Skip to content

scatter plot matrix #935

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 2 commits into from
Closed

scatter plot matrix #935

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9232242
add scatter plot matrix method
jwkvam Mar 18, 2012
913af02
typo
jwkvam Mar 20, 2012
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
60 changes: 60 additions & 0 deletions pandas/core/frame.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4018,6 +4018,66 @@ def hist(self, grid=True, **kwds):
ax.grid(grid)

return axes

def scatter_matrix(self, **kwds):
"""
Draw a matrix of scatter plots.

Parameters
----------
kwds : other plotting keyword arguments
To be passed to scatter function

Examples
--------
>>> df = DataFrame(np.random.randn(1000, 4), columns=['A','B','C','D'])
>>> df.scatter_matrix(alpha=0.2)
"""
import pandas.tools.plotting as gfx

df = self._get_numeric_data()
n = df.columns.size
fig, axes = gfx.subplots(nrows=n, ncols=n)

# no gaps between subplots
fig.subplots_adjust(wspace=0, hspace=0)

for i, a in zip(range(n), df.columns):
for j, b in zip(range(n), df.columns):
axes[i, j].scatter(df[b], df[a], **kwds)
axes[i, j].yaxis.set_visible(False)
axes[i, j].xaxis.set_visible(False)

# setup labels
if i == 0 and j % 2 == 1:
axes[i, j].set_xlabel(b, visible=True)
axes[i, j].xaxis.set_visible(True)
axes[i, j].xaxis.set_ticks_position('top')
axes[i, j].xaxis.set_label_position('top')
if i == n - 1 and j % 2 == 0:
axes[i, j].set_xlabel(b, visible=True)
axes[i, j].xaxis.set_visible(True)
axes[i, j].xaxis.set_ticks_position('bottom')
axes[i, j].xaxis.set_label_position('bottom')
if j == 0 and i % 2 == 0:
axes[i, j].set_ylabel(a, visible=True)
axes[i, j].yaxis.set_visible(True)
axes[i, j].yaxis.set_ticks_position('left')
axes[i, j].yaxis.set_label_position('left')
if j == n - 1 and i % 2 == 1:
axes[i, j].set_ylabel(a, visible=True)
axes[i, j].yaxis.set_visible(True)
axes[i, j].yaxis.set_ticks_position('right')
axes[i, j].yaxis.set_label_position('right')

# ensure {x,y}lim off diagonal are the same as diagonal
for i in range(n):
for j in range(n):
if i != j:
axes[i, j].set_xlim(axes[j, j].get_xlim())
axes[i, j].set_ylim(axes[i, i].get_ylim())

return axes
#----------------------------------------------------------------------
# Deprecated stuff

Expand Down