{ "metadata": { "name": "", "signature": "sha256:30d4e31075d813d052bdbb660414bf5a36cada4ac44613ae9f18cae1b6ca798e" }, "nbformat": 3, "nbformat_minor": 0, "worksheets": [ { "cells": [ { "cell_type": "code", "collapsed": false, "input": [ "import pandas as pd\n", "\n", "pd.options.display.max_columns = 5200\n", "pd.options.display.max_rows = 5200\n", "\n", "# Insert your BigQuery Project ID Here\n", "# Can be found in the Google web console\n", "#projectid = \"dazzling-will-91618\"\n", "\n", "#df = pd.read_gbq('SELECT * FROM dazzling-will-91618:taxi_all.nycb2010_stats LIMIT 200', project_id = projectid)\n", "\n", "#http://stackoverflow.com/questions/18267749/importerror-no-module-named-apiclient-discovery\n", "#sudo pip install --upgrade google-api-python-client\n", "\n", "#data_frame = pd.read_gbq('SELECT * FROM test_dataset.test_table LIMIT 200',index_col='index_c_name',, project_id = projectid)" ], "language": "python", "metadata": {}, "outputs": [], "prompt_number": 2 }, { "cell_type": "code", "collapsed": false, "input": [ "import pandas as pd\n", "\n", "#dfmIN = '/Volumes/Hotel/Dropbox/data/output/all/taxi_2013.csv'\n", "dfsIN = '/Volumes/Hotel/Dropbox/data/output/all/nycb2010_taxi_2013_stats_bldg_cnt.csv'\n", "dfbIN = '/Volumes/Hotel/Dropbox/data/input/building/bldg_dist_height.csv'\n", "\n", "dfs = pd.read_csv(dfsIN, dtype={'geoid':object})\n", "dfb = pd.read_csv(dfbIN).rename(columns=lambda x: x.lower())\n", "dfb = dfb[['geoid','building_block_int_dis_tbl_bulkdens']]\n", "dfb = dfb.fillna(0) \n", "dfb['geoid'] = dfb['geoid'].astype(str)\n", "print dfb.dtypes\n", "\n", "dfs = dfs[(dfs.areasqft >= 50000)]\n", "dfs = dfs[(dfs.areasqft <= 300000)]\n", "\n", "dfs = dfs[(dfs.countbldg >= 1)]\n", "\n", "df = dfs.merge(dfb, on='geoid', how='left')\n", "\n", "df = df[(df.building_block_int_dis_tbl_bulkdens >= 3)]\n", "\n", "df" ], "language": "python", "metadata": {}, "outputs": [ { "output_type": "stream", "stream": "stdout", "text": [ "geoid object\n", "building_block_int_dis_tbl_bulkdens float64\n", "dtype: object\n" ] }, { "html": [ "
\n", " | geoid | \n", "avgbrdist | \n", "medbrdist | \n", "stdbrdist | \n", "count | \n", "areasqft | \n", "countbldg | \n", "building_block_int_dis_tbl_bulkdens | \n", "
---|---|---|---|---|---|---|---|---|
0 | \n", "360850112010001 | \n", "0.000000 | \n", "0.000000 | \n", "0.000000 | \n", "0 | \n", "6807.30 | \n", "NaN | \n", "0.000000 | \n", "
1 | \n", "360850226000001 | \n", "0.000000 | \n", "0.000000 | \n", "0.000000 | \n", "0 | \n", "45247.20 | \n", "NaN | \n", "0.000000 | \n", "
2 | \n", "360850007001000 | \n", "0.000000 | \n", "0.000000 | \n", "0.000000 | \n", "0 | \n", "58960.10 | \n", "1 | \n", "0.037041 | \n", "
3 | \n", "360850009001000 | \n", "2.615134 | \n", "0.000000 | \n", "6.133327 | \n", "30 | \n", "244590.00 | \n", "28 | \n", "1.660016 | \n", "
