{ "metadata": { "name": "", "signature": "sha256:412dd4c8414ddc790ce8d1ec760e59ad3f9a59449e07c8f3003ac7070160afb3" }, "nbformat": 3, "nbformat_minor": 0, "worksheets": [ { "cells": [ { "cell_type": "code", "collapsed": false, "input": [ "import pandas as pd\n", "import numpy as np\n", "import pylab as pl\n", "import matplotlib as mpl\n", "%matplotlib inline\n", "%pylab inline" ], "language": "python", "metadata": {}, "outputs": [ { "output_type": "stream", "stream": "stdout", "text": [ "Populating the interactive namespace from numpy and matplotlib\n" ] } ], "prompt_number": 1 }, { "cell_type": "code", "collapsed": false, "input": [ "# \u0437\u0430\u0433\u0440\u0443\u0437\u043a\u0430 \u0434\u0430\u043d\u043d\u044b\u0445\n", "# data = pd.read_csv('D:\\\\Competitions\\\\Laura\\\\arenda.csv', sep=';', decimal=',')\n", "data = pd.read_excel('D:\\\\Competitions\\\\Laura\\\\arenda.xlsx')\n", "data[:3]" ], "language": "python", "metadata": {}, "outputs": [ { "html": [ "
\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
idSpace SizePrice / SF / MonthSpace Type: Lease Type: Number of transport spotsPopulationPopulation change 2013-2010Land areaDensity of people living in area...Household sizeAverage HH income 2013Income change 2013-2010Change in % of bachelor degrees 2013-2010Average salary of employees ($ 000s)Average salary of employees in new businesses% of employees in new companies vs allNumber of new retail places 2013-2010list idlist
0 1 11324 2.649241 NaN NaN 14 6417.318254 0.104498 780786.644395 0.008219... 2.811673 64039 0.008973 0.034373 43000 42220.615385 12 5 239 ln
1 2 2275 1.583333 NaN NaN 22 3902.848712 0.041712 646901.202888 0.006033... 2.786308 77802-0.069537-0.001562 30000 36709.000000 12 2 388 ln
2 3 2275 1.583333 NaN NaN 22 3902.848712 0.041712 646901.202888 0.006033... 2.786308 77802-0.069537-0.001562 30000 36709.000000 12 2 389 ln
\n", "

3 rows \u00d7 23 columns

\n", "
" ], "metadata": {}, "output_type": "pyout", "prompt_number": 7, "text": [ " id Space Size Price / SF / Month Space Type: Lease Type: \\\n", "0 1 11324 2.649241 NaN NaN \n", "1 2 2275 1.583333 NaN NaN \n", "2 3 2275 1.583333 NaN NaN \n", "\n", " Number of transport spots Population Population change 2013-2010 \\\n", "0 14 6417.318254 0.104498 \n", "1 22 3902.848712 0.041712 \n", "2 22 3902.848712 0.041712 \n", "\n", " Land area Density of people living in area \\\n", "0 780786.644395 0.008219 \n", "1 646901.202888 0.006033 \n", "2 646901.202888 0.006033 \n", "\n", " ... Household size Average HH income 2013 \\\n", "0 ... 2.811673 64039 \n", "1 ... 2.786308 77802 \n", "2 ... 2.786308 77802 \n", "\n", " Income change 2013-2010 Change in % of bachelor degrees 2013-2010 \\\n", "0 0.008973 0.034373 \n", "1 -0.069537 -0.001562 \n", "2 -0.069537 -0.001562 \n", "\n", " Average salary of employees ($ 000s) \\\n", "0 43000 \n", "1 30000 \n", "2 30000 \n", "\n", " Average salary of employees in new businesses \\\n", "0 42220.615385 \n", "1 36709.000000 \n", "2 36709.000000 \n", "\n", " % of employees in new companies vs all \\\n", "0 12 \n", "1 12 \n", "2 12 \n", "\n", " Number of new retail places 2013-2010 list id list \n", "0 5 239 ln \n", "1 2 388 ln \n", "2 2 389 ln \n", "\n", "[3 rows x 23 columns]" ] } ], "prompt_number": 7 }, { "cell_type": "code", "collapsed": false, "input": [ "data.columns" ], "language": "python", "metadata": {}, "outputs": [ { "metadata": {}, "output_type": "pyout", "prompt_number": 5, "text": [ "Index([u'id', u'Space Size', u'Price / SF / Month', u'Space Type: ', u'Lease Type: ', u'Number of transport spots', u'Population', u'Population change 2013-2010', u'Land area', u'Density of people living in area', u'Density of people working in area (based on lat/lon)', u'Total density (living + working)', u'Social chat score', u'Household size', u'Average HH income 2013', u'Income change 2013-2010', u'Change in % of bachelor degrees 2013-2010', u'Average salary of employees ($ 000s)', u'Average salary of employees in new businesses', u'% of employees in new companies vs all', u'Number of new retail places 2013-2010', u'list id', u'list'], dtype='object')" ] } ], "prompt_number": 