def test_make_df_from_expectations_with_categories_expression_validation():
study = StudyDefinition(
population=patients.all(),
category=patients.categorised_as(
{
"A": "sex = 'F'",
"B": "sex = 'M'"
},
sex=patients.sex(),
return_expectations={
"rate": "exponential_increase",
"incidence": 0.2,
"category": {
"ratios": {
"A": 0.3,
"B": 0.6,
"C": 0.1
}
},
"date": {
"earliest": "1900-01-01",
"latest": "today"
},
},
),
)
population_size = 10000
with pytest.raises(ValueError):
study.make_df_from_expectations(population_size)
def test_make_df_from_expectations_with_categories_expression():
study = StudyDefinition(
population=patients.all(),
category=patients.categorised_as(
{
"A": "sex = 'F'",
"B": "sex = 'M'"
},
sex=patients.sex(),
return_expectations={
"rate": "exponential_increase",
"incidence": 0.2,
"category": {
"ratios": {
"A": 0.3,
"B": 0.7
}
},
"date": {
"earliest": "1900-01-01",
"latest": "today"
},
},
),
)
population_size = 10000
result = study.make_df_from_expectations(population_size)
value_counts = result.category.value_counts()
assert value_counts["A"] < value_counts["B"]
def test_patients_categorised_as():
session = make_session()
session.add_all(
[
Patient(
Sex="M",
CodedEvents=[
CodedEvent(CTV3Code="foo1", ConsultationDate="2000-01-01")
],
),
Patient(
Sex="F",
CodedEvents=[
CodedEvent(CTV3Code="foo2", ConsultationDate="2000-01-01"),
CodedEvent(CTV3Code="bar1", ConsultationDate="2000-01-01"),
],
),
Patient(
Sex="M",
CodedEvents=[
CodedEvent(CTV3Code="foo2", ConsultationDate="2000-01-01")
],
),
Patient(
Sex="F",
CodedEvents=[
CodedEvent(CTV3Code="foo3", ConsultationDate="2000-01-01")
],
),
]
)
session.commit()
foo_codes = codelist([("foo1", "A"), ("foo2", "B"), ("foo3", "C")], "ctv3")
bar_codes = codelist(["bar1"], "ctv3")
study = StudyDefinition(
population=patients.all(),
category=patients.categorised_as(
{
"W": "foo_category = 'B' AND female_with_bar",
"X": "sex = 'F' AND (foo_category = 'B' OR foo_category = 'C')",
"Y": "sex = 'M' AND foo_category = 'A'",
"Z": "DEFAULT",
},
sex=patients.sex(),
foo_category=patients.with_these_clinical_events(
foo_codes, returning="category", find_last_match_in_period=True
),
female_with_bar=patients.satisfying(
"has_bar AND sex = 'F'",
has_bar=patients.with_these_clinical_events(bar_codes),
),
),
)
results = study.to_dicts()
assert [x["category"] for x in results] == ["Y", "W", "Z", "X"]
# Assert that internal columns do not appear
assert "foo_category" not in results[0].keys()
assert "female_with_bar" not in results[0].keys()
assert "has_bar" not in results[0].keys()
smoking_status=patients.categorised_as(
{
"S": "most_recent_smoking_code = 'S'",
"E": """
most_recent_smoking_code = 'E' OR (
most_recent_smoking_code = 'N' AND ever_smoked
)
""",
"N": "most_recent_smoking_code = 'N' AND NOT ever_smoked",
"M": "DEFAULT",
},
return_expectations={
"category": {
"ratios": {
"S": 0.6,
"E": 0.1,
"N": 0.2,
"M": 0.1
}
}
},
most_recent_smoking_code=patients.with_these_clinical_events(
clear_smoking_codes,
find_last_match_in_period=True,
on_or_before="2020-02-29",
returning="category",
),
ever_smoked=patients.with_these_clinical_events(
filter_codes_by_category(clear_smoking_codes, include=["S", "E"]),
on_or_before="2020-02-29",
),
),
include_measurement_date=True,
include_month=True,
),
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/6
smoking_status=patients.categorised_as(
{
"S": "most_recent_smoking_code = 'S'",
"E": """
most_recent_smoking_code = 'E' OR (
most_recent_smoking_code = 'N' AND ever_smoked
)
""",
"N": "most_recent_smoking_code = 'N' AND NOT ever_smoked",
"M": "DEFAULT"
},
most_recent_smoking_code=patients.with_these_clinical_events(
clear_smoking_codes,
find_last_match_in_period=True,
on_or_before='2020-02-01',
returning="category",
),
ever_smoked=patients.with_these_clinical_events(
filter_codes_by_category(clear_smoking_codes, include=['S', 'E']),
on_or_before='2020-02-01'
),
),
smoking_status_date=patients.with_these_clinical_events(
clear_smoking_codes,
on_or_before='2020-02-01',
return_last_date_in_period=True,
include_month=True,