ibis 测试

import ibis

import pandas as pd

from ibis import _

penguins = ibis.examples.penguins.fetch()

df = pd.DataFrame(

    [["a", 1, 2], ["b", 3, 4]],

    columns=["one", "two", "three"],

    index=[5, 6],

)

t = ibis.memtable(df, name="t")

(penguins.filter([_.species == "Adelie", _.island.isin(["Biscoe", "Dream"])]))

(penguins.limit(11, offset=9))

(penguins.order_by([_.island, _.bill_length_mm.desc()]))

(penguins.select(_.bill_length_mm, _.sex))

(penguins.rename(bill_length="bill_length_mm", bill_depth="bill_depth_mm"))

(

    penguins.mutate(ones=1, bill_length=_.bill_length_mm / 10)

    .mutate(bill_length_squared=_.bill_length**2)

    .select(_.ones, _.bill_length_mm, _.bill_length, _.bill_length_squared)

)

(

    penguins.select(

        _.island,

        _.bill_depth_mm,

        _.flipper_length_mm,

        _.body_mass_g,

        _.species,

        _.bill_length_mm,

        _.sex,

    )

)

(

    penguins.group_by("island")

    .aggregate(bill_depth_mean=_.bill_depth_mm.mean())

    .order_by("island")

)

(

    penguins.group_by("island")

    .aggregate(

        count=_.count(),

        bill_depth_mean=_.bill_depth_mm.mean(),

        flipper_length_median=_.flipper_length_mm.median(),

        body_mass_sd=_.body_mass_g.std(),

        share_female=(_.sex == "female").mean(),

    )

    .order_by("island")

)

person = ibis.memtable(person2)

#delta 计算间隔 timestamps

person=(

    person.mutate(

        vacc_age=(_.vaccination_date.delta(_.birth_date,'days')/365.25).floor().cast('int64')

    )

    .mutate(

        age_group=ibis.case()

        .when(_.vacc_age < 1, '幼年')

        .when((_.vacc_age >= 1) & (_.vacc_age < 18), '青少年')

        .else_('成年')

        .end()

    )

)

(

    person.group_by("age_group")

    .aggregate(

        count=_.count(),

        max_age=_.vacc_age.max(),

        min_age=_.vacc_age.min()

    )

)