4 | \n", "360850011001000 | \n", "11.767236 | \n", "0.000000 | \n", "23.266198 | \n", "31 | \n", "314611.00 | \n", "84 | \n", "2.380148 | \n", "
5 | \n", "360850017001000 | \n", "11.665143 | \n", "0.000000 | \n", "30.009733 | \n", "10 | \n", "293775.00 | \n", "49 | \n", "1.366823 | \n", "
6 | \n", "360850020011000 | \n", "9.132777 | \n", "0.000000 | \n", "24.635996 | \n", "15 | \n", "111006.00 | \n", "19 | \n", "1.222633 | \n", "
7 | \n", "360850027001000 | \n", "13.078075 | \n", "0.000000 | \n", "23.066772 | \n", "8 | \n", "150407.00 | \n", "44 | \n", "3.716140 | \n", "
8 | \n", "360850029001000 | \n", "4.820950 | \n", "0.499503 | \n", "12.474478 | \n", "10 | \n", "373418.00 | \n", "90 | \n", "1.586655 | \n", "
9 | \n", "360850036001000 | \n", "9.455927 | \n", "0.000000 | \n", "14.165112 | \n", "11 | \n", "244605.00 | \n", "28 | \n", "1.142436 | \n", "
10 | \n", "360850039001000 | \n", "1.230096 | \n", "0.000000 | \n", "4.224633 | \n", "29 | \n", "469846.00 | \n", "61 | \n", "1.710747 | \n", "
11 | \n", "360850040001000 | \n", "15.627651 | \n", "0.000000 | \n", "34.944490 | \n", "5 | \n", "141297.00 | \n", "19 | \n", "1.042037 | \n", "
12 | \n", "360850047001000 | \n", "9.113771 | \n", "0.000000 | \n", "13.433418 | \n", "43 | \n", "1058270.00 | \n", "93 | \n", "0.566017 | \n", "
13 | \n", "360850059001000 | \n", "34.489629 | \n", "0.000000 | \n", "103.354739 | \n", "71 | \n", "4824710.00 | \n", "7 | \n", "0.012687 | \n", "
14 | \n", "360850064001000 | \n", "12.578383 | \n", "0.000000 | \n", "24.247516 | \n", "27 | \n", "200785.00 | \n", "20 | \n", "1.063275 | \n", "
15 | \n", "360850074001000 | \n", "8.874304 | \n", "0.000000 | \n", "15.494223 | \n", "7 | \n", "139084.00 | \n", "36 | \n", "1.875482 | \n", "
16 | \n", "360850075001000 | \n", "0.000000 | \n", "0.000000 | \n", "0.000000 | \n", "3 | \n", "123561.00 | \n", "32 | \n", "1.739414 | \n", "
17 | \n", "360850077001000 | \n", "2.584788 | \n", "0.000000 | \n", "4.974750 | \n", "5 | \n", "205771.00 | \n", "32 | \n", "2.054480 | \n", "
18 | \n", "360850096011000 | \n", "3.783601 | \n", "0.000000 | \n", "7.817140 | \n", "30 | \n", "640395.00 | \n", "96 | \n", "1.226833 | \n", "
19 | \n", "360850105001000 | \n", "0.414795 | \n", "0.000000 | \n", "1.436892 | \n", "12 | \n", "288531.00 | \n", "31 | \n", "1.422864 | \n", "
20 | \n", "360850112011000 | \n", "6.755672 | \n", "0.000000 | \n", "17.918980 | \n", "12 | \n", "196112.00 | \n", "21 | \n", "1.340195 | \n", "
21 | \n", "360850112021000 | \n", "0.000000 | \n", "0.000000 | \n", "0.000000 | \n", "3 | \n", "92737.80 | \n", "12 | \n", "1.092448 | \n", "
22 | \n", "360850114011000 | \n", "0.000000 | \n", "0.000000 | \n", "0.000000 | \n", "2 | \n", "66684.10 | \n", "12 | \n", "1.083342 | \n", "
