def test_annotation_stripes_continuous_transformed():
pdf = mtcars.assign(am=pd.Categorical(mtcars.am))
p = (ggplot(pdf) +
annotation_stripes(fills=["red", "green", "blue"], alpha=0.1) +
geom_jitter(aes("hp", "wt", color="am"), random_state=5) +
scale_x_continuous(trans='log2'))
assert p == "annotation_stripes_continuous_transformed"
def test_annotation_stripes_continuous():
pdf = mtcars.assign(am=pd.Categorical(mtcars.am))
p = (ggplot(pdf) + annotation_stripes(
fills=["red", "green", "blue"], alpha=0.4, size=1, linetype="dashed") +
geom_jitter(aes("gear", "wt", color="am"), random_state=5))
assert p == "annotation_stripes_continuous"
def test_as_type_kwargs():
with pytest.raises(ValueError):
dp(mtcars).astype(X.columns, int).pd
actual = dp(mtcars).astype(X.columns, int, errors="ignore").pd
should = mtcars.assign(
**{x: mtcars[x].astype(int)
for x in mtcars.columns if x != "name"})
assert_frame_equal(should, actual)
def test_select_inverse_with_minus_column_and_normal_column():
# the rule is: if it's ambigous, raise
m2 = mtcars.assign(**{"-name": mtcars.name})
with pytest.raises(ValueError): # this one is ambigous
dp(m2).select("-name").pd
actual = dp(m2).select("--name").pd # this one isn't
assert (actual.columns == [x for x in m2.columns if x not in ["-name"]]).all()
with pytest.raises(KeyError):
dp(m2).select("---name").pd # and this one is not defined
def test_groupby_two_mutate_grouped():
actual = (dp(mtcars).groupby(["cyl", "vs"]).mutate(
grp_rank={grp: sub_df.hp.rank()
for (grp, sub_df) in X.itergroups()}).select(
"grp_rank").ungroup().pd.sort_index())
ac = []
for grp, sub_df in mtcars.groupby(["cyl", "vs"]):
x = sub_df["hp"].rank()
ac.append(x)
ac = pd.concat(ac)
should = mtcars.assign(grp_rank=ac)[["cyl", "vs", "grp_rank"]]
assert_frame_equal(should, actual)
def test_grouped_mutate_callable():
actual = (dp(mtcars).groupby("cyl").mutate(
max_hp=lambda x: x["hp"].max()).select(["cyl", "max_hp",
"name"]).ungroup().pd)
ac = []
for grp, sub_df in mtcars.groupby("cyl"):
x = pd.Series(sub_df["hp"].max(), index=sub_df.index)
ac.append(x)
ac = pd.concat(ac)
should = mtcars.assign(max_hp=ac)[["cyl", "max_hp",
"name"]].sort_values("name")
assert_frame_equal(should, actual.sort_values("name"))
def test_annotation_stripes_double():
pdf = mtcars.assign(gear=pd.Categorical(mtcars.gear),
am=pd.Categorical(mtcars.am))
p = (
ggplot(pdf) + annotation_stripes(
fills=["#0000FF", "#FF0000"], alpha=0.3, direction='vertical') +
annotation_stripes(
fills=["#AAAAAA", "#FFFFFF"], alpha=0.3, direction='horizontal') +
geom_jitter(aes("gear", "wt", shape="gear", color="am"),
random_state=5) +
scale_shape_discrete(guide=guide_legend(order=1)) # work around #229
)
assert p == "annotation_stripes_double"
def test_annotation_stripes_coord_flip():
pdf = mtcars.assign(gear=pd.Categorical(mtcars.gear),
am=pd.Categorical(mtcars.am))
p = (
ggplot(pdf) + annotation_stripes(
fills=["#AAAAAA", "#FFFFFF", "#7F7FFF"], alpha=0.3) + geom_jitter(
aes("gear", "wt", shape="gear", color="am"), random_state=5) +
geom_vline(xintercept=0.5, color="black") +
geom_vline(xintercept=1.5, color="black") +
geom_vline(xintercept=2.5, color="black") +
geom_vline(xintercept=3.5, color="black") +
scale_shape_discrete(guide=guide_legend(order=1)) # work around #229
+ coord_flip())
assert p == "annotation_stripes_coord_flip"
def test_as_type():
actual = dp(mtcars).astype("-hp", str).pd
should = mtcars.assign(
**{x: mtcars[x].astype(str)
for x in mtcars.columns if x != "hp"})
assert_frame_equal(should, actual)
list(zip((mtcars.mpg > 20), (mtcars.cyl == 6)))
mtcars2.loc['Mazda RX4', 'hp'] = 120 # "magic function" __set_item__
mtcars2.loc[:, 'am'] = 99
mtcars2.iloc[:, 8] = pd.Series(range(32))
mtcars2.drop('am', inplace=True)
mtcars2.loc[:, 'am'] = pd.Series(range(32))
mtcars.loc[:, 'am'] = 2 * pd.Series(range(32))
mtcars2.loc[:, 'am'] = list(range(32))
mtcars2.loc[:, 'am'] = pd.Series(range(32)).values
mtcars.assign(am=pd.Series(range(32)))
mtcars2['new_col'] = 0
mtcars2.head()
mtcars2.loc[:, 'new_col2'] = 3
mtcars2.assign(new_col3=mtcars2.hp * 2).head()
mtcars2 = mtcars2.drop(['new_col', 'new_col2'], axis=1)
condition = mtcars2.index.str.contains('Merc')
mtcars2.loc[~condition, :]
# bool ... element-wise
# and ... &