python - 如何在 matplotlib 表中设置列的背景颜色

Question

我在目录中有多个 .txt 文件，例如 d:\memdump\0.txt,1.txt,...10.txt 示例文本文件如下:

 Applications Memory Usage (kB):
 Uptime: 7857410 Realtime: 7857410
** MEMINFO in pid 23875 [com.example.twolibs] **
                 Shared  Private     Heap     Heap     Heap
               Pss    Dirty     Dirty     Size    Alloc     Free
              ------   ------   ------   ------   ------   ------
  Native        0        0        0       13504    10836      459
  Dalvik     6806     7740     6580       24076    18523     5553
  Stack       80        0       80                           
  Cursor        0        0        0                           
  Ashmem        0        0        0                           
  Other dev    14741      836     1028                           
 .so mmap     1367      448     1028                           
 .jar mmap        0        0        0                           
 .apk mmap      225        0        0                           
 .ttf mmap        0        0        0                           
 .dex mmap     1225      340       16                           
  Other mmap        5        8        4                           
  Unknown     3473      564     3432                           
  TOTAL    27922     9936    12168    37580    29359     6012
  Objects
       Views:       62         ViewRootImpl:        2
  AppContexts:        5           Activities:        2
      Assets:        3        AssetManagers:        3
  Local Binders:        9        Proxy Binders:       18
  Death Recipients:        0
  OpenSSL Sockets:        0
  SQL
    MEMORY_USED:        0
   PAGECACHE_OVERFLOW:        0          MALLOC_SIZE:        0

我必须解析这些文件以获取 PID、 native 堆大小、 native 堆分配大小、Dalvik 堆大小、Dalvik 堆分配大小的值，并绘制具有这些堆大小的图表，如下所示

我正在使用以下代码来实现这一点:

import glob
import os
import re
import numpy as np
import matplotlib.pyplot as plt

os.chdir("D:\Python_Trainings\MemInfo\Data")
pid_arr = []
native_heapsize_arr = []
dalvik_heapsize_arr = []
native_heapalloc_arr = []
dalvik_heapalloc_arr = []
pkg_name_arr = []

#Method to parse the memory dump files
def parse_dumpFiles():
  for data_file in glob.glob("*.txt"):
    try:
      fo = open(data_file,"r")
      for line in fo:
        pid_match = re.search('pid\s+(\d+)',line)
        pkg_name_match = re.search("\[(\w+\.+\w+\.+\w+)\]",line)
        native_heapsize_match = re.search('(Native+\s+\d+\s+\d+\s+\d+\s+)+(\d+)',line)
        dalvik_heapsize_match = re.search('(Dalvik+\s+\d+\s+\d+\s+\d+\s+)+(\d+)',line)
        native_heapalloc_match = re.search('(Native+\s+\d+\s+\d+\s+\d+\s+\d+\s+)+(\d+)',line)
        dalvik_heapalloc_match = re.search('(Dalvik+\s+\d+\s+\d+\s+\d+\s+\d+\s+)+(\d+)',line)
        if pid_match:
          pid_arr.append(int(pid_match.group(1)))
        if native_heapsize_match:
          native_heapsize_arr.append(native_heapsize_match.group(2))
        if dalvik_heapsize_match:
          dalvik_heapsize_arr.append(dalvik_heapsize_match.group(2))
        if native_heapalloc_match:
          native_heapalloc_arr.append(native_heapalloc_match.group(2))
        if dalvik_heapalloc_match:
          dalvik_heapalloc_arr.append(dalvik_heapalloc_match.group(2))
        if pkg_name_match:
          if pkg_name_match.group(1) not in pkg_name_arr:
            pkg_name_arr.append(pkg_name_match.group(1))

    except IOError:
      print "Error: can\'t find file or read data"
    finally:
      fo.close()
#end of parse_dumpFiles() Method

#Method to plot from Memory Dumps
def plt_MemDump(pid_arr, native_heapsize_arr, dalvik_heapsize_arr,   native_heapalloc_arr, dalvik_heapalloc_arr, pkg_name_arr):

#Create a figure and axes with room for the table
  fig = plt.figure()
  ax = plt.axes([0.2, 0.2, 0.7, 0.7])

#Create labels for the rows and columns as tuples
  colLabels = ('0','10', '20', '30', '40', '50', '60', '70', '80', '90', '100')
  rowLabels = ('Native Heap Size','Native Heap Allocated','Dalvik Heap Size','Dalvik Heap Allocated','PID')

#Table data as a numpy array
  tableData = np.asarray([native_heapsize_arr,dalvik_heapsize_arr,native_heapalloc_arr,dalvik_heapalloc_arr,pid_arr],dtype=int)

