如何制作直方图和箱型图

Question

我需要创建200个均匀分布的区间，并把我的数据放到这些区间里，这样我就可以用这些数据制作直方图。有没有人能帮我写一个脚本，来生成这200个区间，并把数据放进去。

这是我现在的代码：

#!/usr/bin/python
import operator
import matplotlib.pyplot as plt
import numpy as np

l=[]
with open("testdata") as f:
    line = f.next()
    f.next()# skip headers
    nat = int(line.split()[0])
    print nat

    for line in f:
        if line.strip():
        if line.strip():
            l.append(map(float,line.split()[1:]))  

    b = 0
    a = 1

for b in range(53):
    for a in range(b+1,54):
        vector1 = (l[b][0],l[b][1],l[b][2])
        vector2 = (l[a][0],l[a][1],l[a][2])

        x = vector1
        y = vector2
        vector3 = list(np.array(x) - np.array(y))

        dotProduct = reduce( operator.add, map( operator.mul, vector3, vector3))

        dp = dotProduct**.5
        print dp

        #data = dp
        #num_bins = 200 # <- number of bins for the histogram
        #plt.hist(data, num_bins)
        #plt.show()

错误信息：

/usr/lib64/python2.6/site-packages/matplotlib/backends/backend_gtk.py:621:     DeprecationWarning: Use the new widget gtk.Tooltip
  self.tooltips = gtk.Tooltips()
Traceback (most recent call last):
  File "vector_final", line 42, in <module>
plt.hist(data, num_bins)
  File "/usr/lib64/python2.6/site-packages/matplotlib/pyplot.py", line 2008, in hist
    ret = ax.hist(x, bins, range, normed, weights, cumulative, bottom, histtype, align,    orientation, rwidth, log, **kwargs)
   File "/usr/lib64/python2.6/site-packages/matplotlib/axes.py", line 7098, in hist
    w = [None]*len(x)
TypeError: len() of unsized object

Answer 1

你已经很接近了。你唯一缺少的就是正确地存储你的数据，并把它传递给直方图函数。

#!/usr/bin/python
import operator
import matplotlib.pyplot as plt
import numpy as np

l=[]
with open("testdata") as f:
    line = f.next()
    f.next()# skip headers
    nat = int(line.split()[0])
    print nat

    for line in f:
        # store striped line and only store if there is data on the line. 
        cleaned = line.strip() 
        if cleaned:
            # convert to float and remove characters in first index
            l.append(map(float,cleaned.split()[1:]))  

b = 0
a = 1

# create a list to store our calculations in
distances = []
num_vects = len(l)

for b in range(num_vects-1):
    for a in range(b+1,num_vects):
        vector1 = (l[b][0],l[b][1],l[b][2])
        vector2 = (l[a][0],l[a][1],l[a][2])

        x = vector1
        y = vector2
        vector3 = list(np.array(x) - np.array(y))

        dotProduct = reduce( operator.add, map( operator.mul, vector3, vector3))

        dp = dotProduct**.5

        # store individual data point into the list of calculated distances            
        distances.append(dp)

# plot histogram
num_bins = 200 # <- number of bins for the histogram

# store useful data returned by the histogram function
(n, bins, patches) = plt.hist(distances, num_bins)
plt.show()