房价预测DEMO Posted on 2019-09-01 | Post modified: 2021-09-12 | In pytorch | Words count in article: 794 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128import numpy as npimport pandas as pdimport torchimport torch.nn as nntorch.set_default_tensor_type(torch.FloatTensor)train_data = pd.read_csv('../input/house-prices-advanced-regression-techniques/train.csv')test_data = pd.read_csv('../input/house-prices-advanced-regression-techniques/test.csv')print(train_data.shape)train_data.iloc[0:4, [0, 1, 2, 3, -3, -2, -1]] # 查看前4个样本的前4个和后3个特征#################### 预处理 ###################################### 处理数值型数据 —— 将其标准化,均值填充all_features = pd.concat((train_data.iloc[:, 1:-1], test_data.iloc[:, 1:]))numeric_features = all_features.dtypes[all_features.dtypes != 'object'].index # 通过判断df是否是字符串对象进行二值选择,取其索引all_features[numeric_features] = all_features[numeric_features].apply( # 对每一组数值特征进行标准化 lambda x : (x - x.mean()) / (x.std()))all_features[numeric_features] = all_features[numeric_features].fillna(0) # 缺失值使用均值填充## 处理离散数据 ————one-hot编码## 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all_features = pd.get_dummies(all_features, dummy_na=True)all_features.shape # (2919, 331)all_features.dtypes.index## 统一处理好train和test后,将其拆分,并用.values得到numpy数据,再转化为tensor用以训练n_train = train_data.shape[0]train_features = torch.tensor(all_features[:n_train].values, dtype = torch.float)test_features = torch.tensor(all_features[n_train:].values, dtype = torch.float)train_labels = torch.tensor(train_data.SalePrice.values, dtype = torch.float).view(-1, 1)####################### 搭模型 ################################ 一个基础的LR+MSE模型loss = torch.nn.MSELoss()def get_net(feature_num): net = nn.Linear(feature_num, 1) for param in net.parameters(): nn.init.normal_(param, mean=0, std=0.01) return netdef log_rmse(net, features, labels): with torch.no_grad(): # 将小于1的值设成1,使得取对数时数值更稳定 clipped_preds = torch.max(net(features), torch.tensor(1.0)) rmse = torch.sqrt(loss(clipped_preds.log(), labels.log())) return rmse.item()def train(net, train_features, train_labels, test_features, test_labels, num_epochs, learning_rate, weight_decay, batch_size): train_ls, test_ls = [], [] dataset = torch.utils.data.TensorDataset(train_features, train_labels) train_iter = torch.utils.data.DataLoader(dataset, batch_size, shuffle=True) # 这里使用了Adam优化算法 optimizer = torch.optim.Adam(params=net.parameters(), lr=learning_rate, weight_decay=weight_decay) net = net.float() for epoch in range(num_epochs): for X, y in train_iter: l = loss(net(X.float()), y.float()) optimizer.zero_grad() l.backward() optimizer.step() train_ls.append(log_rmse(net, train_features, train_labels)) if test_labels is not None: test_ls.append(log_rmse(net, test_features, test_labels)) return train_ls, test_ls################# K-交叉验证 ########################import matplotlib.pyplot as plt# y轴使用对数尺度的作图函数,画1到2条曲线def semilogy(x_vals, y_vals, x_label, y_label, x2_vals=None, y2_vals=None, legend=None, figsize=(3.5, 2.5)): plt.figure(figsize = figsize) plt.xlabel(x_label) plt.ylabel(y_label) plt.semilogy(x_vals, y_vals) if x2_vals and y2_vals: plt.semilogy(x2_vals, y2_vals, linestyle=':') plt.legend(legend) def get_k_fold_data(k, i, X, y): # 返回第i折交叉验证时所需要的训练和验证数据 assert k > 1 fold_size = X.shape[0] // k # 将数据分为k份 // 是整除 X_train, y_train = None, None for j in range(k): idx = slice(j * fold_size, (j + 1) * fold_size) # start, end ,一份数据大小的切片位置 X_part, y_part = X[idx, :], y[idx] if j == i: X_valid, y_valid = X_part, y_part # 第i份给验证集 elif X_train is None: X_train, y_train = X_part, y_part # 其余给训练集 else: X_train = torch.cat((X_train, X_part), dim=0) y_train = torch.cat((y_train, y_part), dim=0) return X_train, y_train, X_valid, y_validdef k_fold(k, X_train, y_train, num_epochs, learning_rate, weight_decay, batch_size): train_l_sum, valid_l_sum = 0, 0 for i in range(k): data = get_k_fold_data(k, i, X_train, y_train) # 获取训练集,验证集的打包data net = get_net(X_train.shape[1]) # 特征数量 train_ls, valid_ls = train(net, *data, num_epochs, learning_rate, weight_decay, batch_size) train_l_sum += train_ls[-1] valid_l_sum += valid_ls[-1] if i == 0: semilogy(range(1, num_epochs + 1), train_ls, 'epochs', 'rmse', range(1, num_epochs + 1), valid_ls, ['train', 'valid']) print('fold %d, train rmse %f, valid rmse %f' % (i, train_ls[-1], valid_ls[-1])) return train_l_sum / k, valid_l_sum / k### 设置超参进行训练和验证k, num_epochs, lr, weight_decay, batch_size = 5, 100, 5, 0, 64train_l, valid_l = k_fold(k, train_features, train_labels, num_epochs, lr, weight_decay, batch_size)print('%d-fold validation: avg train rmse %f, avg valid rmse %f' % (k, train_l, valid_l))