#Get the current color cycle as a list, then reset the cycle to be at the beginning
  colors = []     
  while True:
    colors.append(ax._get_lines.color_cycle.next())
    if colors[0] == colors[-1] and len(colors)>1:
      colors.pop(-1)
      break

  for i in xrange(len(colors)-1):
    ax._get_lines.color_cycle.next()

#Show the table
  the_table = plt.table(cellText=tableData, rowLabels=rowLabels, rowColours=colors,    colLabels=colLabels, loc='bottom')

#Make some line plots
  xAxis_val = [0,10,20,30,40,50,60,70,80,90,100]
  ax.plot(xAxis_val,native_heapsize_arr, linewidth=2.5, marker="o", label="Native Heap Size")
  ax.plot(xAxis_val,dalvik_heapsize_arr, linewidth=2.5, marker="D", label="Dalvik Heap Size")
  ax.plot(xAxis_val,native_heapalloc_arr, linewidth=2.5, marker="^",label="Native Heap Allocated")
  ax.plot(xAxis_val,dalvik_heapalloc_arr, linewidth=2.5, marker="h", label="Dalvik Heap Allocated")

#show legend
  plt.legend(loc='upper right', fontsize=10)

#set the column color where PID is different from 1st PID 
  c=the_table.get_celld()[(5,3)]
  c.set_color('r')
  i=0
  while i<=10:
    c=the_table.get_celld()[(5,i)]
if(c.get_text().get_text()!=((the_table.get_celld()[(5,0)]).get_text().get_text())):
  c.set_color('r')
  (the_table.get_celld()[(4,i)]).set_color('r')
  (the_table.get_celld()[(3,i)]).set_color('r')
  (the_table.get_celld()[(2,i)]).set_color('r')
  (the_table.get_celld()[(1,i)]).set_color('r')
  i+=1

#Turn off x-axis ticks and show the plot              
  plt.xticks([])

#Configure Y axis
  plt.ylim(0,60000)
  plt.yticks([10000,20000,30000,40000,50000,60000])
  plt.grid(True)

#Setting the name of the window title of the plot  
  fig.canvas.set_window_title(pkg_name_arr[0] + "- Memory Dump Plot")

#Setting the Title of the plot
  plt.title(pkg_name_arr[0],color='r',fontsize=20)

#Setting Y Label 
  plt.ylabel('Heap Size', fontsize=14, color='r')

#show plot
  plt.show()
#end of plt_MemDump() Method

parse_dumpFiles()
plt_MemDump(pid_arr, native_heapsize_arr, dalvik_heapsize_arr, native_heapalloc_arr, dalvik_heapalloc_arr, pkg_name_arr)

现在我想用一些颜色标记表格中 PID 值与第一个 PID 值不同的列。(例如，第 30,60 和 100 列)。

谁能帮我实现这个目标？

Answer 1

matplotlib.pyplot.table已经为您提供了执行所需操作的工具:

• cellColours(与cellText形状相同):让你为每个单元格选择颜色
• colColours:作为rowColours，但用于列标题

如果您希望一列中的所有单元格都具有特定的颜色，您可以这样做

cellcolours = np.empty_like(tableData, dtype='object')
for i, cl in enumerate(colLabels):
    if cl > 50:
        cellcolours[:,i] = 'r'

然后调用 plt.table(尽管我建议您更改为 ax.table)并添加 cellColours=cellcolours 关键字。

如果您还想对列标题进行着色，只需执行上述操作即可

---

如果您希望在创建表格后能够更改单元格，table.get_celld() 返回一个单元格字典，其键是每个单元格位置的元组，例如:

{(0, 0): <matplotlib.table.Cell at 0x5d750d0>,  # these are column headers
 (0, 1): <matplotlib.table.Cell at 0x5d75290>,
 (0, 2): <matplotlib.table.Cell at 0x5d75450>,
 (0, 3): <matplotlib.table.Cell at 0x5d75610>,
 [...]
 (1, -1): <matplotlib.table.Cell at 0x5d757d0>, # this is a row header
 (1, 0): <matplotlib.table.Cell at 0x5a58110>,  # this is a cell
 (1, 1): <matplotlib.table.Cell at 0x5d74150>,
 (1, 2): <matplotlib.table.Cell at 0x5d74290>,
 (1, 3): <matplotlib.table.Cell at 0x5d743d0>,
 [...]
 (2, -1): <matplotlib.table.Cell at 0x5d75990>, # this is a row header
 [...] }

您可以使用元组访问每个单元格，例如

c=table.get_celld()[(1,1)]

您可以使用 c.set_color() 设置单元格颜色，并使用 c.get_text().get_text() 检查单元格中的文本(第一个 get_text 返回一个 Text 实例，第二个是其中的字符串)