{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Measles Incidence in Altair" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "This is an example of reproducing the Wall Street Journal's famous [Measles Incidence Plot](http://graphics.wsj.com/infectious-diseases-and-vaccines/#b02g20t20w15) in Python using [Altair](http://github.com/ellisonbg/altair/)." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## The Data\n", "\n", "We'll start by downloading the data. Fortunately, others have made the data available in an easily digestible form; a github search revealed the dataset in CSV format here:" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", " | YEAR | \n", "WEEK | \n", "ALABAMA | \n", "ALASKA | \n", "ARIZONA | \n", "ARKANSAS | \n", "CALIFORNIA | \n", "COLORADO | \n", "CONNECTICUT | \n", "DELAWARE | \n", "... | \n", "SOUTH DAKOTA | \n", "TENNESSEE | \n", "TEXAS | \n", "UTAH | \n", "VERMONT | \n", "VIRGINIA | \n", "WASHINGTON | \n", "WEST VIRGINIA | \n", "WISCONSIN | \n", "WYOMING | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", "1928 | \n", "1 | \n", "3.67 | \n", "NaN | \n", "1.90 | \n", "4.11 | \n", "1.38 | \n", "8.38 | \n", "4.50 | \n", "8.58 | \n", "... | \n", "5.69 | \n", "22.03 | \n", "1.18 | \n", "0.4 | \n", "0.28 | \n", "NaN | \n", "14.83 | \n", "3.36 | \n", "1.54 | \n", "0.91 | \n", "
1 | \n", "1928 | \n", "2 | \n", "6.25 | \n", "NaN | \n", "6.40 | \n", "9.91 | \n", "1.80 | \n", "6.02 | \n", "9.00 | \n", "7.30 | \n", "... | \n", "6.57 | \n", "16.96 | \n", "0.63 | \n", "NaN | \n", "0.56 | \n", "NaN | \n", "17.34 | \n", "4.19 | \n", "0.96 | \n", "NaN | \n", "
2 | \n", "1928 | \n", "3 | \n", "7.95 | \n", "NaN | \n", "4.50 | \n", "11.15 | \n", "1.31 | \n", "2.86 | \n", "8.81 | \n", "15.88 | \n", "... | \n", "2.04 | \n", "24.66 | \n", "0.62 | \n", "0.2 | \n", "1.12 | \n", "NaN | \n", "15.67 | \n", "4.19 | \n", "4.79 | \n", "1.36 | \n", "
3 | \n", "1928 | \n", "4 | \n", "12.58 | \n", "NaN | \n", "1.90 | \n", "13.75 | \n", "1.87 | \n", "13.71 | \n", "10.40 | \n", "4.29 | \n", "... | \n", "2.19 | \n", "18.86 | \n", "0.37 | \n", "0.2 | \n", "6.70 | \n", "NaN | \n", "12.77 | \n", "4.66 | \n", "1.64 | \n", "3.64 | \n", "
4 | \n", "1928 | \n", "5 | \n", "8.03 | \n", "NaN | \n", "0.47 | \n", "20.79 | \n", "2.38 | \n", "5.13 | \n", "16.80 | \n", "5.58 | \n", "... | \n", "3.94 | \n", "20.05 | \n", "1.57 | \n", "0.4 | \n", "6.70 | \n", "NaN | \n", "18.83 | \n", "7.37 | \n", "2.91 | \n", "0.91 | \n", "
5 rows × 53 columns
\n", "\n", " | ALABAMA | \n", "ALASKA | \n", "ARIZONA | \n", "ARKANSAS | \n", "CALIFORNIA | \n", "COLORADO | \n", "CONNECTICUT | \n", "DELAWARE | \n", "DISTRICT OF COLUMBIA | \n", "FLORIDA | \n", "... | \n", "SOUTH DAKOTA | \n", "TENNESSEE | \n", "TEXAS | \n", "UTAH | \n", "VERMONT | \n", "VIRGINIA | \n", "WASHINGTON | \n", "WEST VIRGINIA | \n", "WISCONSIN | \n", "WYOMING | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
YEAR | \n", "\n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " |
1928 | \n", "334.99 | \n", "0.0 | \n", "200.75 | \n", "481.77 | \n", "69.22 | \n", "206.98 | \n", "634.95 | \n", "256.02 | \n", "535.63 | \n", "119.58 | \n", "... | \n", "160.16 | \n", "315.43 | \n", "97.35 | \n", "16.83 | \n", "334.80 | \n", "0.0 | \n", "344.82 | \n", "195.98 | \n", "124.61 | \n", "227.00 | \n", "
1929 | \n", "111.93 | \n", "0.0 | \n", "54.88 | \n", "67.22 | \n", "72.80 | \n", "74.24 | \n", "614.82 | \n", "239.82 | \n", "94.20 | \n", "78.01 | \n", "... | \n", "167.77 | \n", "33.04 | \n", "71.28 | \n", "68.90 | \n", "105.31 | \n", "0.0 | \n", "248.60 | \n", "380.14 | \n", "1016.54 | \n", "312.16 | \n", "
1930 | \n", "157.00 | \n", "0.0 | \n", "466.31 | \n", "53.44 | \n", "760.24 | \n", "1132.76 | \n", "112.23 | \n", "109.25 | \n", "182.10 | \n", "356.59 | \n", "... | \n", "346.31 | \n", "179.91 | \n", "73.12 | \n", "1044.79 | \n", "236.69 | \n", "0.0 | \n", "631.64 | \n", "157.70 | \n", "748.58 | \n", "341.55 | \n", "
1931 | \n", "337.29 | \n", "0.0 | \n", "497.69 | \n", "45.91 | \n", "477.48 | \n", "453.27 | \n", "790.46 | \n", "1003.28 | \n", "832.99 | \n", "260.79 | \n", "... | \n", "212.36 | \n", "134.79 | \n", "39.56 | \n", "29.72 | \n", "318.40 | \n", "0.0 | \n", "197.43 | \n", "291.38 | \n", "506.57 | \n", "60.69 | \n", "
1932 | \n", "10.21 | \n", "0.0 | \n", "20.11 | \n", "5.33 | \n", "214.08 | \n", "222.90 | \n", "348.27 | \n", "15.98 | \n", "53.14 | \n", "13.63 | \n", "... | \n", "96.37 | \n", "68.99 | \n", "76.58 | \n", "13.91 | \n", "1146.08 | \n", "53.4 | \n", "631.93 | \n", "599.65 | \n", "935.31 | \n", "242.10 | \n", "
5 rows × 51 columns
\n", "\n", " | YEAR | \n", "state | \n", "incidence | \n", "
---|---|---|---|
0 | \n", "1928 | \n", "ALABAMA | \n", "334.99 | \n", "
1 | \n", "1929 | \n", "ALABAMA | \n", "111.93 | \n", "
2 | \n", "1930 | \n", "ALABAMA | \n", "157.00 | \n", "
3 | \n", "1931 | \n", "ALABAMA | \n", "337.29 | \n", "
4 | \n", "1932 | \n", "ALABAMA | \n", "10.21 | \n", "