分类模型评价指标汇总(持续更新)

0 Previously

        这里列的评价指标都是针对分类问题,回归问题则是利用MSE、RMSE等来评价,之后会陆续进行总结~

1 准确率、精准率、召回率、F1值

1.1 定义

        定义一个混淆矩阵:

分类模型评价指标汇总(持续更新)_第1张图片

准确率(Accuracy):

Accuracy=\frac{TP+TN}{TP+FN+FP+TN}

即预测的正确率

精确率(Precision):

Precision=\frac{TP}{TP+FP}

即模型认为是对的中与实际正确的比值

召回率(Recall):

分类模型评价指标汇总(持续更新)_第2张图片

即真正例率

 F1值

分类模型评价指标汇总(持续更新)_第3张图片

        召回率与精准率在一个模型中往往无法同时提升,是一个此消彼长的关系,所以两者的调和平均作为新的评价标准。

注:确定分子分母:

分子:真正例率、真负例率、假正例率、假负例率中,先根据预测结果判“正负”,再根据实际值对比后决定“真假

分母:“正”对应真实值,即分母横着加,“负”对应预测值,即分母竖着加

1.2 代码实现

1.2.1 混淆矩阵

#混淆矩阵
from sklearn.utils.multiclass import unique_labels
from sklearn.metrics import confusion_matrix
import matplotlib.pyplot as plt
def plot_confusion_matrix(y_true, y_pred, classes,
                          normalize=False,
                          title=None,
                          cmap=plt.cm.Blues):
    if not title:
        if normalize:
            title = 'Normalized confusion matrix'
        else:
            title = 'Confusion matrix, without normalization'

    # Compute confusion matrix
    cm = confusion_matrix(y_true, y_pred)
    # Only use the labels that appear in the data
    classes = classes[unique_labels(y_true, y_pred)]
    if normalize:
        cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]
        #print("Normalized confusion matrix")
    else:
        pass
        #print('Confusion matrix, without normalization')

    #print(cm)

    fig, ax = plt.subplots()
    im = ax.imshow(cm, interpolation='nearest', cmap=cmap)
    ax.figure.colorbar(im, ax=ax)
    # We want to show all ticks...
    ax.set(xticks=np.arange(cm.shape[1]),
           yticks=np.arange(cm.shape[0]),
           # ... and label them with the respective list entries
           xticklabels=classes, yticklabels=classes,
           title=title,
           ylabel='True label',
           xlabel='Predicted label')

    ax.set_ylim(len(classes)-0.5, -0.5)

    # Rotate the tick labels and set their alignment.
    plt.setp(ax.get_xticklabels(), rotation=45, ha="right",
             rotation_mode="anchor")

    # Loop over data dimensions and create text annotations.
    fmt = '.2f' if normalize else 'd'
    thresh = cm.max() / 2.
    for i in range(cm.shape[0]):
        for j in range(cm.shape[1]):
            ax.text(j, i, format(cm[i, j], fmt),
                    ha="center", va="center",
                    color="white" if cm[i, j] > thresh else "black")
    fig.tight_layout()
    return ax

# y_test为真实label,y_pred为预测label,classes为类别名称,是个ndarray数组,内容为string类型的标签
class_names = np.array(["0","1"]) #按你的实际需要修改名称
plot_confusion_matrix(y_test, y_pre, classes=class_names, normalize=False) 

1.2.2 其他指标

from sklearn.metrics import accuracy_score, recall_score, f1_score, precision_score
acc=accuracy_score(y_test, y_pre)#准确率
precision = precision_score(y_test, y_pre)
recall = recall_score(y_test, y_pre)
f1 = f1_score(y_test, y_pre)

1.3 ROC曲线

        以假正例率为横坐标,真正例率为纵坐标形成的曲线为ROC曲线,ROC曲线与坐标轴围成的面积为AUC。

import numpy as np
from sklearn import metrics
from sklearn.metrics import auc
import matplotlib.pyplot as plt

true=np.array([1,0,1,0,0,1,1,1,1,1,0,0,0,0,])
pred=np.array([0.9,0.3,0.63,0.3,0.48,0.6,0.3,0.5,0.7,0.6,0.4,0.2,0.6,0.5])#预测为1的概率
FPR,TPR,threshhold = metrics.roc_curve(true,pred,pos_label=1)#pos_label是定义为正例的标签,与真实值要对应,如二分类问题(0,1)、(-1,1)那么pos_label就是1,如果是(1,2)那么pos_label就是2
AUC = auc(FPR,TPR)
plt.plot(FPR,TPR,label='ROC curvem(area = %0.2f)' % AUC,marker='o',color='b',linestyle='-')
plt.legend(loc='lower right')
plt.xlabel('FPR')
plt.ylabel('TPR')
plt.show()

解读:

        FPR越小、TPR越大效果越好,即越靠近左上角的理想点(0,1)时。或AUC面积越大越好

你可能感兴趣的:(机器学习,python,机器学习)