def _calc_box(srs: dd.Series, qntls: da.Array, cfg: Config) -> Dict[str, Any]:
"""
Box plot calculations
"""
# quartiles
data = {
f"qrtl{i + 1}": qntls.loc[qnt].sum()
for i, qnt in enumerate((0.25, 0.5, 0.75))
}
# inter-quartile range
iqr = data["qrtl3"] - data["qrtl1"]
srs_iqr = srs[srs.between(data["qrtl1"] - 1.5 * iqr,
data["qrtl3"] + 1.5 * iqr)]
# lower and upper whiskers
data["lw"], data["uw"] = srs_iqr.min(), srs_iqr.max()
# outliers
otlrs = srs[~srs.between(data["qrtl1"] - 1.5 * iqr, data["qrtl3"] +
1.5 * iqr)]
# randomly sample at most 100 outliers from each partition without replacement
smp_otlrs = otlrs.map_partitions(lambda x: x.sample(min(100, x.shape[0])),
meta=otlrs)
data["otlrs"] = smp_otlrs.values
if cfg.insight.enable:
data["notlrs"] = otlrs.shape[0]
return data
def calc_box(srs: dd.Series, qntls: da.Array) -> Dict[str, Any]:
"""
Box plot calculations
Parameters
----------
srs
one numerical column
qntls
quantiles of the column
"""
data: Dict[str, Any] = {}
# quartiles
data["qrtl1"] = qntls.loc[0.25].sum()
data["qrtl2"] = qntls.loc[0.5].sum()
data["qrtl3"] = qntls.loc[0.75].sum()
iqr = data["qrtl3"] - data["qrtl1"]
srs_iqr = srs[srs.between(data["qrtl1"] - 1.5 * iqr,
data["qrtl3"] + 1.5 * iqr)]
# outliers
otlrs = srs[~srs.between(data["qrtl1"] - 1.5 * iqr, data["qrtl3"] +
1.5 * iqr)]
# randomly sample at most 100 outliers from each partition without replacement
smp_otlrs = otlrs.map_partitions(lambda x: x.sample(min(100, x.shape[0])),
meta=otlrs)
data["lw"] = srs_iqr.min()
data["uw"] = srs_iqr.max()
data["otlrs"] = smp_otlrs.values
## if cfg.insights_enable
data["notlrs"] = otlrs.shape[0]
return data