{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Exploring data on COVID-19\n", "\n", "> In this post, We will cover the basic syntax of julia language, and explore the data related on COVID-19. This is the summary of lecture \"Introduction to Computational Thinking with Julia, with applications to modeling the COVID-19 Pandemic\" from MIT.\n", "\n", "- toc: true \n", "- badges: true\n", "- comments: true\n", "- author: Chanseok Kang\n", "- categories: [Julia, MIT]\n", "- image: images/US_data.png" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Why Julia?\n", "\n", "- Julia: Developed at MIT by Prof. Alan Edelman's group\n", "- Released in 2012.\n", "- Current release: 1.4\n", "\n", "- Free, open source software\n", "- developed by world-wide community on [Github](https://github.com/JuliaLang/julia)\n", "- Over 3000 registered packages in wide range of domains\n", "\n", "## Julia\n", "\n", "- Modern, powerful language\n", "- Interactive but high performance (fast) - previously mutually exclusive\n", "- Syntax: similar to Python / Matlab / R\n", "- But carefully designed for high-performance computational science & engineering applications\n", "- Design means that most of Julia is written in Julia itself\n", "- Hence much easier to examine and modify algorithms" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "![us_data](image/US_data.png)" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "\"https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_covid19_confirmed_global.csv\"" ] }, "execution_count": 1, "metadata": {}, "output_type": "execute_result" } ], "source": [ "url = \"https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_covid19_confirmed_global.csv\"" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "\"https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_covid19_confirmed_global.csv\"" ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "url" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "String" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "typeof(url)" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "* (generic function with 357 methods)" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "*" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "1 + 7im" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "(1 + 2im) * (3 + im)" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "data": { "text/html": [ "*(z::Complex, w::Complex) in Base at complex.jl:277" ], "text/plain": [ "*(z::Complex, w::Complex) in Base at complex.jl:277" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "@which (1+ 2im) * (3 + im)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Grab the data" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "\"covid_data.csv\"" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "download(url, \"covid_data.csv\")" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "readdir (generic function with 2 methods)" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "readdir" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "234-element