线性代数-Python-02：矩阵的基本运算 - 手写Matrix及numpy中的用法

一、代码仓库

https://github.com/Chufeng-Jiang/Python-Linear-Algebra-for-Beginner/tree/main

二、矩阵的基本运算

2.1 矩阵的加法

2.2 矩阵的数量乘法

2.3 矩阵和向量的乘法

2.4 矩阵和矩阵的乘法

2.5 矩阵的转置

三、手写Matrix代码

Matrix.py

from .Vector import Vector


class Matrix:
    """参数二：是一个二维列表"""
    def __init__(self, list2d):
        self._values = [row[:] for row in list2d]

    @classmethod
    def zero(cls, r, c):
        """返回一个r行c列的零矩阵"""
        return cls([[0] * c for _ in range(r)])

    def T(self):
        """返回矩阵的转置矩阵"""
        return Matrix([[e for e in self.col_vector(i)]
                       for i in range(self.col_num())])

    def __add__(self, another):
        """返回两个矩阵的加法结果"""
        assert self.shape() == another.shape(), \
            "Error in adding. Shape of matrix must be same."
        return Matrix([[a + b for a, b in zip(self.row_vector(i), another.row_vector(i))]
                       for i in range(self.row_num())])

    def __sub__(self, another):
        """返回两个矩阵的减法结果"""
        assert self.shape() == another.shape(), \
            "Error in subtracting. Shape of matrix must be same."
        return Matrix([[a - b for a, b in zip(self.row_vector(i), another.row_vector(i))]
                       for i in range(self.row_num())])

    def dot(self, another):
        """返回矩阵乘法的结果"""
        if isinstance(another, Vector):
            # 矩阵和向量的乘法
            assert self.col_num() == len(another), \
                "Error in Matrix-Vector Multiplication."
            return Vector([self.row_vector(i).dot(another) for i in range(self.row_num())])

        if isinstance(another, Matrix):
            # 矩阵和矩阵的乘法
            assert self.col_num() == another.row_num(), \
                "Error in Matrix-Matrix Multiplication."
            return Matrix([[self.row_vector(i).dot(another.col_vector(j)) for j in range(another.col_num())]
                           for i in range(self.row_num())])

    def __mul__(self, k):
        """返回矩阵的数量乘结果: self * k"""
        return Matrix([[e * k for e in self.row_vector(i)]
                       for i in range(self.row_num())])

    def __rmul__(self, k):
        """返回矩阵的数量乘结果: k * self"""
        return self * k

    def __truediv__(self, k):
        """返回数量除法的结果矩阵：self / k"""
        return (1 / k) * self

    def __pos__(self):
        """返回矩阵取正的结果"""
        return 1 * self

    def __neg__(self):
        """返回矩阵取负的结果"""
        return -1 * self

    def row_vector(self, index):
        """返回矩阵的第index个行向量"""
        return Vector(self._values[index])

    def col_vector(self, index):
        """返回矩阵的第index个列向量"""
        return Vector([row[index] for row in self._values])

    def __getitem__(self, pos):
        """返回矩阵pos位置的元素"""
        r, c = pos
        return self._values[r][c]

    def size(self):
        """返回矩阵的元素个数"""
        r, c = self.shape()
        return r * c

    def row_num(self):
        """返回矩阵的行数"""
        return self.shape()[0]

    __len__ = row_num

    def col_num(self):
        """返回矩阵的列数"""
        return self.shape()[1]

    def shape(self):
        """返回矩阵的形状: (行数， 列数)"""
        return len(self._values), len(self._values[0])

    def __repr__(self):
        return "Matrix({})".format(self._values)

    __str__ = __repr__

main_matrix.py

from playLA.Vector import Vector
from playLA.Matrix import Matrix


if __name__ == "__main__":

    matrix = Matrix([[1, 2], [3, 4]])
    print(matrix)
    print("matrix.shape = {}".format(matrix.shape()))
    print("matrix.size = {}".format(matrix.size()))
    print("len(matrix) = {}".format(len(matrix)))
    print("matrix[0][0] = {}".format(matrix[0, 0]))

    matrix2 = Matrix([[5, 6], [7, 8]])
    print(matrix2)
    print("add: {}".format(matrix + matrix2))
    print("subtract: {}".format(matrix - matrix2))
    print("scalar-mul: {}".format(2 * matrix))
    print("scalar-mul: {}".format(matrix * 2))
    print("zero_2_3: {}".format(Matrix.zero(2, 3)))

    T = Matrix([[1.5, 0], [0, 2]])
    p = Vector([5, 3])
    print("T.dot(p) = {}".format(T.dot(p)))

    P = Matrix([[0, 4, 5], [0, 0, 3]])
    print("T.dot(P) = {}".format(T.dot(P)))

    print("A.dot(B) = {}".format(matrix.dot(matrix2)))
    print("B.dot(A) = {}".format(matrix2.dot(matrix)))

    print("P.T = {}".format(P.T()))

main_numpy_matrix.py

import numpy as np

if __name__ == "__main__":

    # 矩阵的创建
    A = np.array([[1, 2], [3, 4]])
    print(A)

    # 矩阵的属性
    print(A.shape)
    print(A.T)

    # 获取矩阵的元素
    print(A[1, 1])
    print(A[0])
    print(A[:, 0])
    print(A[1, :])

    # 矩阵的基本运算
    B = np.array([[5, 6], [7, 8]])
    print(A + B)
    print(A - B)
    print(10 * A)
    print(A * 10)
    print(A * B)
    print(A.dot(B))

    p = np.array([10, 100])
    print(A + p)
    print(A + 1)

    print(A.dot(p))