1、安装scikit-learn
1.1 Scikit-learn 依赖
·Python (>= 2.6 or >= 3.3),
·NumPy (>= 1.6.1),
·SciPy (>= 0.9).
分别查看上述三个依赖的版本:
python-V
结果:
Python2.7.3
python-c'importscipy;printscipy.version.version'
python-c'importscipy;printscipy.version.version'
python-c'importscipy;printscipy.version.version'
scipy版本结果:
0.9.0
python-c"importnumpy;printnumpy.version.version"
python-c"importnumpy;printnumpy.version.version"
python-c"importnumpy;printnumpy.version.version"
numpy结果:
1.10.2
1.2 Scikit-learn安装
如果你已经安装了NumPy、SciPy和python并且均满足1.1中所需的条件,那么可以直接运行sudo
pipinstall-Uscikit-learn
执行安装。
2、计算auc指标
fromsklearn.metricsimportroc_auc_score
y_true=np.array([0,0,1,1])
y_scores=np.array([0.1,0.4,0.35,0.8])
roc_auc_score(y_true,y_scores)
importnumpyasnp
fromsklearn.metricsimportroc_auc_score
y_true=np.array([0,0,1,1])
y_scores=np.array([0.1,0.4,0.35,0.8])
roc_auc_score(y_true,y_scores)
importnumpyasnp
fromsklearn.metricsimportroc_auc_score
y_true=np.array([0,0,1,1])
y_scores=np.array([0.1,0.4,0.35,0.8])
roc_auc_score(y_true,y_scores)
输出:
0.75
3、计算roc曲线
y=np.array([1,1,2,2])#实际值
scores=np.array([0.1,0.4,0.35,0.8])#预测值
fpr,tpr,thresholds=metrics.roc_curve(y,scores,pos_label=2)#pos_label=2,表示值为2的实际值为正样本
importnumpyasnp
fromsklearnimportmetrics
y=np.array([1,1,2,2])#实际值
scores=np.array([0.1,0.4,0.35,0.8])#预测值
fpr,tpr,thresholds=metrics.roc_curve(y,scores,pos_label=2)#pos_label=2,表示值为2的实际值为正样本
printfpr
printtpr
printthresholds
importnumpyasnp
fromsklearnimportmetrics
y=np.array([1,1,2,2])#实际值
scores=np.array([0.1,0.4,0.35,0.8])#预测值
fpr,tpr,thresholds=metrics.roc_curve(y,scores,pos_label=2)#pos_label=2,表示值为2的实际值为正样本
printfpr
printtpr
printthresholds
输出:
array([0.8,0.4,0.35,0.1])
array([0.,0.5,0.5,1.])
array([0.5,0.5,1.,1.])
array([0.8,0.4,0.35,0.1])
array([0.,0.5,0.5,1.])
array([0.5,0.5,1.,1.])
array([0.8,0.4,0.35,0.1])
python学习网,免费的在线学习python平台,欢迎关注!