5 }, { "cell_type": "code", "collapsed": false, "input": [ "# \u0443\u0434\u0430\u043b\u0438\u0442\u044c id\n", "del data['id']\n", "\n", "# \u043f\u0435\u0440\u0435\u0438\u043c\u0435\u043d\u043e\u0432\u0430\u0442\u044c \u043d\u0430\u0437\u0432\u0430\u043d\u0438\u044f \u043f\u0440\u0438\u0437\u043d\u0430\u043a\u043e\u0432\n", "data = data.rename(columns={\n", "u'Space Size':'spacesize',\n", "u'Price / SF / Month':'price',\n", "u'Space Type: ':'spacetype',\n", "u'Lease Type: ':'leasetype',\n", "u'Number of transport spots':'nspots',\n", "u'Population':'pop', \n", "u'Population change 2013-2010':'popchange',\n", "u'Land area':'land',\n", "u'Density of people living in area':'densliv', \n", "u'Density of people working in area (based on lat/lon)':'denswork',\n", "u'Total density (living + working)':'denstotal',\n", "u'Social chat score':'chat', \n", "u'Household size':'hhsize',\n", "u'Average HH income 2013':'aincome',\n", "u'Income change 2013-2010':'incomechange',\n", "u'Change in % of bachelor degrees 2013-2010':'degrees',\n", "u'Average salary of employees ($ 000s)':'asalary',\n", "u'Average salary of employees in new businesses':'anewsalary', \n", "u'% of employees in new companies vs all':'employees',\n", "u'Number of new retail places 2013-2010':'retails',\n", "u'list id':'listid',\n", "u'list':'list'\n", "})\n", "data[:3]" ], "language": "python", "metadata": {}, "outputs": [ { "html": [ "
\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
spacesizepricespacetypeleasetypenspotspoppopchangelanddenslivdenswork...hhsizeaincomeincomechangedegreesasalaryanewsalaryemployeesretailslistidlist
0 11324 2.649241 NaN NaN 14 6417.318254 0.104498 780786.644395 0.008219 0.001896... 2.811673 64039 0.008973 0.034373 43000 42220.615385 12 5 239 ln
1 2275 1.583333 NaN NaN 22 3902.848712 0.041712 646901.202888 0.006033 0.002220... 2.786308 77802-0.069537-0.001562 30000 36709.000000 12 2 388 ln
2 2275 1.583333 NaN NaN 22 3902.848712 0.041712 646901.202888 0.006033 0.002220... 2.786308 77802-0.069537-0.001562 30000 36709.000000 12 2 389 ln
\n", "

3 rows \u00d7 22 columns

\n", "
" ], "metadata": {}, "output_type": "pyout", "prompt_number": 8, "text": [ " spacesize price spacetype leasetype nspots pop popchange \\\n", "0 11324 2.649241 NaN NaN 14 6417.318254 0.104498 \n", "1 2275 1.583333 NaN NaN 22 3902.848712 0.041712 \n", "2 2275 1.583333 NaN NaN 22 3902.848712 0.041712 \n", "\n", " land densliv denswork ... hhsize aincome \\\n", "0 780786.644395 0.008219 0.001896 ... 2.811673 64039 \n", "1 646901.202888 0.006033 0.002220 ... 2.786308 77802 \n", "2 646901.202888 0.006033 0.002220 ... 2.786308 77802 \n", "\n", " incomechange degrees asalary anewsalary employees retails listid \\\n", "0 0.008973 0.034373 43000 42220.615385 12 5 239 \n", "1 -0.069537 -0.001562 30000 36709.000000 12 2 388 \n", "2 -0.069537 -0.001562 30000 36709.000000 12 2 389 \n", "\n", " list \n", "0 ln \n", "1 ln \n", "2 ln \n", "\n", "[3 rows x 22 columns]" ] } ], "prompt_number": 8 }, { "cell_type": "code", "collapsed": false, "input": [ "# \u0432\u044b\u0432\u043e\u0434 \u0441\u0442\u0430\u0442\u0438\u0441\u0442\u0438\u043a\u0438\n", "data.describe()" ], "language": "python", "metadata": {}, "outputs": [ { "html": [ "
\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
spacesizepricenspotspoppopchangelanddenslivdensworkdenstotalchathhsizeaincomeincomechangedegreesasalaryanewsalaryemployeesretailslistid
count 2227.000000 2227.000000 2227.000000 2227.000000 2227.000000 2227.000000 2227.000000 2227.000000 2227.000000 2227.000000 2227.000000 2227.00000 2227.000000 2227.000000 2227.000000 2227.000000 2227.000000 2227.000000 2227.000000
mean 3884.932645 6.224143 29.325101 15833.326788 0.010618 744267.272294 0.021292 0.025608 0.046900 36.495285 2.513140 63835.55366 0.097281 0.011870 46687.471935 39536.089718 24.637180 34.376291 612.130669
std 16311.985235 6.582278 14.658322 8681.890404 0.055430 74177.247168 0.011673 0.051450 0.053700 68.069988 0.532757 31651.81757 0.103458 0.023377 15010.874771 12852.903269 8.480855 36.063391 337.293657
