F1值的优化macro

1.F1值优化

https://www.jianshu.com/p/51debab91824

from functools import partial
import numpy as np
import scipy as sp
from sklearn.metrics import f1_score
class OptimizedF1(object):
    def __init__(self):
        self.coef_ = []

    def _kappa_loss(self, coef, X, y):
        """
        y_hat = argmax(coef*X, axis=-1)
        :param coef: (1D array) weights
        :param X: (2D array)logits
        :param y: (1D array) label
        :return: -f1
        """
        X_p = np.copy(X)
        X_p = coef*X_p
        ll = f1_score(y, np.argmax(X_p, axis=-1), average='macro')
        return -ll

    def fit(self, X, y):
        loss_partial = partial(self._kappa_loss, X=X, y=y)
        initial_coef = [1. for _ in range(len(set(y)))]#权重都初始化为1
        self.coef_ = sp.optimize.minimize(loss_partial, initial_coef, method='nelder-mead')

    def predict(self, X, y):
        X_p = np.copy(X)
        X_p = self.coef_['x'] * X_p
        return f1_score(y, np.argmax(X_p, axis=-1), average='macro')

    def coefficients(self):
        return self.coef_['x']

 可以发现这个和https://mp.weixin.qq.com/s/jH9grYg-xiuQxMTDq99olg所提供的有序关系的离散标签优化所提供的代码，

主要是_kappa_loss和fit/predict函数的实现不同。

调用时:

op = OptimizedF1()
op.fit(logits,labels)
logits = op.coefficients()*logits 

那么在进行预测时，就使用predict函数和logist相乘，然后再softmax取最值，这样就对每个都有一个缩放的权重。

2.优化分类阈值的实现

https://mp.weixin.qq.com/s/jH9grYg-xiuQxMTDq99olg

from functools import partial
import numpy as np
import scipy as sp

class OptimizedRounder(object):
    def __init__(self):
        self.coef_ = 0

    def _kappa_loss(self, coef, X, y):
        X_p = np.copy(X)
        for i, pred in enumerate(X_p):
            if pred < coef[0]:
                X_p[i] = 0
            elif pred >= coef[0] and pred < coef[1]:
                X_p[i] = 1
            elif pred >= coef[1] and pred < coef[2]:
                X_p[i] = 2
            elif pred >= coef[2] and pred < coef[3]:
                X_p[i] = 3
            else:
                X_p[i] = 4

        ll = quadratic_weighted_kappa(y, X_p)
        return -ll

    def fit(self, X, y):
        loss_partial = partial(self._kappa_loss, X=X, y=y)
        initial_coef = [0.5, 1.5, 2.5, 3.5]
        self.coef_ = sp.optimize.minimize(loss_partial, initial_coef, method='nelder-mead')

    def predict(self, X, coef):
        X_p = np.copy(X)
        for i, pred in enumerate(X_p):
            if pred < coef[0]:
                X_p[i] = 0
            elif pred >= coef[0] and pred < coef[1]:
                X_p[i] = 1
            elif pred >= coef[1] and pred < coef[2]:
                X_p[i] = 2
            elif pred >= coef[2] and pred < coef[3]:
                X_p[i] = 3
            else:
                X_p[i] = 4
        return X_p

    def coefficients(self):
        return self.coef_['x']

也学到了，那么在调用它的时候应该先fit，然后coefficients获取阈值参数，或者调用predict，然后和real labels做交叉熵损失这样。