add python
wanglei
parent
bc95cbbee3
commit
d58c40d3d6
|
|
@ -0,0 +1,825 @@
|
|||
原文链接地址：http://liam0205.me/2014/09/11/matplotlib-tutorial-zh-cn/
|
||||
|
||||
## 1.介绍
|
||||
|
||||
Matplotlib 可能是 Python 2D-绘图领域使用最广泛的套件。它能让使用者很轻松地将数据图形化，并且提供多样化的输出格式。这里将会探索 matplotlib 的常见用法。
|
||||
|
||||
## 2.pylab
|
||||
|
||||
pylab 是 matplotlib 面向对象绘图库的一个接口。它的语法和 Matlab 十分相近。也就是说，它主要的绘图命令和 Matlab 对应的命令有相似的参数。
|
||||
|
||||
## 3.初级绘制
|
||||
|
||||
这一节中，我们将从简到繁：先尝试用默认配置在同一张图上绘制正弦和余弦函数图像，然后逐步美化它。
|
||||
|
||||
### 1.取得正弦函数和预先函数的值：
|
||||
|
||||
```
|
||||
from matplotlib import pylab
|
||||
import numpy as np
|
||||
|
||||
def getData():
|
||||
X = np.linspace(-np.pi, np.pi, 256,endpoint=True)
|
||||
C,S = np.cos(X), np.sin(X)
|
||||
print X
|
||||
|
||||
getData()
|
||||
```
|
||||
|
||||
X 是一个 numpy 数组，包含了从 −π到 +π等间隔的 256 个值。C 和 S 则分别是这 256 个值对应的余弦和正弦函数值组成的 numpy 数组。
|
||||
|
||||
### 2.使用默认配置
|
||||
|
||||
Matplotlib 的默认配置都允许用户自定义。你可以调整大多数的默认配置：图片大小和分辨率（dpi）、线宽、颜色、风格、坐标轴、坐标轴以及网格的属性、文字与字体属性等。不过，matplotlib 的默认配置在大多数情况下已经做得足够好，你可能只在很少的情况下才会想更改这些默认配置。
|
||||
|
||||
### 3.默认配置的具体内容
|
||||
下面的代码中，我们展现了 matplotlib 的默认配置并辅以注释说明，这部分配置包含了有关绘图样式的所有配置。代码中的配置与默认配置完全相同，你可以在交互模式中修改其中的值来观察效果。
|
||||
|
||||
```
|
||||
import numpy as np
|
||||
import matplotlib.pyplot as plt
|
||||
|
||||
# 创建一个 8 * 6 点（point）的图，并设置分辨率为 80
|
||||
plt.figure(figsize=(8,6), dpi=80)
|
||||
|
||||
# 创建一个新的 1 * 1 的子图，接下来的图样绘制在其中的第 1 块（也是唯一的一块）
|
||||
plt.subplot(111)
|
||||
|
||||
X = np.linspace(-np.pi, np.pi, 256,endpoint=True)
|
||||
C,S = np.cos(X), np.sin(X)
|
||||
|
||||
# 绘制余弦曲线，使用蓝色的、连续的、宽度为 1 （像素）的线条
|
||||
plt.plot(X, C, color="blue", linewidth=1.0, linestyle="-")
|
||||
|
||||
# 绘制正弦曲线，使用绿色的、连续的、宽度为 1 （像素）的线条
|
||||
plt.plot(X, S, color="green", linewidth=1.0, linestyle="-")
|
||||
|
||||
# 设置横轴的上下限
|
||||
plt.xlim(-4.0,4.0)
|
||||
|
||||
# 设置横轴记号
|
||||
plt.xticks(np.linspace(-4,4,9,endpoint=True))
|
||||
|
||||
# 设置纵轴的上下限
|
||||
plt.ylim(-1.0,1.0)
|
||||
|
||||
# 设置纵轴记号
|
||||
plt.yticks(np.linspace(-1,1,5,endpoint=True))
|
||||
|
||||
# 以分辨率 72 来保存图片
|
||||
# savefig("../figures/exercice_2.png",dpi=72)
|
||||
|
||||
# 在屏幕上显示
|
||||
plt.show()
|
||||
```
|
||||
|
||||
### 4.改变线条的颜色和粗细
|
||||
首先，我们以蓝色和红色分别表示余弦和正弦函数，而后将线条变粗一点。接下来，我们在水平方向拉伸一下整个图。
|
||||
|
||||
```
|
||||
import numpy as np
|
||||
import matplotlib.pyplot as plt
|
||||
|
||||
plt.figure(figsize=(8,5), dpi=80)
|
||||
plt.subplot(111)
|
||||
|
||||
X = np.linspace(-np.pi, np.pi, 256,endpoint=True)
|
||||
C,S = np.cos(X), np.sin(X)
|
||||
|
||||
plt.plot(X, C, color="blue", linewidth=2.5, linestyle="-")
|
||||
plt.plot(X, S, color="red", linewidth=2.5, linestyle="-")
|
||||
|
||||
plt.xlim(-4.0,4.0)
|
||||
plt.xticks(np.linspace(-4,4,9,endpoint=True))
|
||||
|
||||
plt.ylim(-1.0,1.0)
|
||||
plt.yticks(np.linspace(-1,1,5,endpoint=True))
|
||||
|
||||
plt.show()
|
||||
```
|
||||
|
||||
|
||||
|
||||
### 5.设置图片边界
|
||||
当前的图片边界设置得不好，所以有些地方看得不是很清楚。
|
||||
|
||||
```
|
||||
import numpy as np
|
||||
import matplotlib.pyplot as plt
|
||||
|
||||
|
||||
plt.figure(figsize=(8,5), dpi=80)
|
||||
plt.subplot(111)
|
||||
|
||||
X = np.linspace(-np.pi, np.pi, 256,endpoint=True)
|
||||
C,S = np.cos(X), np.sin(X)
|
||||
|
||||
plt.plot(X, C, color="blue", linewidth=2.5, linestyle="-")
|
||||
plt.plot(X, S, color="red", linewidth=2.5, linestyle="-")
|
||||
|
||||
plt.xlim(X.min()*1.1, X.max()*1.1)
|
||||
plt.ylim(C.min()*1.1,C.max()*1.1)
|
||||
|
||||
plt.show()
|
||||
```
|
||||
|
||||
|
||||
|
||||
### 6.设置记号
|
||||
我们讨论正弦和余弦函数的时候，通常希望知道函数在 $±π$和 $±π/2$的值。这样看来，当前的设置就不那么理想了。
|
||||
|
||||
```
|
||||
import numpy as np
|
||||
import matplotlib.pyplot as plt
|
||||
|
||||
plt.figure(figsize=(8,5), dpi=80)
|
||||
plt.subplot(111)
|
||||
|
||||
X = np.linspace(-np.pi, np.pi, 256,endpoint=True)
|
||||
C,S = np.cos(X), np.sin(X)
|
||||
|
||||
plt.plot(X, C, color="blue", linewidth=2.5, linestyle="-")
|
||||
plt.plot(X, S, color="red", linewidth=2.5, linestyle="-")
|
||||
|
||||
plt.xlim(X.min()*1.1, X.max()*1.1)
|
||||
plt.xticks([-np.pi, -np.pi/2, 0, np.pi/2, np.pi])
|
||||
|
||||
plt.ylim(C.min()*1.1,C.max()*1.1)
|
||||
plt.yticks([-1, 0, +1])
|
||||
|
||||
plt.show()
|
||||
```
|
||||
|
||||
|
||||
|
||||
### 7.设置记号的标签
|
||||
记号现在没问题了，不过标签却不大符合期望。我们可以把 3.142当做是$π$，但毕竟不够精确。当我们设置记号的时候，我们可以同时设置记号的标签。注意这里使用了 LaTeX。
|
||||
|
||||
```
|
||||
import numpy as np
|
||||
import matplotlib.pyplot as plt
|
||||
|
||||
plt.figure(figsize=(8,5), dpi=80)
|
||||
plt.subplot(111)
|
||||
|
||||
X = np.linspace(-np.pi, np.pi, 256,endpoint=True)
|
||||
C,S = np.cos(X), np.sin(X)
|
||||
|
||||
plt.plot(X, C, color="blue", linewidth=2.5, linestyle="-")
|
||||
plt.plot(X, S, color="red", linewidth=2.5, linestyle="-")
|
||||
|
||||
plt.xlim(X.min()*1.1, X.max()*1.1)
|
||||
plt.xticks([-np.pi, -np.pi/2, 0, np.pi/2, np.pi],
|
||||
[r'$-\pi$', r'$-\pi/2$', r'$0$', r'$+\pi/2$', r'$+\pi$'])
|
||||
|
||||
plt.ylim(C.min()*1.1,C.max()*1.1)
|
||||
plt.yticks([-1, 0, +1],
|
||||
[r'$-1$', r'$0$', r'$+1$'])
|
||||
|
||||
plt.show()
|
||||
```
|
||||
|
||||
|
||||
|
||||
### 8.移动脊柱
|
||||
坐标轴线和上面的记号连在一起就形成了脊柱（Spines，一条线段上有一系列的凸起，是不是很像脊柱骨啊~），它记录了数据区域的范围。它们可以放在任意位置，不过至今为止，我们都把它放在图的四边。
|
||||
|
||||
实际上每幅图有四条脊柱（上下左右），为了将脊柱放在图的中间，我们必须将其中的两条（上和右）设置为无色，然后调整剩下的两条到合适的位置——数据空间的 0 点。
|
||||
|
||||
```
|
||||
import numpy as np
|
||||
import matplotlib.pyplot as plt
|
||||
|
||||
plt.figure(figsize=(8,5), dpi=80)
|
||||
ax = plt.subplot(111)
|
||||
|
||||
ax.spines['right'].set_color('none')
|
||||
ax.spines['top'].set_color('none')
|
||||
ax.xaxis.set_ticks_position('bottom')
|
||||
ax.spines['bottom'].set_position(('data',0))
|
||||
ax.yaxis.set_ticks_position('left')
|
||||
ax.spines['left'].set_position(('data',0))
|
||||
|
||||
X = np.linspace(-np.pi, np.pi, 256,endpoint=True)
|
||||
C,S = np.cos(X), np.sin(X)
|
||||
|
||||
plt.plot(X, C, color="blue", linewidth=2.5, linestyle="-")
|
||||
plt.plot(X, S, color="red", linewidth=2.5, linestyle="-")
|
||||
|
||||
|
||||
plt.xlim(X.min()*1.1, X.max()*1.1)
|
||||
plt.xticks([-np.pi, -np.pi/2, 0, np.pi/2, np.pi],
|
||||
[r'$-\pi$', r'$-\pi/2$', r'$0$', r'$+\pi/2$', r'$+\pi$'])
|
||||
|
||||
plt.ylim(C.min()*1.1,C.max()*1.1)
|
||||
plt.yticks([-1, 0, +1],
|
||||
[r'$-1$', r'$0$', r'$+1$'])
|
||||
|
||||
plt.show()
|
||||
```
|
||||
|
||||
|
||||
|
||||
### 9.添加图例
|
||||
我们在图的左上角添加一个图例。为此，我们只需要在 plot 函数里以「键 - 值」的形式增加一个参数。
|
||||
|
||||
```
|
||||
import numpy as np