min 1.000000 0.000192 0.000000 114.945126 -0.141048 198188.986853 0.000199 0.000000 0.000249 0.000000 1.510175 17479.00000 -0.253104 -0.087200 0.000000 0.000000 0.000000 0.000000 1.000000
25% 1000.000000 2.666663 19.000000 9712.109647 -0.028305 741991.143918 0.013105 0.004082 0.019105 5.000000 2.086396 40051.00000 0.031163 -0.002626 36000.000000 30269.422362 20.000000 10.000000 319.500000
50% 1700.000000 4.166666 29.000000 15645.946460 0.008172 780549.167952 0.020760 0.006939 0.028993 13.000000 2.534359 53145.00000 0.093626 0.011536 41000.000000 36652.400004 24.000000 21.000000 615.000000
75% 3400.000000 7.343137 38.000000 21584.540555 0.044095 780832.018612 0.028699 0.020631 0.051848 42.000000 2.894399 88869.50000 0.163718 0.027190 53000.000000 46223.310708 29.000000 42.000000 902.000000
max 600000.000000 83.414634 78.000000 46664.838451 0.313075 780856.610853 0.062810 0.350893 0.369600 988.000000 4.559108 202295.00000 0.429361 0.102018 106000.000000 115360.037590 84.000000 184.000000 1217.000000
\n", "
" ], "metadata": {}, "output_type": "pyout", "prompt_number": 10, "text": [ " spacesize price nspots pop popchange \\\n", "count 2227.000000 2227.000000 2227.000000 2227.000000 2227.000000 \n", "mean 3884.932645 6.224143 29.325101 15833.326788 0.010618 \n", "std 16311.985235 6.582278 14.658322 8681.890404 0.055430 \n", "min 1.000000 0.000192 0.000000 114.945126 -0.141048 \n", "25% 1000.000000 2.666663 19.000000 9712.109647 -0.028305 \n", "50% 1700.000000 4.166666 29.000000 15645.946460 0.008172 \n", "75% 3400.000000 7.343137 38.000000 21584.540555 0.044095 \n", "max 600000.000000 83.414634 78.000000 46664.838451 0.313075 \n", "\n", " land densliv denswork denstotal chat \\\n", "count 2227.000000 2227.000000 2227.000000 2227.000000 2227.000000 \n", "mean 744267.272294 0.021292 0.025608 0.046900 36.495285 \n", "std 74177.247168 0.011673 0.051450 0.053700 68.069988 \n", "min 198188.986853 0.000199 0.000000 0.000249 0.000000 \n", "25% 741991.143918 0.013105 0.004082 0.019105 5.000000 \n", "50% 780549.167952 0.020760 0.006939 0.028993 13.000000 \n", "75% 780832.018612 0.028699 0.020631 0.051848 42.000000 \n", "max 780856.610853 0.062810 0.350893 0.369600 988.000000 \n", "\n", " hhsize aincome incomechange degrees asalary \\\n", "count 2227.000000 2227.00000 2227.000000 2227.000000 2227.000000 \n", "mean 2.513140 63835.55366 0.097281 0.011870 46687.471935 \n", "std 0.532757 31651.81757 0.103458 0.023377 15010.874771 \n", "min 1.510175 17479.00000 -0.253104 -0.087200 0.000000 \n", "25% 2.086396 40051.00000 0.031163 -0.002626 36000.000000 \n", "50% 2.534359 53145.00000 0.093626 0.011536 41000.000000 \n", "75% 2.894399 88869.50000 0.163718 0.027190 53000.000000 \n", "max 4.559108 202295.00000 0.429361 0.102018 106000.000000 \n", "\n", " anewsalary employees retails listid \n", "count 2227.000000 2227.000000 2227.000000 2227.000000 \n", "mean 39536.089718 24.637180 34.376291 612.130669 \n", "std 12852.903269 8.480855 36.063391 337.293657 \n", "min 0.000000 0.000000 0.000000 1.000000 \n", "25% 30269.422362 20.000000 10.000000 319.500000 \n", "50% 36652.400004 24.000000 21.000000 615.000000 \n", "75% 46223.310708 29.000000 42.000000 902.000000 \n", "max 115360.037590 84.000000 184.000000 1217.000000 " ] } ], "prompt_number": 10 }, { "cell_type": "code", "collapsed": false, "input": [ "# \u0443\u0431\u0440\u0430\u0442\u044c \u041d\u0430\u041d\u044b\n", "# \u0442\u0443\u0442 \u043e\u043d\u0438 \u0432\u0441\u0435 \u0432 \u0441\u0442\u0440\u043e\u0447\u043a\u0430\u0445!!!\n", "data = data.fillna('net')\n", "data[:3]" ], "language": "python", "metadata": {}, "outputs": [ { "html": [ "
\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
spacesizepricespacetypeleasetypenspotspoppopchangelanddenslivdenswork...hhsizeaincomeincomechangedegreesasalaryanewsalaryemployeesretailslistidlist
0 11324 2.649241 net net 14 6417.318254 0.104498 780786.644395 0.008219 0.001896... 2.811673 64039 0.008973 0.034373 43000 42220.615385 12 5 239 ln
1 2275 1.583333 net net 22 3902.848712 0.041712 646901.202888 0.006033 0.002220... 2.786308 77802-0.069537-0.001562 30000 36709.000000 12 2 388 ln
