{ "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", " | id | \n", "Space Size | \n", "Price / SF / Month | \n", "Space Type: | \n", "Lease Type: | \n", "Number of transport spots | \n", "Population | \n", "Population change 2013-2010 | \n", "Land area | \n", "Density of people living in area | \n", "... | \n", "Household size | \n", "Average HH income 2013 | \n", "Income change 2013-2010 | \n", "Change in % of bachelor degrees 2013-2010 | \n", "Average salary of employees ($ 000s) | \n", "Average salary of employees in new businesses | \n", "% of employees in new companies vs all | \n", "Number of new retail places 2013-2010 | \n", "list id | \n", "list | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", "1 | \n", "11324 | \n", "2.649241 | \n", "NaN | \n", "NaN | \n", "14 | \n", "6417.318254 | \n", "0.104498 | \n", "780786.644395 | \n", "0.008219 | \n", "... | \n", "2.811673 | \n", "64039 | \n", "0.008973 | \n", "0.034373 | \n", "43000 | \n", "42220.615385 | \n", "12 | \n", "5 | \n", "239 | \n", "ln | \n", "
1 | \n", "2 | \n", "2275 | \n", "1.583333 | \n", "NaN | \n", "NaN | \n", "22 | \n", "3902.848712 | \n", "0.041712 | \n", "646901.202888 | \n", "0.006033 | \n", "... | \n", "2.786308 | \n", "77802 | \n", "-0.069537 | \n", "-0.001562 | \n", "30000 | \n", "36709.000000 | \n", "12 | \n", "2 | \n", "388 | \n", "ln | \n", "
2 | \n", "3 | \n", "2275 | \n", "1.583333 | \n", "NaN | \n", "NaN | \n", "22 | \n", "3902.848712 | \n", "0.041712 | \n", "646901.202888 | \n", "0.006033 | \n", "... | \n", "2.786308 | \n", "77802 | \n", "-0.069537 | \n", "-0.001562 | \n", "30000 | \n", "36709.000000 | \n", "12 | \n", "2 | \n", "389 | \n", "ln | \n", "
3 rows \u00d7 23 columns
\n", "\n", " | spacesize | \n", "price | \n", "spacetype | \n", "leasetype | \n", "nspots | \n", "pop | \n", "popchange | \n", "land | \n", "densliv | \n", "denswork | \n", "... | \n", "hhsize | \n", "aincome | \n", "incomechange | \n", "degrees | \n", "asalary | \n", "anewsalary | \n", "employees | \n", "retails | \n", "listid | \n", "list | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", "11324 | \n", "2.649241 | \n", "NaN | \n", "NaN | \n", "14 | \n", "6417.318254 | \n", "0.104498 | \n", "780786.644395 | \n", "0.008219 | \n", "0.001896 | \n", "... | \n", "2.811673 | \n", "64039 | \n", "0.008973 | \n", "0.034373 | \n", "43000 | \n", "42220.615385 | \n", "12 | \n", "5 | \n", "239 | \n", "ln | \n", "
1 | \n", "2275 | \n", "1.583333 | \n", "NaN | \n", "NaN | \n", "22 | \n", "3902.848712 | \n", "0.041712 | \n", "646901.202888 | \n", "0.006033 | \n", "0.002220 | \n", "... | \n", "2.786308 | \n", "77802 | \n", "-0.069537 | \n", "-0.001562 | \n", "30000 | \n", "36709.000000 | \n", "12 | \n", "2 | \n", "388 | \n", "ln | \n", "
2 | \n", "2275 | \n", "1.583333 | \n", "NaN | \n", "NaN | \n", "22 | \n", "3902.848712 | \n", "0.041712 | \n", "646901.202888 | \n", "0.006033 | \n", "0.002220 | \n", "... | \n", "2.786308 | \n", "77802 | \n", "-0.069537 | \n", "-0.001562 | \n", "30000 | \n", "36709.000000 | \n", "12 | \n", "2 | \n", "389 | \n", "ln | \n", "