|
||||
import matplotlib.pyplot as plt
|
||||
|
||||
plt.figure(figsize=(8,5), dpi=80)
|
||||
ax = plt.subplot(111)
|
||||
ax.spines['right'].set_color('none')
|
||||
ax.spines['top'].set_color('none')
|
||||
ax.xaxis.set_ticks_position('bottom')
|
||||
ax.spines['bottom'].set_position(('data',0))
|
||||
ax.yaxis.set_ticks_position('left')
|
||||
ax.spines['left'].set_position(('data',0))
|
||||
|
||||
X = np.linspace(-np.pi, np.pi, 256,endpoint=True)
|
||||
C,S = np.cos(X), np.sin(X)
|
||||
|
||||
plt.plot(X, C, color="blue", linewidth=2.5, linestyle="-", label="cosine")
|
||||
plt.plot(X, S, color="red", linewidth=2.5, linestyle="-", label="sine")
|
||||
|
||||
plt.xlim(X.min()*1.1, X.max()*1.1)
|
||||
plt.xticks([-np.pi, -np.pi/2, 0, np.pi/2, np.pi],
|
||||
[r'$-\pi$', r'$-\pi/2$', r'$0$', r'$+\pi/2$', r'$+\pi$'])
|
||||
|
||||
plt.ylim(C.min()*1.1,C.max()*1.1)
|
||||
plt.yticks([-1, +1],
|
||||
[r'$-1$', r'$+1$'])
|
||||
|
||||
plt.legend(loc='upper left', frameon=False)
|
||||
# plt.savefig("../figures/exercice_8.png",dpi=72)
|
||||
plt.show()
|
||||
```
|
||||
|
||||
|
||||
|
||||
### 10.给一些特殊点做注释
|
||||
我们希望在 2π/3的位置给两条函数曲线加上一个注释。首先，我们在对应的函数图像位置上画一个点；然后，向横轴引一条垂线，以虚线标记；最后，写上标签。
|
||||
|
||||
```
|
||||
import numpy as np
|
||||
import matplotlib.pyplot as plt
|
||||
|
||||
plt.figure(figsize=(8,5), dpi=80)
|
||||
ax = plt.subplot(111)
|
||||
ax.spines['right'].set_color('none')
|
||||
ax.spines['top'].set_color('none')
|
||||
ax.xaxis.set_ticks_position('bottom')
|
||||
ax.spines['bottom'].set_position(('data',0))
|
||||
ax.yaxis.set_ticks_position('left')
|
||||
ax.spines['left'].set_position(('data',0))
|
||||
|
||||
X = np.linspace(-np.pi, np.pi, 256,endpoint=True)
|
||||
C,S = np.cos(X), np.sin(X)
|
||||
|
||||
plt.plot(X, C, color="blue", linewidth=2.5, linestyle="-", label="cosine")
|
||||
plt.plot(X, S, color="red", linewidth=2.5, linestyle="-", label="sine")
|
||||
|
||||
plt.xlim(X.min()*1.1, X.max()*1.1)
|
||||
plt.xticks([-np.pi, -np.pi/2, 0, np.pi/2, np.pi],
|
||||
[r'$-\pi$', r'$-\pi/2$', r'$0$', r'$+\pi/2$', r'$+\pi$'])
|
||||
|
||||
plt.ylim(C.min()*1.1,C.max()*1.1)
|
||||
plt.yticks([-1, +1],
|
||||
[r'$-1$', r'$+1$'])
|
||||
|
||||
t = 2*np.pi/3
|
||||
plt.plot([t,t],[0,np.cos(t)],
|
||||
color ='blue', linewidth=1.5, linestyle="--")
|
||||
plt.scatter([t,],[np.cos(t),], 50, color ='blue')
|
||||
plt.annotate(r'$\sin(\frac{2\pi}{3})=\frac{\sqrt{3}}{2}$',
|
||||
xy=(t, np.sin(t)), xycoords='data',
|
||||
xytext=(+10, +30), textcoords='offset points', fontsize=16,
|
||||
arrowprops=dict(arrowstyle="->", connectionstyle="arc3,rad=.2"))
|
||||
|
||||
plt.plot([t,t],[0,np.sin(t)],
|
||||
color ='red', linewidth=1.5, linestyle="--")
|
||||
plt.scatter([t,],[np.sin(t),], 50, color ='red')
|
||||
plt.annotate(r'$\cos(\frac{2\pi}{3})=-\frac{1}{2}$',
|
||||
xy=(t, np.cos(t)), xycoords='data',
|
||||
xytext=(-90, -50), textcoords='offset points', fontsize=16,
|
||||
arrowprops=dict(arrowstyle="->", connectionstyle="arc3,rad=.2"))
|
||||
|
||||
plt.legend(loc='upper left', frameon=False)
|
||||
#plt.savefig("../figures/exercice_9.png",dpi=72)
|
||||
plt.show()
|
||||
```
|
||||
|
||||
|
||||
### 11.精益求精
|
||||
坐标轴上的记号标签被曲线挡住了，作为强迫症患者（雾）这是不能忍的。我们可以把它们放大，然后添加一个白色的半透明底色。这样可以保证标签和曲线同时可见。
|
||||
|
||||
```
|
||||
import numpy as np
|
||||
import matplotlib.pyplot as plt
|
||||
|
||||
plt.figure(figsize=(8,5), dpi=80)
|
||||
ax = plt.subplot(111)
|
||||
ax.spines['right'].set_color('none')
|
||||
ax.spines['top'].set_color('none')
|
||||
ax.xaxis.set_ticks_position('bottom')
|
||||
ax.spines['bottom'].set_position(('data',0))
|
||||
ax.yaxis.set_ticks_position('left')
|
||||
ax.spines['left'].set_position(('data',0))
|
||||
|
||||
X = np.linspace(-np.pi, np.pi, 256,endpoint=True)
|
||||
C,S = np.cos(X), np.sin(X)
|
||||
|
||||
plt.plot(X, C, color="blue", linewidth=2.5, linestyle="-", label="cosine")
|
||||
plt.plot(X, S, color="red", linewidth=2.5, linestyle="-", label="sine")
|
||||
|
||||
|
||||
plt.xlim(X.min()*1.1, X.max()*1.1)
|
||||
plt.xticks([-np.pi, -np.pi/2, 0, np.pi/2, np.pi],
|
||||
[r'$-\pi$', r'$-\pi/2$', r'$0$', r'$+\pi/2$', r'$+\pi$'])
|
||||
|
||||
plt.ylim(C.min()*1.1,C.max()*1.1)
|
||||
plt.yticks([-1, +1],
|
||||
[r'$-1$', r'$+1$'])
|
||||
|
||||
plt.legend(loc='upper left', frameon=False)
|
||||
|
||||
t = 2*np.pi/3
|
||||
plt.plot([t,t],[0,np.cos(t)],
|
||||
color ='blue', linewidth=1.5, linestyle="--")
|
||||
plt.scatter([t,],[np.cos(t),], 50, color ='blue')
|
||||
plt.annotate(r'$\sin(\frac{2\pi}{3})=\frac{\sqrt{3}}{2}$',
|
||||
xy=(t, np.sin(t)), xycoords='data',
|
||||
xytext=(+10, +30), textcoords='offset points', fontsize=16,
|
||||
arrowprops=dict(arrowstyle="->", connectionstyle="arc3,rad=.2"))
|
||||
|
||||
plt.plot([t,t],[0,np.sin(t)],
|
||||
color ='red', linewidth=1.5, linestyle="--")
|
||||
plt.scatter([t,],[np.sin(t),], 50, color ='red')
|
||||
plt.annotate(r'$\cos(\frac{2\pi}{3})=-\frac{1}{2}$',
|
||||
xy=(t, np.cos(t)), xycoords='data',
|
||||
xytext=(-90, -50), textcoords='offset points', fontsize=16,
|
||||
arrowprops=dict(arrowstyle="->", connectionstyle="arc3,rad=.2"))
|
||||
|
||||
for label in ax.get_xticklabels() + ax.get_yticklabels():
|
||||
label.set_fontsize(16)
|
||||
label.set_bbox(dict(facecolor='white', edgecolor='None', alpha=0.65 ))
|
||||
|
||||
#plt.savefig("../figures/exercice_10.png",dpi=72)
|
||||
plt.show()
|
||||
```
|
||||
|
||||
|
||||
|
||||
## 4.图像、子图、坐标轴和记号
|
||||
到目前为止，我们都用隐式的方法来绘制图像和坐标轴。快速绘图中，这是很方便的。我们也可以显式地控制图像、子图、坐标轴。Matplotlib 中的「图像」指的是用户界面看到的整个窗口内容。在图像里面有所谓「子图」。子图的位置是由坐标网格确定的，而「坐标轴」却不受此限制，可以放在图像的任意位置。我们已经隐式地使用过图像和子图：当我们调用 plot 函数的时候，matplotlib 调用 gca() 函数以及 gcf() 函数来获取当前的坐标轴和图像；如果无法获取图像，则会调用 figure() 函数来创建一个——严格地说，是用 subplot(1,1,1) 创建一个只有一个子图的图像。
|
||||
|
||||
|
||||
### 1.图像
|
||||
所谓「图像」就是 GUI 里以「Figure #」为标题的那些窗口。图像编号从 1 开始，与 MATLAB 的风格一致，而于 Python 从 0 开始编号的风格不同。以下参数是图像的属性：
|
||||
<table border="1"><colgroup><col width="17%"><col width="28%"><col width="54%"></colgroup><thead valign="bottom"><tr><th class="head">参数</th><th class="head">默认值</th><th class="head">描述</th></tr></thead><tbody valign="top"><tr><td>num</td><td>1</td><td>图像的数量</td></tr><tr><td>figsize</td><td>figure.figsize</td><td>图像的长和宽（英寸）</td></tr><tr><td>dpi</td><td>figure.dpi</td><td>分辨率（点/英寸）</td></tr><tr><td>facecolor</td><td>figure.facecolor</td><td>绘图区域的背景颜色</td></tr><tr><td>edgecolor</td><td>figure.edgecolor</td><td>绘图区域边缘的颜色</td></tr><tr><td>frameon</td><td>True</td><td>是否绘制图像边缘</td></tr></tbody></table>
