INT104-lab13[Parzen Window Method][此方法无数据集划分]

 1 import numpy as np
 2 from collections import Counter
 3 
 4 
 5 def read(path: str) -> tuple:
 6     f = open(path, "r")
 7     text = f.readlines()
 8     f.close()
 9     X, y = [], []
10     class_map, class_idx = {}, 0
11     class_anti_map = {}
12     for row in text:
13         row = row.strip()
14         if len(row) == 0:
15             continue
16         items = row.split(",")
17         X.append([float(item) for item in items[:-1]])
18         if items[-1] not in class_map:
19             class_map[items[-1]] = class_idx
20             class_anti_map[class_idx] = items[-1]
21             class_idx += 1
22         y.append(class_map[items[-1]])
23     return X, y, len(y), len(X[0]), class_map, class_idx, class_anti_map
24 
25 
26 def parzenWindowAlgorithm(X, y, class_map, class_anti_map, class_size, n, m, hyperparameter):
27     dic = Counter(y)
28     P0 = [(dic[class_map[class_anti_map[i]]] / n) for i in range(class_size)]
29     P1 = []
30     hd = np.power(hyperparameter, m)
31     for x in X:
32         p = [0 for _ in range(class_size)]
33         for i in range(n):
34             dis = np.linalg.norm((np.array(x) - np.array(X[i]) / hyperparameter))
35             fai = gaussianKernel(dis)
36             p[y[i]] += fai / hd
37         P1.append(p)
38     predict_y = []
39     for i in range(n):
40         p = []
41         for k in range(class_size):
42             p.append([-P0[k] * P1[i][k], k])
43         p.sort(key=lambda x: x[0])
44         predict_y.append(p[0][1])
45     return predict_y
46 
47 
48 def gaussianKernel(u):
49     return np.exp(-u * u / 2) / np.sqrt(2 * np.pi)
50 
51 
52 if __name__ == ‘__main__‘:
53     X, y, n, m, class_map, class_size, class_anti_map = read("iris.data")
54 
55     predict_y = parzenWindowAlgorithm(X, y, class_map, class_anti_map, class_size, n, m, 1)
56 
57     for i in range(n):
58         print("No.", (i + 1), X[i], "y =", y[i], "predict_y =", predict_y[i], (y[i] == predict_y[i]))
59     print("Accuracy =", (len([i for i in range(n) if y[i] == predict_y[i]]) / n))