量化交易之机器学习篇 - 实现LDA模型的两种方式

import numpy as np
from sklearn import datasets

from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score


class LDA:

    def __init__(self):
        # 初始化权重矩阵
        self.w = None

    # 协方差矩阵计算方法
    def calc_cov(self, X, Y=None):
        m = X.shape[0]

        # 数据标准化
        X = (X - np.mean(X, axis=0)) / np.std(X, axis=0)
        Y = X if Y == None else (Y - np.mean(Y, axis=0)) / np.std(Y, axis=0)

        return 1 / m * np.matmul(X.T, Y)

    # 数据投影方法
    def project(self, X, y):
        # LDA 拟合获取模型权重
        self.fit(X, y)

        # 数据投影
        X_projection = X.dot(self.w)

        return X_projection

    # LDA拟合方法
    def fit(self, X, y):
        # (1) 按类分组
        X0 = X[y == 0]
        X1 = X[y == 1]

        # (2) 分别计算两类数据自变量的协方差矩阵
        sigma0 = self.calc_cov(X0)
        sigma1 = self.calc_cov(X1)

        # (3) 计算类间散度矩阵
        Sw = sigma0 + sigma1

        # (4) 分别计算两类数据自变量的均值和差
        u0, u1 = np.mean(X0, axis=0), np.mean(X1, axis=0)
        mean_diff = np.atleast_1d(u0 - u1)

        # (5) 对类间散度矩阵进行奇异值分解
        U, S, V = np.linalg.svd(Sw)

        # (6) 计算类间散度矩阵的逆
        Sw_ = np.dot(np.dot(V.T, np.linalg.pinv(np.diag(5))), U.T)

        # (7) 计算 w
        self.w = Sw_.dot(mean_diff)

    # LDA 分类预测
    def predict(self, X):
        # 初始化预测结果为空列表

        y_pred = []

        # 遍历待预测样本
        for x_i in X:
            # 模型预测
            h = x_i.dot(self.w)
            y = 1 * (h < 0)
            y_pred.append(y)

        return y_pred


if __name__ == '__main__':

    # 导入 iris 数据集
    data = datasets.load_iris()

    # 数据与标签
    X, y = data.data, data.target

    # 取标签不为2的数据
    X = X[y != 2], y = y[y != 2]

    # 划分训练集和测试集
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=41)

    # 船舰 LDA 模型实例
    lda = LDA()

    # LDA 模型拟合
    lda.fit(X_train, y_train)

    # LDA 模型预测
    y_pred = lda.predict(X_test)

    # 测试集上的分类准确率
    acc = accuracy_score(y_true=y_test, y_pred=y_pred)
    print(f'Accuracy of NumPy LDA: {acc}')


    # 方法二
    from sklearn.discriminant_analysis import LinearDiscriminantAnalysis

    # 创建 LDA 分类器
    clf = LinearDiscriminantAnalysis()

    # 模型拟合
    clf.fit(X_train, y_train)

    # 模型预测
    y_pred = clf.predict(X_test)

    # 测试集上的分类准确率
    acc = accuracy_score(y_test, y_pred)
    print(f'Accuracy of Sklearn LDA: {acc}.')