3 rows \u00d7 22 columns
\n", "\n", " | spacesize | \n", "price | \n", "nspots | \n", "pop | \n", "popchange | \n", "land | \n", "densliv | \n", "denswork | \n", "denstotal | \n", "chat | \n", "hhsize | \n", "aincome | \n", "incomechange | \n", "degrees | \n", "asalary | \n", "anewsalary | \n", "employees | \n", "retails | \n", "listid | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
count | \n", "2227.000000 | \n", "2227.000000 | \n", "2227.000000 | \n", "2227.000000 | \n", "2227.000000 | \n", "2227.000000 | \n", "2227.000000 | \n", "2227.000000 | \n", "2227.000000 | \n", "2227.000000 | \n", "2227.000000 | \n", "2227.00000 | \n", "2227.000000 | \n", "2227.000000 | \n", "2227.000000 | \n", "2227.000000 | \n", "2227.000000 | \n", "2227.000000 | \n", "2227.000000 | \n", "
mean | \n", "3884.932645 | \n", "6.224143 | \n", "29.325101 | \n", "15833.326788 | \n", "0.010618 | \n", "744267.272294 | \n", "0.021292 | \n", "0.025608 | \n", "0.046900 | \n", "36.495285 | \n", "2.513140 | \n", "63835.55366 | \n", "0.097281 | \n", "0.011870 | \n", "46687.471935 | \n", "39536.089718 | \n", "24.637180 | \n", "34.376291 | \n", "612.130669 | \n", "
std | \n", "16311.985235 | \n", "6.582278 | \n", "14.658322 | \n", "8681.890404 | \n", "0.055430 | \n", "74177.247168 | \n", "0.011673 | \n", "0.051450 | \n", "0.053700 | \n", "68.069988 | \n", "0.532757 | \n", "31651.81757 | \n", "0.103458 | \n", "0.023377 | \n", "15010.874771 | \n", "12852.903269 | \n", "8.480855 | \n", "36.063391 | \n", "337.293657 | \n", "
min | \n", "1.000000 | \n", "0.000192 | \n", "0.000000 | \n", "114.945126 | \n", "-0.141048 | \n", "198188.986853 | \n", "0.000199 | \n", "0.000000 | \n", "0.000249 | \n", "0.000000 | \n", "1.510175 | \n", "17479.00000 | \n", "-0.253104 | \n", "-0.087200 | \n", "0.000000 | \n", "0.000000 | \n", "0.000000 | \n", "0.000000 | \n", "1.000000 | \n", "
25% | \n", "1000.000000 | \n", "2.666663 | \n", "19.000000 | \n", "9712.109647 | \n", "-0.028305 | \n", "741991.143918 | \n", "0.013105 | \n", "0.004082 | \n", "0.019105 | \n", "5.000000 | \n", "2.086396 | \n", "40051.00000 | \n", "0.031163 | \n", "-0.002626 | \n", "36000.000000 | \n", "30269.422362 | \n", "20.000000 | \n", "10.000000 | \n", "319.500000 | \n", "
50% | \n", "1700.000000 | \n", "4.166666 | \n", "29.000000 | \n", "15645.946460 | \n", "0.008172 | \n", "780549.167952 | \n", "0.020760 | \n", "0.006939 | \n", "0.028993 | \n", "13.000000 | \n", "2.534359 | \n", "53145.00000 | \n", "0.093626 | \n", "0.011536 | \n", "41000.000000 | \n", "36652.400004 | \n", "24.000000 | \n", "21.000000 | \n", "615.000000 | \n", "
75% | \n", "3400.000000 | \n", "7.343137 | \n", "38.000000 | \n", "21584.540555 | \n", "0.044095 | \n", "780832.018612 | \n", "0.028699 | \n", "0.020631 | \n", "0.051848 | \n", "42.000000 | \n", "2.894399 | \n", "88869.50000 | \n", "0.163718 | \n", "0.027190 | \n", "53000.000000 | \n", "46223.310708 | \n", "29.000000 | \n", "42.000000 | \n", "902.000000 | \n", "
