NumPy 数组拼接与分割的使用详解

import numpy as np

a = np.array([[1, 2], [3, 4]])  # shape (2,2)
b = np.array([[5, 6]])          # shape (1,2)

# 沿轴0（行方向）拼接
c = np.concatenate((a, b), axis=0)  
print(c)
# 输出:
# [[1 2]
#  [3 4]
#  [5 6]]

# 垂直拼接（等效于 concatenate(axis=0）
v_combined = np.vstack([a, b])  # 结果同上

# 水平拼接（要求行数相同）
d = np.array([[7], [8]])        # shape (2,1)
h_combined = np.hstack([a, d])  
print(h_combined)
# 输出:
# [[1 2 7]
#  [3 4 8]]

x = np.array([1, 2, 3])
y = np.array([4, 5, 6])

# 沿新轴0堆叠（创建三维数组）
stacked = np.stack([x, y], axis=0)  # shape (2,3)
print(stacked)
# 输出:
# [[1 2 3]
#  [4 5 6]]

arr = np.arange(9).reshape(3, 3)  # [[0 1 2], [3 4 5], [6 7 8]]

# 沿轴0分割为3个子数组（每行一个）
sub_arrays = np.split(arr, 3, axis=0)  
# 结果: [array([[0,1,2]]), array([[3,4,5]]), array([[6,7,8]])]

# 将6个元素分割为4个子数组（允许不等分）
arr = np.arange(6)  # [0 1 2 3 4 5]
subs = np.array_split(arr, 4)  
# 结果: [array([0,1]), array([2,3]), array([4]), array([5])]
subs

matrix = np.array([[1, 2, 3, 4], [5, 6, 7, 8]])

# 在第2列和第3列间分割
split_cols = np.hsplit(matrix, [2])  
# 结果: 
# [array([[1, 2], [5, 6]]), 
#  array([[3, 4], [7, 8]])]
split_cols

arr = np.arange(9).reshape(3, 3)
sub_arrays = np.split(arr, 3, axis=0)
sub_arrays[0][0,0] = 100
print(sub_arrays)  # 输出: [array([[100, 1, 2]]), array([[3, 4, 5]]), array([[6, 7, 8]])]
print(arr[0, 0])  # 输出: 100 → 原数组被修改！

# 合并训练集和验证集
X_train = np.random.rand(100, 5)
X_val = np.random.rand(20, 5)
X_combined = np.concatenate([X_train, X_val], axis=0)

# 将大图像分割为8x8小块
image = np.random.rand(256, 256)
blocks = np.split(image, 32, axis=0)  # 先垂直分割
blocks = [np.split(block, 32, axis=1) for block in blocks]  # 再水平分割

image
blocks

data = np.loadtxt("dataset.csv", delimiter=",")
X, y = np.hsplit(data, [-1])  # 最后一列为标签