李宏毅2023机器学习作业1--homework1
一、前期准备
下载训练数据和测试数据
# dropbox link
!wget -O covid_train.csv https://www.dropbox.com/s/lmy1riadzoy0ahw/covid.train.csv?dl=0
!wget -O covid_test.csv https://www.dropbox.com/s/zalbw42lu4nmhr2/covid.test.csv?dl=0
导入包
# Numerical Operations
import math
import numpy as np # numpy操作数据，增加删除查找修改
# Reading/Writing Data
import pandas as pd # pandas读取csv文件
import os # 进行文件夹操作
import csv
# For Progress Bar
from tqdm import tqdm # 可视化
# Pytorch
import torch # pytorch
import torch.nn as nn
from torch.utils.data import Dataset, DataLoader, random_split
# For plotting learning curve
from torch.utils.tensorboard import SummaryWriter
定义一些功能函数
def same_seed(seed):
'''Fixes random number generator seeds for reproducibility.'''
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)
# 划分训练数据集和验证数据集
def train_valid_split(data_set, valid_ratio, seed):
'''Split provided training data into training set and validation set'''
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)
配置项
device = 'cuda' if torch.cuda.is_available() else 'cpu'
config = {
'seed': 5201314, # Your seed number, you can pick your lucky number. :)
'select_all': False, # Whether to use all features.
'valid_ratio': 0.2, # validation_size = train_size * valid_ratio
'n_epochs': 5000, # Number of epochs.
'batch_size': 256,
'learning_rate': 1e-5,
'early_stop': 600, # If model has not improved for this many consecutive epochs, stop training.
'save_path': './models/model.ckpt' # Your model will be saved here.
}
二、创建数据
创建Dataset
class COVID19Dataset(Dataset):
'''
x: Features.
y: Targets, if none, do prediction.
'''
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, idx):
if self.y is None:
return self.x[idx]
else:
return self.x[idx], self.y[idx]
def __len__(self):
return len(self.x)
特征选择
删除了belife和mental 的特征，belife和mental都是心理上精神上的特征，感觉可能和阳性率的偏差较大，就删去了这两类的特征
def select_feat(train_data, valid_data, test_data, select_all=True):
'''Selects useful features to perform regression'''
# [:,-1]第一个维度选择所有，选取所有行，第二个维度选择-1，-1是倒数第一个元素，也就是标签label
y_train, y_valid = train_data[:,-1], valid_data[:,-1] # 选择标签元素
# [:,:-1]第一个维度选择所有，所有行，第二个维度从开始元素到倒数第一个元素（不包含倒数第一个元素）
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 = list(range(35, raw_x_train.shape[1])) # TODO: Select suitable feature columns.
"""删除了belife和mental 的特征
[0, 38, 39, 46, 51, 56, 57, 64, 69, 74, 75, 82, 87]是belife和mental所在列
"""
del_col = [0, 38, 39, 46, 51, 56, 57, 64, 69, 74, 75, 82, 87]
raw_x_train = np.delete(raw_x_train, del_col, axis=1) # numpy数组增删查改方法
raw_x_valid = np.delete(raw_x_valid, del_col, axis=1)
raw_x_test = np.delete(raw_x_test, del_col, axis=1)
return raw_x_train, raw_x_valid, raw_x_test, y_train, y_valid
return raw_x_train[:,feat_idx], raw_x_valid[:,feat_idx], raw_x_test[:,feat_idx], y_train, y_valid
创建 Dataloader
读取文件，设置训练，验证和测试数据集
# Set seed for reproducibility
same_seed(config['seed'])
# train_data size: 3009 x 89 (35 states + 18 features x 3 days)
# train_data共3009条数据，每条数据89个维度
# test_data size: 997 x 88 (without last day's positive rate)
# test_data共997条数据，每条数据88个维度，没有最后一天的最后一列数据positive rate
# pands读取csv数据
train_data, test_data = pd.read_csv('./covid_train.csv').values, pd.read_csv('./covid_test.csv').values
# train_valid_split切分训练集和验证集
train_data, valid_data = train_valid_split(train_data, config['valid_ratio'], config['seed'])
# Print out the data size.打印数据尺寸
print(f"""train_data size: {train_data.shape}
valid_data size: {valid_data.shape}
test_data size: {test_data.shape}""")
# Select features 选择特征
x_train, x_valid, x_test, y_train, y_valid = select_feat(train_data, valid_data, test_data, config['select_all'])
# Print out the number of features. 打印特征数
print(f'number of features: {x_train.shape[1]}')
# 生成dataset
train_dataset, valid_dataset, test_dataset = COVID19Dataset(x_train, y_train), \
COVID19Dataset(x_valid, y_valid), \
COVID19Dataset(x_test)
