def _grouped_plot(plotf, data, column=None, by=None, numeric_only=True,
figsize=None, sharex=True, sharey=True, layout=None,
rot=0, ax=None, **kwargs):
if figsize == 'default':
# allowed to specify mpl default with 'default'
warnings.warn("figsize='default' is deprecated. Specify figure "
"size by tuple instead", FutureWarning, stacklevel=5)
figsize = None
grouped = data.groupby(by)
if column is not None:
grouped = grouped[column]
naxes = len(grouped)
fig, axes = _subplots(naxes=naxes, figsize=figsize,
sharex=sharex, sharey=sharey, ax=ax,
layout=layout)
_axes = _flatten(axes)
for i, (key, group) in enumerate(grouped):
ax = _axes[i]
if numeric_only and isinstance(group, ABCDataFrame):
group = group._get_numeric_data()
plotf(group, ax, **kwargs)
ax.set_title(pprint_thing(key))
return fig, axes
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 = _subplots(naxes=naxes, squeeze=False,
ax=ax, sharex=sharex, sharey=sharey,
figsize=figsize, layout=layout)
axes = _flatten(axes)
from pandas.core.series import Series
ret = Series()
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
fig.subplots_adjust(bottom=0.15, top=0.9, left=0.1,
right=0.9, wspace=0.2)
else:
from pandas.core.reshape.concat import concat
keys, frames = zip(*grouped)
if grouped.axis == 0:
df = concat(frames, keys=keys, axis=1)
else:
if len(frames) > 1:
df = frames[0].join(frames[1::])
else:
df = frames[0]
ret = df.boxplot(column=column, fontsize=fontsize, rot=rot,
grid=grid, ax=ax, figsize=figsize,
layout=layout, **kwds)
return ret
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 = _subplots(naxes=naxes,
sharex=True,
sharey=True,
figsize=figsize,
ax=ax,
layout=layout)
_axes = _flatten(axes)
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, **kwargs)
ax.set_title(col)
ax.set_xlabel(pprint_thing(by))
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}")
fig.subplots_adjust(bottom=0.15, top=0.9, left=0.1, right=0.9, wspace=0.2)
return result
def _grouped_plot(plotf,
data,
column=None,
by=None,
numeric_only=True,
figsize=None,
sharex=True,
sharey=True,
layout=None,
rot=0,
ax=None,
**kwargs):
if figsize == "default":
# allowed to specify mpl default with 'default'
warnings.warn(
"figsize='default' is deprecated. Specify figure "
"size by tuple instead",
FutureWarning,
stacklevel=5,
)
figsize = None
grouped = data.groupby(by)
if column is not None:
grouped = grouped[column]
naxes = len(grouped)
fig, axes = _subplots(naxes=naxes,
figsize=figsize,
sharex=sharex,
sharey=sharey,
ax=ax,
layout=layout)
_axes = _flatten(axes)
for i, (key, group) in enumerate(grouped):
ax = _axes[i]
if numeric_only and isinstance(group, ABCDataFrame):
group = group._get_numeric_data()
plotf(group, ax, **kwargs)
ax.set_title(pprint_thing(key))
return fig, axes
def _setup_subplots(self):
if self.subplots:
fig, axes = _subplots(
naxes=self.nseries,
sharex=self.sharex,
sharey=self.sharey,
figsize=self.figsize,
ax=self.ax,
layout=self.layout,
layout_type=self._layout_type,
)
else:
if self.ax is None:
fig = self.plt.figure(figsize=self.figsize)
axes = fig.add_subplot(111)
else:
fig = self.ax.get_figure()
if self.figsize is not None:
fig.set_size_inches(self.figsize)
axes = self.ax
axes = _flatten(axes)
valid_log = {False, True, "sym", None}
input_log = {self.logx, self.logy, self.loglog}
if input_log - valid_log:
invalid_log = next(iter((input_log - valid_log)))
raise ValueError(
"Boolean, None and 'sym' are valid options,"
" '{}' is given.".format(invalid_log)
)
if self.logx is True or self.loglog is True:
[a.set_xscale("log") for a in axes]
elif self.logx == "sym" or self.loglog == "sym":
[a.set_xscale("symlog") for a in axes]
if self.logy is True or self.loglog is True:
[a.set_yscale("log") for a in axes]
elif self.logy == "sym" or self.loglog == "sym":
[a.set_yscale("symlog") for a in axes]
self.fig = fig
self.axes = 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):
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, **kwds)
return axes
if column is not None:
if not isinstance(column, (list, np.ndarray, ABCIndexClass)):
column = [column]
data = data[column]
data = data._get_numeric_data()
naxes = len(data.columns)
if naxes == 0:
raise ValueError("hist method requires numerical columns, "
"nothing to plot.")
