五、精準率和召回率的平衡

Precision-Recall 的平衡

六、精準率-召回率曲線

七、ROC曲線

Receiver Operation Characteristic Curve

描述 TPR 和 FPR 之間的關系

metrics.py

import numpy as np
from math import sqrt


def accuracy_score(y_true, y_predict):
    """計算y_true和y_predict之間的準確率"""
    assert len(y_true) == len(y_predict),         
 
"the size of y_true must be equal to the size of y_predict"

    return np.sum(y_true == y_predict) / len(y_true)


def mean_squared_error(y_true, y_predict):
    """計算y_true和y_predict之間的MSE"""
    assert len(y_true) == len(y_predict),         "the size of y_true must be equal to the size of y_predict
 
"

    return np.sum((y_true - y_predict)**2) / len(y_true)


def root_mean_squared_error(y_true, y_predict):
    """計算y_true和y_predict之間的RMSE"""

    return sqrt(mean_squared_error(y_true, y_predict))


def mean_absolute_error(y_true, y_predict):
    """計算y_true和y_predict之間的MAE"""
    assert
 
 len(y_true) == len(y_predict),         "the size of y_true must be equal to the size of y_predict"

    return np.sum(np.absolute(y_true - y_predict)) / len(y_true)


def r2_score(y_true, y_predict):
    """計算y_true和y_predict之間的R Square"""

    return 1 - mean_squared_error(y_true, y_predict)/np.var(y_true)


def TN(y_true, y_predict):
    assert len(y_true) == len(y_predict)
    return np.sum((y_true == 0) & (y_predict == 0))


def FP(y_true, y_predict):
    assert len(y_true) == len(y_predict)
    return np.sum((y_true == 0) & (y_predict == 1))


def FN(y_true, y_predict):
    assert len(y_true) == len(y_predict)
    return np.sum((y_true == 1) & (y_predict == 0))


def TP(y_true, y_predict):
    assert len(y_true) == len(y_predict)
    return np.sum((y_true == 1) & (y_predict == 1))


def confusion_matrix(y_true, y_predict):
    return np.array([
        [TN(y_true, y_predict), FP(y_true, y_predict)],
        [FN(y_true, y_predict), TP(y_true, y_predict)]
    ])


def precision_score(y_true, y_predict):
    assert len(y_true) == len(y_predict)
    tp = TP(y_true, y_predict)
    fp = FP(y_true, y_predict)
    try:
        return tp / (tp + fp)
    except:
        return 0.0


def recall_score(y_true, y_predict):
    assert len(y_true) == len(y_predict)
    tp = TP(y_true, y_predict)
    fn = FN(y_true, y_predict)
    try:
        return tp / (tp + fn)
    except:
        return 0.0


def f1_score(y_true, y_predict):
    precision = precision_score(y_true, y_predict)
    recall = recall_score(y_true, y_predict)

    try:
        return 2. * precision * recall / (precision + recall)
    except:
        return 0.


def TPR(y_true, y_predict):
    tp = TP(y_true, y_predict)
    fn = FN(y_true, y_predict)
    try:
        return tp / (tp + fn)
    except:
        return 0.


def FPR(y_true, y_predict):
    fp = FP(y_true, y_predict)
    tn = TN(y_true, y_predict)
    try:
        return fp / (fp + tn)
    except:
        return 0.
    

八、多分類問題中的混淆矩陣

我寫的文章只是我自己對bobo老師講課內容的理解和整理，也只是我自己的弊見。bobo老師的課 是慕課網出品的。歡迎大家一起學習。

機器學習(十) 評價分類結果 (下)