我正在尝试在列表中查找给定百分比的数据范围。我希望我的结果是该范围内的最高值和最低值。这是我到目前为止最简单的可行解决方案。 “字符串格式仅用于测试，当我实现它时，它将仅返回所需的值”。如果您不理解我要实现的目标，请运行我的代码，您应该能够理解我要实现的目标。
#Sample Data List
data = [
4.252, 5.878, 1.435, -0.112, 6.97, -1.812, 0.887, 1.724, -1.452, 5.193,
-1.001, 11.085, 1.335, 11.763, -7.284, -1.733, 3.175, 3.077, 0.249, -2.095,
-0.253, 11.095, 5.184, 1.45, -3.882, 8.251, -4.234, -0.096, 5.957, -4.473,
-3.874, 3.246, -0.929, -1.707, 2.079, 0.647, -8.189, 2.074, 3.226, 0.123,
-3.097, -5.706, 4.276, 7.377, -5.861, 0.357, 0.966, -0.63, 2.129, 1.514,
6.82, -1.854, 8.394, 5.141, -4.501, 1.307, -2.812, -0.348, 2.729, 2.232,
4.096, -2.257, -4.802, -1.116, 1.346, 4.733, -1.391, -2.986, 2.8, 4.949,
-4.101, 2.727, -1.267, -15.034, 5.322, 7.011, 6.36, 0.16, 0.719, 4.302,
1.365, 3.098, -2.892, -4.589, -5.516, 2.182, -6.019, -6.75, 15.499, -4.58,
3.516, 1.18, 9.648, -1.21, -10.911, -0.583, -0.545, 3.286, 0.51, 9.578,
-2.444, 2.771, -3.846, -3.819, 1.877, 1.392, -2.784, -5.907, 4.206, 1.42,
-2.279, -0.358, -0.649, 2.052, 1.04, 1.764, -3.156, -2.685, 0.106, 3.569,
0.944, 3.797, -0.76, 4.89, -3.014, -2.118, -1.142, -1.578, -8.84, 3.034,
-2.693, -2.989, -0.815, -2.504, 3.147, 1.596, -2.94, 0.906, -0.154, -3.765
]
#Input for percent range
percent = 50
#Get half of percentage
halfPercent = int(int((len(data) * float('.'+str(percent))/2)))
#Build string for printing later and create a counter
string = str(percent)+'% of data entries are beween values '
counter = 0
#Sort data and iterate up until it get to the counter gets to the halfPercent
for item in sorted(data):
if item >= 0:
counter += 1
if counter >= halfPercent:
string += str(item)
counter = 0
break
string += ' and '
#Sort data and iterate up until it get to the counter gets to the halfPercent
for item in sorted(data, reverse=True):
if item <= 0:
counter += 1
if counter >= halfPercent:
string += str(item)
break
#Do the printing
print 'Min is ' + str(min(data)) + ' and Max is ' + str(max(data))
print string
这似乎不是很pythonic，它所做的几乎没有很多代码。有哪些更好，更有效的方法？
编辑和更新... 使用和略微更改@DMfll发布的答案代码很有帮助。这是我的新代码。
#Sample data
data = [
4.252, 5.878, 1.435, -0.112, 6.97, -1.812, 0.887, 1.724, -1.452, 5.193,
-1.001, 11.085, 1.335, 11.763, -7.284, -1.733, 3.175, 3.077, 0.249, -2.095,
-0.253, 11.095, 5.184, 1.45, -3.882, 8.251, -4.234, -0.096, 5.957, -4.473,
-3.874, 3.246, -0.929, -1.707, 2.079, 0.647, -8.189, 2.074, 3.226, 0.123,
-3.097, -5.706, 4.276, 7.377, -5.861, 0.357, 0.966, -0.63, 2.129, 1.514,
6.82, -1.854, 8.394, 5.141, -4.501, 1.307, -2.812, -0.348, 2.729, 2.232,
4.096, -2.257, -4.802, -1.116, 1.346, 4.733, -1.391, -2.986, 2.8, 4.949,
-4.101, 2.727, -1.267, -15.034, 5.322, 7.011, 6.36, 0.16, 0.719, 4.302,
1.365, 3.098, -2.892, -4.589, -5.516, 2.182, -6.019, -6.75, 15.499, -4.58,