max | \n", "600000.000000 | \n", "83.414634 | \n", "78.000000 | \n", "46664.838451 | \n", "0.313075 | \n", "780856.610853 | \n", "0.062810 | \n", "0.350893 | \n", "0.369600 | \n", "988.000000 | \n", "4.559108 | \n", "202295.00000 | \n", "0.429361 | \n", "0.102018 | \n", "106000.000000 | \n", "115360.037590 | \n", "84.000000 | \n", "184.000000 | \n", "1217.000000 | \n", "
\n", " | spacesize | \n", "price | \n", "spacetype | \n", "leasetype | \n", "nspots | \n", "pop | \n", "popchange | \n", "land | \n", "densliv | \n", "denswork | \n", "... | \n", "hhsize | \n", "aincome | \n", "incomechange | \n", "degrees | \n", "asalary | \n", "anewsalary | \n", "employees | \n", "retails | \n", "listid | \n", "list | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", "11324 | \n", "2.649241 | \n", "net | \n", "net | \n", "14 | \n", "6417.318254 | \n", "0.104498 | \n", "780786.644395 | \n", "0.008219 | \n", "0.001896 | \n", "... | \n", "2.811673 | \n", "64039 | \n", "0.008973 | \n", "0.034373 | \n", "43000 | \n", "42220.615385 | \n", "12 | \n", "5 | \n", "239 | \n", "ln | \n", "
1 | \n", "2275 | \n", "1.583333 | \n", "net | \n", "net | \n", "22 | \n", "3902.848712 | \n", "0.041712 | \n", "646901.202888 | \n", "0.006033 | \n", "0.002220 | \n", "... | \n", "2.786308 | \n", "77802 | \n", "-0.069537 | \n", "-0.001562 | \n", "30000 | \n", "36709.000000 | \n", "12 | \n", "2 | \n", "388 | \n", "ln | \n", "
2 | \n", "2275 | \n", "1.583333 | \n", "net | \n", "net | \n", "22 | \n", "3902.848712 | \n", "0.041712 | \n", "646901.202888 | \n", "0.006033 | \n", "0.002220 | \n", "... | \n", "2.786308 | \n", "77802 | \n", "-0.069537 | \n", "-0.001562 | \n", "30000 | \n", "36709.000000 | \n", "12 | \n", "2 | \n", "389 | \n", "ln | \n", "
3 rows \u00d7 22 columns
\n", "\n", " | spacesize | \n", "price | \n", "spacetype | \n", "leasetype | \n", "nspots | \n", "pop | \n", "popchange | \n", "land | \n", "densliv | \n", "denswork | \n", "... | \n", "hhsize | \n", "aincome | \n", "incomechange | \n", "degrees | \n", "asalary | \n", "anewsalary | \n", "employees | \n", "retails | \n", "listid | \n", "list | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", "11324 | \n", "2.649241 | \n", "4 | \n", "427 | \n", "14 | \n", "6417.318254 | \n", "0.104498 | \n", "780786.644395 | \n", "0.008219 | \n", "0.001896 | \n", "... | \n", "2.811673 | \n", "64039 | \n", "0.008973 | \n", "0.034373 | \n", "43000 | \n", "42220.615385 | \n", "12 | \n", "5 | \n", "239 | \n", "1196 | \n", "
1 | \n", "2275 | \n", "1.583333 | \n", "4 | \n", "427 | \n", "22 | \n", "3902.848712 | \n", "0.041712 | \n", "646901.202888 | \n", "0.006033 | \n", "0.002220 | \n", "... | \n", "2.786308 | \n", "77802 | \n", "-0.069537 | \n", "-0.001562 | \n", "30000 | \n", "36709.000000 | \n", "12 | \n", "2 | \n", "388 | \n", "1196 | \n", "
2 | \n", "2275 | \n", "1.583333 | \n", "4 | \n", "427 | \n", "22 | \n", "3902.848712 | \n", "0.041712 | \n", "646901.202888 | \n", "0.006033 | \n", "0.002220 | \n", "... | \n", "2.786308 | \n", "77802 | \n", "-0.069537 | \n", "-0.001562 | \n", "30000 | \n", "36709.000000 | \n", "12 | \n", "2 | \n", "389 | \n", "1196 | \n", "
3 rows \u00d7 22 columns
\n", "