#练习一
import numpy as np

image = np.array([
    [100, 150, 200],
    [80,  120, 180],
    [60,  90,  140]
], dtype=np.uint8)

print("原图：")
print(image)
print("-" * 30)

image_dark = image - 20
print("变暗20后：")
print(image_dark)
print("-" * 30)

image_crop = image[0:2, 0:2]
print("裁剪左上角 2×2 区域：")
print(image_crop)
print("-" * 30)

image_flip = np.fliplr(image)
print("水平翻转后：")
print(image_flip)

#练习二
import numpy as np

img = np.array([
    [255, 255, 0,   0  ],
    [255, 255, 0,   0  ],
    [0,   0,   255, 255],
    [0,   0,   255, 255]
], dtype=np.uint8)

print("=== 原图 ===")
print(img)
print("-" * 30)

white_count = np.sum(img == 255)
black_count = np.sum(img == 0)

print("白色像素（255）数量：", white_count)
print("黑色像素（0）数量：", black_count)
print("-" * 30)

img_flip_lr = np.fliplr(img)
print("=== 水平翻转后 ===")
print(img_flip_lr)
print("-" * 30)

img_rot90_ccw = np.flipud(img.T)
print("=== 逆时针旋转90度后 ===")
print(img_rot90_ccw)

#练习三
import numpy as np

feature_map1 = np.array([[1, 0, 1], [0, 1, 0], [1, 0, 1]])
feature_map2 = np.array([[1, 1, 1], [1, 0, 0], [1, 0, 0]])

vector1 = feature_map1.flatten()
vector2 = feature_map2.flatten()

print("vector1:", vector1)
print("vector2:", vector2)
print("-" * 40)

euclidean_dist = np.linalg.norm(vector1 - vector2)
print("欧几里得距离：", euclidean_dist)

cos_sim = np.dot(vector1, vector2) / (np.linalg.norm(vector1) * np.linalg.norm(vector2))
print("余弦相似度：", cos_sim)

#练习四
import numpy as np

vocab = ["Python", "学习", "数据", "人工智能", "编程"]

doc1 = "Python学习编程"
doc2 = "Python人工智能数据"

def text_to_vector(text, vocab):
    words = text.split()
    vector = np.zeros(len(vocab))
    for i, word in enumerate(vocab):
        vector[i] = words.count(word)
    return vector

v1 = text_to_vector(doc1, vocab)
v2 = text_to_vector(doc2, vocab)

print("===== 原始结果 =====")
print("doc1向量:", v1)
print("doc2向量:", v2)

cos_sim = np.dot(v1, v2) / (np.linalg.norm(v1) * np.linalg.norm(v2))
print("余弦相似度:", cos_sim)
print("-" * 40)

vocab_new = ["Python", "学习", "数据", "人工智能", "编程", "机器"]
doc3 = "机器学习"

v3 = text_to_vector(doc3, vocab_new)
print("===== 新增词汇后 =====")
print("新词汇表:", vocab_new)
print("doc3 = 机器学习 的向量:", v3)