3.516, 1.18, 9.648, -1.21, -10.911, -0.583, -0.545, 3.286, 0.51, 9.578,
-2.444, 2.771, -3.846, -3.819, 1.877, 1.392, -2.784, -5.907, 4.206, 1.42,
-2.279, -0.358, -0.649, 2.052, 1.04, 1.764, -3.156, -2.685, 0.106, 3.569,
0.944, 3.797, -0.76, 4.89, -3.014, -2.118, -1.142, -1.578, -8.84, 3.034,
-2.693, -2.989, -0.815, -2.504, 3.147, 1.596, -2.94, 0.906, -0.154, -3.765
]
#Percent value needs to be variable
percent = 90
#Sorting and finding the percentage of data
half_way = int(len(data)*(float(""".{}""".format(percent))/2))
#Dictionary that will be returned from function later
returnDict = {
'max' : max(data),
'min' : min(data),
'high' : max([item for item in sorted(data) if item >= 0][0:half_way]),
'low' : min([item for item in reversed(sorted(data)) if item <= 0][0:half_way])
}
#Print simply to view data
print """Max is {}, Min is {} and {}% of data entries are between values {} and {}""".format(returnDict['max'],
returnDict['min'],
percent,
returnDict['low'],
returnDict['high'])
输出看起来像这样。
Max is 15.499, Min is -15.034 and 90% of data entries are between values -8.84 and 6.36
我仍然想知道是否可以用更少的代码来完成。也许使用numpy或其他库？
答案 0 :(得分：0)
此代码的输出与问题中代码的输出相同。
data = [
4.252, 5.878, 1.435, -0.112, 6.97, -1.812, 0.887, 1.724, -1.452, 5.193,
-1.001, 11.085, 1.335, 11.763, -7.284, -1.733, 3.175, 3.077, 0.249, -2.095,
-0.253, 11.095, 5.184, 1.45, -3.882, 8.251, -4.234, -0.096, 5.957, -4.473,
-3.874, 3.246, -0.929, -1.707, 2.079, 0.647, -8.189, 2.074, 3.226, 0.123,
-3.097, -5.706, 4.276, 7.377, -5.861, 0.357, 0.966, -0.63, 2.129, 1.514,
6.82, -1.854, 8.394, 5.141, -4.501, 1.307, -2.812, -0.348, 2.729, 2.232,
4.096, -2.257, -4.802, -1.116, 1.346, 4.733, -1.391, -2.986, 2.8, 4.949,
-4.101, 2.727, -1.267, -15.034, 5.322, 7.011, 6.36, 0.16, 0.719, 4.302,
1.365, 3.098, -2.892, -4.589, -5.516, 2.182, -6.019, -6.75, 15.499, -4.58,
3.516, 1.18, 9.648, -1.21, -10.911, -0.583, -0.545, 3.286, 0.51, 9.578,
-2.444, 2.771, -3.846, -3.819, 1.877, 1.392, -2.784, -5.907, 4.206, 1.42,
-2.279, -0.358, -0.649, 2.052, 1.04, 1.764, -3.156, -2.685, 0.106, 3.569,
0.944, 3.797, -0.76, 4.89, -3.014, -2.118, -1.142, -1.578, -8.84, 3.034,
-2.693, -2.989, -0.815, -2.504, 3.147, 1.596, -2.94, 0.906, -0.154, -3.765]
half_way = len(data) // 4 # // division returns an int
sorted_data = sorted(data)
print("""Min is {} and Max is {}
50% of data entries are between values {} and {}""".format(
max(sorted_data),
min(sorted_data),
max([item for item in sorted_data if item >= 0][0:half_way]),
min([item for item in reversed(sorted_data) if item <= 0][0:half_way]),
)) # an alternate way of reversing an array is sorted_data[::-1]
最佳做法是不使用Python内置变量名。
我将list更改为data。 list是Python内置的用于创建列表（例如list(range(10))。