怎样自己创建一个网站,互联网服务行业,sae wordpress 安装主题,深圳app网站Deep Learning 1. 回归算法思路2. 代码2.1 基础操作2.2 定义相关函数2.3.1 定义图像绘制函数2.3.2 数据集加载及预处理2.3.3 构造数据加载器2.3.4 构建前馈神经网络#xff08;Feedforward Neural Network#xff09;模型2.3.5 神经网络的训练过程2.3.6 模型评估2.3.7 模型测… Deep Learning 1. 回归算法思路2. 代码2.1 基础操作2.2 定义相关函数2.3.1 定义图像绘制函数2.3.2 数据集加载及预处理2.3.3 构造数据加载器2.3.4 构建前馈神经网络Feedforward Neural Network模型2.3.5 神经网络的训练过程2.3.6 模型评估2.3.7 模型测试2.3.8 模型初始化 2.3 模型运行 1. 回归算法思路
基于3层神经网络的回归优化
2. 代码
2.1 基础操作
切换文件路径并创建新的文件夹
%cd /content/drive/MyDrive
#change directory to google drive
#!mkdir ML2023
#make a directory named ML2023
%cd ./ML2023
#change directory to ML2023/content/drive/MyDrive /content/drive/MyDrive/ML2023
查看当前路径下的文件
!lscovid.test.csv covid.train.csv models
显示当前文件路径:
!pwd #output the current directory/content/drive/MyDrive/ML2023
文件下载
# Download Data
tr_path covid.train.csv # path to training data
tt_path covid.test.csv # path to testing data!gdown --id 19CCyCgJrUxtvgZF53vnctJiOJ23T5mqF --output covid.train.csv
!gdown --id 1CE240jLm2npU-tdz81-oVKEF3T2yfT1O --output covid.test.csvDownloading… From: https://drive.google.com/uc?id19CCyCgJrUxtvgZF53vnctJiOJ23T5mqF To: /content/covid.train.csv 100% 2.00M/2.00M [00:0000:00, 31.7MB/s] Downloading… From: https://drive.google.com/uc?id1CE240jLm2npU-tdz81-oVKEF3T2yfT1O To: /content/covid.test.csv 100% 651k/651k [00:0000:00, 10.2MB/s]
导入所需要的相关包
# Import Some Packages
# PyTorch
import torch
import torch.nn as nn
from torch.utils.data import Dataset, DataLoader# For data preprocess
import numpy as np
import csv
import os# For plotting
import matplotlib.pyplot as plt
from matplotlib.pyplot import figure# For feature selection
from sklearn.feature_selection import SelectKBest
from sklearn.feature_selection import mutual_info_regression2.2 定义相关函数
2.3.1 定义图像绘制函数
def get_device(): Get device (if GPU is available, use GPU) return cuda if torch.cuda.is_available() else cpudef plot_learning_curve(loss_record, title): Plot learning curve of your DNN (train dev loss) devdevelopmenttotal_steps len(loss_record[train]) #x_1 range(total_steps)figure(figsize(6, 4))plt.plot(x_1, loss_record[train], ctab:red, labeltrain)if len(loss_record[dev])!0:x_2 x_1[::len(loss_record[train]) // len(loss_record[dev])] # 计算步长保持训练集和开发集步长一致plt.plot(x_2, loss_record[dev], ctab:cyan, labeldev)plt.ylim(0.0, 20.0) # 设置纵坐标的范围将其限制在0.0到20.0之间plt.xlabel(Training steps)plt.ylabel(MSE loss) # RMSEplt.title(Learning curve of {}.format(title))plt.legend()plt.show()# 绘制预测结果的散点图
def plot_pred(dv_set, model, device, lim35., predsNone, targetsNone):# dv_set开发集或验证集的数据集包含输入特征和实际目标值。# model训练好的深度神经网络模型用于进行预测。# device指定模型在哪个设备上运行通常是CPU或GPU。# lim横纵坐标的限制范围默认为35。# preds模型的预测值可选参数如果未提供则会重新计算。# targets实际目标值可选参数如果未提供则会重新获取 Plot prediction of your DNN if preds is None or targets is None:model.eval()preds, targets [], []for x, y in dv_set: # x是输入特征y是实际目标值x, y x.to(device), y.to(device)with torch.no_grad():pred model(x)preds.append(pred.detach().cpu())targets.append(y.detach().cpu())preds torch.cat(preds, dim0).numpy()targets torch.cat(targets, dim0).numpy()figure(figsize(5, 5))plt.scatter(targets, preds, cr, alpha0.5)plt.plot([-0.2, lim], [-0.2, lim], cb)plt.xlim(-0.2, lim)plt.ylim(-0.2, lim)plt.xlabel(ground truth value)plt.ylabel(predicted value)plt.title(Ground Truth v.s. Prediction)plt.show()2.3.2 数据集加载及预处理