|
||||
|
||||
|
||||
这些默认值可以在源文件中指明。不过除了图像数量这个参数，其余的参数都很少修改。
|
||||
你在图形界面中可以按下右上角的 X 来关闭窗口（OS X 系统是左上角）。Matplotlib 也提供了名为 close 的函数来关闭这个窗口。close 函数的具体行为取决于你提供的参数：
|
||||
1.不传递参数：关闭当前窗口；
|
||||
2.传递窗口编号或窗口实例（instance）作为参数：关闭指定的窗口；
|
||||
3.all：关闭所有窗口。
|
||||
|
||||
和其他对象一样，你可以使用 setp 或者是 set_something 这样的方法来设置图像的属性。
|
||||
|
||||
### 2.子图
|
||||
你可以用子图来将图样（plot）放在均匀的坐标网格中。用 subplot 函数的时候，你需要指明网格的行列数量，以及你希望将图样放在哪一个网格区域中。此外，gridspec 的功能更强大，你也可以选择它来实现这个功能。
|
||||
|
||||
```
|
||||
from pylab import *
|
||||
|
||||
subplot(2,1,1)
|
||||
xticks([]), yticks([])
|
||||
text(0.5,0.5, 'subplot(2,1,1)',ha='center',va='center',size=24,alpha=.5)
|
||||
|
||||
subplot(2,1,2)
|
||||
xticks([]), yticks([])
|
||||
text(0.5,0.5, 'subplot(2,1,2)',ha='center',va='center',size=24,alpha=.5)
|
||||
|
||||
# plt.savefig('../figures/subplot-horizontal.png', dpi=64)
|
||||
show()
|
||||
```
|
||||
|
||||
|
||||
|
||||
```
|
||||
from pylab import *
|
||||
|
||||
subplot(1,2,1)
|
||||
xticks([]), yticks([])
|
||||
text(0.5,0.5, 'subplot(1,2,1)',ha='center',va='center',size=24,alpha=.5)
|
||||
|
||||
subplot(1,2,2)
|
||||
xticks([]), yticks([])
|
||||
text(0.5,0.5, 'subplot(1,2,2)',ha='center',va='center',size=24,alpha=.5)
|
||||
|
||||
# plt.savefig('../figures/subplot-vertical.png', dpi=64)
|
||||
show()
|
||||
```
|
||||
|
||||
|
||||
|
||||
```
|
||||
from pylab import *
|
||||
|
||||
subplot(2,2,1)
|
||||
xticks([]), yticks([])
|
||||
text(0.5,0.5, 'subplot(2,2,1)',ha='center',va='center',size=20,alpha=.5)
|
||||
|
||||
subplot(2,2,2)
|
||||
xticks([]), yticks([])
|
||||
text(0.5,0.5, 'subplot(2,2,2)',ha='center',va='center',size=20,alpha=.5)
|
||||
|
||||
subplot(2,2,3)
|
||||
xticks([]), yticks([])
|
||||
text(0.5,0.5, 'subplot(2,2,3)',ha='center',va='center',size=20,alpha=.5)
|
||||
|
||||
subplot(2,2,4)
|
||||
xticks([]), yticks([])
|
||||
text(0.5,0.5, 'subplot(2,2,4)',ha='center',va='center',size=20,alpha=.5)
|
||||
|
||||
# savefig('../figures/subplot-grid.png', dpi=64)
|
||||
show()
|
||||
```
|
||||
|
||||
|
||||
|
||||
```
|
||||
from pylab import *
|
||||
import matplotlib.gridspec as gridspec
|
||||
|
||||
G = gridspec.GridSpec(3, 3)
|
||||
|
||||
axes_1 = subplot(G[0, :])
|
||||
xticks([]), yticks([])
|
||||
text(0.5,0.5, 'Axes 1',ha='center',va='center',size=24,alpha=.5)
|
||||
|
||||
axes_2 = subplot(G[1,:-1])
|
||||
xticks([]), yticks([])
|
||||
text(0.5,0.5, 'Axes 2',ha='center',va='center',size=24,alpha=.5)
|
||||
|
||||
axes_3 = subplot(G[1:, -1])
|
||||
xticks([]), yticks([])
|
||||
text(0.5,0.5, 'Axes 3',ha='center',va='center',size=24,alpha=.5)
|
||||
|
||||
axes_4 = subplot(G[-1,0])
|
||||
xticks([]), yticks([])
|
||||
text(0.5,0.5, 'Axes 4',ha='center',va='center',size=24,alpha=.5)
|
||||
|
||||
axes_5 = subplot(G[-1,-2])
|
||||
xticks([]), yticks([])
|
||||
text(0.5,0.5, 'Axes 5',ha='center',va='center',size=24,alpha=.5)
|
||||
|
||||
#plt.savefig('../figures/gridspec.png', dpi=64)
|
||||
show()
|
||||
```
|
||||
|
||||
|
||||
|
||||
### 3.坐标轴
|
||||
坐标轴和子图功能类似，不过它可以放在图像的任意位置。因此，如果你希望在一副图中绘制一个小图，就可以用这个功能。
|
||||
|
||||
```
|
||||
from pylab import *
|
||||
|
||||
axes([0.1,0.1,.8,.8])
|
||||
xticks([]), yticks([])
|
||||
text(0.6,0.6, 'axes([0.1,0.1,.8,.8])',ha='center',va='center',size=20,alpha=.5)
|
||||
|
||||
axes([0.2,0.2,.3,.3])
|
||||
xticks([]), yticks([])
|
||||
text(0.5,0.5, 'axes([0.2,0.2,.3,.3])',ha='center',va='center',size=16,alpha=.5)
|
||||
|
||||
#plt.savefig("../figures/axes.png",dpi=64)
|
||||
show()
|
||||
```
|
||||
|
||||
|
||||
|
||||
```
|
||||
from pylab import *
|
||||
|
||||
axes([0.1,0.1,.5,.5])
|
||||
xticks([]), yticks([])
|
||||
text(0.1,0.1, 'axes([0.1,0.1,.8,.8])',ha='left',va='center',size=16,alpha=.5)
|
||||
|
||||
axes([0.2,0.2,.5,.5])
|
||||
xticks([]), yticks([])
|
||||
text(0.1,0.1, 'axes([0.2,0.2,.5,.5])',ha='left',va='center',size=16,alpha=.5)
|
||||
|
||||
axes([0.3,0.3,.5,.5])
|
||||
xticks([]), yticks([])
|
||||
text(0.1,0.1, 'axes([0.3,0.3,.5,.5])',ha='left',va='center',size=16,alpha=.5)
|
||||
|
||||
axes([0.4,0.4,.5,.5])
|
||||
xticks([]), yticks([])
|
||||
text(0.1,0.1, 'axes([0.4,0.4,.5,.5])',ha='left',va='center',size=16,alpha=.5)
|
||||
|
||||
# plt.savefig("../figures/axes-2.png",dpi=64)
|
||||
show()
|
||||
```
|
||||
|
||||
|
||||
|
||||
### 4.记号
|
||||
良好的记号是图像的重要组成部分。Matplotlib 里的记号系统里的各个细节都是可以由用户个性化配置的。你可以用 Tick Locators 来指定在那些位置放置记号，用 Tick Formatters 来调整记号的样式。主要和次要的记号可以以不同的方式呈现。默认情况下，每一个次要的记号都是隐藏的，也就是说，默认情况下的次要记号列表是空的——NullLocator。
|
||||
|
||||
下面有为不同需求设计的一些 Locators。
|
||||
<table border="1"><tr><th class="head">类型</th> <th class="head">说明</th></tr><tr><td><tt>NullLocator</tt></td><td><p>No ticks.</p><img src="http://www.loria.fr/~rougier/teaching/matplotlib/figures/ticks-NullLocator.png"></td></tr><tr><td><tt>IndexLocator</tt></td><td><p>Place a tick on every multiple of some base number of points plotted.</p><img src="http://www.loria.fr/~rougier/teaching/matplotlib/figures/ticks-IndexLocator.png"></td></tr><tr><td><tt>FixedLocator</tt></td><td><p>Tick locations are fixed.</p><img src="http://www.loria.fr/~rougier/teaching/matplotlib/figures/ticks-FixedLocator.png"></td></tr><tr><td><tt>LinearLocator</tt></td><td><p>Determine the tick locations.</p><img src="http://www.loria.fr/~rougier/teaching/matplotlib/figures/ticks-LinearLocator.png"></td></tr><tr><td><tt>MultipleLocator</tt></td><td><p>Set a tick on every integer that is multiple of some base.</p><img src="http://www.loria.fr/~rougier/teaching/matplotlib/figures/ticks-MultipleLocator.png"></td></tr><tr><td><tt>AutoLocator</tt></td><td><p>Select no more than n intervals at nice locations.</p><img src="http://www.loria.fr/~rougier/teaching/matplotlib/figures/ticks-AutoLocator.png"></td></tr><tr><td><tt>LogLocator</tt></td><td><p>Determine the tick locations for log axes.</p><img src="http://www.loria.fr/~rougier/teaching/matplotlib/figures/ticks-LogLocator.png"></td></tr></table>
|
||||
|
||||
这些 Locators 都是 matplotlib.ticker.Locator 的子类，你可以据此定义自己的 Locator。以日期为 ticks 特别复杂，因此 Matplotlib 提供了 matplotlib.dates 来实现这一功能。
|
||||
|
||||
## 5.其他类型的图
|
||||
接下来的内容是练习。请运用你学到的知识，从提供的代码开始，实现配图所示的效果。具体的答案可以点击配图下载。
|
||||
|
||||
### 1.普通图
|
||||
```
|
||||
import numpy as np
|
||||
import matplotlib.pyplot as plt
|
||||
|
||||
n = 256
|
||||
X = np.linspace(-np.pi,np.pi,n,endpoint=True)
