educoder机器学习 --- 多分类学习

第1关：OvO多分类策略

import numpy as np

# 逻辑回归
class tiny_logistic_regression(object):
    def __init__(self):
        #W
        self.coef_ = None
        #b
        self.intercept_ = None
        #所有的W和b
        self._theta = None
        #01到标签的映射
        self.label_map = {
   }


    def _sigmoid(self, x):
        return 1. / (1. + np.exp(-x))


    #训练
    def fit(self, train_datas, train_labels, learning_rate=1e-4, n_iters=1e3):
        #loss
        def J(theta, X_b, y):
            y_hat = self._sigmoid(X_b.dot(theta))
            try:
                return -np.sum(y*np.log(y_hat)+(1-y)*np.log(1-y_hat)) / len(y)
            except:
                return float('inf')

        # 算theta对loss的偏导
        def dJ(theta, X_b, y):
            return X_b.T.dot(self._sigmoid(X_b.dot(theta)) - y) / len(y)

        # 批量梯度下降
        def gradient_descent(X_b, y, initial_theta, leraning_rate, n_iters=1e2, epsilon=1e-6):
            theta = initial_theta
            cur_iter = 0
            while cur_iter < n_iters:
                gradient = dJ(theta, X_b, y)
                last_theta = theta
                theta = theta - leraning_rate * gradient
                if (abs(J(theta, X_b, y) - J(last_theta, X_b, y)) < epsilon):
                    break
                cur_iter += 1
            return theta

        unique_labels = list(set(train_labels))
        labels = train_labels.copy()

        self.label_map[0] = unique_labels[0]
        labels[train_labels == unique_labels[