2 2275 1.583333 net net 22 3902.848712 0.041712 646901.202888 0.006033 0.002220... 2.786308 77802-0.069537-0.001562 30000 36709.000000 12 2 389 ln
\n", "

3 rows \u00d7 22 columns

\n", "
" ], "metadata": {}, "output_type": "pyout", "prompt_number": 11, "text": [ " spacesize price spacetype leasetype nspots pop popchange \\\n", "0 11324 2.649241 net net 14 6417.318254 0.104498 \n", "1 2275 1.583333 net net 22 3902.848712 0.041712 \n", "2 2275 1.583333 net net 22 3902.848712 0.041712 \n", "\n", " land densliv denswork ... hhsize aincome \\\n", "0 780786.644395 0.008219 0.001896 ... 2.811673 64039 \n", "1 646901.202888 0.006033 0.002220 ... 2.786308 77802 \n", "2 646901.202888 0.006033 0.002220 ... 2.786308 77802 \n", "\n", " incomechange degrees asalary anewsalary employees retails listid \\\n", "0 0.008973 0.034373 43000 42220.615385 12 5 239 \n", "1 -0.069537 -0.001562 30000 36709.000000 12 2 388 \n", "2 -0.069537 -0.001562 30000 36709.000000 12 2 389 \n", "\n", " list \n", "0 ln \n", "1 ln \n", "2 ln \n", "\n", "[3 rows x 22 columns]" ] } ], "prompt_number": 11 }, { "cell_type": "code", "collapsed": false, "input": [ "# \u0447\u0438\u0441\u043b\u043e \u0443\u043d\u0438\u043a\u0430\u043b\u044c\u043d\u044b\u0445 \u0437\u043d\u0430\u0447\u0435\u043d\u0438\u0439 \u043f\u043e \u0441\u0442\u043e\u043b\u0431\u0446\u0430\u043c\n", "# \u043f\u0440\u0430\u0432\u0434\u0430... \u043f\u0440\u043e\u0431\u043b\u0435\u043c\u044b \u0441 \u041d\u0430\u041d\u0430\u043c\u0438\n", "lengths = []\n", "for i in xrange(data.shape[1]):\n", " lengths.append(data[data.columns[i]].unique().__len__())\n", "pyplot.bar(np.arange(data.shape[1]), lengths)\n", "# \u0440\u0430\u0437\u043c\u0435\u0440\u044b\n", "data.shape" ], "language": "python", "metadata": {}, "outputs": [ { "metadata": {}, "output_type": "pyout", "prompt_number": 12, "text": [ "(2227, 22)" ] }, { "metadata": {}, "output_type": "display_data", "png": "iVBORw0KGgoAAAANSUhEUgAAAX4AAAEACAYAAAC08h1NAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAFp1JREFUeJzt3X+QnVd93/H3pzhKIVg4KjPClk2tYHmwUicFB4tMSX2T\nUI2S6VjuP/4xU9clLi1VAjTTSSvRKdq/iKFJijuNPdNiG7kBdTSEunZrFAvXt3EnwYLEgEBWLHmi\n1FLQQoipl2kzkYZv/7iPvNeLtHv32dW9q33er5kdPffcc+4599Gznz177r17UlVIkrrjr0x6AJKk\n8TL4JaljDH5J6hiDX5I6xuCXpI4x+CWpY+YN/iQPJplOcmio7MYkB5M8m+SLSd4xdN+uJEeTHEmy\ndaj8hiSHmvvuvTBPRZI0ioVm/A8B2+aUfQz411X1NuDDzW2SbAZuAzY3be5LkqbN/cDdVbUJ2JRk\n7mNKksZk3uCvqqeBl+YUfwN4Q3N8GXCyOd4O7K2q01V1HDgGbElyOXBpVR1s6j0M3LIMY5cktXBJ\nizY7gf+V5NcY/OD4yab8CuALQ/VOABuA083xWSebcknSBLR5cfcB4ANV9Wbgl4EHl3dIkqQLqc2M\n/8aqendz/BngE83xSeCqoXpXMpjpn2yOh8tPcg7XXHNNvfDCCy2GJEmd9kJVXTNq5TYz/mNJbmqO\nfwZ4vjl+FLg9yZokG4FNwMGqOgW8nGRL82LvncAj5xz5Cy9QVX5VsXv37omPYaV8eS48F56L+b+A\ntywmxOed8SfZC9wEvDHJiwzexfOPgd9M8oPA/2tuU1WHk+wDDgNngB3VjAjYAXwSeC3weFXtX8wg\nJUnLZ97gr6o7znPXlvPU/wjwkXOU/wFw/aJHJ0ladn5yd4Xq9XqTHsKK4bmY5bmY5bloL7OrMZOX\npFbSeCTpYpCEqsrCNQec8UtSxxj8K9TatetIsuDX2rXrFt2mbbvl6Gtc52Kl9zXO/ytpLpd6VqjB\nO19HORc5+3auRbRp227pfbXRZnwrva9x/l9p9XOpR5I0L4NfkjrG4Jf0fcb5Go7Gr83f6pG0ys3M\nvMSor0HMzIy8tKwVwhm/JHWMwS9JHWPwS1LHGPyS1DEGvyR1jMEvSR1j8EtSx8wb/EkeTDKd5NCc\n8vcneS7J15J8dKh8V5KjSY4k2TpUfkOSQ8199y7/05AkjWqhGf9DwLbhgiQ/DdwM/FhV/Q3g15ry\nzcBtwOamzX3NHrsA9wN3V9UmYFOSVz2mJGl85g3+qnoaeGlO8T8FfrWqTjd1vtWUbwf2VtXpqjoO\nHAO2JLkcuLSqDjb1HgZuWabxS5IWqc0a/ybgbyf5QpJ+kp9oyq8ATgzVOwFsOEf5yaZckjQBbf5W\nzyXAD1fVO5O8A9gH/MhyDWhqauqV416v576akjRHv9+n3++3br/gRixJrgYeq6rrm9ufA+6pqv/Z\n3D4GvBP4RwBVdU9Tvh/YDfwJ8FRVXdeU3wHcVFXvO0dfbsTScCOWodZuxDL2jVjG+f+rpRvHRiyP\nAD/TdHYtsKaq/gx4FLg9yZokGxksCR2sqlPAy0m2NC/23tk8hiRpAuZd6kmyF7gJ+GtJXgQ+DDwI\nPNi8xfMvgX8AUFWHk+wDDgNngB1D0/cdwCeB1wKPV9X+C/BcJEkjcM/dFcqlnqHWLvW41KN5ueeu\nJGleBr8kdYzBL0kdY/BLUscY/JLUMQa/JHWMwS9JHWPwS1LHGPyS1DEGvyR1jMEvSR1j8EtSxxj8\nktQxBr8kdYzBL0kdY/BLUsfMG/xJHkwy3ey2Nfe+f57ke0nWDZXtSnI0yZEkW4fKb0hyqLnv3uV9\nCpKkxVhoxv8QsG1uYZKrgL/DYCP1s2WbgduAzU2b+5o9dgHuB+6uqk3ApiTf95iSpPGYN/ir6mng\npXPc9RvAv5hTth3YW1Wnq+o4cAzYkuRy4NKqOtjUexi4ZUmjliS1tug1/iTbgRNV9dU5d10BnBi6\nfQLYcI7yk025JGkCLllM5SSvAz7EYJnnleLlHNDU1NQrx71ej16vt5wPL0kXvX6/T7/fb90+VTV/\nheRq4LGquj7J9cDngf/b3H0lgxn8FuA9AFV1T9NuP7CbwesAT1XVdU35HcBNVfW+c/RVC42nKwYv\nj4xyLsLZczZ6m7btlt5XG23Gt9L7Guf/VRvj/P/V0iWhqkaehC9qqaeqDlXV+qraWFUbGSzhvL2q\npoFHgduTrEmyEdgEHKyqU8DLSbY0L/beCTyymH4lSctnobdz7gV+D7g2yYtJ3jOnyis/5qvqMLAP\nOAx8DtgxNH3fAXwCOAocq6r9yzR+SdIiLbjUM04u9cxyqWeotUs9LvVoXhd0qUdairVr15FkpK+1\na9ct/IArxGp9Xlq9nPGvUKtxxr/SZ7lt+1qN58IZ/8XFGb8kaV4GvyR1jMEvSR1j8EtSxxj8ktQx\nBr8kdYzBL0kdY/BLUscY/JLUMQa/JHWMwS9JHWPwS1LHGPyS1DEGvyR1zEI7cD2YZDrJoaGyf5Pk\nuSRfSfLZJG8Yum9XkqNJjiTZOlR+Q5JDzX33XpinIkkaxUIz/oeAbXPKngB+tKp+HHge2AWQZDNw\nG7C5aXNfs8cuwP3A3VW1CdiUZO5jSpLGZN7gr6qngZfmlB2oqu81N58BrmyOtwN7q+p0VR0HjgFb\nklwOXFpVB5t6DwO3LNP4JUmLtNQ1/l8AHm+OrwBODN13AthwjvKTTbkktTbqlpdud/n9LmnbMMm/\nAv6yqj69jONhamrqleNer0ev11vOh5e0SszMvMQo20POzIy8I+FFo9/v0+/3W7dfcM/dJFcDj1XV\n9UNl/xB4L/CzVfUXTdlOgKq6p7m9H9gN/AnwVFVd15TfAdxUVe87R1/uudtwz1333F1aX6t/z91x\nXhcr3QXfc7d5YfZXgO1nQ7/xKHB7kjVJNgKbgINVdQp4OcmW5sXeO4FHFtuvJGl5zLvUk2QvcBPw\nxiQvMpjB7wLWAAeaN+38flXtqKrDSfYBh4EzwI6h6fsO4JPAa4HHq2r/hXgykqSFLbjUM04u9cxy\nqcelnqX15VLPUE2Xeubwk7uS1DEGvyR1jMEvSR1j8EtSxxj8ktQxBr8kdYzBL0kdY/BLUscY/JLU\nMQa/JHWMwS9JHWPwS1LHGPyS1DEGvyR1jMEvSR0zb/AneTDJdJJDQ2XrkhxI8nySJ5JcNnTfriRH\nkxxJsnWo/IYkh5r77r0wT0WSNIqFZvwPAdvmlO0EDlTVtcCTzW2SbAZuAzY3be5rtloEuB+4u6o2\nAZua7RslSRMwb/BX1dPAS3OKbwb2NMd7gFua4+3A3qo6XVXHgWPAliSXA5dW1cGm3sNDbSRJY9Zm\njX99VU03x9PA+ub4CuDEUL0TwIZzlJ9syiVJE7CkF3ebDXJX92aWkrTKXNKizXSSN1XVqWYZ55tN\n+UngqqF6VzKY6Z9sjofLT57vwaempl457vV69Hq9FkOUpNWr3+/T7/dbt89Cu88nuRp4rKqub25/\nDPh2VX00yU7gsqra2by4+2ngRgZLOZ8HrqmqSvIM8AHgIPDfgX9XVfvP0VctNJ6uGLwuPsq5CGfP\n2eht2rZbWl/jHF9bngsW2c/S+2prnNfFSpeEqsrCNQfmnfEn2QvcBLwxyYvAh4F7gH1J7gaOA7cC\nVNXhJPuAw8AZYMdQiu8APgm8Fnj8XKEvSRqPBWf84+SMf5Yzfmf8S+vLGf9QTWf8c/jJXUnqGINf\nkjrG4JekjjH4JaljDH5J6hiDX5I6xuCXpI4x+CWpYwx+SeqYiz74165dR5KRvtauXTfp4UrSxLX5\n65wryszMS4z60fKZmZE/0SxJq9ZFP+OXJC2OwS9JHWPwS1LHGPyS1DEGvyR1TOvgT7IrydeTHEry\n6SQ/mGRdkgNJnk/yRJLL5tQ/muRIkq3LM3xJ0mK1Cv5mH973Am9v9uJ9DXA7sBM4UFXXAk82t2n2\n470N2AxsA+5L4m8bkjQBbcP3ZeA08LoklwCvA/4UuBnY09TZA9zSHG8H9lbV6ao6DhxjsCm7JGnM\nWgV/Vf058OvA/2YQ+N+pqgPA+qqabqpNA+ub4yuAE0MPcQLY0GrEkqQlabvU8xbgnwFXMwj11yf5\n+8N1ml3T5/tI7ere/ViSVqi2f7LhJ4Dfq6pvAyT5LPCTwKkkb6qqU0kuB77Z1D8JXDXU/sqm7PtM\nTU29ctzr9ej1ei2HKEmrU7/fp9/vt26fwcR8kY2SHwc+BbwD+Avgk8BB4K8D366qjybZCVxWVTub\nF3c/zWBdfwPweeCamtN5krlFo4yF0X95CG2e7ySM/rxmn1PbczGuvsY5vrY8Fyyyn6X31dY4r4uV\nLglVNfIfI2s146+qryR5GPgS8D3gD4H/AFwK7EtyN3AcuLWpfzjJPuAwcAbYseiElyQti1Yz/gvF\nGf8sZ/zO+JfWlzP+oZoXzfd9W4ud8fteeknqGINfkjrG4JekjjH4JaljDH5J6hiDX5I6xuCXpI4x\n+CWpYwx+SeoYg1+SOsbgl6SOMfglqWMMfknqGINfkjrG4JekjjH4JaljWgd/ksuSfCbJc0kOJ9mS\nZF2SA0meT/JEksuG6u9KcjTJkSRbl2f4kqTFWsqM/17g8aq6Dvgx4AiwEzhQVdcCTza3afbcvQ3Y\nDGwD7kvibxuSNAGtwjfJG4CfqqoHAarqTFX9H+BmYE9TbQ9wS3O8HdhbVaer6jhwjMHG65KkMWs7\n694IfCvJQ0n+MMl/TPJDwPqqmm7qTAPrm+MrgBND7U8AG1r2LUlagkuW0O7twC9V1ReTfJxmWees\nqqok8+1wfM77pqamXjnu9Xr0er2WQ5Sk1anf79Pv91u3T5vd55O8Cfj9qtrY3H4XsAv4EeCnq+pU\nksuBp6rqrUl2AlTVPU39/cDuqnpmzuPWYseThPP8DDlXbdo830kY/XnNPqe252JcfY1zfG15Llhk\nP0vvq61xXhcrXRKqKqPWb7XUU1WngBeTXNsUvRv4OvAYcFdTdhfwSHP8KHB7kjVJNgKbgINt+pYk\nLU3bpR6A9wOfSrIGeAF4D/AaYF+Su4HjwK0AVXU4yT7gMHAG2LHoqb0kaVm0Wuq5UFzqmeVSj0s9\nS+vLpZ6hmhfN931bY1nqkSRdvAx+SeoYg1+SOsbgl6SOMfglqWMMfknqGINfkjrG4JekjjH4Jalj\nDH5J6hiDX5I6xuCXpI4x+CWpY1Zc8CcZ6Wvt2nWTHqokXZSW8vf4L5DR/nzqzMzIf4FUkjRkxc34\nJUkX1pKCP8lrkjyb5LHm9rokB5I8n+SJJJcN1d2V5GiSI0m2LnXgkqR2ljrj/yCD7RTPrs/sBA5U\n1bXAk81tkmwGbgM2A9uA+5L424YkTUDr8E1yJfDzwCeAswvuNwN7muM9wC3N8XZgb1WdrqrjwDHg\nxrZ9S5LaW8qs+98CvwJ8b6hsfVVNN8fTwPrm+ArgxFC9E8CGJfQtSWqp1bt6kvxd4JtV9WyS3rnq\nVFUlme8tOue5b2rouNd8SZLO6vf79Pv91u3TZvf5JB8B7gTOAH8VWAt8FngH0KuqU0kuB56qqrcm\n2QlQVfc07fcDu6vqmTmPW6O+nRNCVZGExba5GIz+vGafU9tzMa6+xjm+tjwXLLKfpffV1jivi5Uu\nCVU18nvcWy31VNWHquqqqtoI3A78j6q6E3gUuKupdhfwSHP8KHB7kjVJNgKbgINt+pYkLc1yfYDr\n7I/Te4B9Se4GjgO3AlTV4ST7GLwD6Aywo1b7j2BJWqFaLfVcKC71zHKpx6WepfXlUs9QzYvm+76t\nsSz1SJIuXga/JHWMwS9JHWPwS1LHGPyS1DEGvyR1jMEvSR1j8EtSxxj8ktQxBr8kdYzBL0kdY/BL\nUscY/JLUMQa/JHWMwS9JHWPwS1LHtAr+JFcleSrJ15N8LckHmvJ1SQ4keT7JE0kuG2qzK8nRJEeS\nbF2uJyBJWpy2M/7TwC9X1Y8C7wR+Mcl1wE7gQFVdCzzZ3CbJZuA2YDOwDbgvib9tSNIEtN1s/VRV\nfbk5/i7wHLABuBnY01TbA9zSHG8H9lbV6ao6DhwDblzCuCVJLS151p3kauBtwDPA+qqabu6aBtY3\nx1cAJ4aanWDwg0KSNGaXLKVxktcDvw18sKpmBpsfD1RVDTZPP6/z3Dc1dNxrviRJZ/X7ffr9fuv2\nabv7fJIfAP4b8Lmq+nhTdgToVdWpJJcDT1XVW5PsBKiqe5p6+4HdVfXMnMes8/48+P4RUFUMftgs\nrs3FYPTnNfuc2p6LcfU1zvG15blgkf0sva+2xnldrHRJqKosXHOg7bt6AjwAHD4b+o1Hgbua47uA\nR4bKb0+yJslGYBNwsE3f0ijWrl1HkpG+1q5dN+nhSmPVasaf5F3A7wJfZfZH7i4GYb4PeDNwHLi1\nqr7TtPkQ8AvAGQZLQ79zjsd1xt9wxj/+8Y2zL2f8S+eMf9ZiZ/ytl3ouBIN/lmFn8C/X+Nq4GL6v\nDP5ZY1nqkSRdvAx+SRPl6zHjt6S3c0rSUs3MvMSoy0ozMyOvZmgezvglqWMMfknqGINfkjrG4Jek\njjH4JaljDH5J6hiDX5I6xuC/wPxwiibNa1Bz+QGuC8wPp2jSvAY1lzN+SeoYg1/SsnFZ6eLgUo+k\nZeOy0sVhrDP+JNuSHElyNMm/HGffkqSBsQV/ktcA/x7YBmwG7khy3bj6n2vUX0n9dVTSajPOGf+N\nwLGqOl5Vp4H/DGwfY/+vMvsr6fxfg3qStHqMM/g3AC8O3T7RlEmSxmicwX/Rb3rpOxYkrQbjfFfP\nSeCqodtXMZj1D3sB8pZRH3Cw2TLA6O8OmG0zertXtxnNzMxLExrfSu9rpY9vnH11e3zj7KvN9/BF\n5oXFVM64dp9PcgnwR8DPAn8KHATuqKrnxjIASRIwxhl/VZ1J8kvA7wCvAR4w9CVp/MY245ckrQwr\n4k82+MGuWUmOJ/lqkmeTHJz0eMYpyYNJppMcGipbl+RAkueTPJHkskmOcVzOcy6mkpxoro1nk2yb\n5BjHJclVSZ5K8vUkX0vygaa8c9fGPOdiUdfGxGf8zQe7/gh4N4MXgL9Ih9f+k/wxcENV/fmkxzJu\nSX4K+C7wcFVd35R9DPizqvpYMyn44araOclxjsN5zsVuYKaqfmOigxuzJG8C3lRVX07yeuAPgFuA\n99Cxa2Oec3Eri7g2VsKMf0V9sGuFWPVvQTiXqnoamPuJuZuBPc3xHgYX+ap3nnMBHbw2qupUVX25\nOf4u8ByDzwB17tqY51zAIq6NlRD8frDr1Qr4fJIvJXnvpAezAqyvqunmeBpYP8nBrADvT/KVJA90\nYWljriRXA28DnqHj18bQufhCUzTytbESgt9Xl1/tb1XV24CfA36x+ZVfQA3WJbt8vdwPbAT+JvAN\n4NcnO5zxapY2fhv4YFXNDN/XtWujORefYXAuvssir42VEPyjfLCrM6rqG82/3wL+C4OlsC6bbtY1\nSXI58M0Jj2diquqb1QA+QYeujSQ/wCD0/1NVPdIUd/LaGDoXv3X2XCz22lgJwf8lYFOSq5OsAW4D\nHp3wmCYiyeuSXNoc/xCwFTg0f6tV71Hgrub4LuCReequak24nfX36Mi1kcHHbh8ADlfVx4fu6ty1\ncb5zsdhrY+Lv6gFI8nPAx5n9YNevTnhIE5FkI4NZPgw+XPepLp2LJHuBm4A3Mliz/TDwX4F9wJuB\n48CtVfWdSY1xXM5xLnYDPQa/yhfwx8A/GVrjXrWSvAv4XeCrzC7n7GLw6f9OXRvnORcfAu5gEdfG\nigh+SdL4rISlHknSGBn8ktQxBr8kdYzBL0kdY/BLUscY/JLUMQa/JHWMwS9JHfP/AdluFykOBhLJ\nAAAAAElFTkSuQmCC\n", "text": [ "" ] } ], "prompt_number": 12 }, { "cell_type": "code", "collapsed": false, "input": [ "# \u0430\u043d\u0430\u043b\u0438\u0437 \u043f\u0440\u0438\u0437\u043d\u0430\u043a\u043e\u0432 \u0441 \u043c\u0430\u043b\u044b\u043c \u0447\u0438\u0441\u043b\u043e\u043c \u0437\u043d\u0430\u0447\u0435\u043d\u0438\u0439\n", "for i in xrange(data.shape[1]):\n", " u = data[data.columns[i]].unique()\n", " if u.__len__()<10:\n", " print data.columns[i], u" ], "language": "python", "metadata": {}, "outputs": [ { "output_type": "stream", "stream": "stdout", "text": [ "leasetype ['net' u'Full Service' u'Industrial Gross' u'Modified Gross'\n", " u'Modified Net' u'NNN' u'Other']\n", "list [u'ln' u'cf']\n" ] } ], "prompt_number": 13 }, { "cell_type": "code", "collapsed": false, "input": [ "# \u0444\u0430\u043a\u0442\u043e\u0440\u044b \u0437\u0430\u043c\u0435\u043d\u0438\u0442\u044c \u043c\u043e\u0449\u043d\u043e\u0441\u0442\u044f\u043c\u0438 \u0432\u0445\u043e\u0436\u0434\u0435\u043d\u0438\u0439\n", "factorfeatures = ['spacetype', 'leasetype', 'list']\n", "for f in factorfeatures:\n", " set = data.groupby(f).size()\n", " data[f] = data[f].apply(lambda x: set[x])\n", "data[:3]" ], "language": "python", "metadata": {}, "outputs": [ { "html": [ "
\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
spacesizepricespacetypeleasetypenspotspoppopchangelanddenslivdenswork...hhsizeaincomeincomechangedegreesasalaryanewsalaryemployeesretailslistidlist
0 11324 2.649241 4 427 14 6417.318254 0.104498 780786.644395 0.008219 0.001896... 2.811673 64039 0.008973 0.034373 43000 42220.615385 12 5 239 1196
1 2275 1.583333 4 427 22 3902.848712 0.041712 646901.202888 0.006033 0.002220... 2.786308 77802-0.069537-0.001562 30000 36709.000000 12 2 388 1196
2 2275 1.583333 4 427 22 3902.848712 0.041712 646901.202888 0.006033 0.002220... 2.786308 77802-0.069537-0.001562 30000 36709.000000 12 2 389 1196
\n", "

3 rows \u00d7 22 columns

\n", "