|
||||
Y = np.sin(2*X)
|
||||
|
||||
plt.axes([0.025,0.025,0.95,0.95])
|
||||
|
||||
plt.plot (X, Y+1, color='blue', alpha=1.00)
|
||||
plt.fill_between(X, 1, Y+1, color='blue', alpha=.25)
|
||||
|
||||
plt.plot (X, Y-1, color='blue', alpha=1.00)
|
||||
plt.fill_between(X, -1, Y-1, (Y-1) > -1, color='blue', alpha=.25)
|
||||
plt.fill_between(X, -1, Y-1, (Y-1) < -1, color='red', alpha=.25)
|
||||
|
||||
plt.xlim(-np.pi,np.pi), plt.xticks([])
|
||||
plt.ylim(-2.5,2.5), plt.yticks([])
|
||||
# savefig('../figures/plot_ex.png',dpi=48)
|
||||
plt.show()
|
||||
```
|
||||
|
||||
|
||||
|
||||
### 2.散点图
|
||||
|
||||
```
|
||||
import numpy as np
|
||||
import matplotlib.pyplot as plt
|
||||
|
||||
n = 1024
|
||||
X = np.random.normal(0,1,n)
|
||||
Y = np.random.normal(0,1,n)
|
||||
T = np.arctan2(Y,X)
|
||||
|
||||
plt.axes([0.025,0.025,0.95,0.95])
|
||||
plt.scatter(X,Y, s=75, c=T, alpha=.5)
|
||||
|
||||
plt.xlim(-1.5,1.5), plt.xticks([])
|
||||
plt.ylim(-1.5,1.5), plt.yticks([])
|
||||
# savefig('../figures/scatter_ex.png',dpi=48)
|
||||
plt.show()
|
||||
```
|
||||
|
||||
|
||||
|
||||
### 3.条形图
|
||||
|
||||
```
|
||||
import numpy as np
|
||||
import matplotlib.pyplot as plt
|
||||
|
||||
n = 12
|
||||
X = np.arange(n)
|
||||
Y1 = (1-X/float(n)) * np.random.uniform(0.5,1.0,n)
|
||||
Y2 = (1-X/float(n)) * np.random.uniform(0.5,1.0,n)
|
||||
|
||||
plt.axes([0.025,0.025,0.95,0.95])
|
||||
plt.bar(X, +Y1, facecolor='#9999ff', edgecolor='white')
|
||||
plt.bar(X, -Y2, facecolor='#ff9999', edgecolor='white')
|
||||
|
||||
for x,y in zip(X,Y1):
|
||||
plt.text(x+0.4, y+0.05, '%.2f' % y, ha='center', va= 'bottom')
|
||||
|
||||
for x,y in zip(X,Y2):
|
||||
plt.text(x+0.4, -y-0.05, '%.2f' % y, ha='center', va= 'top')
|
||||
|
||||
plt.xlim(-.5,n), plt.xticks([])
|
||||
plt.ylim(-1.25,+1.25), plt.yticks([])
|
||||
|
||||
# savefig('../figures/bar_ex.png', dpi=48)
|
||||
plt.show()
|
||||
```
|
||||
|
||||
|
||||
|
||||
### 4.等高线图
|
||||
|
||||
```
|
||||
import numpy as np
|
||||
import matplotlib.pyplot as plt
|
||||
|
||||
def f(x,y):
|
||||
return (1-x/2+x**5+y**3)*np.exp(-x**2-y**2)
|
||||
|
||||
n = 256
|
||||
x = np.linspace(-3,3,n)
|
||||
y = np.linspace(-3,3,n)
|
||||
X,Y = np.meshgrid(x,y)
|
||||
|
||||
plt.axes([0.025,0.025,0.95,0.95])
|
||||
|
||||
plt.contourf(X, Y, f(X,Y), 8, alpha=.75, cmap=plt.cm.hot)
|
||||
C = plt.contour(X, Y, f(X,Y), 8, colors='black', linewidth=.5)
|
||||
plt.clabel(C, inline=1, fontsize=10)
|
||||
|
||||
plt.xticks([]), plt.yticks([])
|
||||
# savefig('../figures/contour_ex.png',dpi=48)
|
||||
plt.show()
|
||||
```
|
||||
|
||||
|
||||
|
||||
### 5.灰度图（Imshow）
|
||||
|
||||
```
|
||||
import numpy as np
|
||||
import matplotlib.pyplot as plt
|
||||
|
||||
def f(x,y):
|
||||
return (1-x/2+x**5+y**3)*np.exp(-x**2-y**2)
|
||||
|
||||
n = 10
|
||||
x = np.linspace(-3,3,3.5*n)
|
||||
y = np.linspace(-3,3,3.0*n)
|
||||
X,Y = np.meshgrid(x,y)
|
||||
Z = f(X,Y)
|
||||
|
||||
plt.axes([0.025,0.025,0.95,0.95])
|
||||
plt.imshow(Z,interpolation='nearest', cmap='bone', origin='lower')
|
||||
plt.colorbar(shrink=.92)
|
||||
|
||||
plt.xticks([]), plt.yticks([])
|
||||
# savefig('../figures/imshow_ex.png', dpi=48)
|
||||
plt.show()
|
||||
```
|
||||
|
||||
|
||||
|
||||
### 6.饼状图
|
||||
|
||||
```
|
||||
import numpy as np
|
||||
import matplotlib.pyplot as plt
|
||||
|
||||
n = 20
|
||||
Z = np.ones(n)
|
||||
Z[-1] *= 2
|
||||
|
||||
plt.axes([0.025,0.025,0.95,0.95])
|
||||
|
||||
plt.pie(Z, explode=Z*.05, colors = ['%f' % (i/float(n)) for i in range(n)])
|
||||
plt.gca().set_aspect('equal')
|
||||
plt.xticks([]), plt.yticks([])
|
||||
|
||||
# savefig('../figures/pie_ex.png',dpi=48)
|
||||
plt.show()
|
||||
```
|
||||
|
||||
|
||||
|
||||
### 7.量场图（Quiver Plots）
|
||||
|
||||
```
|
||||
import numpy as np
|
||||
import matplotlib.pyplot as plt
|
||||
|
||||
n = 8
|
||||
X,Y = np.mgrid[0:n,0:n]
|
||||
T = np.arctan2(Y-n/2.0, X-n/2.0)
|
||||
R = 10+np.sqrt((Y-n/2.0)**2+(X-n/2.0)**2)
|
||||
U,V = R*np.cos(T), R*np.sin(T)
|
||||
|
||||
plt.axes([0.025,0.025,0.95,0.95])
|
||||
plt.quiver(X,Y,U,V,R, alpha=.5)
|
||||
plt.quiver(X,Y,U,V, edgecolor='k', facecolor='None', linewidth=.5)
|
||||
|
||||
plt.xlim(-1,n), plt.xticks([])
|
||||
plt.ylim(-1,n), plt.yticks([])
|
||||
|
||||
# savefig('../figures/quiver_ex.png',dpi=48)
|
||||
plt.show()
|
||||
```
|
||||
|
||||
|
||||
|
||||
### 8.网格
|
||||
|
||||
```
|
||||
import numpy as np
|
||||
import matplotlib.pyplot as plt
|
||||
|
||||
ax = plt.axes([0.025,0.025,0.95,0.95])
|
||||
|
||||
ax.set_xlim(0,4)
|
||||
ax.set_ylim(0,3)
|
||||
ax.xaxis.set_major_locator(plt.MultipleLocator(1.0))
|
||||
ax.xaxis.set_minor_locator(plt.MultipleLocator(0.1))
|
||||
ax.yaxis.set_major_locator(plt.MultipleLocator(1.0))
|
||||
ax.yaxis.set_minor_locator(plt.MultipleLocator(0.1))
|
||||
ax.grid(which='major', axis='x', linewidth=0.75, linestyle='-', color='0.75')
|
||||
ax.grid(which='minor', axis='x', linewidth=0.25, linestyle='-', color='0.75')
|
||||
ax.grid(which='major', axis='y', linewidth=0.75, linestyle='-', color='0.75')
|
||||
ax.grid(which='minor', axis='y', linewidth=0.25, linestyle='-', color='0.75')
|
||||
ax.set_xticklabels([])
|
||||
ax.set_yticklabels([])
|
||||
|
||||
# savefig('../figures/grid_ex.png',dpi=48)
|
||||
plt.show()
|
||||
```
|
||||
|
||||
|
||||
|
||||
### 9.多重网格
|
||||
|
||||
```
|
||||
import numpy as np
|
||||
import matplotlib.pyplot as plt
|
||||
|
||||
fig = plt.figure()
|
||||
fig.subplots_adjust(bottom=0.025, left=0.025, top = 0.975, right=0.975)
|
||||
|
||||
plt.subplot(2,1,1)
|
||||
plt.xticks([]), plt.yticks([])
|
||||
|
||||
plt.subplot(2,3,4)
|
||||
plt.xticks([]), plt.yticks([])
|
||||
|
||||
plt.subplot(2,3,5)
|
||||
plt.xticks([]), plt.yticks([])
|
||||
|
||||
plt.subplot(2,3,6)
|
||||
plt.xticks([]), plt.yticks([])
|
||||
|
||||
# plt.savefig('../figures/multiplot_ex.png',dpi=48)
|
||||
plt.show()
|
||||
```
|
||||
|
||||
|
||||
|
||||
### 10.极轴图
|
||||
|
||||
```
|
||||
import numpy as np
|
||||
import matplotlib.pyplot as plt
|
||||
|
||||
ax = plt.axes([0.025,0.025,0.95,0.95], polar=True)
|
||||
|
||||
N = 20
|
||||
theta = np.arange(0.0, 2*np.pi, 2*np.pi/N)
|
||||
radii = 10*np.random.rand(N)
|
||||
width = np.pi/4*np.random.rand(N)
|
||||
bars = plt.bar(theta, radii, width=width, bottom=0.0)
|
||||
|
||||
for r,bar in zip(radii, bars):
|
||||
bar.set_facecolor( plt.cm.jet(r/10.))
