INT104-lab10 测试新数据集

 1 import numpy as np
 2 from sklearn.manifold import TSNE
 3 import matplotlib.pyplot as plt
 4 from mpl_toolkits.mplot3d import Axes3D
 5 
 6 
 7 def read(path: str) -> list:
 8     with open(path, "r") as f:
 9         text = f.readlines()
10         D = []
11         for row in text:
12             substr = str.split(str.split(row, "\n")[0], ",")
13             X = []
14             for a in substr:
15                 if a == ‘?‘:
16                     continue
17                 X.append(int(a))
18             D.append(X)
19     return D
20 
21 
22 def init(D: list) -> tuple:
23     n, m = len(D), len(D[0])
24     X, Y = [], []
25     for i in range(n):
26         x = []
27         if len(D[i]) != m:
28             n -= 1
29             continue
30         for j in range(1, m - 1, 1):
31             x.append(D[i][j])
32         X.append(x)
33         Y.append(D[i][m - 1])
34     # print(n, m)
35     return X, Y, n, m - 2
36 
37 
38 if __name__ == ‘__main__‘:
39 
40     D = read("breast-cancer-wisconsin.data")
41     X, Y, n, m = init(D)
42 
43     x = np.array(X)
44 
45     tsne = TSNE(n_components=3)
46 
47     tsne.fit_transform(x)
48 
49     one_x, one_y, one_z, zero_x, zero_y, zero_z = [], [], [], [], [], []
50     for i in range(n):
51         _x, _y, _z = tsne.embedding_[i][0], tsne.embedding_[i][1], tsne.embedding_[i][2]
52         if Y[i] == 4:
53             zero_x.append(_x)
54             zero_y.append(_y)
55             zero_z.append(_z)
56         else:
57             one_x.append(_x)
58             one_y.append(_y)
59             one_z.append(_z)
60     ‘‘‘
61     ax = plt.axes(projection=‘3d‘)
62     ax.scatter3D(one_x, one_y, one_z)
63     ax.scatter3D(zero_x, zero_y, zero_z)
64     ‘‘‘
65     plt.subplot(311)
66     plt.scatter(one_x, one_y)
67     plt.scatter(zero_x, zero_y)
68     plt.subplot(312)
69     plt.scatter(one_x, one_z)
70     plt.scatter(zero_x, zero_z)
71     plt.subplot(313)
72     plt.scatter(one_y, one_z)
73     plt.scatter(zero_y, zero_z)
74 
75     plt.show()