class COVID19Dataset(Dataset): Dataset for loading and preprocessing the COVID19 dataset # target_only一个布尔值表示是否仅使用目标特征在这里是最后一列# 如果target_only为True则只选择目标特征否则选择一组特定的特征def __init__(self,path,modetrain,target_onlyFalse):self.mode mode# Read data into numpy arrayswith open(path, r) as fp:data list(csv.reader(fp))data np.array(data[1:])[:, 1:].astype(float) # 切片操作去掉第1列和行if not target_only:feats list(range(93)) # 一共94个特征但是需要除去最后一个特征最后一个特征是用来预测的else:# TODO: Using 40 states 2 tested_positive features (indices 57 75)!!!# 使用硬编码feats [40, 41, 42, 43, 57, 58, 59, 60, 61, 75, 76, 77, 78, 79] # sklean mutual infoif mode test:# Testing data# data: 893 x 93 (40 states day 1 (18) day 2 (18) day 3 (17))data data[:, feats]self.data torch.FloatTensor(data)else:# Training data (train/dev sets)# data: 2700 x 94 (40 states day 1 (18) day 2 (18) day 3 (18))target data[:, -1]data data[:, feats]# 整个traindev一起mean/stdself.mean torch.FloatTensor(data).mean(dim0, keepdimTrue) # 计算张量中每列的均值# keepdimTrue保持结果的维度与输入张量相同结果将仍然是一个包含均值的张量但它将具有与每列相同的维度self.std torch.FloatTensor(data).std(dim0, keepdimTrue)# Splitting training data into train dev setsif mode train:indices [i for i in range(len(data)) if i % 5 ! 0]elif mode dev:indices [i for i in range(len(data)) if i % 5 0]# Convert data into PyTorch tensorsself.data torch.FloatTensor(data[indices])self.target torch.FloatTensor(target[indices])self.dim self.data.shape[1] # 获取数据集self.data的列数也就是特征的数量print(Finished reading the {} set of COVID19 Dataset ({} samples found, each dim {}).format(mode, len(self.data), self.dim))# All subclasses should overwrite __getitem__, # supporting fetching a data sample for a given key. def __getitem__(self, index):# Returns one sample at a timeif self.mode in [train, dev]:# For trainingreturn self.data[index], self.target[index]else:# For testing (no target)return self.data[index]def __len__(self):# Returns the size of the datasetreturn len(self.data)def normalization(self, meanNone, stdNone):# Normalize features (you may remove this part to see what will happen)# The mean and standard variance of training data will be reused to normalize testing data.if self.mode train or self.mode dev:mean self.meanstd self.stdself.data (self.data-mean) / stdelse:self.data (self.data-mean) / stdreturn mean, std
Z-Score 标准化标准差标准化 将数据缩放到均值为0标准差为1的标准正态分布 计算特征的均值mean μ 1 N ∑ i 1 N x i \mu \frac{1}{N} \sum_{i1}^{N} x_i μN1∑i1Nxi 计算特征的标准差standard deviation σ 1 N ∑ i 1 N ( x i − μ ) 2 \sigma \sqrt{\frac{1}{N} \sum_{i1}^{N} (x_i - \mu)^2} σN1∑i1N(xi−μ)2 对每个数据点 x i x_i xi应用以下标准化公式 z i x i − μ σ z_i \frac{x_i - \mu}{\sigma} ziσxi−μ 数据的均值为0即标准化后的数据集的均值接近于0。 数据的标准差为1即标准化后的数据集的标准差接近于1。 数据的分布形状不会改变只是尺度和位置发生了变化。 Z-Score 标准化适用于许多统计和机器学习算法特别是对于需要计算距离或涉及梯度下降等数值计算的算法。通过标准化可以确保不同特征的尺度不会对模型的训练产生不适当的影响帮助模型更快地收敛并提高性能。
Min-Max 标准化最小-最大值缩放 计算特征的最小值 x min min ( x 1 , x 2 , … , x N ) x_{\text{min}} \min(x_1, x_2, \ldots, x_N) xminmin(x1,x2,…,xN) 计算特征的最大值 x max max ( x 1 , x 2 , … , x N ) x_{\text{max}} \max(x_1, x_2, \ldots, x_N) xmaxmax(x1,x2,…,xN) 对每个数据点 x i x_i xi应用以下标准化公式 x i ′ x i − x min x max − x min x_i \frac{x_i - x_{\text{min}}}{x_{\text{max}}- x_{\text{min}}} xi′xmax−xminxi−xmin σ \sigma σ 表示标准差。 N N N 表示数据点的总数。 x i x_i xi 表示数据集中的第 i 个数据点。 μ \mu μ 表示数据集的均值平均值计算方式为 μ 1 N ∑ i 1 N x i \mu \frac{1}{N} \sum_{i1}^{N} x_i μN1∑i1Nxi
2.3.3 构造数据加载器
构造数据加载器用于训练、验证或测试机器学习模型。
