def reformat_hist_y_given_by(y: Series | np.ndarray,
by: IndexLabel | None) -> Series | np.ndarray:
"""Internal function to reformat y given `by` is applied or not for hist plot.
If by is None, input y is 1-d with NaN removed; and if by is not None, groupby
will take place and input y is multi-dimensional array.
"""
if by is not None and len(y.shape) > 1:
return np.array([remove_na_arraylike(col) for col in y.T]).T
return remove_na_arraylike(y)
def plot_group(keys, values, ax: Axes):
keys = [pprint_thing(x) for x in keys]
values = [
np.asarray(remove_na_arraylike(v), dtype=object) for v in values
]
bp = ax.boxplot(values, **kwds)
if fontsize is not None:
ax.tick_params(axis="both", labelsize=fontsize)
if kwds.get("vert", 1):
ticks = ax.get_xticks()
if len(ticks) != len(keys):
i, remainder = divmod(len(ticks), len(keys))
assert remainder == 0, remainder
keys *= i
ax.set_xticklabels(keys, rotation=rot)
else:
ax.set_yticklabels(keys, rotation=rot)
maybe_color_bp(bp, **kwds)
# Return axes in multiplot case, maybe revisit later # 985
if return_type == "dict":
return bp
elif return_type == "both":
return BoxPlot.BP(ax=ax, lines=bp)
else:
return ax
def plot_group(keys, values, ax: Axes, **kwds):
# GH 45465: xlabel/ylabel need to be popped out before plotting happens
xlabel, ylabel = kwds.pop("xlabel", None), kwds.pop("ylabel", None)
if xlabel:
ax.set_xlabel(pprint_thing(xlabel))
if ylabel:
ax.set_ylabel(pprint_thing(ylabel))
keys = [pprint_thing(x) for x in keys]
values = [np.asarray(remove_na_arraylike(v), dtype=object) for v in values]
bp = ax.boxplot(values, **kwds)
if fontsize is not None:
ax.tick_params(axis="both", labelsize=fontsize)
# GH 45465: x/y are flipped when "vert" changes
is_vertical = kwds.get("vert", True)
ticks = ax.get_xticks() if is_vertical else ax.get_yticks()
if len(ticks) != len(keys):
i, remainder = divmod(len(ticks), len(keys))
assert remainder == 0, remainder
keys *= i
if is_vertical:
ax.set_xticklabels(keys, rotation=rot)
else:
ax.set_yticklabels(keys, rotation=rot)
maybe_color_bp(bp, **kwds)
# Return axes in multiplot case, maybe revisit later # 985
if return_type == "dict":
return bp
elif return_type == "both":
return BoxPlot.BP(ax=ax, lines=bp)
else:
return ax
def _plot(cls, ax, y, column_num=None, return_type="axes", **kwds):
if y.ndim == 2:
y = [remove_na_arraylike(v) for v in y]
# Boxplot fails with empty arrays, so need to add a NaN
# if any cols are empty
# GH 8181
y = [v if v.size > 0 else np.array([np.nan]) for v in y]
else:
y = remove_na_arraylike(y)
bp = ax.boxplot(y, **kwds)
if return_type == "dict":
return bp, bp
elif return_type == "both":
return cls.BP(ax=ax, lines=bp), bp
else:
return ax, bp
def _plot(cls, ax, y, style=None, bw_method=None, ind=None,
column_num=None, stacking_id=None, **kwds):
from scipy.stats import gaussian_kde
y = remove_na_arraylike(y)
gkde = gaussian_kde(y, bw_method=bw_method)
y = gkde.evaluate(ind)
lines = MPLPlot._plot(ax, ind, y, style=style, **kwds)
return lines
def _plot(cls,
ax,
y,
style=None,
bw_method=None,
ind=None,
column_num=None,
stacking_id=None,
**kwds):
from scipy.stats import gaussian_kde
y = remove_na_arraylike(y)
gkde = gaussian_kde(y, bw_method=bw_method)
y = gkde.evaluate(ind)
lines = MPLPlot._plot(ax, ind, y, style=style, **kwds)
return lines
def plot_group(keys, values, ax):
keys = [pprint_thing(x) for x in keys]
values = [np.asarray(remove_na_arraylike(v)) for v in values]
bp = ax.boxplot(values, **kwds)
if fontsize is not None:
ax.tick_params(axis='both', labelsize=fontsize)
if kwds.get('vert', 1):
ax.set_xticklabels(keys, rotation=rot)
else:
ax.set_yticklabels(keys, rotation=rot)
maybe_color_bp(bp)
# Return axes in multiplot case, maybe revisit later # 985
if return_type == 'dict':
return bp
elif return_type == 'both':
return BoxPlot.BP(ax=ax, lines=bp)
else:
return ax
def nunique(self, dropna: bool = True) -> int:
"""
Return number of unique elements in the object.
Excludes NA values by default.
Parameters
----------
dropna : bool, default True
Don't include NaN in the count.
Returns
-------
int
See Also
--------
DataFrame.nunique: Method nunique for DataFrame.
Series.count: Count non-NA/null observations in the Series.
Examples
--------
>>> s = pd.Series([1, 3, 5, 7, 7])
>>> s
0 1
1 3
2 5
3 7
4 7
dtype: int64
>>> s.nunique()
4
"""
uniqs = self.unique()
if dropna:
uniqs = remove_na_arraylike(uniqs)
return len(uniqs)
def skipna_wrapper(x):
nona = remove_na_arraylike(x)
if len(nona) == 0:
return np.nan
return alternative(nona)
def skipna_wrapper(x):
nona = remove_na_arraylike(x)
if len(nona) == 0:
return np.nan
return alternative(nona)
