{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# 3.16 实战Kaggle比赛:房价预测" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "1.2.0\n" ] } ], "source": [ "# 如果没有安装pandas,则反注释下面一行\n", "# !pip install pandas\n", "\n", "%matplotlib inline\n", "import torch\n", "import torch.nn as nn\n", "import numpy as np\n", "import pandas as pd\n", "import sys\n", "sys.path.append(\"..\") \n", "import d2lzh_pytorch as d2l\n", "\n", "print(torch.__version__)\n", "torch.set_default_tensor_type(torch.FloatTensor)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## 3.16.2 获取和读取数据集" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "collapsed": true }, "outputs": [], "source": [ "train_data = pd.read_csv('../../data/kaggle_house/train.csv')\n", "test_data = pd.read_csv('../../data/kaggle_house/test.csv')" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(1460, 81)" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "train_data.shape" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(1459, 80)" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "test_data.shape" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", " | Id | \n", "MSSubClass | \n", "MSZoning | \n", "LotFrontage | \n", "SaleType | \n", "SaleCondition | \n", "SalePrice | \n", "
---|---|---|---|---|---|---|---|
0 | \n", "1 | \n", "60 | \n", "RL | \n", "65.0 | \n", "WD | \n", "Normal | \n", "208500 | \n", "
1 | \n", "2 | \n", "20 | \n", "RL | \n", "80.0 | \n", "WD | \n", "Normal | \n", "181500 | \n", "
2 | \n", "3 | \n", "60 | \n", "RL | \n", "68.0 | \n", "WD | \n", "Normal | \n", "223500 | \n", "
3 | \n", "4 | \n", "70 | \n", "RL | \n", "60.0 | \n", "WD | \n", "Abnorml | \n", "140000 | \n", "