1 %matplotlib inline 2 import torch 3 import torch.nn as nn 4 import numpy as np 5 import pandas as pd 6 import sys 7 sys.path.append("/home/kesci/input") 8 import d2lzh1981 as d2l 9 print(torch.__version__) 10 torch.set_default_tensor_type(torch.FloatTensor) 11 12 13 test_data = pd.read_csv("/home/kesci/input/houseprices2807/house-prices-advanced-regression-techniques/test.csv") 14 train_data = pd.read_csv("/home/kesci/input/houseprices2807/house-prices-advanced-regression-techniques/train.csv") 15 16 all_features = pd.concat((train_data.iloc[:, 1:-1], test_data.iloc[:, 1:])) 17 18 # 数据预处理 19 numeric_features = all_features.dtypes[all_features.dtypes != 'object'].index 20 all_features[numeric_features] = all_features[numeric_features].apply( 21 lambda x: (x - x.mean()) / (x.std())) 22 # 标准化后,每个数值特征的均值变为0,所以可以直接用0来替换缺失值 23 all_features[numeric_features] = all_features[numeric_features].fillna(0) 24 25 26 # dummy_na=True将缺失值也当作合法的特征值并为其创建指示特征 27 all_features = pd.get_dummies(all_features, dummy_na=True) 28 all_features.shape 29 30 n_train = train_data.shape[0] 31 train_features = torch.tensor(all_features[:n_train].values, dtype=torch.float) 32 test_features = torch.tensor(all_features[n_train:].values, dtype=torch.float) 33 train_labels = torch.tensor(train_data.SalePrice.values, dtype=torch.float).view(-1, 1) 34 35 # 训练模型 36 loss = torch.nn.MSELoss() 37 38 def get_net(feature_num): 39 net = nn.Linear(feature_num, 1) 40 for param in net.parameters(): 41 nn.init.normal_(param, mean=0, std=0.01) 42 return net 43 44 45 def log_rmse(net, features, labels): 46 with torch.no_grad(): 47 # 将小于1的值设成1,使得取对数时数值更稳定 48 clipped_preds = torch.max(net(features), torch.tensor(1.0)) 49 rmse = torch.sqrt(2 * loss(clipped_preds.log(), labels.log()).mean()) 50 return rmse.item() 51 52 53 def train(net, train_features, train_labels, test_features, test_labels, 54 num_epochs, learning_rate, weight_decay, batch_size): 55 train_ls, test_ls = [], [] 56 dataset = torch.utils.data.TensorDataset(train_features, train_labels) 57 train_iter = torch.utils.data.DataLoader(dataset, batch_size, shuffle=True) 58 # 这里使用了Adam优化算法 59 optimizer = torch.optim.Adam(params=net.parameters(), lr=learning_rate, weight_decay=weight_decay) 60 net = net.float() 61 for epoch in range(num_epochs): 62 for X, y in train_iter: 63 l = loss(net(X.float()), y.float()) 64 optimizer.zero_grad() 65 l.backward() 66 optimizer.step() 67 train_ls.append(log_rmse(net, train_features, train_labels)) 68 if test_labels is not None: 69 test_ls.append(log_rmse(net, test_features, test_labels)) 70 return train_ls, test_ls 71 72 73 # K折交叉验证 74 def get_k_fold_data(k, i, X, y): 75 # 返回第i折交叉验证时所需要的训练和验证数据 76 assert k > 1 77 fold_size = X.shape[0] // k 78 X_train, y_train = None, None 79 for j in range(k): 80 idx = slice(j * fold_size, (j + 1) * fold_size) 81 X_part, y_part = X[idx, :], y[idx] 82 if j == i: 83 X_valid, y_valid = X_part, y_part 84 elif X_train is None: 85 X_train, y_train = X_part, y_part 86 else: 87 X_train = torch.cat((X_train, X_part), dim=0) 88 y_train = torch.cat((y_train, y_part), dim=0) 89 return X_train, y_train, X_valid, y_valid 90 91 def k_fold(k, X_train, y_train, num_epochs, 92 learning_rate, weight_decay, batch_size): 93 train_l_sum, valid_l_sum = 0, 0 94 for i in range(k): 95 data = get_k_fold_data(k, i, X_train, y_train) 96 net = get_net(X_train.shape[1]) 97 train_ls, valid_ls = train(net, *data, num_epochs, learning_rate, 98 weight_decay, batch_size) 99 train_l_sum += train_ls[-1] 100 valid_l_sum += valid_ls[-1] 101 if i == 0: 102 d2l.semilogy(range(1, num_epochs + 1), train_ls, 'epochs', 'rmse', 103 range(1, num_epochs + 1), valid_ls, 104 ['train', 'valid']) 105 print('fold %d, train rmse %f, valid rmse %f' % (i, train_ls[-1], valid_ls[-1])) 106 return train_l_sum / k, valid_l_sum / k 107 108 # 模型选择 109 k, num_epochs, lr, weight_decay, batch_size = 5, 100, 5, 0, 64 110 train_l, valid_l = k_fold(k, train_features, train_labels, num_epochs, lr, weight_decay, batch_size) 111 print('%d-fold validation: avg train rmse %f, avg valid rmse %f' % (k, train_l, valid_l)) 112 113 114 # 预测 115 def train_and_pred(train_features, test_features, train_labels, test_data, 116 num_epochs, lr, weight_decay, batch_size): 117 net = get_net(train_features.shape[1]) 118 train_ls, _ = train(net, train_features, train_labels, None, None, 119 num_epochs, lr, weight_decay, batch_size) 120 d2l.semilogy(range(1, num_epochs + 1), train_ls, 'epochs', 'rmse') 121 print('train rmse %f' % train_ls[-1]) 122 preds = net(test_features).detach().numpy() 123 test_data['SalePrice'] = pd.Series(preds.reshape(1, -1)[0]) 124 submission = pd.concat([test_data['Id'], test_data['SalePrice']], axis=1) 125 submission.to_csv('./submission.csv', index=False) 126 # sample_submission_data = pd.read_csv("../input/house-prices-advanced-regression-techniques/sample_submission.csv") 127 128 train_and_pred(train_features, test_features, train_labels, test_data, num_epochs, lr, weight_decay, batch_size)
PyTorch实现Kaggle房价预测
猜你喜欢
转载自www.cnblogs.com/hahasd/p/12333176.html
今日推荐
周排行