# Pytorch data loader loads pytorch dataset into batches.
# pytorch的dataloder加载dataset
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)
三、创建神经网络模型
class My_Model(nn.Module):
def __init__(self, input_dim):
super(My_Model, self).__init__()
# TODO: modify model's structure, be aware of dimensions.
self.layers = nn.Sequential(
nn.Linear(input_dim, 16),
nn.ReLU(),
nn.Linear(16, 8),
nn.ReLU(),
nn.Linear(8, 1)
)
def forward(self, x):
x = self.layers(x)
x = x.squeeze(1) # (B, 1) -> (B)
return x
四、模型训练和模型测试
模型训练
def trainer(train_loader, valid_loader, model, config, device):
criterion = nn.MSELoss(reduction='mean') # Define your loss function, do not modify this.
# Define your optimization algorithm.
# TODO: Please check https://pytorch.org/docs/stable/optim.html to get more available algorithms.
# TODO: L2 regularization (optimizer(weight decay...) or implement by your self).
optimizer = torch.optim.SGD(model.parameters(), lr=config['learning_rate'], momentum=0.9)
writer = SummaryWriter() # Writer of tensoboard.
# 如果没有models文件夹，创建名称为models的文件夹，保存模型
if not os.path.isdir('./models'):
os.mkdir('./models') # Create directory of saving models.
# math.inf为无限大
n_epochs, best_loss, step, early_stop_count = config['n_epochs'], math.inf, 0, 0
for epoch in range(n_epochs):
model.train() # Set your model to train mode.
loss_record = [] # 记录损失
# tqdm is a package to visualize your training progress.
train_pbar = tqdm(train_loader, position=0, leave=True)
for x, y in train_pbar:
optimizer.zero_grad() # Set gradient to zero.
x, y = x.to(device), y.to(device) # Move your data to device.
pred = model(x) # 数据传入模型model，生成预测值pred
loss = criterion(pred, y) # 预测值pred和真实值y计算损失loss
loss.backward() # Compute gradient(backpropagation).
optimizer.step() # Update parameters.
step += 1
loss_record.append(loss.detach().item()) # 当前步骤的loss加到loss_record[]
# Display current epoch number and loss on tqdm progress bar.
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) # 计算训练集上平均损失
writer.add_scalar('Loss/train', mean_train_loss, step)
model.eval() # Set your model to evaluation mode.
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) # 计算验证集上平均损失
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)
# 保存验证集上平均损失最小的模型
if mean_valid_loss < best_loss:
best_loss = mean_valid_loss
torch.save(model.state_dict(), config['save_path']) # Save your best model
print('Saving model with loss {:.3f}...'.format(best_loss))
early_stop_count = 0
else:
early_stop_count += 1
# 设置早停early_stop_count
# 如果early_stop_count次数，验证集上的平均损失没有变化，模型性能没有提升，停止训练
if early_stop_count >= config['early_stop']:
print('\nModel is not improving, so we halt the training session.')
return
模型测试
# 测试数据集的预测
def predict(test_loader, model, device):
model.eval() # Set your model to evaluation mode.
preds = []
for x in tqdm(test_loader):
x = x.to(device)
with torch.no_grad(): # 关闭梯度
pred = model(x)
preds.append(pred.detach().cpu())
preds = torch.cat(preds, dim=0).numpy()
return preds
五、训练模型
model = My_Model(input_dim=x_train.shape[1]).to(device) # put your model and data on the same computation device.
trainer(train_loader, valid_loader, model, config, device)
六、测试模型，生成预测值
def save_pred(preds, file):
''' Save predictions to specified 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])
model = My_Model(input_dim=x_train.shape[1]).to(device)
model.load_state_dict(torch.load(config['save_path'])) # 加载模型
preds = predict(test_loader, model, device) # 生成预测结果preds
save_pred(preds, 'pred.csv') # 保存preds到pred.csv
tensorboard可视化训练和验证损失图像
%reload_ext tensorboard
%tensorboard --logdir=./runs/
参考：
李宏毅_机器学习_作业1（详解）_COVID-19 Cases Prediction (Regression)-物联沃-IOTWORD物联网
【深度学习】2023李宏毅homework1作业一代码详解_李宏毅作业1-博客
np.delete详解-博客
