1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
|
import torch
model = torch.load('t-sne模型文件/AliExpress_US_sharedbottom.pt')
model.eval()
from datasets.aliexpress import AliExpressDataset
train_dataset = AliExpressDataset('tsne.csv')
from torch.utils.data import DataLoader
import random
import numpy as np
seed = 2022
random.seed(seed)
np.random.seed(seed)
torch.manual_seed(seed)
torch.cuda.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
train_data_loader = DataLoader(train_dataset, batch_size=1, num_workers=4, shuffle=False)
"""t-SNE对手写数字进行可视化"""
from time import time
import numpy as np
import matplotlib.pyplot as plt
import tqdm
device = 'cuda:0'
from sklearn import datasets
from sklearn.manifold import TSNE
from sklearn.decomposition import PCA
def plot_embedding(data, label, title):
x_min, x_max = np.min(data, 0), np.max(data, 0)
data = (data - x_min) / (x_max - x_min)
fig = plt.figure()
ax = plt.subplot(111)
colors = ['r', 'b']
for i in range(data.shape[0]):
plt.scatter(data[i, 0], data[i, 1], c=colors[label[i]], alpha=0.5)
plt.xticks([])
plt.yticks([])
plt.title(title)
return fig
def main():
with torch.no_grad():
data1 = []
data2 = []
for categorical_fields, numerical_fields, labels in tqdm.tqdm(train_data_loader, smoothing=0, mininterval=1.0):
categorical_fields, numerical_fields, labels = categorical_fields.to(device), numerical_fields.to(device), labels.to(device)
y, _ ,cross= model(categorical_fields, numerical_fields)
data1 += cross[0].cpu().numpy().tolist()
data2 += cross[1].cpu().numpy().tolist()
data = np.concatenate((data1, data2), axis=0)
label = len(data1)*[0] + len(data2)*[1]
n_samples, n_features = data.shape
print(data.shape)
print('data.shape',data.shape)
print('label',label)
print('label中数字有',len(set(label)),'个不同的数字')
print('data有',n_samples,'个样本')
print('每个样本',n_features,'维数据')
print('Computing t-SNE embedding')
tsne = TSNE(n_components=2, init='pca', random_state=0)
t0 = time()
result = tsne.fit_transform(data)
print('result.shape',result.shape)
fig = plot_embedding(result, label,
't-SNE embedding of the digits (time %.2fs)'
% (time() - t0))
plt.show(fig)
if __name__ == '__main__':
main()
|
