def hist_series(
self,
by=None,
ax=None,
grid=True,
xlabelsize=None,
xrot=None,
ylabelsize=None,
yrot=None,
figsize=None,
bins=10,
**kwds,
):
import matplotlib.pyplot as plt
if by is None:
if kwds.get("layout", None) is not None:
raise ValueError("The 'layout' keyword is not supported when "
"'by' is None")
# hack until the plotting interface is a bit more unified
fig = kwds.pop(
"figure",
plt.gcf() if plt.get_fignums() else plt.figure(figsize=figsize))
if figsize is not None and tuple(figsize) != tuple(
fig.get_size_inches()):
fig.set_size_inches(*figsize, forward=True)
if ax is None:
ax = fig.gca()
elif ax.get_figure() != fig:
raise AssertionError("passed axis not bound to passed figure")
self_bins, self_weights = self._hist(num_bins=bins)
# As this is a series, squeeze Series to arrays
self_bins = self_bins.squeeze()
self_weights = self_weights.squeeze()
ax.hist(self_bins[:-1], bins=self_bins, weights=self_weights, **kwds)
ax.grid(grid)
axes = np.array([ax])
set_ticks_props(axes,
xlabelsize=xlabelsize,
xrot=xrot,
ylabelsize=ylabelsize,
yrot=yrot)
else:
raise NotImplementedError("TODO")
if hasattr(axes, "ndim"):
if axes.ndim == 1 and len(axes) == 1:
return axes[0]
return axes
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, ABCIndexClass)):
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)
fig.subplots_adjust(wspace=0.3, hspace=0.3)
return axes
def hist_series(
self,
by=None,
ax=None,
grid=True,
xlabelsize=None,
xrot=None,
ylabelsize=None,
yrot=None,
figsize=None,
bins=10,
legend: bool = False,
**kwds,
):
import matplotlib.pyplot as plt
if legend and "label" in kwds:
raise ValueError("Cannot use both legend and label")
if by is None:
if kwds.get("layout", None) is not None:
raise ValueError(
"The 'layout' keyword is not supported when 'by' is None")
# hack until the plotting interface is a bit more unified
fig = kwds.pop(
"figure",
plt.gcf() if plt.get_fignums() else plt.figure(figsize=figsize))
if figsize is not None and tuple(figsize) != tuple(
fig.get_size_inches()):
fig.set_size_inches(*figsize, forward=True)
if ax is None:
ax = fig.gca()
elif ax.get_figure() != fig:
raise AssertionError("passed axis not bound to passed figure")
values = self.dropna().values
if legend:
kwds["label"] = self.name
ax.hist(values, bins=bins, **kwds)
if legend:
ax.legend()
ax.grid(grid)
axes = np.array([ax])
set_ticks_props(axes,
xlabelsize=xlabelsize,
xrot=xrot,
ylabelsize=ylabelsize,
yrot=yrot)
else:
if "figure" in kwds:
raise ValueError(
"Cannot pass 'figure' when using the "
"'by' argument, since a new 'Figure' instance will be created")
axes = _grouped_hist(
self,
by=by,
ax=ax,
grid=grid,
figsize=figsize,
bins=bins,
xlabelsize=xlabelsize,
xrot=xrot,
ylabelsize=ylabelsize,
yrot=yrot,
legend=legend,
**kwds,
)
if hasattr(axes, "ndim"):
if axes.ndim == 1 and len(axes) == 1:
return axes[0]
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)
fig.subplots_adjust(bottom=0.15,
top=0.9,
left=0.1,
right=0.9,
hspace=0.5,
wspace=0.3)
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,
**kwds,
):
# Start with empty pandas data frame derived from
ed_df_bins, ed_df_weights = data._hist(num_bins=bins)
converter._WARN = False # no warning for pandas plots
if by is not None:
raise NotImplementedError("TODO")
if column is not None:
if not isinstance(column, (list, np.ndarray, ABCIndexClass)):
column = [column]
ed_df_bins = ed_df_bins[column]
ed_df_weights = ed_df_weights[column]
naxes = len(ed_df_bins.columns)
if naxes == 0:
raise ValueError("hist method requires numerical 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)
for i, col in enumerate(try_sort(data.columns)):
ax = _axes[i]
ax.hist(
ed_df_bins[col][:-1],
bins=ed_df_bins[col],
weights=ed_df_weights[col],
**kwds,
)
ax.set_title(col)
ax.grid(grid)
set_ticks_props(axes,
xlabelsize=xlabelsize,
xrot=xrot,
ylabelsize=ylabelsize,
yrot=yrot)
fig.subplots_adjust(wspace=0.3, hspace=0.3)
return axes