|
||||
bar.set_alpha(0.5)
|
||||
|
||||
ax.set_xticklabels([])
|
||||
ax.set_yticklabels([])
|
||||
# savefig('../figures/polar_ex.png',dpi=48)
|
||||
plt.show()
|
||||
```
|
||||
|
||||
|
||||
|
||||
### 11.3D 图
|
||||
|
||||
```
|
||||
import numpy as np
|
||||
import matplotlib.pyplot as plt
|
||||
from mpl_toolkits.mplot3d import Axes3D
|
||||
|
||||
fig = plt.figure()
|
||||
ax = Axes3D(fig)
|
||||
X = np.arange(-4, 4, 0.25)
|
||||
Y = np.arange(-4, 4, 0.25)
|
||||
X, Y = np.meshgrid(X, Y)
|
||||
R = np.sqrt(X**2 + Y**2)
|
||||
Z = np.sin(R)
|
||||
|
||||
ax.plot_surface(X, Y, Z, rstride=1, cstride=1, cmap=plt.cm.hot)
|
||||
ax.contourf(X, Y, Z, zdir='z', offset=-2, cmap=plt.cm.hot)
|
||||
ax.set_zlim(-2,2)
|
||||
|
||||
# savefig('../figures/plot3d_ex.png',dpi=48)
|
||||
plt.show()
|
||||
```
|
||||
|
||||
|
||||
|
||||
## 参考文献：
|
||||
1.https://www.jianshu.com/p/dade014011ca Python数字图像处理:图像的绘制
|
||||
2.https://www.jianshu.com/p/f380169aee6c?utm_campaign=maleskine&utm_content=note&utm_medium=seo_notes&utm_source=recommendation Matplotlib - 用Python绘制2D和3D图像
|
||||
|
|
@ -0,0 +1,206 @@
|
|||
这是最受欢迎的Python模块的前200名, 评比的依据是模块在github上开源Python项目中被使用的次数. 看看有没有跌破你的眼镜!
|
||||
|
||||
名次 模块名称 被使用项目数
|
||||
|
||||
```
|
||||
1 sys 7858
|
||||
2 os 6983
|
||||
3 re 5663
|
||||
4 time 5268
|
||||
5 random 3339
|
||||
6 datetime 3310
|
||||
7 setuptools 3225
|
||||
8 logging 3189
|
||||
9 subprocess 2991
|
||||
10 unittest 2923
|
||||
11 json 2865
|
||||
12 urllib 2641
|
||||
13 __future__ 2541
|
||||
14 collections 2295
|
||||
15 shutil 2255
|
||||
16 string 2254
|
||||
17 threading 2220
|
||||
18 math 2205
|
||||
19 tempfile 2151
|
||||
20 urllib2 2095
|
||||
21 socket 2079
|
||||
22 traceback 2070
|
||||
23 copy 2055
|
||||
24 optparse 2053
|
||||
25 hashlib 2025
|
||||
26 StringIO 1812
|
||||
27 django.db 1780
|
||||
28 distutils.core 1780
|
||||
29 struct 1753
|
||||
30 itertools 1720
|
||||
31 django.conf 1719
|
||||
32 types 1667
|
||||
33 django.core.management 1658
|
||||
34 django.contrib 1604
|
||||
35 glob 1582
|
||||
36 urlparse 1559
|
||||
37 base64 1555
|
||||
38 inspect 1523
|
||||
39 django.http 1510
|
||||
40 django 1496
|
||||
41 cStringIO 1447
|
||||
42 os.path 1432
|
||||
43 django.shortcuts 1419
|
||||
44 functools 1395
|
||||
45 argparse 1379
|
||||
46 operator 1360
|
||||
47 warnings 1345
|
||||
48 codecs 1308
|
||||
49 django.template 1262
|
||||
50 django.test 1216
|
||||
51 pickle 1200
|
||||
52 errno 1133
|
||||
53 pprint 1107
|
||||
54 signal 1102
|
||||
55 requests 1082
|
||||
56 cgi 1052
|
||||
57 django.contrib.auth.models 1018
|
||||
58 getopt 1010
|
||||
59 ConfigParser 972
|
||||
60 django.core.urlresolvers 963
|
||||
61 httplib 947
|
||||
62 uuid 938
|
||||
63 pkg_resources 906
|
||||
64 imp 901
|
||||
65 doctest 899
|
||||
66 csv 893
|
||||
67 django.db.models 877
|
||||
68 zipfile 861
|
||||
69 textwrap 860
|
||||
70 django.utils 844
|
||||
71 gzip 817
|
||||
72 io 804
|
||||
73 platform 798
|
||||
74 django.core.exceptions 775
|
||||
75 md5 755
|
||||
76 xml.dom 753
|
||||
77 binascii 751
|
||||
78 fnmatch 750
|
||||
79 Queue 744
|
||||
80 getpass 719
|
||||
81 select 701
|
||||
82 utils 699
|
||||
83 stat 693
|
||||
84 numpy 685
|
||||
85 mimetypes 683
|
||||
86 ctypes 678
|
||||
87 models 673
|
||||
88 django.contrib.auth.decorators 669
|
||||
89 django.core.management.base 664
|
||||
90 zlib 649
|
||||
91 simplejson 648
|
||||
92 thread 644
|
||||
93 distutils 643
|
||||
94 django.template.loader 632
|
||||
95 fcntl 617
|
||||
96 contextlib 614
|
||||
97 django.utils.encoding 605
|
||||
98 decimal 592
|
||||
99 atexit 576
|
||||
100 locale 575
|
||||
101 django.core 572
|
||||
102 PIL 554
|
||||
103 cPickle 552
|
||||
104 calendar 551
|
||||
105 yaml 547
|
||||
106 multiprocessing 544
|
||||
107 hmac 540
|
||||
108 django.utils.safestring 540
|
||||
109 django.conf.urls 537
|
||||
110 weakref 533
|
||||
111 unicodedata 527
|
||||
112 mock 517
|
||||
113 tarfile 504
|
||||
114 django.contrib.auth 504
|
||||
115 settings 500
|
||||
116 smtplib 480
|
||||
117 htmlentitydefs 475
|
||||
118 array 474
|
||||
119 sqlite3 462
|
||||
120 google.appengine.api 457
|
||||
121 email 457
|
||||
122 django.template.defaultfilters 455
|
||||
123 util 454
|
||||
124 sha 452
|
||||
125 flask 452
|
||||
126 config 444
|
||||
127 UserDict 440
|
||||
128 django.contrib.sites.models 439
|
||||
129 shlex 438
|
||||
130 lxml 436
|
||||
131 difflib 432
|
||||
132 django.core.mail 431
|
||||
133 BaseHTTPServer 424
|
||||
134 webbrowser 424
|
||||
135 gc 419
|
||||
136 django.forms 417
|
||||
137 django.contrib.contenttypes.models 413
|
||||
138 Image 407
|
||||
139 jinja2 406
|
||||
140 django.utils.html 396
|
||||
141 bisect 394
|
||||
142 twisted.internet 384
|
||||
143 django.conf.urls.defaults 379
|
||||
144 commands 375
|
||||
145 pdb 374
|
||||
146 pwd 373
|
||||
147 sqlalchemy 368
|
||||
148 pytest 366
|
||||
149 django.core.cache 364
|
||||
150 BeautifulSoup 359
|
||||
151 xml.dom.minidom 357
|
||||
152 django.views.generic.simple 355
|
||||
153 django.views.generic 355
|
||||
154 xmlrpclib 355
|
||||
155 Cookie 355
|
||||
156 exceptions 353
|
||||
157 sets 349
|
||||
158 posixpath 348
|
||||
159 SocketServer 347
|
||||
160 code 343
|
||||
161 django.core.paginator 338
|
||||
162 gettext 338
|
||||
163 google.appengine.ext.webapp 336
|
||||
164 urllib.request 334
|
||||
165 south.db 332
|
||||
166 urllib.parse 329
|
||||
167 new 329
|
||||
168 pstats 329
|
||||
169 msvcrt 328
|
||||
170 __builtin__ 325
|
||||
171 ez_setup 324
|
||||
172 gtk 323
|
||||
173 django.dispatch 321
|
||||
174 MySQLdb 318
|
||||
175 HTMLParser 315
|
||||
176 termios 311
|
||||
177 scipy 311
|
||||
178 pkgutil 309
|
||||
179 abc 309
|
||||
180 matplotlib 307
|
||||
181 django.db.models.signals 306
|
||||
182 six 306
|
||||
183 xml.sax.saxutils 303
|
||||
184 xml.sax 301
|
||||
185 chardet 298
|
||||
186 heapq 296
|
||||
187 django.test.client 295
|
||||
188 cProfile 295
|
||||
189 bs4 290
|
||||
190 sgmllib 289
|
||||
191 django.utils.functional 287
|
||||
192 xml.etree 286
|
||||
193 ssl 283
|
||||
194 tokenize 282
|
||||
195 django.db.models.query 281
|
||||
196 xml 281
|
||||
197 nose.tools 281
|
||||
198 nose 275
|
||||
199 pygments 273
|
||||
200 gobject 270
|
||||
```
|
||||
|
|
@ -0,0 +1,192 @@
|
|||
## 1.json是什么
|
||||
JSON(JavaScript Object Notation) 是一种轻量级的数据交换格式。它基于JavaScript Programming Language, Standard ECMA-262 3rd Edition - December 1999的一个子集。json最大的优势就是独立于编程语言， 易于人阅读和编写，同时也易于机器解析和生成。所以，如果我们需要在不同的编程语言之间传递对象，或者需要在网络世界中传输数据，我们都可以将数据序列化为json格式。当将其序列化为json格式以后，可以方便地被所有编程语言读取与解析，也可以方便地被存储在磁盘中或者用于网络传输。正因为有这些优点，json在实际中使用非常广泛。
|
||||
|
||||
JSON构建于两种结构：
