def test_make_df_from_expectations_with_mean_recorded_value():
study = StudyDefinition(
population=patients.all(),
drug_x=patients.mean_recorded_value(
codelist(["X"], system="ctv3"),
on_most_recent_day_of_measurement=True,
return_expectations={
"rate": "exponential_increase",
"date": {
"earliest": "1900-01-01",
"latest": "today"
},
"incidence": 0.6,
"float": {
"distribution": "normal",
"mean": 35,
"stddev": 10
},
},
),
)
population_size = 10000
result = study.make_df_from_expectations(population_size)
nonzero_results = result[result["drug_x"] != 0.0]
assert abs(35 - int(nonzero_results["drug_x"].mean())) < 5
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"],
}
minimum_age_at_measurement=16,
include_measurement_date=True,
include_month=True,
return_expectations={
"incidence": 0.6,
"float": {"distribution": "normal", "mean": 35, "stddev": 10},
},
),
# https://github.com/opensafely/risk-factors-research/issues/48
bp_sys=patients.mean_recorded_value(
systolic_blood_pressure_codes,
on_most_recent_day_of_measurement=True,
on_or_before="2020-02-01",
include_measurement_date=True,
include_month=True,
return_expectations={
"incidence": 0.6,
"float": {"distribution": "normal", "mean": 80, "stddev": 10},
},
),
# https://github.com/opensafely/risk-factors-research/issues/48
bp_dias=patients.mean_recorded_value(
diastolic_blood_pressure_codes,
on_most_recent_day_of_measurement=True,
on_or_before="2020-02-01",
include_measurement_date=True,
include_month=True,
return_expectations={
"incidence": 0.6,
return_expectations={"rate" : "universal", "int" : {"distribution" : "population_ages"}}),
## bmi
bmi=patients.most_recent_bmi(between=["2010-02-01", "2020-01-31"],
minimum_age_at_measurement=18, include_measurement_date=True, date_format="YYYY-MM",
return_expectations={"date": {"earliest": "2010-02-01", "latest": "2020-01-31"},
"float": {"distribution": "normal", "mean": 28, "stddev": 8},
"incidence": 0.80,}),
## systolic blood pressure
bp_sys=patients.mean_recorded_value(systolic_blood_pressure_codes,
on_most_recent_day_of_measurement=True,
between=["2017-02-01", "2020-01-31"],
include_measurement_date=True,
date_format="YYYY-MM",
return_expectations={"float": {"distribution": "normal", "mean": 80, "stddev": 10},
"date": {"earliest": "2019-02-01", "latest": "2020-01-31"},
"incidence": 0.95,}),
## ace inhibitor
ace_inhibitor = patients.with_these_medications(ace_inhibitor_codes,
between=["1900-01-01", "2020-02-01"],
include_date_of_match = True,
date_format="YYYY-MM-DD",
returning="binary_flag",
return_expectations = {"incidence": 0.05,
"date": {"earliest": "1980-02-01",
"latest": "2020-01-31"}}),
