def _grouped_plot_by_column(
plotf,
data,
columns=None,
by=None,
numeric_only=True,
grid=False,
figsize=None,
ax=None,
layout=None,
return_type=None,
**kwargs,
):
grouped = data.groupby(by)
if columns is None:
if not isinstance(by, (list, tuple)):
by = [by]
columns = data._get_numeric_data().columns.difference(by)
naxes = len(columns)
fig, axes = create_subplots(
naxes=naxes,
sharex=kwargs.pop("sharex", True),
sharey=kwargs.pop("sharey", True),
figsize=figsize,
ax=ax,
layout=layout,
)
_axes = flatten_axes(axes)
# GH 45465: move the "by" label based on "vert"
xlabel, ylabel = kwargs.pop("xlabel", None), kwargs.pop("ylabel", None)
if kwargs.get("vert", True):
xlabel = xlabel or by
else:
ylabel = ylabel or by
ax_values = []
for i, col in enumerate(columns):
ax = _axes[i]
gp_col = grouped[col]
keys, values = zip(*gp_col)
re_plotf = plotf(keys, values, ax, xlabel=xlabel, ylabel=ylabel, **kwargs)
ax.set_title(col)
ax_values.append(re_plotf)
ax.grid(grid)
result = pd.Series(ax_values, index=columns)
# Return axes in multiplot case, maybe revisit later # 985
if return_type is None:
result = axes
byline = by[0] if len(by) == 1 else by
fig.suptitle(f"Boxplot grouped by {byline}")
maybe_adjust_figure(fig, bottom=0.15, top=0.9, left=0.1, right=0.9, wspace=0.2)
return result
def boxplot_frame_groupby(
grouped,
subplots=True,
column=None,
fontsize=None,
rot=0,
grid=True,
ax=None,
figsize=None,
layout=None,
sharex=False,
sharey=True,
**kwds,
):
if subplots is True:
naxes = len(grouped)
fig, axes = create_subplots(
naxes=naxes,
squeeze=False,
ax=ax,
sharex=sharex,
sharey=sharey,
figsize=figsize,
layout=layout,
)
axes = flatten_axes(axes)
ret = pd.Series(dtype=object)
for (key, group), ax in zip(grouped, axes):
d = group.boxplot(
ax=ax, column=column, fontsize=fontsize, rot=rot, grid=grid, **kwds
)
ax.set_title(pprint_thing(key))
ret.loc[key] = d
maybe_adjust_figure(fig, bottom=0.15, top=0.9, left=0.1, right=0.9, wspace=0.2)
else:
keys, frames = zip(*grouped)
if grouped.axis == 0:
df = pd.concat(frames, keys=keys, axis=1)
else:
if len(frames) > 1:
df = frames[0].join(frames[1::])
else:
df = frames[0]
# GH 16748, DataFrameGroupby fails when subplots=False and `column` argument
# is assigned, and in this case, since `df` here becomes MI after groupby,
# so we need to couple the keys (grouped values) and column (original df
# column) together to search for subset to plot
if column is not None:
column = com.convert_to_list_like(column)
multi_key = pd.MultiIndex.from_product([keys, column])
column = list(multi_key.values)
ret = df.boxplot(
column=column,
fontsize=fontsize,
rot=rot,
grid=grid,
ax=ax,
figsize=figsize,
layout=layout,
**kwds,
)
return ret
def scatter_matrix(
frame: DataFrame,
alpha=0.5,
figsize=None,
ax=None,
grid=False,
diagonal="hist",
marker=".",
density_kwds=None,
hist_kwds=None,
range_padding=0.05,
**kwds,
):
df = frame._get_numeric_data()
n = df.columns.size
naxes = n * n
fig, axes = create_subplots(naxes=naxes, figsize=figsize, ax=ax, squeeze=False)
# no gaps between subplots
maybe_adjust_figure(fig, wspace=0, hspace=0)
mask = notna(df)
marker = _get_marker_compat(marker)
hist_kwds = hist_kwds or {}
density_kwds = density_kwds or {}
# GH 14855
kwds.setdefault("edgecolors", "none")
boundaries_list = []
for a in df.columns:
values = df[a].values[mask[a].values]
rmin_, rmax_ = np.min(values), np.max(values)
rdelta_ext = (rmax_ - rmin_) * range_padding / 2
boundaries_list.append((rmin_ - rdelta_ext, rmax_ + rdelta_ext))
for i, a in enumerate(df.columns):
for j, b in enumerate(df.columns):
ax = axes[i, j]
if i == j:
values = df[a].values[mask[a].values]