|
||||
1.“名称/值”对的集合（A collection of name/value pairs）。不同的语言中，它被理解为对象（object），纪录（record），结构（struct），字典（dictionary），哈希表（hash table），有键列表（keyed list），或者关联数组 （associative array）。
|
||||
2.值的有序列表（An ordered list of values）。在大部分语言中，它被理解为数组（array）。
|
||||
|
||||
## 2.python数据类型与json数据类型的映射关系
|
||||
Python类型 JSON类型
|
||||
dict $\hspace{1.3cm}$ {}
|
||||
list $\hspace{1.5cm}$ []
|
||||
str(unicode) $\hspace{0.5cm}$ string
|
||||
int(float,long) $\hspace{0.3cm}$number
|
||||
True(False) $\hspace{0.7cm}$ true(false)
|
||||
None $\hspace{1.7cm}$ null
|
||||
|
||||
## 3.python中json模块的简单用法
|
||||
python中内置的json模块就可以完成从python对象到json格式数据的转换。
|
||||
先来看看怎么把一个python对象变为一个json串：
|
||||
|
||||
```
|
||||
>>> import json
|
||||
>>> dic = dict(name='James',age=18)
|
||||
>>> dic_to_str = json.dumps(dic)
|
||||
>>> dic_to_str
|
||||
'{"age": 18, "name": "James"}'
|
||||
>>> type(dic_to_str)
|
||||
<type 'str'>
|
||||
```
|
||||
|
||||
通过dumps方法，就把一个dict变为了一个json串，返回的是一个str对象。dumps方法相当于一个encoding过程，是对简单数据类型的编码。也可以理解是对python对象的一个序列化的过程。
|
||||
|
||||
接下来看看如何把一个json串变为一个python对象：
|
||||
|
||||
```
|
||||
>>> str_to_dic = json.loads(dic_to_str)
|
||||
>>> str_to_dic
|
||||
{u'age': 18, u'name': u'James'}
|
||||
>>> type(str_to_dic)
|
||||
<type 'dict'>
|
||||
```
|
||||
|
||||
同理通过loads方法，将一个json串，变为了一个dict对象，返回的是一个dict。loads方法相当于是一个decoding过程，是对字符串的一个解码。当然也可以理解为是对python对象的反序列化！
|
||||
|
||||
## 4.将自己的类转成json串
|
||||
前面我们看了怎样将python中的内置dict对象转化为json串的过程。在很多时候，我们希望将自己定义的类也转化为json串。比如我们自己定义了person类，并且希望将其序列化为json串：
|
||||
|
||||
```
|
||||
#!/usr/bin/env python
|
||||
#coding:utf-8
|
||||
|
||||
import json
|
||||
|
||||
class Person(object):
|
||||
|
||||
def __init__(self,name,age):
|
||||
self.name = name
|
||||
self.age = age
|
||||
|
||||
person = Person("James",18)
|
||||
print (json.dumps(person))
|
||||
```
|
||||
|
||||
将上面的代码run起来以后，会有以下错误：
|
||||
|
||||
```
|
||||
Traceback (most recent call last):
|
||||
File "./person.py", line 13, in <module>
|
||||
print (json.dumps(person))
|
||||
File "/Users/lei.wang/anaconda/lib/python2.7/json/__init__.py", line 244, in dumps
|
||||
return _default_encoder.encode(obj)
|
||||
File "/Users/lei.wang/anaconda/lib/python2.7/json/encoder.py", line 207, in encode
|
||||
chunks = self.iterencode(o, _one_shot=True)
|
||||
File "/Users/lei.wang/anaconda/lib/python2.7/json/encoder.py", line 270, in iterencode
|
||||
return _iterencode(o, 0)
|
||||
File "/Users/lei.wang/anaconda/lib/python2.7/json/encoder.py", line 184, in default
|
||||
raise TypeError(repr(o) + " is not JSON serializable")
|
||||
TypeError: <__main__.Person object at 0x101a00090> is not JSON serializable
|
||||
```
|
||||
|
||||
很明显可以看出，是我们无法将person对象序列化！
|
||||
我们再仔细观察一下dumps()方法：
|
||||
|
||||
```
|
||||
json.dumps(obj, skipkeys=False, ensure_ascii=True, check_circular=True, allow_nan=True, cls=None, indent=None, separators=None, encoding="utf-8", default=None, sort_keys=False, **kw)
|
||||
|
||||
Serialize obj to a JSON formatted str using this conversion table. If ensure_ascii is false, the result may contain non-ASCII characters and the return value may be a unicode instance.
|
||||
```
|
||||
|
||||
参数default选项就是将一个对象变为一个可序列化的Json对象。前面的Person类就是因为没有指定default选项，所以无法序列化。现在我们为Person类写一个专门的序列化方法：
|
||||
|
||||
```
|
||||
!/usr/bin/env python
|
||||
#coding:utf-8
|
||||
|
||||
import json
|
||||
|
||||
class Person(object):
|
||||
|
||||
def __init__(self,name,age):
|
||||
self.name = name
|
||||
self.age = age
|
||||
|
||||
def person_to_dict(person):
|
||||
return {
|
||||
'name': person.name,
|
||||
'age': person.age
|
||||
}
|
||||
|
||||
person = Person("James",18)
|
||||
print json.dumps(person,default = person_to_dict)
|
||||
```
|
||||
|
||||
将代码运行起来：
|
||||
|
||||
```
|
||||
{"age": 18, "name": "James"}
|
||||
```
|
||||
|
||||
上面这么做的目的，就是通过person_to_dict方法，将person对象转化为dict对象，然后通过将default选项设置为person_to_dict，就可以使用dumps方法将person对象序列化为json对象了！
|
||||
|
||||
当然，如果我们想偷点懒，也是可以的。可以不写person_to_dict方法，直接调用person类的__dict__方法：
|
||||
|
||||
```
|
||||
!/usr/bin/env python
|
||||
#coding:utf-8
|
||||
|
||||
import json
|
||||
|
||||
class Person(object):
|
||||
|
||||
def __init__(self,name,age):
|
||||
self.name = name
|
||||
self.age = age
|
||||
|
||||
def person_to_dict(person):
|
||||
return {
|
||||
'name': person.name,
|
||||
'age': person.age
|
||||
}
|
||||
|
||||
person = Person("James",18)
|
||||
print json.dumps(person,default = lambda obj:obj.__dict__)
|
||||
print json.dumps(person,default = person_to_dict)
|
||||
```
|
||||
|
||||
让代码run起来：
|
||||
|
||||
```
|
||||
{"age": 18, "name": "James"}
|
||||
{"age": 18, "name": "James"}
|
||||
```
|
||||
|
||||
由此可见，print两行代码的效果是一致的！
|
||||
|
||||
同样的道理，既然能将自己定义的类转化为json串，同理也能将json串变为类。我们先看看loads方法：
|
||||
|
||||
```
|
||||
json.loads(s[, encoding[, cls[, object_hook[, parse_float[, parse_int[, parse_constant[, object_pairs_hook[, **kw]]]]]]]])
|
||||
Deserialize s (a str or unicode instance containing a JSON document) to a Python object using this conversion table.
|
||||
|
||||
object_hook is an optional function that will be called with the result of any object literal decoded (a dict). The return value of object_hook will be used instead of the dict. This feature can be used to implement custom decoders (e.g. JSON-RPC class hinting).
|
||||
```
|
||||
|
||||
仿照上面的思路：
|
||||
|
||||
```
|
||||
#!/usr/bin/env python
|
||||
#coding:utf-8
|
||||
|
||||
import json
|
||||
|
||||
class Person(object):
|
||||
|
||||
def __init__(self,name,age):
|
||||
self.name = name
|
||||
self.age = age
|
||||
|
||||
def dic_to_person(dic):
|
||||
return Person(dic['name'],dic['age'])
|
||||
|
||||
json_person = '{"name":"James","age":18}'
|
||||
print json.loads(json_person,object_hook = dic_to_person)
|
||||
```
|
||||
|
||||
让代码run起来：
|
||||
|
||||
```
|
||||
<__main__.Person object at 0x1022071d0>
|
||||
```
|
||||
|
||||
由此可见，我们通过loads方法，达到了将json字符串反序列化为Person对象的目的！
|
||||
|
|
@ -0,0 +1,101 @@
|
|||
代码中经常有一些生成随机数的需求。特意整理了一下python中random模块的一些相关用法。
|
||||
|
||||
## python生成随机数
|
||||
|
||||
随机整数：
|
||||
|
||||
```
|
||||
>>> import random
|
||||
>>> random.randint(0,99)
|
||||
21
|
||||
```
|
||||
|
||||
随机选取0到100间的偶数：
|
||||
|
||||
```
|
||||
>>> import random
|
||||
>>> random.randrange(0, 101, 2)
|
||||
42
|
||||
```
|
||||
|
||||
随机浮点数：
|
||||
|
||||
```
|
||||
>>> import random
|
||||
>>> random.random()
|
||||
0.85415370477785668 范围0-1.0
|
||||
>>> random.uniform(1, 10)
|
||||
5.4221167969800881
|
||||
```
|
||||
|
||||
## 选择一个随机元素
|
||||
|
||||
```
|
||||
>>> random.choice("abc")
|
||||
'b'
|
||||
```
|
||||
|
||||
## 将一个列表中的元素打乱
|
||||
|
||||
```
|
||||
>>> p = ["Python","is", "powerful","simple", "and so on..."]
