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_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"],
}
return_last_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-02-29"
}},
),
ckd=first_diagnosis_in_period(ckd_codes),
organ_transplant=first_diagnosis_in_period(organ_transplant_codes),
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/10
bmi=patients.most_recent_bmi(
on_or_after="2010-02-01",
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/ebmdatalab/tpp-sql-notebook/issues/54
stp=patients.registered_practice_as_of(
"2020-03-01",
returning="stp_code",
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"STP1": 0.5,
# define the study index date
index_date = "2020-01-01",
# define the study population
population = patients.all(),
# define the study variables
age = patients.age_as_of("2020-02-01",
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
with_complete_gp_consultation_history_between(
"2019-02-01",
"2020-01-31",
return_expectations={"incidence": 0.9},
),
# CONTINUOUS MEASURED COVARIATES IN 12 MONTHS PRIOR TO BASELINE (10 years for BMI)
bmi=patients.most_recent_bmi(
between=["2010-02-01", "2020-01-31"],
minimum_age_at_measurement=16,
include_measurement_date=True,
include_month=True,
return_expectations={
"date": {
"earliest": "2010-02-01",
"latest": "2020-01-31"
},
"float": {
"distribution": "normal",
"mean": 35,
"stddev": 10
},
"incidence": 0.95,
},
),
# 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,
"5": 0.19,
}
},
},
),
# BMI
bmi=patients.categorised_as(
{
"Not obese": "DEFAULT",
"Obese I (30-34.9)": """ bmi_value >= 30 AND bmi_value < 35""",
"Obese II (35-39.9)": """ bmi_value >= 35 AND bmi_value < 40""",
"Obese III (40+)": """ bmi_value >= 40 AND bmi_value < 100""",
# set maximum to avoid any impossibly extreme values being classified as obese
},
bmi_value=patients.most_recent_bmi(on_or_after="2015-12-01",
minimum_age_at_measurement=16),
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"Not obese": 0.7,
"Obese I (30-34.9)": 0.1,
"Obese II (35-39.9)": 0.1,
"Obese III (40+)": 0.1,
}
},
},
),
# CLINICAL CO-MORBIDITIES WORK IN PROGRESS IN COLLABORATION WITH NHSX
# https://github.com/opensafely/vaccine-eligibility/blob/master/analysis/study_definition.py