" ], "metadata": {}, "output_type": "pyout", "prompt_number": 14, "text": [ " spacesize price spacetype leasetype nspots pop popchange \\\n", "0 11324 2.649241 4 427 14 6417.318254 0.104498 \n", "1 2275 1.583333 4 427 22 3902.848712 0.041712 \n", "2 2275 1.583333 4 427 22 3902.848712 0.041712 \n", "\n", " land densliv denswork ... hhsize aincome \\\n", "0 780786.644395 0.008219 0.001896 ... 2.811673 64039 \n", "1 646901.202888 0.006033 0.002220 ... 2.786308 77802 \n", "2 646901.202888 0.006033 0.002220 ... 2.786308 77802 \n", "\n", " incomechange degrees asalary anewsalary employees retails listid \\\n", "0 0.008973 0.034373 43000 42220.615385 12 5 239 \n", "1 -0.069537 -0.001562 30000 36709.000000 12 2 388 \n", "2 -0.069537 -0.001562 30000 36709.000000 12 2 389 \n", "\n", " list \n", "0 1196 \n", "1 1196 \n", "2 1196 \n", "\n", "[3 rows x 22 columns]" ] } ], "prompt_number": 14 }, { "cell_type": "code", "collapsed": false, "input": [ "# \u042d\u0422\u041e \u041d\u0410\u0414\u041e \u041b\u0418\u0428\u042c \u0412 CSV-\u0424\u041e\u0420\u041c\u0410\u0422\u0415\n", "# \u043f\u0435\u0440\u0435\u0432\u0435\u0441\u0442\u0438 \u043f\u0440\u043e\u0446\u0435\u043d\u0442\u044b \u0432 \u0447\u0438\u0441\u043b\u0430\n", "# def per2num(x):\n", "# x = x.replace(',','.')\n", "# i = x.find('%')\n", "# if (i>0):\n", "# x = x[:i]\n", "# x = str(float(x)/100)\n", "# return (x)\n", "\n", "# percentfeatures = ['degrees', 'popchange']\n", "# for f in percentfeatures:\n", "# data[f] = data[f].apply(per2num)\n", "# data[f] = data[f].astype(float)\n", "\n", "# data[:3]" ], "language": "python", "metadata": {}, "outputs": [], "prompt_number": 19 }, { "cell_type": "code", "collapsed": false, "input": [ "# \u0432\u044b\u0432\u043e\u0434 \u0437\u043d\u0430\u0447\u0435\u043d\u0438\u0439 \u043f\u043e \u043f\u0440\u0438\u0437\u043d\u0430\u043a\u0430\u043c\n", "for i in xrange(data.shape[1]):\n", " print data.columns[i], data[data.columns[i]].values[:3]\n", "#a = data[data.columns[0]][:3]\n", "#a.values" ], "language": "python", "metadata": {}, "outputs": [ { "output_type": "stream", "stream": "stdout", "text": [ "spacesize [11324 2275 2275]\n", "price [ 2.64924055 1.58333333 1.58333333]\n", "spacetype [4 4 4]\n", "leasetype [427 427 427]\n", "nspots [14 22 22]\n", "pop [ 6417.31825428 3902.84871166 3902.84871166]\n", "popchange [ 0.10449835 0.04171197 0.04171197]\n", "land [ 780786.64439507 646901.20288793 646901.20288793]\n", "densliv [ 0.00821904 0.00603314 0.00603314]\n", "denswork [ 0.00189552 0.00221981 0.00221981]\n", "denstotal [ 0.01011457 0.00825296 0.00825296]\n", "chat [7 7 7]\n", "hhsize [ 2.81167288 2.78630753 2.78630753]\n", "aincome [64039 77802 77802]\n", "incomechange [ 0.00897258 -0.06953688 -0.06953688]\n", "degrees [ 0.03437302 -0.0015618 -0.0015618 ]\n", "asalary [43000 30000 30000]\n", "anewsalary [ 42220.61538462 36709. 36709. ]\n", "employees [12 12 12]\n", "retails [5 2 2]\n", "listid [239 388 389]\n", "list [1196 1196 1196]\n" ] } ], "prompt_number": 20 }, { "cell_type": "code", "collapsed": false, "input": [ "# \u043f\u043e\u0434\u0433\u043e\u0442\u043e\u0432\u0438\u0442\u044c \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u0435 \u0438 \u043a\u043e\u043d\u0442\u0440\u043e\u043b\u044c\n", "itest = data.index % 3 == 0\n", "test = data[itest]\n", "ytest = test['price']\n", "test = test[test.columns - ['price']]\n", "train = data[~itest]\n", "ytrain = train['price']\n", "train = train[train.columns - ['price']]" ], "language": "python", "metadata": {}, "outputs": [], "prompt_number": 68 }, { "cell_type": "code", "collapsed": false, "input": [ "# \u043a\u043e\u043d\u0441\u0442\u0430\u043d\u0442\u043d\u044b\u0439 \u0431\u0435\u043d\u0447\u043c\u0430\u0440\u043a\n", "y = data['price'].values\n", "# \u043d\u0430\u0448\u0438 \u0444\u0443\u043d\u043a\u0446\u0438\u0438 \u043e\u0448\u0438\u0431\u043a\u0438\n", "def ma(a,y):\n", " return np.abs(a-y).mean()\n", "\n", "def rmse(a,y):\n", " return np.sqrt((((a-y)**2).mean()))\n", " \n", "print '\u0421\u0440\u0435\u0434\u043d\u0435\u0435 \u043e\u0442\u043a\u043b\u043e\u043d\u0435\u043d\u0438\u0435:' + str(ma(y.mean(),y))\n", "print '\u0421\u041a-\u043e\u0442\u043a\u043b\u043e\u043d\u0435\u043d\u0438\u0435:' + str(rmse(y.mean(),y))" ], "language": "python", "metadata": {}, "outputs": [ { "output_type": "stream", "stream": "stdout", "text": [ "\u0421\u0440\u0435\u0434\u043d\u0435\u0435 \u043e\u0442\u043a\u043b\u043e\u043d\u0435\u043d\u0438\u0435:4.03197129723\n", "\u0421\u041a-\u043e\u0442\u043a\u043b\u043e\u043d\u0435\u043d\u0438\u0435:6.58079959213\n" ] } ], "prompt_number": 70 }, { "cell_type": "code", "collapsed": false, "input": [ "# RF\n", "y = ytest.values\n", "\n", "import sklearn\n", "from sklearn