|
||||
>>> random.shuffle(p)
|
||||
>>> print p
|
||||
['and so on...', 'Python', 'powerful', 'is', 'simple']
|
||||
```
|
||||
|
||||
## 从指定序列中随机获取指定长度片段
|
||||
|
||||
```
|
||||
>>> list = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
|
||||
>>> a=random.sample(list,5)
|
||||
>>> a
|
||||
[5, 2, 9, 1, 3]
|
||||
>>> list
|
||||
[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
|
||||
```
|
||||
|
||||
## 随机字符：
|
||||
|
||||
```
|
||||
>>> import random
|
||||
>>> random.choice('abcdefg&#%^*f')
|
||||
'd'
|
||||
```
|
||||
|
||||
## 多个字符中选取特定数量的字符：
|
||||
|
||||
```
|
||||
>>> import random
|
||||
random.sample('abcdefghij',3)
|
||||
['a', 'd', 'b']
|
||||
```
|
||||
|
||||
## 多个字符中选取特定数量的字符组成新字符串：
|
||||
|
||||
```
|
||||
>>> import random
|
||||
>>> import string
|
||||
>>> string.join(random.sample(['a','b','c','d','e','f','g','h','i','j'], 3)).replace(" ","")
|
||||
'fih'
|
||||
```
|
||||
|
||||
## 随机选取字符串：
|
||||
|
||||
```
|
||||
>>> import random
|
||||
>>> random.choice ( ['apple', 'pear', 'peach', 'orange', 'lemon'] )
|
||||
'lemon'
|
||||
```
|
||||
|
||||
## 洗牌：
|
||||
|
||||
```
|
||||
>>> import random
|
||||
>>> items = [1, 2, 3, 4, 5, 6]
|
||||
>>> random.shuffle(items)
|
||||
>>> items
|
||||
[3, 2, 5, 6, 4, 1]
|
||||
```
|
||||
|
||||
|
||||
|
|
@ -0,0 +1,155 @@
|
|||
## 1.set类型用途
|
||||
在python中，dict是一种非常重要的数据结构，几乎无处不见。dict是一种典型的k-v结构，不管其中的元素多少，查找速度是非常快的，可以认为是近似的$O(1)$的查找速度而与dict本身的大小无关。
|
||||
|
||||
在许多场景中，我们只关注dict的key，而对value不care，目的只是确保这个集合中元素的唯一性。这个时候，set就能派上用场了。set中是一系列元素的集合，这一点与list很类似。但是，set中的元素有最重要的两点性质：1.无序，这一点与dict很像，意味着就不能用索引访问里面的元素；2.没有重复元素，保证了里面元素的唯一性。
|
||||
|
||||
## 2.set的一些简单用法
|
||||
先看看如何初始化
|
||||
|
||||
```
|
||||
>>> x1 = set("abc")
|
||||
>>> x1
|
||||
set(['a', 'c', 'b'])
|
||||
>>> x2 = set(['a','b','d','e'])
|
||||
>>> x2
|
||||
set(['a', 'b', 'e', 'd'])
|
||||
>>> x3 = set("hello")
|
||||
>>> x3
|
||||
set(['h', 'e', 'l', 'o'])
|
||||
```
|
||||
|
||||
需要稍微注意的一点是，`x2 = set(['a','b','d','e'])`中，`['a','b','d','e']`是指传入的参数是一个list。而x2显示出来的`set(['a', 'b', 'e', 'd'])`只是说明set中有'a','b','c','d'四个元素，这个[]并不是表示一个list。
|
||||
|
||||
从x3可以看出，重复元素在set中已经自动被干掉！
|
||||
|
||||
如果要添加元素，可以有add或者update：
|
||||
|
||||
```
|
||||
>>> y = set("123")
|
||||
>>> y
|
||||
set(['1', '3', '2'])
|
||||
>>> y.add("4")
|
||||
>>> y
|
||||
set(['1', '3', '2', '4'])
|
||||
>>> y.update("456")
|
||||
>>> y
|
||||
set(['1', '3', '2', '5', '4', '6'])
|
||||
```
|
||||
|
||||
add不用多解释。update的解释如下：
|
||||
|
||||
```
|
||||
Update a set with the union of itself and others.
|
||||
```
|
||||
|
||||
不难看出，update是将两个set做并集的操作。或者说，是将一个set中的元素添加到原set中！而且由set的不重复性可知，不管是add操作还是update操作，都不会添加进重复元素！
|
||||
|
||||
如果想要删除元素，可以用remove方法：
|
||||
|
||||
```
|
||||
>>> y.remove('1')
|
||||
>>> y
|
||||
set(['3', '2', '5', '4', '6'])
|
||||
```
|
||||
|
||||
需要注意的是，使用remove方法的时候，需要先判断元素在不在set中。如果元素不在集合中，会报KeyError的错误：
|
||||
|
||||
```
|
||||
>>> y.remove('a')
|
||||
Traceback (most recent call last):
|
||||
File "<stdin>", line 1, in <module>
|
||||
KeyError: 'a'
|
||||
```
|
||||
|
||||
## 3.遍历set
|
||||
对于任意一种集合类型，遍历都是最基本也是最重要的操作。因为set是一种无序集合，所以遍历的时候，不能通过下标索引的方式。而且不同的机器，遍历出来的顺序也不尽相同：
|
||||
|
||||
```
|
||||
>>> x = set("abc")
|
||||
>>> for i in x:
|
||||
... print i
|
||||
...
|
||||
a
|
||||
c
|
||||
b
|
||||
```
|
||||
|
||||
## 4.set求交并差集等操作
|
||||
求两个set的并集：
|
||||
|
||||
```
|
||||
>>> x1 = set("abc")
|
||||
>>> x2 = set("abde")
|
||||
>>> x1 | x2
|
||||
set(['a', 'c', 'b', 'e', 'd'])
|
||||
>>> x1.union(x2)
|
||||
set(['a', 'c', 'b', 'e', 'd'])
|
||||
```
|
||||
|
||||
求交集：
|
||||
|
||||
```
|
||||
>>> x1 & x2
|
||||
set(['a', 'b'])
|
||||
>>> x1.intersection(x2)
|
||||
set(['a', 'b'])
|
||||
```
|
||||
|
||||
在x1中但不在x2中：
|
||||
|
||||
```
|
||||
>>> x1 - x2
|
||||
set(['c'])
|
||||
>>> x1.difference(x2)
|
||||
set(['c'])
|
||||
```
|
||||
|
||||
不同时在x1,x2中出现：
|
||||
|
||||
```
|
||||
>>> x1 ^ x2
|
||||
set(['c', 'e', 'd'])
|
||||
>>> x1.symmetric_difference(x2)
|
||||
set(['c', 'e', 'd'])
|
||||
```
|
||||
|
||||
## 5.set(dict)中的key只能为不可变对象
|
||||
不管是set也好，还是dict也罢，里面的key只能为不可变对象。这一点非常重要！
|
||||
在python中，像数值型(number)，字符串(str)，元祖(tuple)为不可变类型(immutable)，而像列表(list)，字典(dict)，集合(set)等为可变类型(mutable)。
|
||||
|
||||
看一个不可变类型的例子：
|
||||
|
||||
```
|
||||
>>>a = 1 #将名字a与内存中值为1的内存绑定在一起
|
||||
>>>a = 2 #将名字a与内存中值为2的内存绑定在一起，而不是修改原来a绑定的内存中的值，这时，内存中值为1的内存地址引用计数-1，当引用计数为0时，内存地址被回收
|
||||
>>>b = a #变量b执行与a绑定的内存
|
||||
>>>b = 3 #创建一个内存值为3的内存地址与变量名字b进行绑定。这是a还是指向值为2的内存地址。
|
||||
>>>a,b
|
||||
>>>(2,3)
|
||||
```
|
||||
|
||||
再看一个可变类型的例子：
|
||||
|
||||
```
|
||||
def mutable(b = []): #函数使用了缺省变量
|
||||
b.append(0)
|
||||
return b
|
||||
>>>mutable()
|
||||
[0]
|
||||
>>>mutable()
|
||||
[0,0]
|
||||
>>>mutable()
|
||||
[0,0,0]
|
||||
```
|
||||
|
||||
对于set类型来说，所有的key均为不可变对象。如果添加可变对象，会报错：
|
||||
|
||||
```
|
||||
>>> x1 = set("abc")
|
||||
>>> x1.add([1,2])
|
||||
Traceback (most recent call last):
|
||||
File "<stdin>", line 1, in <module>
|
||||
TypeError: unhashable type: 'list'
|
||||
```
|
||||
|
||||
我们在上面想对一个set添加一个list类型的元素，list是可变对象，所以unhashable无法添加成功！
|
||||
|
|
@ -0,0 +1,44 @@
|
|||
在所有介绍正则表达式元字符的资料中，都会提到\b，表示单词边界的意思。在python里写了一段小测试代码测试一下\b:
|
||||
|
||||
```
|
||||
#!/usr/bin/env python
|
||||
|
||||
import re
|
||||
|
||||
def t1():
|
||||
pattern = re.compile("\bprint\b")
|
||||
search = pattern.search('aaa print 123 hello')
|
||||
if search:
|
||||
print search.group(0)
|
||||
else:
|
||||
print "NO"
|
||||
|
||||
t1()
|
||||
```
|
||||
|
||||
运行此脚本以后，控制台华丽丽地输出一个大大的"NO",瞬间懵逼了。咋回事，难道我理解能力太差。又换了好多种自认为没问题的方式，都华丽丽地跟预期不对头。
|
||||
|
||||
经过长时间的google（百度你是查不出来滴骚年们），终于找到了问题所在。各位同学请先看代码：
|
||||
|
||||
```
|
||||
#!/usr/bin/env python
|
||||
|
||||
import re
|
||||
|
||||
def t2():
|
||||
pattern = re.compile(r"\bprint\b")
|
||||
search = pattern.search('aaa print 123 hello')
|
||||
if search:
|
||||
print "YES"
|
||||
print search.group(0)
|
||||
else:
|
||||
print "NO"
|
||||
|
||||
t2()
|
||||
```
|
||||
|
||||
各位看官看出区别来了么。没错，就"\bprint\b"前头多了个"r"。为什么会酱紫呢。
|
||||
|
||||
这是python字符串与正则表达式最糟糕，没有之一的冲突。在python字符串中，"b"是反斜杠字符，ASCII值是8。如果你没有使用 raw 字符串时，那么 Python 将会把 "\b" 转换成一个回退符，你的 RE 将无法象你希望的那样匹配它了。
|
||||
所以同学们，在使用python做正则的时候，当你想使用\b元字符的时候，一定得注意咯。怎么做，不用我再说了吧。
|
||||
为了解决这个问题，花了大概得有一个半小时查资料。所以虽然时间已经很晚了，还是赶紧记下来再睡觉，心里才踏实。
|
||||
|
|
@ -0,0 +1,85 @@
|
|||
获取当前路径
|
||||
```
|
||||
>>> import os
|
||||
>>> os.getcwd()
|
||||
'/home/lei.wang/merge_user_labels'
|
||||
>>> os.path.abspath('.')
