[英]example-based f-score is smaller than precision and recall in Sklearn
I am doing multi-label classification and the evaluation is done by precision_recall_fscore_support
with average = 'samples'
:我正在做多标签分类,评估是由
precision_recall_fscore_support
与average = 'samples'
:
predict = array(([1,1,0,0], [1,0,0,1], [1,1,1,1]))
expect = array(([1,1,1,1], [1,1,1,0], [1,0,0,0]))
smp_report = precision_recall_fscore_support(expect, predict, average = 'samples')
f_report = f1_score(expect, predict, average = 'samples')
There are three instances in this examples and the binary value stand for the existence of corresponding four classes.本例中有三个实例,二进制值代表对应的四个类的存在。
then smp_report
and f_report
give me (0.58333333333333337, 0.61111111111111105, 0.48888888888888893, None)
and 0.488888888889
respectively.然后
smp_report
和f_report
给我(0.58333333333333337, 0.61111111111111105, 0.48888888888888893, None)
和0.488888888889
。
The f-score is not equal to the result of 2*smp_report[0]*smp_report[1]/(smp_report[0]+smp_report[1])
which is the harmonic mean of precision and recall. f-score 不等于
2*smp_report[0]*smp_report[1]/(smp_report[0]+smp_report[1])
,即精度和召回率的调和平均值。
Could anyone tell me how does Sklearn implement this one?谁能告诉我 Sklearn 是如何实现这个的? The version I am using is 0.15.0.
我使用的版本是 0.15.0。
Scikit-learn first calculates the precision, recall, and harmonic F-measure for each item in your set of lists ( [1,1,0,0], [1,0,0,1], [1,1,1,1]
). Scikit-learn 首先计算列表集中每个项目的准确率、召回率和谐波 F 度量 (
[1,1,0,0], [1,0,0,1], [1,1,1,1]
)。 It then calculates the mean of those precision values, the mean of those recall values, and the mean of those f-measures, and returns those mean values.然后计算这些精度值的均值、这些召回值的均值以及这些 f 度量的均值,并返回这些均值。 These are the P, R, and F values you report above.
这些是您在上面报告的 P、R 和 F 值。
It is helpful to calculate the precision, recall, and f-measure values for a single item in your list.计算列表中单个项目的精度、召回率和 f 度量值很有帮助。 To calculate the P, R, and F values for the third item in your list, you can run:
要计算列表中第三项的 P、R 和 F 值,您可以运行:
import numpy as np
from sklearn import metrics
predict = np.array([[1,1,1,1]])
expect = np.array([[1,0,0,0]])
smp_report = metrics.precision_recall_fscore_support(expect, predict, beta=1, average = 'samples')
f_report = metrics.f1_score(expect, predict, average = 'samples')
print f_report, smp_report
Running this code gives you 0.4 (0.25, 1.0, 0.40000000000000002)
.运行此代码为您提供
0.4 (0.25, 1.0, 0.40000000000000002)
。 The values inside the parenthetical indicate the precision, recall, and f-measure for the classification (in that order).括号内的值表示分类的精度、召回率和 f 度量(按此顺序)。 As you can see, the f-measure is the harmonic mean between precision and recall:
如您所见,f-measure是精度和召回率之间的调和平均值:
2 * [(.25 * 1) / (.25 + 1) ] = .4
By swapping your first two lists into the code above, you can calculate the precision, recall, and harmonic f-measures for each of the three items in your data set:通过将前两个列表交换到上面的代码中,您可以计算数据集中三个项目中每一个的精度、召回率和谐波 f 度量:
first item values:第一项值:
0.666666666667 (1.0, 0.5, 0.66666666666666663)
second item values第二项值
0.4 (0.5, 0.33333333333333331, 0.40000000000000002)
third item values第三项值
0.4 (0.25, 1.0, 0.40000000000000002)
SK then calculates the mean precision among these precision values, ie: 1 + .5 + .25 / 3 = .5833333333333333)
, the mean recall among these recall values, (.5 + .333 + 1 / 3 = 0.61111111111111105)
, and the mean f-measure among these f-measures (.666 + .4 + .4 / 3 = 0.48888888888888893)
, and returns those mean values. SK 然后计算这些精度值之间的平均精度,即:
1 + .5 + .25 / 3 = .5833333333333333)
,这些召回值之间的平均召回率, (.5 + .333 + 1 / 3 = 0.61111111111111105)
这些 f-measures 中的平均 f-measure (.666 + .4 + .4 / 3 = 0.48888888888888893)
,并返回这些平均值。 These are the values you report above.这些是您在上面报告的值。 SK is calculating the harmonic mean for each classification event--it's simply returning the mean of those harmonic means.
SK 正在计算每个分类事件的调和平均值——它只是返回这些调和平均值的平均值。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.