Array{String,1}:\n", " \".ipynb_checkpoints\"\n", " \"2020-05-21-Software-Engineering-Practices-Pt-1.ipynb\"\n", " \"2020-05-22-01-Decorator.ipynb\"\n", " \"2020-05-22-02-More-On-Decorators.ipynb\"\n", " \"2020-05-23-01-Read-clean-and-validate.ipynb\"\n", " \"2020-05-23-02-Distributions.ipynb\"\n", " \"2020-05-24-01-Relationships.ipynb\"\n", " \"2020-05-24-02-Multivariate-Thinking.ipynb\"\n", " \"2020-05-25-01-Preparing-the-data-for-analysis.ipynb\"\n", " \"2020-05-25-02-Exploring-the-relationship-between-gender-and-policing.ipynb\"\n", " \"2020-05-25-03-Visual-exploratory-data-analysis.ipynb\"\n", " \"2020-05-25-04-Software-Engineering-Practices-Pt-2.ipynb\"\n", " \"2020-05-26-01-Analyzing-the-effect-of-weather-on-policing.ipynb\"\n", " ⋮\n", " \"2020-12-28-01-Exploring-data-on-COVID-19.ipynb\"\n", " \"README.md\"\n", " \"checkpoints\"\n", " \"covid_data.csv\"\n", " \"dataset\"\n", " \"html\"\n", " \"image\"\n", " \"models\"\n", " \"my_icons\"\n", " \"spark-warehouse\"\n", " \"utils\"\n", " \"video\"" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "readdir()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Install Package" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "\u001b[32m\u001b[1m Updating\u001b[22m\u001b[39m registry at `C:\\Users\\kcsgo\\.julia\\registries\\General`\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\u001b[?25l" ] }, { "name": "stderr", "output_type": "stream", "text": [ "\u001b[32m\u001b[1m Updating\u001b[22m\u001b[39m git-repo `https://github.com/JuliaRegistries/General.git`\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\u001b[2K\u001b[?25h" ] }, { "name": "stderr", "output_type": "stream", "text": [ "\u001b[32m\u001b[1m Resolving\u001b[22m\u001b[39m package versions...\n", "\u001b[32m\u001b[1m Updating\u001b[22m\u001b[39m `C:\\Users\\kcsgo\\.julia\\environments\\v1.4\\Project.toml`\n", "\u001b[90m [no changes]\u001b[39m\n", "\u001b[32m\u001b[1m Updating\u001b[22m\u001b[39m `C:\\Users\\kcsgo\\.julia\\environments\\v1.4\\Manifest.toml`\n", "\u001b[90m [no changes]\u001b[39m\n" ] } ], "source": [ "using Pkg # built-in package manager in Julia: Pkg\n", "Pkg.add(\"CSV\") # calls the `add` function from the module Pkg. This installs a package" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "\u001b[32m\u001b[1m Resolving\u001b[22m\u001b[39m package versions...\n", "\u001b[32m\u001b[1m Updating\u001b[22m\u001b[39m `C:\\Users\\kcsgo\\.julia\\environments\\v1.4\\Project.toml`\n", "\u001b[90m [no changes]\u001b[39m\n", "\u001b[32m\u001b[1m Updating\u001b[22m\u001b[39m `C:\\Users\\kcsgo\\.julia\\environments\\v1.4\\Manifest.toml`\n", "\u001b[90m [no changes]\u001b[39m\n" ] } ], "source": [ "Pkg.add(\"DataFrames\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Load a package\n", "\n", "Load a package every time we run a Julia session:" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [], "source": [ "using CSV, DataFrames" ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [ { "data": { "text/html": [ "

271 rows × 347 columns (omitted printing of 342 columns)

Province/StateCountry/RegionLatLong1/22/20
String?StringFloat64?Float64?Int64
1missingAfghanistan33.939167.710
2missingAlbania41.153320.16830
3missingAlgeria28.03391.65960
4missingAndorra42.50631.52180
5missingAngola-11.202717.87390
6missingAntigua and Barbuda17.0608-61.79640
7missingArgentina-38.4161-63.61670
8missingArmenia40.069145.03820
9Australian Capital TerritoryAustralia-35.4735149.0120
10New South WalesAustralia-33.8688151.2090
11Northern TerritoryAustralia-12.4634130.8460
12QueenslandAustralia-27.4698153.0250
13South AustraliaAustralia-34.9285138.6010
14TasmaniaAustralia-42.8821147.3270