# Deal with the diagonal by drawing a histogram there.
if diagonal == "hist":
ax.hist(values, **hist_kwds)
elif diagonal in ("kde", "density"):
from scipy.stats import gaussian_kde
y = values
gkde = gaussian_kde(y)
ind = np.linspace(y.min(), y.max(), 1000)
ax.plot(ind, gkde.evaluate(ind), **density_kwds)
ax.set_xlim(boundaries_list[i])
else:
common = (mask[a] & mask[b]).values
ax.scatter(
df[b][common], df[a][common], marker=marker, alpha=alpha, **kwds
)
ax.set_xlim(boundaries_list[j])
ax.set_ylim(boundaries_list[i])
ax.set_xlabel(b)
ax.set_ylabel(a)
if j != 0:
ax.yaxis.set_visible(False)
if i != n - 1:
ax.xaxis.set_visible(False)
if len(df.columns) > 1:
lim1 = boundaries_list[0]
locs = axes[0][1].yaxis.get_majorticklocs()
locs = locs[(lim1[0] <= locs) & (locs <= lim1[1])]
adj = (locs - lim1[0]) / (lim1[1] - lim1[0])
lim0 = axes[0][0].get_ylim()
adj = adj * (lim0[1] - lim0[0]) + lim0[0]
axes[0][0].yaxis.set_ticks(adj)
if np.all(locs == locs.astype(int)):
# if all ticks are int
locs = locs.astype(int)
axes[0][0].yaxis.set_ticklabels(locs)
set_ticks_props(axes, xlabelsize=8, xrot=90, ylabelsize=8, yrot=0)
return axes
def hist_frame(
data,
column=None,
by=None,
grid=True,
xlabelsize=None,
xrot=None,
ylabelsize=None,
yrot=None,
ax=None,
sharex=False,
sharey=False,
figsize=None,
layout=None,
bins=10,
legend: bool = False,
**kwds,
):
if legend and "label" in kwds:
raise ValueError("Cannot use both legend and label")
if by is not None:
axes = _grouped_hist(
data,
column=column,
by=by,
ax=ax,
grid=grid,
figsize=figsize,
sharex=sharex,
sharey=sharey,
layout=layout,
bins=bins,
xlabelsize=xlabelsize,
xrot=xrot,
ylabelsize=ylabelsize,
yrot=yrot,
legend=legend,
**kwds,
)
return axes
if column is not None:
if not isinstance(column, (list, np.ndarray, ABCIndex)):
column = [column]
data = data[column]
# GH32590
data = data.select_dtypes(
include=(np.number, "datetime64", "datetimetz"), exclude="timedelta"
)
naxes = len(data.columns)
if naxes == 0:
raise ValueError(
"hist method requires numerical or datetime columns, nothing to plot."
)
fig, axes = create_subplots(
naxes=naxes,
ax=ax,
squeeze=False,
sharex=sharex,
sharey=sharey,
figsize=figsize,
layout=layout,
)
_axes = flatten_axes(axes)
can_set_label = "label" not in kwds
for i, col in enumerate(data.columns):
ax = _axes[i]
if legend and can_set_label:
kwds["label"] = col
ax.hist(data[col].dropna().values, bins=bins, **kwds)
ax.set_title(col)
ax.grid(grid)
if legend:
ax.legend()
set_ticks_props(
axes, xlabelsize=xlabelsize, xrot=xrot, ylabelsize=ylabelsize, yrot=yrot
)
maybe_adjust_figure(fig, wspace=0.3, hspace=0.3)
return axes
def _grouped_hist(
data,
column=None,
by=None,
ax=None,
bins=50,
figsize=None,
layout=None,
sharex=False,
sharey=False,
rot=90,
grid=True,
xlabelsize=None,
xrot=None,
ylabelsize=None,
yrot=None,
legend=False,
**kwargs,
):
"""
Grouped histogram
Parameters
----------
data : Series/DataFrame
column : object, optional
by : object, optional
ax : axes, optional
bins : int, default 50
figsize : tuple, optional
layout : optional
sharex : bool, default False
sharey : bool, default False
rot : int, default 90
grid : bool, default True
legend: : bool, default False
kwargs : dict, keyword arguments passed to matplotlib.Axes.hist
Returns
-------
collection of Matplotlib Axes
"""
if legend:
assert "label" not in kwargs
if data.ndim == 1:
kwargs["label"] = data.name
elif column is None:
kwargs["label"] = data.columns
else:
kwargs["label"] = column
def plot_group(group, ax):
ax.hist(group.dropna().values, bins=bins, **kwargs)
if legend:
ax.legend()
if xrot is None:
xrot = rot
fig, axes = _grouped_plot(
plot_group,
data,
column=column,
by=by,
sharex=sharex,
sharey=sharey,
ax=ax,
figsize=figsize,
layout=layout,
rot=rot,
)
set_ticks_props(
axes, xlabelsize=xlabelsize, xrot=xrot, ylabelsize=ylabelsize, yrot=yrot
)
maybe_adjust_figure(
fig, bottom=0.15, top=0.9, left=0.1, right=0.9, hspace=0.5, wspace=0.3
)
return axes
