python - 如何将日期数组传递给 pcolor 图？

Question

我有矩阵数据，其中一个轴与日期相关。但是，我在将此数据作为轴传递给 pcolor 时遇到问题。我的虚拟数据如下:

In [219]: X = [datetime.date.today() + datetime.timedelta(days=i) for i in range(4)]

In [220]: Y = arange(5)

In [221]: Z = arange(4*5).reshape(4, 5)

天真的尝试 pcolor(Y, X, Z) 失败了，因为 pcolor 不喜欢获取 list 对象:

In [222]: pcolor(Y, X, Z)
---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-222-1ece18b4bc13> in <module>()
----> 1 pcolor(Y, X, Z)

/export/data/home/gholl/venv/gerrit/lib/python3.4/site-packages/matplotlib/pyplot.py in pcolor(*args, **kwargs)
   2926         ax.hold(hold)
   2927     try:
-> 2928         ret = ax.pcolor(*args, **kwargs)
   2929         draw_if_interactive()
   2930     finally:

/export/data/home/gholl/venv/gerrit/lib/python3.4/site-packages/matplotlib/axes.py in pcolor(self, *args, **kwargs)
   7545         shading = kwargs.pop('shading', 'flat')
   7546 
-> 7547         X, Y, C = self._pcolorargs('pcolor', *args, allmatch=False)
   7548         Ny, Nx = X.shape
   7549 

/export/data/home/gholl/venv/gerrit/lib/python3.4/site-packages/matplotlib/axes.py in _pcolorargs(funcname, *args, **kw)
   7357 
   7358         Nx = X.shape[-1]
-> 7359         Ny = Y.shape[0]
   7360         if len(X.shape) != 2 or X.shape[0] == 1:
   7361             x = X.reshape(1, Nx)

AttributeError: 'list' object has no attribute 'shape'

将其转换为包含 datetime.date 的 array 失败并出现 TypeError: float() argument must be a string or a number, not 'datetime.date ':

In [223]: pcolor(Y, numpy.array(X), Z)                                                                                                                                 
---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-223-a00423a6d479> in <module>()
----> 1 pcolor(Y, numpy.array(X), Z)

/export/data/home/gholl/venv/gerrit/lib/python3.4/site-packages/matplotlib/pyplot.py in pcolor(*args, **kwargs)
   2926         ax.hold(hold)
   2927     try:
-> 2928         ret = ax.pcolor(*args, **kwargs)
   2929         draw_if_interactive()
   2930     finally:

/export/data/home/gholl/venv/gerrit/lib/python3.4/site-packages/matplotlib/axes.py in pcolor(self, *args, **kwargs)
   7606             kwargs['antialiaseds'] = False
   7607 
-> 7608         collection = mcoll.PolyCollection(verts, **kwargs)
   7609 
   7610         collection.set_alpha(alpha)

/export/data/home/gholl/venv/gerrit/lib/python3.4/site-packages/matplotlib/collections.py in __init__(self, verts, sizes, closed, **kwargs)
    743         Collection.__init__(self, **kwargs)
    744         self._sizes = sizes
--> 745         self.set_verts(verts, closed)
    746 
    747     def set_verts(self, verts, closed=True):

/export/data/home/gholl/venv/gerrit/lib/python3.4/site-packages/matplotlib/collections.py in set_verts(self, verts, closed)
    763                     codes[0] = mpath.Path.MOVETO
    764                     codes[-1] = mpath.Path.CLOSEPOLY
--> 765                     self._paths.append(mpath.Path(xy, codes))
    766                 else:
    767                     self._paths.append(mpath.Path(xy))

/export/data/home/gholl/venv/gerrit/lib/python3.4/site-packages/matplotlib/path.py in __init__(self, vertices, codes, _interpolation_steps, closed, readonly)
    131             vertices = vertices.astype(np.float_).filled(np.nan)
    132         else:
--> 133             vertices = np.asarray(vertices, np.float_)
    134 
    135         if codes is not None:

/export/data/home/gholl/venv/gerrit/lib/python3.4/site-packages/numpy/core/numeric.py in asarray(a, dtype, order)
    460 
    461     """
--> 462     return array(a, dtype, copy=False, order=order)
    463 
    464 def asanyarray(a, dtype=None, order=None):

TypeError: float() argument must be a string or a number, not 'datetime.date'

最后，将其转换为适当的 numpy.datetime64 对象也无法解决问题，并因 Invalid type promotion 而失败:

In [224]: pcolor(Y, numpy.array(X, dtype="datetime64[D]"), Z)
---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-224-0ac06cfafa35> in <module>()
----> 1 pcolor(Y, numpy.array(X, dtype="datetime64[D]"), Z)

/export/data/home/gholl/venv/gerrit/lib/python3.4/site-packages/matplotlib/pyplot.py in pcolor(*args, **kwargs)
   2926         ax.hold(hold)
   2927     try:
-> 2928         ret = ax.pcolor(*args, **kwargs)
   2929         draw_if_interactive()
   2930     finally:

/export/data/home/gholl/venv/gerrit/lib/python3.4/site-packages/matplotlib/axes.py in pcolor(self, *args, **kwargs)
   7577                              X4[:, newaxis], Y4[:, newaxis],
   7578                              X1[:, newaxis], Y1[:, newaxis]),
-> 7579                              axis=1)
   7580         verts = xy.reshape((npoly, 5, 2))
   7581 

TypeError: invalid type promotion

在这里进行的正确方法是什么？在

请注意 the question plotting date data with pcolor 的答案使用 scatter，而不是 pcolor，因此对我的情况没有帮助。

Answer 1

Matplotlib 使用简单的 float 来表示日期时间。因此，您必须先转换它们，然后告诉轴必须将标签格式化为日期。 Matplotlib 为此提供了函数 date2num:

import matplotlib.pyplot as plt
import matplotlib.dates as mdates
import datetime
import numpy as np

# Your original data (with adapted sizes)
x = [datetime.date.today() + datetime.timedelta(days=i) for i in range(4)]
y = np.arange(5)
z = np.arange(3*4).reshape(3, 4).T

# Convert to numbers
x = mdates.date2num(x)

# Create the figure
fig, ax = plt.subplots(1,1)
plt.pcolor(x,y,z)

# Setup the DateFormatter for the x axis
date_format = mdates.DateFormatter('%D')
ax.xaxis.set_major_formatter(date_format)

# Rotates the labels to fit
fig.autofmt_xdate()

plt.show()

一些其他的说明:

• 对于 pcolor，x 和 y 向量表示图 block 的角点。因此它们需要比数据长 1 个元素。
• documentation很好地概述了如何在 matplotlib 中处理日期。

结果: