def test_make_df_from_expectations_with_distribution_and_date():
study = StudyDefinition(
population=patients.all(),
bmi=patients.most_recent_bmi(
on_or_after="2010-02-01",
minimum_age_at_measurement=16,
return_expectations={
"rate": "exponential_increase",
"incidence": 0.6,
"float": {
"distribution": "normal",
"mean": 35,
"stddev": 10
},
"date": {
"earliest": "1900-01-01",
"latest": "today"
},
},
),
bmi_date_measured=patients.date_of(
"bmi",
date_format="YYYY-MM",
),
)
population_size = 10000
result = study.make_df_from_expectations(population_size)
assert list(sorted(result.columns)) == ["bmi", "bmi_date_measured"]
# Check that the null-valued rows are aligned with each other
assert ((result["bmi"] == 0.0) == pd.isnull(
result["bmi_date_measured"])).all()
def test_clinical_events_numeric_value_dtype_generation():
test_codelist = codelist(["X"], system="ctv3")
study = StudyDefinition(
population=patients.all(),
creatinine=patients.with_these_clinical_events(
test_codelist,
find_last_match_in_period=True,
on_or_before="2020-02-01",
returning="numeric_value",
),
creatinine_date=patients.date_of("creatinine", date_format="YYYY-MM"),
)
result = _converters_to_names(study.pandas_csv_args)
assert result == {
"converters": {
"creatinine_date": "add_day_to_date"
},
"dtype": {
"creatinine": "float"
},
"date_col_for": {
"creatinine": "creatinine_date"
},
"parse_dates": ["creatinine_date"],
}
def test_categorical_clinical_events_with_date_dtype_generation():
categorised_codelist = codelist([("X", "Y")], system="ctv3")
categorised_codelist.has_categories = True
study = StudyDefinition(
population=patients.all(),
ethnicity=patients.with_these_clinical_events(
categorised_codelist,
returning="category",
find_last_match_in_period=True,
),
ethnicity_date=patients.date_of("ethnicity"),
)
result = _converters_to_names(study.pandas_csv_args)
assert result == {
"converters": {
"ethnicity_date": "add_month_and_day_to_date"
},
"date_col_for": {
"ethnicity": "ethnicity_date"
},
"dtype": {
"ethnicity": "category"
},
"parse_dates": ["ethnicity_date"],
}
def test_bmi_dtype_generation():
categorised_codelist = codelist([("X", "Y")], system="ctv3")
categorised_codelist.has_categories = True
study = StudyDefinition(
population=patients.all(),
bmi=patients.most_recent_bmi(
on_or_after="2010-02-01",
minimum_age_at_measurement=16,
),
bmi_date_measured=patients.date_of("bmi", date_format="YYYY-MM"),
)
result = _converters_to_names(study.pandas_csv_args)
assert result == {
"converters": {
"bmi_date_measured": "add_day_to_date"
},
"dtype": {
"bmi": "float"
},
"date_col_for": {
"bmi": "bmi_date_measured"
},
"parse_dates": ["bmi_date_measured"],
}
def test_mean_recorded_value_dtype_generation():
test_codelist = codelist(["X"], system="ctv3")
study = StudyDefinition(
population=patients.all(),
bp_sys=patients.mean_recorded_value(
test_codelist,
on_most_recent_day_of_measurement=True,
on_or_before="2020-02-01",
),
bp_sys_date_measured=patients.date_of("bp_sys", date_format="YYYY-MM"),
)
result = _converters_to_names(study.pandas_csv_args)
assert result == {
"converters": {"bp_sys_date_measured": "add_day_to_date"},
"dtype": {"bp_sys": "float"},
"date_col_for": {"bp_sys": "bp_sys_date_measured"},
"parse_dates": ["bp_sys_date_measured"],
}
