{ "cells": [ { "cell_type": "code", "execution_count": 2, "metadata": { "collapsed": false }, "outputs": [], "source": [ "import pandas as pd\n", "import numpy as np\n", "from sklearn import tree\n", "from sklearn.externals.six import StringIO\n", "from IPython.display import Image\n", "import pydotplus" ] }, { "cell_type": "code", "execution_count": 14, "metadata": { "collapsed": true }, "outputs": [], "source": [ "df = pd.read_csv(\"../../data/homes_sf_ny/data.csv\")" ] }, { "cell_type": "code", "execution_count": 15, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/html": [ "
\n", " | in_sf | \n", "beds | \n", "bath | \n", "price | \n", "year_built | \n", "sqft | \n", "price_per_sqft | \n", "elevation | \n", "
---|---|---|---|---|---|---|---|---|
0 | \n", "0 | \n", "2.0 | \n", "1.0 | \n", "999000 | \n", "1960 | \n", "1000 | \n", "999 | \n", "10 | \n", "
1 | \n", "0 | \n", "2.0 | \n", "2.0 | \n", "2750000 | \n", "2006 | \n", "1418 | \n", "1939 | \n", "0 | \n", "
2 | \n", "0 | \n", "2.0 | \n", "2.0 | \n", "1350000 | \n", "1900 | \n", "2150 | \n", "628 | \n", "9 | \n", "
3 | \n", "0 | \n", "1.0 | \n", "1.0 | \n", "629000 | \n", "1903 | \n", "500 | \n", "1258 | \n", "9 | \n", "
4 | \n", "0 | \n", "0.0 | \n", "1.0 | \n", "439000 | \n", "1930 | \n", "500 | \n", "878 | \n", "10 | \n", "