23 | \n", "360850114021000 | \n", "54.202656 | \n", "54.202656 | \n", "10.059157 | \n", "2 | \n", "183061.00 | \n", "43 | \n", "1.538521 | \n", "
24 | \n", "360850121001000 | \n", "16.750273 | \n", "0.000000 | \n", "24.619993 | \n", "5 | \n", "170251.00 | \n", "43 | \n", "1.644445 | \n", "
25 | \n", "360850122001000 | \n", "6.492126 | \n", "1.490844 | \n", "11.085928 | \n", "4 | \n", "139819.00 | \n", "24 | \n", "1.239573 | \n", "
26 | \n", "360850125001000 | \n", "7.792671 | \n", "0.000000 | \n", "13.168025 | \n", "6 | \n", "215178.00 | \n", "51 | \n", "1.971548 | \n", "
27 | \n", "360850128041000 | \n", "32.096027 | \n", "0.026801 | \n", "55.767375 | \n", "47 | \n", "2184280.00 | \n", "88 | \n", "1.767975 | \n", "
28 | \n", "360850128051000 | \n", "0.587746 | \n", "0.000000 | \n", "1.097798 | \n", "12 | \n", "635446.00 | \n", "118 | \n", "1.299699 | \n", "
29 | \n", "360850128061000 | \n", "0.000000 | \n", "0.000000 | \n", "0.000000 | \n", "0 | \n", "281051.00 | \n", "48 | \n", "1.138468 | \n", "
... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "
38686 | \n", "360470644001003 | \n", "4.748647 | \n", "0.000000 | \n", "14.293095 | \n", "56 | \n", "126338.00 | \n", "28 | \n", "1.424973 | \n", "
38687 | \n", "360470642001000 | \n", "6.843542 | \n", "0.000000 | \n", "15.789983 | \n", "256 | \n", "401457.00 | \n", "92 | \n", "3.244198 | \n", "
38688 | \n", "360470644001004 | \n", "14.778127 | \n", "0.000000 | \n", "34.967502 | \n", "15 | \n", "16403.10 | \n", "NaN | \n", "0.000000 | \n", "
38689 | \n", "360470644002004 | \n", "6.599847 | \n", "0.000000 | \n", "18.427728 | \n", "83 | \n", "197433.00 | \n", "65 | \n", "2.601140 | \n", "
38690 | \n", "360471010001002 | \n", "3.207278 | \n", "0.000000 | \n", "7.562953 | \n", "55 | \n", "202878.00 | \n", "65 | \n", "2.243298 | \n", "
38691 | \n", "360471010001003 | \n", "11.044633 | \n", "0.000000 | \n", "20.867847 | \n", "57 | \n", "202716.00 | \n", "56 | \n", "3.036255 | \n", "
38692 | \n", "360471010002002 | \n", "4.459066 | \n", "0.000000 | \n", "13.049675 | \n", "48 | \n", "202659.00 | \n", "72 | \n", "1.803503 | \n", "
38693 | \n", "360471010002003 | \n", "2.933292 | \n", "0.000000 | \n", "7.813724 | \n", "26 | \n", "109458.00 | \n", "31 | \n", "1.710231 | \n", "
38694 | \n", "360810171001003 | \n", "6.939177 | \n", "0.000000 | \n", "19.450770 | \n", "2633 | \n", "119689.00 | \n", "1 | \n", "10.133345 | \n", "
38695 | \n", "360810171001004 | \n", "7.080989 | \n", "0.000000 | \n", "22.479680 | \n", "6735 | \n", "369285.00 | \n", "9 | \n", "9.983437 | \n", "
38696 | \n", "360810055001006 | \n", "5.237518 | \n", "0.000000 | \n", "16.423084 | \n", "574 | \n", "9436.48 | \n", "NaN | \n", "0.000000 | \n", "