15VictoriaAustralia-37.8136144.9630
16Western AustraliaAustralia-31.9505115.8610
17missingAustria47.516214.55010
18missingAzerbaijan40.143147.57690
19missingBahamas25.0259-78.03590
20missingBahrain26.027550.550
21missingBangladesh23.68590.35630
22missingBarbados13.1939-59.54320
23missingBelarus53.709827.95340
24missingBelgium50.83334.469940
25missingBelize17.1899-88.49760
26missingBenin9.30772.31580
27missingBhutan27.514290.43360
28missingBolivia-16.2902-63.58870
29missingBosnia and Herzegovina43.915917.67910
30missingBotswana-22.328524.68490
⋮⋮⋮⋮⋮⋮
" ], "text/latex": [ "\\begin{tabular}{r|cccccc}\n", "\t& Province/State & Country/Region & Lat & Long & 1/22/20 & \\\\\n", "\t\\hline\n", "\t& String? & String & Float64? & Float64? & Int64 & \\\\\n", "\t\\hline\n", "\t1 & \\emph{missing} & Afghanistan & 33.9391 & 67.71 & 0 & $\\dots$ \\\\\n", "\t2 & \\emph{missing} & Albania & 41.1533 & 20.1683 & 0 & $\\dots$ \\\\\n", "\t3 & \\emph{missing} & Algeria & 28.0339 & 1.6596 & 0 & $\\dots$ \\\\\n", "\t4 & \\emph{missing} & Andorra & 42.5063 & 1.5218 & 0 & $\\dots$ \\\\\n", "\t5 & \\emph{missing} & Angola & -11.2027 & 17.8739 & 0 & $\\dots$ \\\\\n", "\t6 & \\emph{missing} & Antigua and Barbuda & 17.0608 & -61.7964 & 0 & $\\dots$ \\\\\n", "\t7 & \\emph{missing} & Argentina & -38.4161 & -63.6167 & 0 & $\\dots$ \\\\\n", "\t8 & \\emph{missing} & Armenia & 40.0691 & 45.0382 & 0 & $\\dots$ \\\\\n", "\t9 & Australian Capital Territory & Australia & -35.4735 & 149.012 & 0 & $\\dots$ \\\\\n", "\t10 & New South Wales & Australia & -33.8688 & 151.209 & 0 & $\\dots$ \\\\\n", "\t11 & Northern Territory & Australia & -12.4634 & 130.846 & 0 & $\\dots$ \\\\\n", "\t12 & Queensland & Australia & -27.4698 & 153.025 & 0 & $\\dots$ \\\\\n", "\t13 & South Australia & Australia & -34.9285 & 138.601 & 0 & $\\dots$ \\\\\n", "\t14 & Tasmania & Australia & -42.8821 & 147.327 & 0 & $\\dots$ \\\\\n", "\t15 & Victoria & Australia & -37.8136 & 144.963 & 0 & $\\dots$ \\\\\n", "\t16 & Western Australia & Australia & -31.9505 & 115.861 & 0 & $\\dots$ \\\\\n", "\t17 & \\emph{missing} & Austria & 47.5162 & 14.5501 & 0 & $\\dots$ \\\\\n", "\t18 & \\emph{missing} & Azerbaijan & 40.1431 & 47.5769 & 0 & $\\dots$ \\\\\n", "\t19 & \\emph{missing} & Bahamas & 25.0259 & -78.0359 & 0 & $\\dots$ \\\\\n", "\t20 & \\emph{missing} & Bahrain & 26.0275 & 50.55 & 0 & $\\dots$ \\\\\n", "\t21 & \\emph{missing} & Bangladesh & 23.685 & 90.3563 & 0 & $\\dots$ \\\\\n", "\t22 & \\emph{missing} & Barbados & 13.1939 & -59.5432 & 0 & $\\dots$ \\\\\n", "\t23 & \\emph{missing} & Belarus & 53.7098 & 27.9534 & 0 & $\\dots$ \\\\\n", "\t24 & \\emph{missing} & Belgium & 50.8333 & 4.46994 & 0 & $\\dots$ \\\\\n", "\t25 & \\emph{missing} & Belize & 17.1899 & -88.4976 & 0 & $\\dots$ \\\\\n", "\t26 & \\emph{missing} & Benin & 9.3077 & 2.3158 & 0 & $\\dots$ \\\\\n", "\t27 & \\emph{missing} & Bhutan & 27.5142 & 90.4336 & 0 & $\\dots$ \\\\\n", "\t28 & \\emph{missing} & Bolivia & -16.2902 & -63.5887 & 0 & $\\dots$ \\\\\n", "\t29 & \\emph{missing} & Bosnia and Herzegovina & 43.9159 & 17.6791 & 0 & $\\dots$ \\\\\n", "\t30 & \\emph{missing} & Botswana & -22.3285 & 24.6849 & 0 & $\\dots$ \\\\\n", "\t$\\dots$ & $\\dots$ & $\\dots$ & $\\dots$ & $\\dots$ & $\\dots$ & \\\\\n", "\\end{tabular}\n" ], "text/plain": [ "\u001b[1m271×347 DataFrame\u001b[0m\n", "\u001b[1m Row \u001b[0m│\u001b[1m