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
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
| import math, csv, os
import numpy as np
import pandas as pd
from tqdm import tqdm
import torch
import torch.nn as nn
from torch.utils.data import Dataset, DataLoader, random_split
from torch.utils.tensorboard import SummaryWriter
device = 'cuda' if torch.cuda.is_available() else 'cpu'
config = {
'seed': 114514,
'select_all': True,
'valid_ratio': 0.2,
'n_epochs': 50000,
'batch_size': 512,
'learning_rate': 1e-5,
'early_stop': 400,
'save_path': './models/model.ckpt'
}
def same_seed(seed):
torch.backends.cudnn.deterministic = True
torch.backends.cudnn.benchmark = False
np.random.seed(seed)
torch.manual_seed(seed)
if torch.cuda.is_available():
torch.cuda.manual_seed_all(seed)
def train_valid_split(data_set, valid_ratio, seed):
valid_set_size = int(valid_ratio * len(data_set))
train_set_size = len(data_set) - valid_set_size
train_set, valid_set = random_split(data_set, [train_set_size, valid_set_size],
generator=torch.Generator().manual_seed(seed))
return np.array(train_set), np.array(valid_set)
def select_feat(train_data, valid_data, test_data, select_all=True):
y_train, y_valid = train_data[:, -1], valid_data[:, -1]
raw_x_train, raw_x_valid, raw_x_test = train_data[:, :-1], valid_data[:, :-1], test_data
if select_all:
feat_idx = list(range(raw_x_train.shape[1]))
else:
feat_idx = [0, 1, 2, 3, 4]
return raw_x_train[:, feat_idx], raw_x_valid[:, feat_idx], raw_x_test[:, feat_idx], y_train, y_valid
def predict(test_loader, model, device):
model.eval()
preds = []
for x in tqdm(test_loader):
x = x.to(device)
with torch.no_grad():
pred = model(x)
preds.append(pred.detach().cpu())
preds = torch.cat(preds, dim=0).numpy()
return preds
def trainer(train_loader, valid_loader, model, config, device):
criterion = nn.MSELoss(reduction='mean')
optimizer = torch.optim.Adam(model.parameters(), lr=config['learning_rate'])
writer = SummaryWriter()
if not os.path.isdir('./models'):
os.mkdir('./models')
n_epochs, best_loss, step, early_stop_count = config['n_epochs'], math.inf, 0, 0
for epoch in range(n_epochs):
model.train()
loss_record = []
train_pbar = tqdm(train_loader, position=0, leave=True)
for x, y in train_pbar:
optimizer.zero_grad()
x, y = x.to(device), y.to(device)
pred = model(x)
loss = criterion(pred, y)
loss.backward()
optimizer.step()
step += 1
loss_record.append(loss.detach().item())
train_pbar.set_description(f'Epoch [{epoch + 1}/{n_epochs}]')
train_pbar.set_postfix({'loss': loss.detach().item()})
mean_train_loss = sum(loss_record) / len(loss_record)
writer.add_scalar('Loss/train', mean_train_loss, step)
model.eval()
loss_record =[]
for x, y in valid_loader:
x, y = x.to(device), y.to(device)
with torch.no_grad():
pred = model(x)
loss = criterion(pred, y)
loss_record.append(loss.item())
mean_valid_loss = sum(loss_record) / len(loss_record)
print(f'Epoch [{epoch + 1}/{n_epochs}]: Train loss: {mean_train_loss:.4f}, Valid loss: {mean_valid_loss:.4f}')
writer.add_scalar('Loss/valid', mean_valid_loss, step)
if mean_valid_loss < best_loss:
best_loss = mean_valid_loss
torch.save(model.state_dict(), config['save_path'])
print('Saving model with loss {:.3f}...'.format(best_loss))
early_stop_count = 0
else:
early_stop_count += 1
if early_stop_count >= config['early_stop']:
print('\nModel is not improving, so we halt the training session.')
return
def save_pred(preds, file):
with open(file, 'w') as fp:
writer = csv.writer(fp)
writer.writerow(['id', 'tested_positive'])
for i, p in enumerate(preds):
writer.writerow([i, p])
class COVID19Dataset(Dataset):
def __init__(self, x, y=None):
if y is None:
self.y = y
else:
self.y = torch.FloatTensor(y)
self.x = torch.FloatTensor(x)
def __getitem__(self, item):
if self.y is None:
return self.x[item]
else:
return self.x[item], self.y[item]
def __len__(self):
return len(self.x)
class My_Model(nn.Module):
def __init__(self, input_dim):
super(My_Model, self).__init__()
self.layers = nn.Sequential(
nn.Linear(input_dim, 16),
nn.LeakyReLU(),
nn.Linear(16, 8),
nn.LeakyReLU(),
nn.Linear(8, 1)
)
def forward(self, x):
x = self.layers(x)
print(type(x))
print(x.shape)
x = x.squeeze(1)
return x
train_data, test_data = pd.read_csv('./covid_train.csv').values, pd.read_csv('./covid_test.csv').values
train_data, valid_data = train_valid_split(train_data, config['valid_ratio'], config['seed'])
x_train, x_valid, x_test, y_train, y_valid = select_feat(train_data, valid_data, test_data, config['select_all'])
train_dataset, valid_dataset, test_dataset = COVID19Dataset(x_train, y_train), COVID19Dataset(x_valid, y_valid), COVID19Dataset(x_test)
train_loader = DataLoader(train_dataset, batch_size=config['batch_size'], shuffle=True, pin_memory=True)
valid_loader = DataLoader(valid_dataset, batch_size=config['batch_size'], shuffle=True, pin_memory=True)
test_loader = DataLoader(test_dataset, batch_size=config['batch_size'], shuffle=False, pin_memory=True)
model = My_Model(input_dim=x_train.shape[1]).to(device)
trainer(train_loader, valid_loader, model, config, device)
model.load_state_dict(torch.load(config['save_path']))
preds = predict(test_loader, model, device)
save_pred(preds, 'pred.csv')
|
