def test_is_duration_events(self):
schema = StructType([
StructField("patientID", IntegerType(), True),
StructField("start", TimestampType(), True),
StructField("end", TimestampType(), True),
])
patients_pd = pd.DataFrame({"patientID": [1, 2, 3]})
patients = self.spark.createDataFrame(patients_pd)
cohort1 = Cohort("patients", "patients", patients, None)
self.assertFalse(cohort1.is_duration_events())
data = [(1, datetime(1993, 10, 9), datetime(1993, 10, 9))]
events = self.spark.createDataFrame(data=data, schema=schema)
cohort2 = Cohort("patients", "patients", patients, events)
self.assertTrue(cohort2.is_duration_events())
data = [(1, datetime(1993, 10, 9), None),
(2, datetime(1993, 10, 9), None)]
events = self.spark.createDataFrame(data=data, schema=schema)
cohort2 = Cohort("patients", "patients", patients, events)
self.assertFalse(cohort2.is_duration_events())
def plot_mean_duration_per_value(figure: Figure, cohort: Cohort) -> Figure:
assert cohort.is_duration_events()
df = agg_by_col(cohort.events, frozenset(["value"]), "duration",
"mean").sort_values("value")
ax = figure.gca()
ax.barh(range(len(df.value)), df["avg(duration)"].values)
ax.set_yticklabels(df.value.values)
ax.set_yticks(range(len(df.value)))
return figure
def plot_duration_distribution_per_month_as_bar(figure: Figure,
cohort: Cohort) -> Figure:
assert cohort.is_duration_events()
df = event_duration_agg(cohort, "count").sort_values("duration")
df.duration = np.ceil(df.duration / 30)
df.duration = df.duration.astype("int32")
df = df.groupby("duration").sum().reset_index()
ax = figure.gca()
ax.bar(range(len(df)), df["count(1)"].values)
ax.set_xticklabels(df.duration.values)
ax.set_xticks(range(len(df)))
return figure
def plot_duration_distribution_per_day_as_line(figure: Figure,
cohort: Cohort) -> Figure:
assert cohort.is_duration_events()
df = event_duration_agg(cohort, "count").sort_values("duration")
ax = figure.gca()
ax.plot(df.duration, df["count(1)"])
ax.set_yscale("log")
major = IndexLocator(365, +0.0)
minor = IndexLocator(30, +0.0)
ax.xaxis.set_minor_locator(minor)
ax.xaxis.set_major_locator(major)
ax.grid(True, which="major", axis="x")
return figure