# 定义函数可接受多个参数包括数据文件路径path、数据集模式mode、批量大小batch_size、并行工作数n_jobs、
# 是否仅使用目标数据target_only以及均值和标准差的参数。
def prep_dataloader(path, mode, batch_size, n_jobs0, target_onlyFalse, meanNone, stdNone): Generates a dataset, then is put into a dataloader. # Construct datasetdataset COVID19Dataset(path, modemode, target_onlytarget_only) mean, std dataset.normalization(mean, std)# 创建数据加载器对象将数据集划分成小批量并提供批量数据以供模型训练dataloader DataLoader(dataset, batch_size,shuffle(mode train), # shuffle为一个布尔值指示是否在每个周期epoch之前随机打乱数据。# 通常在训练模型时设置为True确保每个周期中的样本顺序不同。drop_lastFalse,num_workersn_jobs, pin_memoryTrue) return dataloader, mean, std2.3.4 构建前馈神经网络Feedforward Neural Network模型 class NeuralNet(nn.Module): A simple fully-connected deep neural network def __init__(self, input_dim):super(NeuralNet, self).__init__()# Define neural network here# TODO: How to modify this model to achieve better performance?# 定义了神经网络的结构包括输入层、隐藏层和输出层。self.net nn.Sequential(nn.Linear(input_dim, 64),nn.ReLU(),nn.Linear(64, 16),nn.ReLU(),nn.Linear(16,8),nn.ReLU(),nn.Linear(8,4),nn.ReLU(),nn.Linear(4,1) # 单个输出神经元的线性层用于回归任务)# Mean squared error loss# reductionmean损失值会被平均计算self.criterion nn.MSELoss(reductionmean) def forward(self, x): Given input of size (batch_size x input_dim), compute output of the network return self.net(x).squeeze(1)def cal_loss(self, pred, target, l1_lambda):# target真实的目标值# l1_lambdaL1正则化的超参数用于控制正则化的强度 Calculate loss # TODO: you may implement L2 regularization hereloss self.criterion(pred, target)# L1 regularizationl1_reg torch.tensor(0.).to(device)for param in model.parameters():l1_reg torch.sum(torch.abs(param))loss l1_lambda * l1_regreturn loss2.3.5 神经网络的训练过程
设置训练超参数和优化器 代码从配置文件中获取了训练超参数包括最大的训练周期数n_epochs、优化器类型optimizer、以及优化器的超参数optim_hparas。然后通过 PyTorch 中的 getattr 函数创建了相应类型的优化器如 Adam、SGD 等。初始化记录器和计数器 代码初始化了一些变量包括损失记录器 loss_record用于记录每个训练周期的训练和开发验证集损失以及用于早停Early Stopping的计数器 early_stop_cnt。开始训练循环 代码进入了一个训练循环该循环在最大训练周期数内运行或者在出现早停情况下提前结束训练。模型训练 在每个训练周期内代码设置模型为训练模式model.train()然后迭代训练数据集中的每个批次。验证集评估 每个训练周期结束后代码使用验证集开发集对模型进行评估计算验证集上的均方误差。如果验证集上的均方误差小于之前的最小值min_mse则保存模型参数并重置早停计数器 early_stop_cnt。这有助于防止过拟合并在性能改善时保存模型。早停策略 如果连续 early_stop 个训练周期内都没有性能改善验证集损失不再降低训练过程将提前结束。训练结束 训练结束后代码打印出训练周期数然后返回最小的验证集均方误差和损失记录器 loss_record。
def train(tr_set, dv_set, model, config, device): DNN training n_epochs config[n_epochs] # Maximum number of epochs# Setup optimizeroptimizer getattr(torch.optim, config[optimizer])(model.parameters(), **config[optim_hparas])min_mse 1000.loss_record {train: [], dev: []} # for recording training lossearly_stop_cnt 0epoch 0while epoch n_epochs:model.train() # set model to training modefor x, y in tr_set: # iterate through the dataloaderoptimizer.zero_grad() # set gradient to zerox, y x.to(device), y.to(device) # move data to device (cpu/cuda)pred model(x) # forward pass (compute output)mse_loss model.cal_loss(pred, y, config[l1_lambda]) # compute lossmse_loss.backward() # compute gradient (backpropagation)optimizer.step() # update model with optimizerloss_record[train].append(mse_loss.detach().cpu().item())# After each epoch, test your model on the validation (development) set.dev_mse dev(dv_set, model, device)if dev_mse min_mse:# Save model if your model improvedmin_mse dev_mseprint(Saving model (epoch {:4d}, val_loss {:.4f}).format(epoch 1, min_mse))torch.save(model.state_dict(), config[save_path]) # Save model to specified pathearly_stop_cnt 0else:early_stop_cnt 1epoch 1loss_record[dev].append(dev_mse)if early_stop_cnt config[early_stop]:# Stop training if your model stops improving for config[early_stop] epochs.breakprint(Finished training after {} epochs.format(epoch))return min_mse, loss_record2.3.6 模型评估
