LOINC related name(s) inserted.
+    """
+    words = text.split()
+    if not loinc_names or len(words) < 1:
+        return text
+
+    # Ensure num_inserts does not exceed the number of loinc_names
+    num_inserts = random.randint(min_inserts, min(len(loinc_names), max_inserts))
+
+    # Select indices to insert at (can repeat)
+    indices_to_insert = [random.randrange(len(words) + 1) for _ in range(num_inserts)]
+
+    # Select unique LOINC names to insert
+    loinc_names_to_insert = random.sample(loinc_names, num_inserts)
+
+    for _ in range(num_inserts):
+        name_to_insert = loinc_names_to_insert.pop()
+        idx_to_insert = indices_to_insert.pop()
+        words.insert(idx_to_insert, name_to_insert)
+
+    return " ".join(words)

tests/unit/test_augmentation.py

@@ -24,3 +24,34 @@ class TestScrambleWordOrder:
     def test_scramble_word_order(self, text, max_perms, expected):
         result = augmentation.scramble_word_order(text, max_perms=max_perms)
         assert result == expected
+
+
+@pytest.mark.parametrize(
+    "text, loinc_names, max_inserts,expected ",
+    [
+        # Empty string
+        ("", ["Blood", "Erythrocytes", "Calculation", "CalcRBC", "Volume fraction"], 3, ""),
+        # Single word
+        (
+            "Blood",
+            ["Blood", "Erythrocytes", "Calculation", "CalcRBC", "Volume fraction"],
+            3,
+            "Erythrocytes Blood Volume fraction",
+        ),
+        # No LOINC names
+        ("Hematocrit of Blood", [], 3, "Hematocrit of Blood"),
+        # More inserts than LOINC names
+        (
+            "Hematocrit [Volume Fraction] of Blood by calculation",
+            ["Blood", "Erythrocytes", "Calculation", "CalcRBC", "Volume fraction"],
+            5,
+            "Erythrocytes Hematocrit [Volume Fraction] of Volume fraction Blood by calculation",
+        ),
+    ],
+)
+class TestInsertLoincRelatedNames:
+    def test_insert_loinc_related_names(self, text, loinc_names, max_inserts, expected):
+        result = augmentation.insert_loinc_related_names(
+            text, loinc_names, min_inserts=2, max_inserts=max_inserts
+        )
+        assert result == expected