Province/State \u001b[0m\u001b[1m Country/Region \u001b[0m\u001b[1m Lat \u001b[0m\u001b[1m Long \u001b[0m\u001b[1m \u001b[0m ⋯\n", "\u001b[1m \u001b[0m│\u001b[90m String? \u001b[0m\u001b[90m String \u001b[0m\u001b[90m Float64? \u001b[0m\u001b[90m Float64? \u001b[0m\u001b[90m \u001b[0m ⋯\n", "─────┼──────────────────────────────────────────────────────────────────────────\n", " 1 │\u001b[90m missing \u001b[0m Afghanistan 33.9391 67.71 ⋯\n", " 2 │\u001b[90m missing \u001b[0m Albania 41.1533 20.1683\n", " 3 │\u001b[90m missing \u001b[0m Algeria 28.0339 1.6596\n", " 4 │\u001b[90m missing \u001b[0m Andorra 42.5063 1.5218\n", " 5 │\u001b[90m missing \u001b[0m Angola -11.2027 17.8739 ⋯\n", " 6 │\u001b[90m missing \u001b[0m Antigua and Barbuda 17.0608 -61.7964\n", " 7 │\u001b[90m missing \u001b[0m Argentina -38.4161 -63.6167\n", " 8 │\u001b[90m missing \u001b[0m Armenia 40.0691 45.0382\n", " 9 │ Australian Capital Territory Australia -35.4735 149.012 ⋯\n", " 10 │ New South Wales Australia -33.8688 151.209\n", " 11 │ Northern Territory Australia -12.4634 130.846\n", " ⋮ │ ⋮ ⋮ ⋮ ⋮ ⋱\n", " 262 │\u001b[90m missing \u001b[0m United Kingdom 55.3781 -3.436\n", " 263 │\u001b[90m missing \u001b[0m Uruguay -32.5228 -55.7658 ⋯\n", " 264 │\u001b[90m missing \u001b[0m Uzbekistan 41.3775 64.5853\n", " 265 │\u001b[90m missing \u001b[0m Vanuatu -15.3767 166.959\n", " 266 │\u001b[90m missing \u001b[0m Venezuela 6.4238 -66.5897\n", " 267 │\u001b[90m missing \u001b[0m Vietnam 14.0583 108.277 ⋯\n", " 268 │\u001b[90m missing \u001b[0m West Bank and Gaza 31.9522 35.2332\n", " 269 │\u001b[90m missing \u001b[0m Yemen 15.5527 48.5164\n", " 270 │\u001b[90m missing \u001b[0m Zambia -13.1339 27.8493\n", " 271 │\u001b[90m missing \u001b[0m Zimbabwe -19.0154 29.1549 ⋯\n", "\u001b[31m 343 columns and 250 rows omitted\u001b[0m" ] }, "execution_count": 13, "metadata": {}, "output_type": "execute_result" } ], "source": [ "CSV.read(\"./covid_data.csv\", DataFrame)" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [ { "data": { "text/html": [ "

271 rows × 347 columns (omitted printing of 342 columns)

Province/StateCountry/RegionLatLong1/22/20
String?StringFloat64?Float64?Int64
1missingAfghanistan33.939167.710
2missingAlbania41.153320.16830
3missingAlgeria28.03391.65960
4missingAndorra42.50631.52180
5missingAngola-11.202717.87390
6missingAntigua and Barbuda17.0608-61.79640
7missingArgentina-38.4161-63.61670
8missingArmenia40.069145.03820
9Australian Capital TerritoryAustralia-35.4735149.0120
10New South WalesAustralia-33.8688151.2090
11Northern TerritoryAustralia-12.4634130.8460
12QueenslandAustralia-27.4698153.0250
13South AustraliaAustralia-34.9285138.6010
14TasmaniaAustralia-42.8821147.3270
15VictoriaAustralia-37.8136144.9630
16Western AustraliaAustralia-31.9505115.8610
17missingAustria47.516214.55010
18missingAzerbaijan40.143147.57690
19missingBahamas25.0259-78.03590
20missingBahrain26.027550.550
21missingBangladesh23.68590.35630
22missingBarbados13.1939-59.54320
23missingBelarus53.709827.95340
24missingBelgium50.83334.469940
25missingBelize17.1899-88.49760
26missingBenin9.30772.31580
27missingBhutan27.514290.43360
28missingBolivia-16.2902-63.58870
29missingBosnia and Herzegovina43.915917.67910
30missingBotswana-22.328524.68490
⋮⋮⋮⋮⋮⋮
