Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Remove old normalising code from plt.hist #9121

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

Merged
merged 4 commits into from
Oct 19, 2017
Merged

Remove old normalising code from plt.hist #9121

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
096ce51
Remove old numpy histogram note
dstansby Aug 29, 2017
02cfe85
Clear up variable naming
dstansby Aug 29, 2017
d79d6bb
Remove un-used code
dstansby Aug 29, 2017
2dde48a
Add test for density histogram:
dstansby Aug 30, 2017
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
40 changes: 16 additions & 24 deletions lib/matplotlib/axes/_axes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5988,13 +5988,6 @@ def hist(self, x, bins=None, range=None, density=None, weights=None,
--------
hist2d : 2D histograms

Notes
-----
Until numpy release 1.5, the underlying numpy histogram function was
incorrect with ``normed=True`` if bin sizes were unequal. MPL
inherited that error. It is now corrected within MPL when using
earlier numpy versions.

"""
# Avoid shadowing the builtin.
bin_range = range
Expand Down Expand Up @@ -6087,38 +6080,37 @@ def hist(self, x, bins=None, range=None, density=None, weights=None,
else:
hist_kwargs = dict(range=bin_range)

n = []
# List to store all the top coordinates of the histograms
tops = []
mlast = None
# Loop through datasets
for i in xrange(nx):
# this will automatically overwrite bins,
# so that each histogram uses the same bins
m, bins = np.histogram(x[i], bins, weights=w[i], **hist_kwargs)
m = m.astype(float) # causes problems later if it's an int
if mlast is None:
mlast = np.zeros(len(bins)-1, m.dtype)
if density and not stacked:
Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is the old normalising code

db = np.diff(bins)
m = (m.astype(float) / db) / m.sum()
if stacked:
if mlast is None:
Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This if statement is never used due to the same statement on line 6097

mlast = np.zeros(len(bins)-1, m.dtype)
m += mlast
mlast[:] = m
n.append(m)
tops.append(m)

# If a stacked density plot, normalize so the area of all the stacked
# histograms together is 1
if stacked and density:
db = np.diff(bins)
for m in n:
m[:] = (m.astype(float) / db) / n[-1].sum()
for m in tops:
m[:] = (m.astype(float) / db) / tops[-1].sum()
if cumulative:
slc = slice(None)
if cbook.is_numlike(cumulative) and cumulative < 0:
slc = slice(None, None, -1)

if density:
n = [(m * np.diff(bins))[slc].cumsum()[slc] for m in n]
tops = [(m * np.diff(bins))[slc].cumsum()[slc] for m in tops]
else:
n = [m[slc].cumsum()[slc] for m in n]
tops = [m[slc].cumsum()[slc] for m in tops]

patches = []

Expand All @@ -6136,7 +6128,7 @@ def hist(self, x, bins=None, range=None, density=None, weights=None,

if rwidth is not None:
dr = np.clip(rwidth, 0, 1)
elif (len(n) > 1 and
elif (len(tops) > 1 and
((not stacked) or rcParams['_internal.classic_mode'])):
dr = 0.8
else:
Expand All @@ -6162,7 +6154,7 @@ def hist(self, x, bins=None, range=None, density=None, weights=None,
_barfunc = self.bar
bottom_kwarg = 'bottom'

for m, c in zip(n, color):
for m, c in zip(tops, color):
if bottom is None:
bottom = np.zeros(len(m))
if stacked:
Expand Down Expand Up @@ -6206,7 +6198,7 @@ def hist(self, x, bins=None, range=None, density=None, weights=None,
# For data that is normed to form a probability density,
# set to minimum data value / logbase
# (gives 1 full tick-label unit for the lowest filled bin)
ndata = np.array(n)
ndata = np.array(tops)
minimum = (np.min(ndata[ndata > 0])) / logbase
else:
# For non-normed (density = False) data,
Expand All @@ -6229,7 +6221,7 @@ def hist(self, x, bins=None, range=None, density=None, weights=None,
fill = (histtype == 'stepfilled')

xvals, yvals = [], []
for m in n:
for m in tops:
if stacked:
# starting point for drawing polygon
y[0] = y[1]
Expand Down Expand Up @@ -6292,9 +6284,9 @@ def hist(self, x, bins=None, range=None, density=None, weights=None,
p.set_label('_nolegend_')

if nx == 1:
return n[0], bins, cbook.silent_list('Patch', patches[0])
return tops[0], bins, cbook.silent_list('Patch', patches[0])
else:
return n, bins, cbook.silent_list('Lists of Patches', patches)
return tops, bins, cbook.silent_list('Lists of Patches', patches)

@_preprocess_data(replace_names=["x", "y", "weights"], label_namer=None)
def hist2d(self, x, y, bins=10, range=None, normed=False, weights=None,
Expand Down
Binary file added lib/matplotlib/tests/baseline_images/test_axes/hist_density.png
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
8 changes: 8 additions & 0 deletions lib/matplotlib/tests/test_axes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1464,6 +1464,14 @@ def test_hist_step_filled():
assert all([p.get_facecolor() == p.get_edgecolor() for p in patches])


@image_comparison(baseline_images=['hist_density'], extensions=['png'])
def test_hist_density():
np.random.seed(19680801)
data = np.random.standard_normal(2000)
fig, ax = plt.subplots()
ax.hist(data, density=True)
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Does this actually need an image test, or can we just test that np.histogram properly applies the density kwarg?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I don't think there was ever any image test that used the 'density' or 'norm' kwargs, so I thought it would be a good idea to add one.

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think we are trying to keep image tests to things where the actual image appearance might change if code changes. So sure if there is no hist image test there should be one. If such a test does exist then this just tests the value of the bars, and I think you can do that w/o an image comparison. But I’m not passionate about it or anything.

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Beating a dead horse, but:

np.random.seed(19680801)
data = np.random.standard_normal(2000)
fig, ax = plt.subplots()
n, bins, patches = ax.hist(data, density=True)
assert np.isclose(np.sum(n * np.diff(bins)), 1.0)



@image_comparison(baseline_images=['hist_step_log_bottom'],
remove_text=True, extensions=['png'])
def test_hist_step_log_bottom():
Expand Down