如何将非对称误差线添加到 Pandas 分组条形图？
How add asymmetric errorbars to Pandas grouped barplot?
根据 this question 的已接受答案，我能够为自己的数据重现相同的结果。但是，我需要绘制 非对称 误差线。
dfdict = {'ID': ['A', 'A', 'B', 'B', 'C', 'C', 'D', 'D'],
'quarter': ['2015 2Q', '2016 1Q', '2015 2Q', '2016 1Q', '2015 2Q',
'2016 1Q', '2015 2Q', '2016 1Q'],
'Percent': [0.851789, 0.333333, 0.355240, 0.167224, 1.533220,
0.333333, 0.170358, 0.000000],
'AgrCoullLower': [ 0.378046, 0.057962, 0.061850, -0.027515,
0.866025, 0.057962, -0.028012, -0.092614],
'AgrCoullUpper': [1.776511, 1.054612, 1.123492, 0.810851,
2.645141, 1.054612, 0.825960, 0.541513]}
df = pd.DataFrame(dfdict)
df
ID quarter Percent AgrCoullLower AgrCoullUpper
0 A 2015 2Q 0.851789 0.378046 1.776511
1 A 2016 1Q 0.333333 0.057962 1.054612
2 B 2015 2Q 0.355240 0.061850 1.123492
3 B 2016 1Q 0.167224 -0.027515 0.810851
4 C 2015 2Q 1.533220 0.866025 2.645141
5 C 2016 1Q 0.333333 0.057962 1.054612
6 D 2015 2Q 0.170358 -0.028012 0.825960
7 D 2016 1Q 0.000000 -0.092614 0.541513
errLo = df.pivot(index='ID', columns='quarter', values='AgrCoullLower')
errHi = df.pivot(index='ID', columns='quarter', values='AgrCoullUpper')
df.pivot(index='ID', columns='quarter', values='Percent')\
.plot(kind='bar', yerr=errLo)
由于 matplotlib 允许使用 yerr=[ylo, yhi] 构造的非对称错误栏，我希望这里有类似的东西。不幸的是，不可能简单地替换 yerr=[errLo, errHi] 因为数组（具有形状（4,2））不能简单地以这种方式插入（稍后堆栈跟踪），使用 yerr=np.column_stack((errLo, errHi)) 该图包含对称误差条（从不使用第二个数组值）。使用 yerr=np.row_stack((errLo, errHi))，我得到
ValueError: yerr must be a scalar, the same dimensions as y, or 2xN.
有没有办法哄骗 Pandas 提供分组的、非对称 错误栏？
堆栈跟踪：
ValueError Traceback (most recent call last)
<ipython-input-26-336a22db15e6> in <module>()
----> 1 df.pivot(index='ID', columns='quarter', values='Percent') .plot(kind='bar', yerr=[errLo, errHi])
/usr/local/lib/python3.4/dist-packages/pandas/tools/plotting.py in __call__(self, x, y, kind, ax, subplots, sharex, sharey, layout, figsize, use_index, title, grid, legend, style, logx, logy, loglog, xticks, yticks, xlim, ylim, rot, fontsize, colormap, table, yerr, xerr, secondary_y, sort_columns, **kwds)
3669 fontsize=fontsize, colormap=colormap, table=table,
3670 yerr=yerr, xerr=xerr, secondary_y=secondary_y,
-> 3671 sort_columns=sort_columns, **kwds)
3672 __call__.__doc__ = plot_frame.__doc__
3673
/usr/local/lib/python3.4/dist-packages/pandas/tools/plotting.py in plot_frame(data, x, y, kind, ax, subplots, sharex, sharey, layout, figsize, use_index, title, grid, legend, style, logx, logy, loglog, xticks, yticks, xlim, ylim, rot, fontsize, colormap, table, yerr, xerr, secondary_y, sort_columns, **kwds)
2554 yerr=yerr, xerr=xerr,
2555 secondary_y=secondary_y, sort_columns=sort_columns,
-> 2556 **kwds)
2557
2558
/usr/local/lib/python3.4/dist-packages/pandas/tools/plotting.py in _plot(data, x, y, subplots, ax, kind, **kwds)
2380 pass
2381 data = series
-> 2382 plot_obj = klass(data, subplots=subplots, ax=ax, kind=kind, **kwds)
2383
2384 plot_obj.generate()
/usr/local/lib/python3.4/dist-packages/pandas/tools/plotting.py in __init__(self, data, **kwargs)
1843
1844 self.log = kwargs.pop('log',False)
-> 1845 MPLPlot.__init__(self, data, **kwargs)
1846
1847 if self.stacked or self.subplots:
/usr/local/lib/python3.4/dist-packages/pandas/tools/plotting.py in __init__(self, data, kind, by, subplots, sharex, sharey, use_index, figsize, grid, legend, rot, ax, fig, title, xlim, ylim, xticks, yticks, sort_columns, fontsize, secondary_y, colormap, table, layout, **kwds)
904 self.errors = {}
905 for kw, err in zip(['xerr', 'yerr'], [xerr, yerr]):
--> 906 self.errors[kw] = self._parse_errorbars(kw, err)
907
908 if not isinstance(secondary_y, (bool, tuple, list, np.ndarray, Index)):
/usr/local/lib/python3.4/dist-packages/pandas/tools/plotting.py in _parse_errorbars(self, label, err)
1423 else:
1424 # raw error values
-> 1425 err = np.atleast_2d(err)
1426
1427 err_shape = err.shape
/usr/local/lib/python3.4/dist-packages/numpy/core/shape_base.py in atleast_2d(*arys)
98 res = []
99 for ary in arys:
--> 100 ary = asanyarray(ary)
101 if len(ary.shape) == 0:
102 result = ary.reshape(1, 1)
/usr/local/lib/python3.4/dist-packages/numpy/core/numeric.py in asanyarray(a, dtype, order)
523
524 """
--> 525 return array(a, dtype, copy=False, order=order, subok=True)
526
527 def ascontiguousarray(a, dtype=None):
ValueError: cannot copy sequence with size 4 to array axis with dimension 2
经过反复试验，我弄明白了。正如您提到的：
matplotlib allows for asymmetric errorbars using a yerr=[ylo, yhi]
construct
但事实证明，由于您有两个条形组（即“2015 2Q”和“2016 1Q”），matplotlib 期望的形状是 (2, 2, 4)，或者：[组数] x 2 x [每组的条数]。
这是我的代码，在您的代码中定义 errLo 和 errHi 之后开始：
err = []
for col in errLo: # Iterate over bar groups (represented as columns)
err.append([errLo[col].values, errHi[col].values])
err = np.abs(err) # Absolute error values (you had some negatives)
pprint(err)
print 'Shape:', np.shape(err)
df.pivot(index='ID', columns='quarter', values='Percent').plot(kind='bar', yerr=err)
plt.show()
输出：
array([[[ 0.378046, 0.06185 , 0.866025, 0.028012],
[ 1.776511, 1.123492, 2.645141, 0.82596 ]],
[[ 0.057962, 0.027515, 0.057962, 0.092614],
[ 1.054612, 0.810851, 1.054612, 0.541513]]])
Shape: (2L, 2L, 4L)
根据 this question 的已接受答案，我能够为自己的数据重现相同的结果。但是，我需要绘制 非对称 误差线。
dfdict = {'ID': ['A', 'A', 'B', 'B', 'C', 'C', 'D', 'D'],
'quarter': ['2015 2Q', '2016 1Q', '2015 2Q', '2016 1Q', '2015 2Q',
'2016 1Q', '2015 2Q', '2016 1Q'],
'Percent': [0.851789, 0.333333, 0.355240, 0.167224, 1.533220,
0.333333, 0.170358, 0.000000],
'AgrCoullLower': [ 0.378046, 0.057962, 0.061850, -0.027515,
0.866025, 0.057962, -0.028012, -0.092614],
'AgrCoullUpper': [1.776511, 1.054612, 1.123492, 0.810851,
2.645141, 1.054612, 0.825960, 0.541513]}
df = pd.DataFrame(dfdict)
df
ID quarter Percent AgrCoullLower AgrCoullUpper
0 A 2015 2Q 0.851789 0.378046 1.776511
1 A 2016 1Q 0.333333 0.057962 1.054612
2 B 2015 2Q 0.355240 0.061850 1.123492
3 B 2016 1Q 0.167224 -0.027515 0.810851
4 C 2015 2Q 1.533220 0.866025 2.645141
5 C 2016 1Q 0.333333 0.057962 1.054612
6 D 2015 2Q 0.170358 -0.028012 0.825960
7 D 2016 1Q 0.000000 -0.092614 0.541513
errLo = df.pivot(index='ID', columns='quarter', values='AgrCoullLower')
errHi = df.pivot(index='ID', columns='quarter', values='AgrCoullUpper')
df.pivot(index='ID', columns='quarter', values='Percent')\
.plot(kind='bar', yerr=errLo)
由于 matplotlib 允许使用 yerr=[ylo, yhi] 构造的非对称错误栏，我希望这里有类似的东西。不幸的是，不可能简单地替换 yerr=[errLo, errHi] 因为数组（具有形状（4,2））不能简单地以这种方式插入（稍后堆栈跟踪），使用 yerr=np.column_stack((errLo, errHi)) 该图包含对称误差条（从不使用第二个数组值）。使用 yerr=np.row_stack((errLo, errHi))，我得到
ValueError: yerr must be a scalar, the same dimensions as y, or 2xN.