import ensemble\n", "clf = sklearn.ensemble.RandomForestRegressor(n_estimators = 100, max_features = 10)\n", "\n", "asum = 0\n", "e1s = []\n", "e2s = []\n", "for i in range(10):\n", " clf.fit(train, ytrain)\n", " a = clf.predict(test)\n", " asum = asum + a\n", " aa = asum/(i+1)\n", " e1 = ma(aa,y)\n", " e2 = rmse(aa,y)\n", " e1s.append(e1)\n", " e2s.append(e2)\n", " print 'it=' + str(i) + ' ma=' + str(e1) + ' rmse=' + str(e2)\n", "plt1, = plot(e1s, label='ma')\n", "plt2, = plot(e2s, label='rmse')\n", "#print '\u0421\u0440\u0435\u0434\u043d\u0435\u0435 \u043e\u0442\u043a\u043b\u043e\u043d\u0435\u043d\u0438\u0435:' + str(np.abs((a-y)).mean())\n", "#print '\u0421\u041a-\u043e\u0442\u043a\u043b\u043e\u043d\u0435\u043d\u0438\u0435:' + str(np.sqrt((((a-y))**2).mean()))\n", "legend((plt1, plt2), ['ma', 'rmse'])" ], "language": "python", "metadata": {}, "outputs": [ { "output_type": "stream", "stream": "stdout", "text": [ "it=0 ma=2.13302605262 rmse=4.87093633505\n", "it=1 ma=2.12375079444 rmse=4.89879348639" ] }, { "output_type": "stream", "stream": "stdout", "text": [ "\n", "it=2 ma=2.1206627149 rmse=4.88795847537" ] }, { "output_type": "stream", "stream": "stdout", "text": [ "\n", "it=3 ma=2.12332802429 rmse=4.90191429436" ] }, { "output_type": "stream", "stream": "stdout", "text": [ "\n", "it=4 ma=2.12098464857 rmse=4.90193331669" ] }, { "output_type": "stream", "stream": "stdout", "text": [ "\n", "it=5 ma=2.11688809906 rmse=4.90190626714" ] }, { "output_type": "stream", "stream": "stdout", "text": [ "\n", "it=6 ma=2.11774837786 rmse=4.90049089551" ] }, { "output_type": "stream", "stream": "stdout", "text": [ "\n", "it=7 ma=2.116069004 rmse=4.88800749006" ] }, { "output_type": "stream", "stream": "stdout", "text": [ "\n", "it=8 ma=2.11885322327 rmse=4.8968311695" ] }, { "output_type": "stream", "stream": "stdout", "text": [ "\n", "it=9 ma=2.12141815394 rmse=4.90396149632" ] }, { "output_type": "stream", "stream": "stdout", "text": [ "\n" ] }, { "metadata": {}, "output_type": "pyout", "prompt_number": 73, "text": [ "" ] }, { "metadata": {}, "output_type": "display_data", "png": "iVBORw0KGgoAAAANSUhEUgAAAXIAAAEACAYAAACuzv3DAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAABJRU5ErkJggg==\n", "text": [ "" ] } ], "prompt_number": 73 }, { "cell_type": "code", "collapsed": false, "input": [ "print train.shape\n", "print test.shape" ], "language": "python", "metadata": {}, "outputs": [ { "output_type": "stream", "stream": "stdout", "text": [ "(1484, 21)\n", "(743, 21)\n" ] } ], "prompt_number": 69 }, { "cell_type": "code", "collapsed": false, "input": [ "# \u043f\u0435\u0440\u0435\u0431\u043e\u0440 \u0432\u0441\u0435\u0445 \u0444\u043e\u043b\u0434\u043e\u0432\n", "clf = sklearn.ensemble.RandomForestRegressor(n_estimators = 100, \\\n", " max_features = 5)\n", "\n", "y = data['price'].values\n", "a = y*0\n", "\n", "for jfold in range(3):\n", " # \u043f\u043e\u0434\u0433\u043e\u0442\u043e\u0432\u0438\u0442\u044c \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u0435 \u0438 \u043a\u043e\u043d\u0442\u0440\u043e\u043b\u044c\n", " itest = data.index % 3 == jfold\n", " test = data[itest]\n", " ytest = test['price']\n", " test = test[test.columns - ['price']]\n", " train = data[~itest]\n", " ytrain = train['price']\n", " train = train[train.columns - ['price']]\n", " clf.fit(train, ytrain)\n", " a[itest] = clf.predict(test)\n", " \n", "print '\u0421\u0440\u0435\u0434\u043d\u0435\u0435 \u043e\u0442\u043a\u043b\u043e\u043d\u0435\u043d\u0438\u0435:' + str(np.abs((a-y)).mean())\n", "print '\u0421\u041a-\u043e\u0442\u043a\u043b\u043e\u043d\u0435\u043d\u0438\u0435:' + str(np.sqrt((((a-y))**2).mean()))" ], "language": "python", "metadata": {}, "outputs": [ { "output_type": "stream", "stream": "stdout", "text": [ "\u0421\u0440\u0435\u0434\u043d\u0435\u0435 \u043e\u0442\u043a\u043b\u043e\u043d\u0435\u043d\u0438\u0435:2.25390001005\n", "\u0421\u041a-\u043e\u0442\u043a\u043b\u043e\u043d\u0435\u043d\u0438\u0435:5.05519437016\n" ] } ], "prompt_number": 82 }, { "cell_type": "code", "collapsed": false, "input": [], "language": "python", "metadata": {}, "outputs": [] } ], "metadata": {} } ] }