def dev(dv_set, model, device):model.eval() # set model to evalutation modetotal_loss 0for x, y in dv_set: # iterate through the dataloaderx, y x.to(device), y.to(device) # move data to device (cpu/cuda)with torch.no_grad(): # disable gradient calculationpred model(x) # forward pass (compute output)mse_loss model.cal_loss(pred, y, config[l1_lambda]) # compute losstotal_loss mse_loss.detach().cpu().item() * len(x) # accumulate losstotal_loss total_loss / len(dv_set.dataset) # compute averaged lossreturn total_loss2.3.7 模型测试
def test(tt_set, model, device):model.eval() # set model to evalutation modepreds []for x in tt_set: # iterate through the dataloaderx x.to(device) # move data to device (cpu/cuda)with torch.no_grad(): # disable gradient calculationpred model(x) # forward pass (compute output)preds.append(pred.detach().cpu()) # collect predictionpreds torch.cat(preds, dim0).numpy() # concatenate all predictions and convert to a numpy arrayreturn preds2.3.8 模型初始化
初始化训练过程中需要的设备、目录和超参数配置以便在训练模型之前进行必要的准备工作。
device get_device() # get the current available device (cpu or cuda)
os.makedirs(models, exist_okTrue) # The trained model will be saved to ./models/
target_only True # TODO: Using 40 states 2 tested_positive featuresseed 459
np.random.seed(seed)
delta np.random.normal(loc0,scale 0.000001)# TODO: How to tune these hyper-parameters to improve your models performance?
config {n_epochs: 3000, # maximum number of epochsbatch_size: 270, # mini-batch size for dataloaderoptimizer: Adam, # optimization algorithm (optimizer in torch.optim)optim_hparas: { # hyper-parameters for the optimizer (depends on which optimizer you are using)lr: 0.003, # learning rate of Adam#weight_decay: 1e-8 # weight decay (L2 regularization)},l1_lambda:1e-5 delta, # L1 regularizationearly_stop: 200, # early stopping epochs (the number epochs since your models last improvement)save_path: models/model.pth # your model will be saved here
}myseed 42069 # set a random seed for reproducibility
torch.backends.cudnn.deterministic True
torch.backends.cudnn.benchmark False
np.random.seed(myseed)
torch.manual_seed(myseed)
if torch.cuda.is_available():torch.cuda.manual_seed_all(myseed)2.3 模型运行
tr_set, mean, std prep_dataloader(tr_path, train, config[batch_size], target_onlytarget_only)
dv_set, _, _ prep_dataloader(tr_path, dev, config[batch_size], target_onlytarget_only, meanmean, stdstd)
tt_set, _, _ prep_dataloader(tt_path, test, config[batch_size], target_onlytarget_only, meanmean, stdstd)Finished reading the train set of COVID19 Dataset (2160 samples found, each dim 14) Finished reading the dev set of COVID19 Dataset (540 samples found, each dim 14) Finished reading the test set of COVID19 Dataset (893 samples found, each dim 14)
model NeuralNet(tr_set.dataset.dim).to(device) # Construct model and move to devicemodel_loss, model_loss_record train(tr_set, dv_set, model, config, device)plot_learning_curve(model_loss_record, titledeep model)del model
model NeuralNet(tr_set.dataset.dim).to(device)
ckpt torch.load(config[save_path], map_locationcpu) # Load your best model
model.load_state_dict(ckpt)
if len(dv_set) 0:plot_pred(dv_set, model, device) # Show prediction on the validation setdef save_pred(preds, file): Save predictions to specified file print(Saving results to {}.format(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])preds test(tt_set, model, device) # predict COVID-19 cases with your model
save_pred(preds, COVID-19 pred.csv) # save prediction file to COVID-19 pred.csv
