import numpy as np

image = np.array([[100, 150, 200],[80, 120, 180],[60, 90, 140]], dtype=np.uint8)
print(image)
darker = image - 20
print(darker)
crop = image[0:2, 0:2]
print(crop)
flip_lr = np.fliplr(image)
print(flip_lr)

img = np.array([[255,255,0,0],[255,255,0,0],[0,0,255,255],[0,0,255,255]], dtype=np.uint8)
white = np.sum(img == 255)
black = np.sum(img == 0)
print(white)
print(black)
print(np.fliplr(img))
rot = np.transpose(img)
rot90 = np.flipud(rot)
print(rot90)

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)
print(vector2)
euclidean = np.linalg.norm(vector1 - vector2)
print(euclidean)
cos = np.dot(vector1, vector2) / (np.linalg.norm(vector1) * np.linalg.norm(vector2))
print(cos)

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(v1)
print(v2)
def cos_sim(a, b):
    return np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b))
print(cos_sim(v1, v2))
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(v3)

def cosine_similarity(a, b):
    return np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b))
v1 = np.array([1,0,1,0])
v2 = np.array([2,0,0,0])
print(v1)
print(v2)
print(cosine_similarity(v1, v2))
v2 = v1 * 2
print(cosine_similarity(v1, v2))