fig, axes = _subplots(naxes=naxes, ax=ax, squeeze=False,
sharex=sharex, sharey=sharey, figsize=figsize,
layout=layout)
_axes = _flatten(axes)
for i, col in enumerate(com.try_sort(data.columns)):
ax = _axes[i]
ax.hist(data[col].dropna().values, bins=bins, **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
def scatter_matrix(
frame,
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 = _subplots(naxes=naxes, figsize=figsize, ax=ax, squeeze=False)
# no gaps between subplots
fig.subplots_adjust(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 / 2.0
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,
**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 = _subplots(
naxes=naxes,
ax=ax,
squeeze=False,
sharex=sharex,
sharey=sharey,
figsize=figsize,
layout=layout,
)
_axes = _flatten(axes)
for i, col in enumerate(com.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
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):
converter._WARN = False # no warning for pandas plots
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,
**kwds)
return axes
if column is not None:
if not isinstance(column, (list, np.ndarray, ABCIndexClass)):
column = [column]
data = data[column]
data = data._get_numeric_data()
naxes = len(data.columns)
if naxes == 0:
raise ValueError("hist method requires numerical columns, "
"nothing to plot.")
fig, axes = _subplots(naxes=naxes,
ax=ax,
squeeze=False,
sharex=sharex,
sharey=sharey,
figsize=figsize,
layout=layout)
_axes = _flatten(axes)
for i, col in enumerate(com.try_sort(data.columns)):
ax = _axes[i]
ax.hist(data[col].dropna().values, bins=bins, **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
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]
data = data._get_numeric_data()
naxes = len(data.columns)
if naxes == 0:
raise ValueError(
"hist method requires numerical columns, nothing to plot.")
fig, axes = _subplots(
naxes=naxes,
ax=ax,
squeeze=False,
sharex=sharex,
sharey=sharey,
figsize=figsize,
layout=layout,
)
_axes = _flatten(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 scatter_matrix(frame, 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 = _subplots(naxes=naxes, figsize=figsize, ax=ax,
squeeze=False)
# no gaps between subplots
fig.subplots_adjust(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 scatter_matrix(
frame,
alpha=0.5,
figsize=None,
ax=None,
grid=False,
diagonal="hist",
marker=".",
density_kwds=None,
hist_kwds=None,
range_padding=0.05,
plot_axes="all", # "all", "lower", "upper"
ylabel_direction=None, # "left", "right",
refresh_labels=False,
scales=None, # list of scale ["linear" or "log"]
**kwds):
'''
Modification of pandas.scatter_matrix.
'''
if scales is None: scales = ["linear"] * len(frame.columns)
def _get_marker_compat(marker):
if marker not in mlines.lineMarkers:
return "o"
return marker
df = frame._get_numeric_data()
n = df.columns.size
naxes = n * n
fig, axes = _subplots(naxes=naxes, figsize=figsize, ax=ax, squeeze=False)
if axes.ndim != 2: # Note: axに二次元配列入れてても_subplotsは一次元配列を生成する
axes = axes.reshape((n, n))
ylabel_direction = ylabel_direction or (
"left" if plot_axes != "upper" else "right"
) # default: "lower" --> "left", "upper" --> "right"
# no gaps between subplots
fig.subplots_adjust(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 i, a in enumerate(df.columns):
values = df[a].values[mask[a].values]
rmin_, rmax_ = np.min(values), np.max(values)
if scales[i] == "linear":
rdelta_ext = (rmax_ - rmin_) * range_padding / 2.0
boundaries_list.append((rmin_ - rdelta_ext, rmax_ + rdelta_ext))
elif scales[i] == "log":
rdelta_ext = np.exp(
(np.log(rmax_) - np.log(rmin_)) * range_padding / 2.0)
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]
ax.set_visible(False) # 一旦非表示にしておく
if i == j:
values = df[a].values[mask[a].values]
# Deal with the diagonal by drawing a histogram there.
if diagonal == "hist":
if "bins" not in hist_kwds: hist_kwds["bins"] = 16
_hist_kwds = {key: val for key, val in hist_kwds.items()}
if scales[i] == "log" and type(hist_kwds["bins"]) is int:
_hist_kwds["bins"] = np.logspace(
np.log10(np.min(values)), np.log10(np.max(values)),
hist_kwds["bins"])
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_xscale(scales[i])
ax.set_xlim(boundaries_list[i])
ax.set_visible(True)
elif plot_axes == "all" or (i > j and plot_axes == "lower") or (
i < j and plot_axes == "upper"):
common = (mask[a] & mask[b]).values
ax.scatter(df[b][common],
df[a][common],
marker=marker,
alpha=alpha,
**kwds)
ax.set_xscale(scales[j])
ax.set_yscale(scales[i])
ax.set_xlim(boundaries_list[j])
ax.set_ylim(boundaries_list[i])
ax.set_visible(True)
ax.set_xlabel(b)
ax.set_ylabel(a)
if refresh_labels:
ax.xaxis.set_visible(True)
ax.yaxis.set_visible(True)
if plot_axes in ("all", "lower"):
if j != 0:
ax.yaxis.set_visible(False)
if i != n - 1:
ax.xaxis.set_visible(False)
elif plot_axes == "upper":
if ylabel_direction == "left" and i != j:
ax.yaxis.set_visible(False)
else: # elif ylabel_direction == "right":
if j == n - 1:
ax.yaxis.tick_right()
ax.yaxis.set_label_position('right')
else:
ax.yaxis.set_visible(False)
if i == 0:
ax.xaxis.tick_top()
ax.xaxis.set_label_position('top')
else:
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