|
||||
'/home/lei.wang/merge_user_labels'
|
||||
>>> os.path.abspath(os.curdir)
|
||||
'/home/lei.wang/merge_user_labels'
|
||||
```
|
||||
|
||||
获取上层路径
|
||||
```
|
||||
>>> os.path.abspath('..')
|
||||
'/home/lei.wang'
|
||||
```
|
||||
|
||||
将path分割成目录和文件名二元组返回。
|
||||
```
|
||||
>>> os.path.split('/home/webopa/lei.wang/datas/datas_stable/good_rate')
|
||||
('/home/webopa/lei.wang/datas/datas_stable', 'good_rate')
|
||||
```
|
||||
|
||||
返回path的目录。其实就是os.path.split(path)的第一个元素。
|
||||
```
|
||||
>>> os.path.dirname('/home/webopa/lei.wang/datas/datas_stable/good_rate')
|
||||
'/home/webopa/lei.wang/datas/datas_stable'
|
||||
```
|
||||
|
||||
返回path最后的文件名。如何path以／或\结尾，那么就会返回空值。即os.path.split(path)的第二个元素。
|
||||
```
|
||||
>>> os.path.basename('/home/webopa/lei.wang/datas/datas_stable/good_rate')
|
||||
'good_rate'
|
||||
```
|
||||
|
||||
改变路径
|
||||
```
|
||||
>>> os.chdir('/home/lei.wang/datas')
|
||||
>>> os.getcwd()
|
||||
'/home/lei.wang/datas'
|
||||
```
|
||||
这样大部分的文件操作现在是相对于 /home/lei.wang/datas 来了，例如fobj = open('Hello.txt')，实际上打开的是/home/lei.wang/datas/Hello.txt
|
||||
|
||||
|
||||
判断是否是文件
|
||||
```
|
||||
>>> os.path.isfile('/home/webopa/lei.wang/datas/datas_stable/good_rate')
|
||||
True
|
||||
>>> os.path.isfile('/home/webopa/lei.wang/datas/datas_stable')
|
||||
False
|
||||
```
|
||||
|
||||
判断是否是文件夹
|
||||
```
|
||||
>>> os.path.isdir('/home/webopa/lei.wang/datas/datas_stable/good_rate')
|
||||
False
|
||||
>>> os.path.isdir('/home/webopa/lei.wang/datas/datas_stable')
|
||||
True
|
||||
```
|
||||
|
||||
判断路径是否存在（包括文件以及文件夹）
|
||||
```
|
||||
>>> os.path.exists('/home/webopa/lei.wang/datas/datas_stable/good_rate')
|
||||
True
|
||||
>>> os.path.exists('/home/webopa/lei.wang/datas/datas_stable')
|
||||
True
|
||||
```
|
||||
|
||||
返回文件的大小
|
||||
```
|
||||
>>> os.path.getsize('/home/webopa/lei.wang/datas/datas_stable/good_rate')
|
||||
751
|
||||
```
|
||||
|
||||
返回path所指向的文件或者目录的最后存取时间
|
||||
```
|
||||
>>> os.path.getatime('/home/webopa/lei.wang/datas/datas_stable')
|
||||
1458617090.3319671
|
||||
```
|
||||
|
||||
返回path所指向的文件或者目录的最后修改时间
|
||||
```
|
||||
>>> os.path.getmtime('/home/webopa/lei.wang/datas/datas_stable/good_rate')
|
||||
1457424457.9110916
|
||||
```
|
||||
|
|
@ -0,0 +1,24 @@
|
|||
1.按value对dic进行排序,返回一个列表，列表的元素是k-v对：
|
||||
|
||||
```
|
||||
list_open = sorted(dic_open_app.items(),key = lambda d:d[1],reverse = True)
|
||||
```
|
||||
|
||||
2.为整个dic设置默认值：
|
||||
|
||||
```
|
||||
from collections import defaultdict
|
||||
dic_device = defaultdict(int)
|
||||
```
|
||||
|
||||
3.用dict函数生成字典：
|
||||
```
|
||||
>>> a=[1,2,3]
|
||||
>>> b=['a','b','c']
|
||||
>>> zip(a,b)
|
||||
[(1, 'a'), (2, 'b'), (3, 'c')]
|
||||
>>> dict(zip(a,b))
|
||||
{1: 'a', 2: 'b', 3: 'c'}
|
||||
```
|
||||
|
||||
|
||||
|
|
@ -0,0 +1,68 @@
|
|||
现在有如下格式的json串：
|
||||
```
|
||||
"detail_time":"2016-03-30 16:00:00","device_id":"123456","os":"Html5Wap","session_flow_id":"1d1819f3-8e19-4597-b50d-ba379adcd8e5","user_longitude":0.0000,"user_latitude":0.0000,"search_id":xxx,"search_guid":-543326548,"search_type":7,"AAA":4,"BBB":-1,"CCC":[],"DDD":3,"EEE":2,"FFF":1459267200,"GGG":1459353600,"aaa":90954603,"bbb":[{"xxx":1500848,"x":1,"bf":0,"pp":2,"sroom":2,"ppp":108,"cost":97.2,"coupon":108,"drr":108},{"xxx":1500851,"x":1,"bf":0,"pp":1,"sroom":2,"ppp":108,"cost":97.2,"coupon":108,"drr":108},{"xxx":2336691,"x":1,"bf":1,"pp":1,"sroom":3,"ppp":199,"cost":169.15,"coupon":191,"drr":199},{"xxx":2336692,"x":1,"bf":1,"pp":2,"sroom":4,"ppp":102,"cost":91.8,"coupon":102,"drr":102},{"xxx":1500848,"x":1,"bf":0,"pp":2,"sroom":3,"ppp":118,"cost":106.2,"coupon":118,"drr":118},{"xxx":1500851,"x":1,"bf":0,"pp":1,"sroom":3,"ppp":118,"cost":106.2,"coupon":118,"drr":118},{"xxx":2336693,"x":1,"bf":1,"pp":1,"sroom":5,"ppp":199,"cost":169.15,"coupon":191,"drr":199},{"xxx":2336694,"x":1,"bf":1,"pp":2,"sroom":6,"ppp":112,"cost":100.3,"coupon":112,"drr":112},{"xxx":1500848,"x":1,"bf":0,"pp":2,"sroom":1,"ppp":98,"cost":88.2,"coupon":98,"drr":98},{"xxx":1500851,"x":1,"bf":0,"pp":1,"sroom":1,"ppp":98,"cost":88.2,"coupon":98,"drr":98},{"xxx":2336687,"x":1,"bf":1,"pp":1,"sroom":1,"ppp":189,"cost":160.65,"coupon":182,"drr":189},{"xxx":2336689,"x":1,"bf":1,"pp":2,"sroom":2,"ppp":93,"cost":83.3,"coupon":93,"drr":93},{"xxx":1500848,"x":1,"bf":0,"pp":2,"sroom":4,"ppp":128,"cost":115.2,"coupon":128,"drr":128},{"xxx":1500851,"x":1,"bf":0,"pp":1,"sroom":4,"ppp":128,"cost":115.2,"coupon":128,"drr":128},{"xxx":2336695,"x":1,"bf":1,"pp":1,"sroom":7,"ppp":239,"cost":203.15,"coupon":230,"drr":239},{"xxx":2336696,"x":1,"bf":1,"pp":2,"sroom":8,"ppp":121,"cost":108.8,"coupon":121,"drr":121}],"ppp_min":93.00,"ppp_max":239.00,"ppp_avg":134.88,"ppp_med":118.00,"ppp_min_cost":83.30,"ppp_min_promotion_type":-1,"ppp_min_promotion_amount":-1,"bf_ppp_min":149.00,"bf_ppp_min_cost":83.30,"bf_ppp_min_promotion_type":-1,"bf_ppp_min_promotion_amount":-1}
|
||||
```
|
||||
|
||||
现在想拿到device_id的具体值。最简单的方式就是用解析json串的方式得到，代码如下：
|
||||
|
||||
```
|
||||
#!/usr/bin/env python
|
||||
#coding:utf-8
|
||||
|
||||
import json
|
||||
import sys
|
||||
import collections
|
||||
import time
|
||||
|
||||
def t1():
|
||||
start = time.clock()
|
||||
for line in sys.stdin:
|
||||
try:
|
||||
line = line.strip()
|
||||
decoded = json.loads(line)
|
||||
device_id = decoded["device_id"]
|
||||
print device_id
|
||||
except Exception,ex:
|
||||
pass
|
||||
|
||||
end = time.clock()
|
||||
print "The cost time is: %f" %(end - start)
|
||||
|
||||
t1()
|
||||
```
|
||||
|
||||
以上代码能顺利完成任务。
|
||||
|
||||
不幸的是，现在是大数据时代，数据量嘛，自然都很大。用了一万条数据做测试，耗时达到了惊人的。。。将近10s。
|
||||
|
||||
转换下思路，采用正则匹配的方式
|
||||
|
||||
```
|
||||
#!/usr/bin/env python
|
||||
|
||||
import re
|
||||
import sys
|
||||
import time
|
||||
|
||||
def t1():
|
||||
start = time.clock()
|
||||
count = 0
|
||||
for line in sys.stdin:
|
||||
line = line.strip()
|
||||
pattern = re.compile("(?:\"device_id\":\")([^\"]+)")
|
||||
search = pattern.search(line)
|
||||
if search:
|
||||
count += 1
|
||||
#print search.groups()[0]
|
||||
end = time.clock()
|
||||
print "The count is: %d" %(count)
|
||||
print "The cost time is: %f" %(end - start)
|
||||
|
||||
t1()
|
||||
```
|
||||
|
||||
注意匹配的时候
|
||||
|
||||
`re.compile("(?:\"device_id\":\")([^\"]+)")`
|
||||
第一个分组表示不捕获，只捕获后面的分组。
|
||||
同样一万条数据，运行耗时是。。。0.05s。效率提高了多少倍，表示算不过来了。
|
||||
Loading…
Reference in New Issue