有没有办法哄骗 Pandas 提供分组的、非对称 错误栏？
堆栈跟踪：
ValueError Traceback (most recent call last)
<ipython-input-26-336a22db15e6> in <module>()
----> 1 df.pivot(index='ID', columns='quarter', values='Percent') .plot(kind='bar', yerr=[errLo, errHi])
/usr/local/lib/python3.4/dist-packages/pandas/tools/plotting.py in __call__(self, x, y, kind, ax, subplots, sharex, sharey, layout, figsize, use_index, title, grid, legend, style, logx, logy, loglog, xticks, yticks, xlim, ylim, rot, fontsize, colormap, table, yerr, xerr, secondary_y, sort_columns, **kwds)
3669 fontsize=fontsize, colormap=colormap, table=table,
3670 yerr=yerr, xerr=xerr, secondary_y=secondary_y,
-> 3671 sort_columns=sort_columns, **kwds)
3672 __call__.__doc__ = plot_frame.__doc__
3673
/usr/local/lib/python3.4/dist-packages/pandas/tools/plotting.py in plot_frame(data, x, y, kind, ax, subplots, sharex, sharey, layout, figsize, use_index, title, grid, legend, style, logx, logy, loglog, xticks, yticks, xlim, ylim, rot, fontsize, colormap, table, yerr, xerr, secondary_y, sort_columns, **kwds)
2554 yerr=yerr, xerr=xerr,
2555 secondary_y=secondary_y, sort_columns=sort_columns,
-> 2556 **kwds)
2557
2558
/usr/local/lib/python3.4/dist-packages/pandas/tools/plotting.py in _plot(data, x, y, subplots, ax, kind, **kwds)
2380 pass
2381 data = series
-> 2382 plot_obj = klass(data, subplots=subplots, ax=ax, kind=kind, **kwds)
2383
2384 plot_obj.generate()
/usr/local/lib/python3.4/dist-packages/pandas/tools/plotting.py in __init__(self, data, **kwargs)
1843
1844 self.log = kwargs.pop('log',False)
-> 1845 MPLPlot.__init__(self, data, **kwargs)
1846
1847 if self.stacked or self.subplots:
/usr/local/lib/python3.4/dist-packages/pandas/tools/plotting.py in __init__(self, data, kind, by, subplots, sharex, sharey, use_index, figsize, grid, legend, rot, ax, fig, title, xlim, ylim, xticks, yticks, sort_columns, fontsize, secondary_y, colormap, table, layout, **kwds)
904 self.errors = {}
905 for kw, err in zip(['xerr', 'yerr'], [xerr, yerr]):
--> 906 self.errors[kw] = self._parse_errorbars(kw, err)
907
908 if not isinstance(secondary_y, (bool, tuple, list, np.ndarray, Index)):
/usr/local/lib/python3.4/dist-packages/pandas/tools/plotting.py in _parse_errorbars(self, label, err)
1423 else:
1424 # raw error values
-> 1425 err = np.atleast_2d(err)
1426
1427 err_shape = err.shape
/usr/local/lib/python3.4/dist-packages/numpy/core/shape_base.py in atleast_2d(*arys)
98 res = []
99 for ary in arys:
--> 100 ary = asanyarray(ary)
101 if len(ary.shape) == 0:
102 result = ary.reshape(1, 1)
/usr/local/lib/python3.4/dist-packages/numpy/core/numeric.py in asanyarray(a, dtype, order)
523
524 """
--> 525 return array(a, dtype, copy=False, order=order, subok=True)
526
527 def ascontiguousarray(a, dtype=None):
ValueError: cannot copy sequence with size 4 to array axis with dimension 2
经过反复试验，我弄明白了。正如您提到的：
matplotlib allows for asymmetric errorbars using a
yerr=[ylo, yhi]construct
但事实证明，由于您有两个条形组（即“2015 2Q”和“2016 1Q”），matplotlib 期望的形状是 (2, 2, 4)，或者：[组数] x 2 x [每组的条数]。
这是我的代码，在您的代码中定义 errLo 和 errHi 之后开始：
err = []
for col in errLo: # Iterate over bar groups (represented as columns)
err.append([errLo[col].values, errHi[col].values])
err = np.abs(err) # Absolute error values (you had some negatives)
pprint(err)
print 'Shape:', np.shape(err)
df.pivot(index='ID', columns='quarter', values='Percent').plot(kind='bar', yerr=err)
plt.show()
输出：
array([[[ 0.378046, 0.06185 , 0.866025, 0.028012],
[ 1.776511, 1.123492, 2.645141, 0.82596 ]],
[[ 0.057962, 0.027515, 0.057962, 0.092614],
[ 1.054612, 0.810851, 1.054612, 0.541513]]])
Shape: (2L, 2L, 4L)