38697 | \n", "360810055001007 | \n", "5.929513 | \n", "0.000000 | \n", "19.269368 | \n", "2529 | \n", "70482.60 | \n", "1 | \n", "2.416705 | \n", "
38698 | \n", "360810945002022 | \n", "20.544891 | \n", "0.000000 | \n", "43.236024 | \n", "581 | \n", "3553480.00 | \n", "84 | \n", "2.260479 | \n", "
38699 | \n", "360810945002023 | \n", "12.476821 | \n", "0.000000 | \n", "20.423062 | \n", "35 | \n", "118509.00 | \n", "20 | \n", "1.532482 | \n", "
38700 | \n", "360810945002024 | \n", "7.718515 | \n", "0.000000 | \n", "20.488599 | \n", "63 | \n", "192455.00 | \n", "63 | \n", "1.750790 | \n", "
38701 | \n", "360850226002020 | \n", "0.000000 | \n", "0.000000 | \n", "0.000000 | \n", "0 | \n", "591.06 | \n", "NaN | \n", "0.000000 | \n", "
38702 | \n", "360850226003000 | \n", "9.074053 | \n", "0.000000 | \n", "20.077495 | \n", "30 | \n", "2356680.00 | \n", "231 | \n", "0.823473 | \n", "
38703 | \n", "360850226003001 | \n", "1.090007 | \n", "0.000000 | \n", "2.437330 | \n", "5 | \n", "126572.00 | \n", "35 | \n", "2.327165 | \n", "
38704 | \n", "360850239002005 | \n", "2.557576 | \n", "0.000000 | \n", "5.115152 | \n", "4 | \n", "178216.00 | \n", "32 | \n", "1.420231 | \n", "
38705 | \n", "360850239002006 | \n", "1.332799 | \n", "0.000000 | \n", "2.590392 | \n", "6 | \n", "81905.40 | \n", "16 | \n", "1.400480 | \n", "
38706 | \n", "360850239002002 | \n", "1.466704 | \n", "0.000000 | \n", "2.518669 | \n", "7 | \n", "259159.00 | \n", "62 | \n", "1.695666 | \n", "
38707 | \n", "360850239002003 | \n", "0.000000 | \n", "0.000000 | \n", "0.000000 | \n", "3 | \n", "141550.00 | \n", "24 | \n", "1.222984 | \n", "
38708 | \n", "360850239002007 | \n", "18.457392 | \n", "0.000000 | \n", "28.704296 | \n", "7 | \n", "273797.00 | \n", "53 | \n", "1.362336 | \n", "
38709 | \n", "360050274020001 | \n", "0.000000 | \n", "0.000000 | \n", "0.000000 | \n", "0 | \n", "66837.40 | \n", "NaN | \n", "0.000000 | \n", "
38710 | \n", "360850248003001 | \n", "0.000000 | \n", "0.000000 | \n", "0.000000 | \n", "0 | \n", "633172.00 | \n", "2 | \n", "1.220499 | \n", "
38711 | \n", "360850248003002 | \n", "0.000000 | \n", "0.000000 | \n", "0.000000 | \n", "0 | \n", "857302.00 | \n", "7 | \n", "0.047088 | \n", "
38712 | \n", "360850226004017 | \n", "25.372098 | \n", "3.201143 | \n", "43.240281 | \n", "6 | \n", "484725.00 | \n", "54 | \n", "1.346176 | \n", "
38713 | \n", "360850226004027 | \n", "25.617130 | \n", "7.881637 | \n", "39.441979 | \n", "9 | \n", "1755900.00 | \n", "41 | \n", "0.531735 | \n", "
38714 | \n", "360610275001006 | \n", "7.036360 | \n", "0.000000 | \n", "19.466528 | \n", "133 | \n", "93888.00 | \n", "NaN | \n", "0.000000 | \n", "
38715 | \n", "360610265003002 | \n", "6.298910 | \n", "0.000000 | \n", "18.609811 | \n", "1696 | \n", "57478.40 | \n", "NaN | \n", "0.000000 | \n", "
38716 rows \u00d7 8 columns
\n", "