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):
"""
Draw a matrix of scatter plots.
Parameters
----------
frame : DataFrame
alpha : float, optional
amount of transparency applied
figsize : (float,float), optional
a tuple (width, height) in inches
ax : Matplotlib axis object, optional
grid : bool, optional
setting this to True will show the grid
diagonal : {'hist', 'kde'}
pick between 'kde' and 'hist' for
either Kernel Density Estimation or Histogram
plot in the diagonal
marker : str, optional
Matplotlib marker type, default '.'
hist_kwds : other plotting keyword arguments
To be passed to hist function
density_kwds : other plotting keyword arguments
To be passed to kernel density estimate plot
range_padding : float, optional
relative extension of axis range in x and y
with respect to (x_max - x_min) or (y_max - y_min),
default 0.05
kwds : other plotting keyword arguments
To be passed to scatter function
Examples
--------
>>> df = DataFrame(np.random.randn(1000, 4), columns=['A','B','C','D'])
>>> scatter_matrix(df, alpha=0.2)
"""
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 zip(lrange(n), df.columns):
for j, b in zip(lrange(n), 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 plot_scatter_matrix(
data,
cols,
alpha=0.8,
figsize=None,
ax=None,
grid=False,
diagonal="hist",
marker=".",
density_kwds=None,
hist_kwds={'bins': 20},
range_padding=0.05,
plot_axes="lower", # "all", "lower", "upper"
**kwds):
features = data[cols]
# plt.figure(figsize=(15,9))
def _get_marker_compat(marker):
if marker not in mlines.lineMarkers:
return "o"
return marker
df = features._get_numeric_data()
n = df.columns.size
naxes = n * n
fig, axes = _subplots(naxes=naxes, figsize=(15, 9), 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 {}
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]
ax.set_visible(False)
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"):
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])
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_xlim(boundaries_list[j])
ax.set_ylim(boundaries_list[i])
ax.set_visible(True)
ax.set_xlabel(b, rotation=40)
ax.set_ylabel(a, rotation=40)
# plt.xticks(rotation=90)
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 i != j:
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=6, xrot=0, ylabelsize=6, yrot=0)
axes[0][0].yaxis.set_visible(False)
corrs = df.corr().values
for i, j in zip(*plt.np.tril_indices_from(axes, k=1)):
axes[i, j].annotate('Corr. coef = %.3f' % corrs[i, j], (0.8, 0.2),
xycoords='axes fraction',
ha='center',
va='center',
size=12)
plt.show()
return axes