" ], "text/latex": [ "\\begin{tabular}{r|cccccc}\n", "\t& Province/State & Country/Region & Lat & Long & 1/22/20 & \\\\\n", "\t\\hline\n", "\t& String? & String & Float64? & Float64? & Int64 & \\\\\n", "\t\\hline\n", "\t1 & \\emph{missing} & Afghanistan & 33.9391 & 67.71 & 0 & $\\dots$ \\\\\n", "\t2 & \\emph{missing} & Albania & 41.1533 & 20.1683 & 0 & $\\dots$ \\\\\n", "\t3 & \\emph{missing} & Algeria & 28.0339 & 1.6596 & 0 & $\\dots$ \\\\\n", "\t4 & \\emph{missing} & Andorra & 42.5063 & 1.5218 & 0 & $\\dots$ \\\\\n", "\t5 & \\emph{missing} & Angola & -11.2027 & 17.8739 & 0 & $\\dots$ \\\\\n", "\t6 & \\emph{missing} & Antigua and Barbuda & 17.0608 & -61.7964 & 0 & $\\dots$ \\\\\n", "\t7 & \\emph{missing} & Argentina & -38.4161 & -63.6167 & 0 & $\\dots$ \\\\\n", "\t8 & \\emph{missing} & Armenia & 40.0691 & 45.0382 & 0 & $\\dots$ \\\\\n", "\t9 & Australian Capital Territory & Australia & -35.4735 & 149.012 & 0 & $\\dots$ \\\\\n", "\t10 & New South Wales & Australia & -33.8688 & 151.209 & 0 & $\\dots$ \\\\\n", "\t11 & Northern Territory & Australia & -12.4634 & 130.846 & 0 & $\\dots$ \\\\\n", "\t12 & Queensland & Australia & -27.4698 & 153.025 & 0 & $\\dots$ \\\\\n", "\t13 & South Australia & Australia & -34.9285 & 138.601 & 0 & $\\dots$ \\\\\n", "\t14 & Tasmania & Australia & -42.8821 & 147.327 & 0 & $\\dots$ \\\\\n", "\t15 & Victoria & Australia & -37.8136 & 144.963 & 0 & $\\dots$ \\\\\n", "\t16 & Western Australia & Australia & -31.9505 & 115.861 & 0 & $\\dots$ \\\\\n", "\t17 & \\emph{missing} & Austria & 47.5162 & 14.5501 & 0 & $\\dots$ \\\\\n", "\t18 & \\emph{missing} & Azerbaijan & 40.1431 & 47.5769 & 0 & $\\dots$ \\\\\n", "\t19 & \\emph{missing} & Bahamas & 25.0259 & -78.0359 & 0 & $\\dots$ \\\\\n", "\t20 & \\emph{missing} & Bahrain & 26.0275 & 50.55 & 0 & $\\dots$ \\\\\n", "\t21 & \\emph{missing} & Bangladesh & 23.685 & 90.3563 & 0 & $\\dots$ \\\\\n", "\t22 & \\emph{missing} & Barbados & 13.1939 & -59.5432 & 0 & $\\dots$ \\\\\n", "\t23 & \\emph{missing} & Belarus & 53.7098 & 27.9534 & 0 & $\\dots$ \\\\\n", "\t24 & \\emph{missing} & Belgium & 50.8333 & 4.46994 & 0 & $\\dots$ \\\\\n", "\t25 & \\emph{missing} & Belize & 17.1899 & -88.4976 & 0 & $\\dots$ \\\\\n", "\t26 & \\emph{missing} & Benin & 9.3077 & 2.3158 & 0 & $\\dots$ \\\\\n", "\t27 & \\emph{missing} & Bhutan & 27.5142 & 90.4336 & 0 & $\\dots$ \\\\\n", "\t28 & \\emph{missing} & Bolivia & -16.2902 & -63.5887 & 0 & $\\dots$ \\\\\n", "\t29 & \\emph{missing} & Bosnia and Herzegovina & 43.9159 & 17.6791 & 0 & $\\dots$ \\\\\n", "\t30 & \\emph{missing} & Botswana & -22.3285 & 24.6849 & 0 & $\\dots$ \\\\\n", "\t$\\dots$ & $\\dots$ & $\\dots$ & $\\dots$ & $\\dots$ & $\\dots$ & \\\\\n", "\\end{tabular}\n" ], "text/plain": [ "\u001b[1m271×347 DataFrame\u001b[0m\n", "\u001b[1m Row \u001b[0m│\u001b[1m Province/State \u001b[0m\u001b[1m Country/Region \u001b[0m\u001b[1m Lat \u001b[0m\u001b[1m Long \u001b[0m\u001b[1m \u001b[0m ⋯\n", "\u001b[1m \u001b[0m│\u001b[90m String? \u001b[0m\u001b[90m String \u001b[0m\u001b[90m Float64? \u001b[0m\u001b[90m Float64? \u001b[0m\u001b[90m \u001b[0m ⋯\n", "─────┼──────────────────────────────────────────────────────────────────────────\n", " 1 │\u001b[90m missing \u001b[0m Afghanistan 33.9391 67.71 ⋯\n", " 2 │\u001b[90m missing \u001b[0m Albania 41.1533 20.1683\n", " 3 │\u001b[90m missing \u001b[0m Algeria 28.0339 1.6596\n", " 4 │\u001b[90m missing \u001b[0m Andorra 42.5063 1.5218\n", " 5 │\u001b[90m missing \u001b[0m Angola -11.2027 17.8739 ⋯\n", " 6 │\u001b[90m missing \u001b[0m Antigua and Barbuda 17.0608 -61.7964\n", " 7 │\u001b[90m missing \u001b[0m Argentina -38.4161 -63.6167\n", " 8 │\u001b[90m missing \u001b[0m Armenia 40.0691 45.0382\n", " 9 │ Australian Capital Territory Australia -35.4735 149.012 ⋯\n", " 10 │ New South Wales Australia -33.8688 151.209\n", " 11 │ Northern Territory Australia -12.4634 130.846\n", " ⋮ │ ⋮ ⋮ ⋮ ⋮ ⋱\n", " 262 │\u001b[90m missing \u001b[0m United Kingdom 55.3781 -3.436\n", " 263 │\u001b[90m missing \u001b[0m Uruguay -32.5228 -55.7658 ⋯\n", " 264 │\u001b[90m missing \u001b[0m Uzbekistan 41.3775 64.5853\n", " 265 │\u001b[90m missing \u001b[0m Vanuatu -15.3767 166.959\n", " 266 │\u001b[90m missing \u001b[0m Venezuela 6.4238 -66.5897\n", " 267 │\u001b[90m missing \u001b[0m Vietnam 14.0583 108.277 ⋯\n", " 268 │\u001b[90m missing \u001b[0m West Bank and Gaza 31.9522 35.2332\n", " 269 │\u001b[90m missing \u001b[0m Yemen 15.5527 48.5164\n", " 270 │\u001b[90m missing \u001b[0m Zambia -13.1339 27.8493\n", " 271 │\u001b[90m missing \u001b[0m Zimbabwe -19.0154 29.1549 ⋯\n", "\u001b[31m 343 columns and 250 rows omitted\u001b[0m" ] }, "execution_count": 14, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data = CSV.read(\"covid_data.csv\", DataFrame)\n", "data" ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "DataFrame" ] }, "execution_count": 15, "metadata": {}, "output_type": "execute_result" } ], "source": [ "typeof(data)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We can rename each column name." ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [ { "data": { "text/html": [ "

271 rows × 347 columns (omitted printing of 342 columns)

provincecountryLatLong1/22/20
String?StringFloat64?Float64?Int64
1missingAfghanistan33.939167.710
2missingAlbania41.153320.16830
3missingAlgeria28.03391.65960
4missingAndorra42.50631.52180
5missingAngola-11.202717.87390
6missingAntigua and Barbuda17.0608-61.79640
7missingArgentina-38.4161-63.61670
8missingArmenia40.069145.03820
9Australian Capital TerritoryAustralia-35.4735149.0120
10New South WalesAustralia-33.8688151.2090
11Northern TerritoryAustralia-12.4634130.8460
12QueenslandAustralia-27.4698153.0250
13South AustraliaAustralia-34.9285138.6010
14TasmaniaAustralia-42.8821147.3270
15VictoriaAustralia-37.8136144.9630
16Western AustraliaAustralia-31.9505115.8610
17missingAustria47.516214.55010
18missingAzerbaijan40.143147.57690
19missingBahamas25.0259-78.03590
20missingBahrain26.027550.550
21missingBangladesh23.68590.35630
22missingBarbados13.1939-59.54320
23missingBelarus53.709827.95340
24missingBelgium50.83334.469940
25missingBelize17.1899-88.49760
26missingBenin9.30772.31580
27missingBhutan27.514290.43360
28missingBolivia-16.2902-63.58870
29missingBosnia and Herzegovina43.915917.67910
30missingBotswana-22.328524.68490
⋮⋮⋮⋮⋮⋮
" ], "text/latex": [ "\\begin{tabular}{r|cccccc}\n", "\t& province & country & Lat & Long & 1/22/20 & \\\\\n", "\t\\hline\n", "\t& String? & String & Float64? & Float64? & Int64 & \\\\\n", "\t\\hline\n", "\t1 & \\emph{missing} & Afghanistan & 33.9391 & 67.71 & 0 & $\\dots$ \\\\\n", "\t2 & \\emph{missing} & Albania & 41.1533 & 20.1683 & 0 & $\\dots$ \\\\\n", "\t3 & \\emph{missing} & Algeria & 28.0339 & 1.6596 & 0 & $\\dots$ \\\\\n", "\t4 & \\emph{missing} & Andorra & 42.5063 & 1.5218 & 0 & $\\dots$ \\\\\n", "\t5 & \\emph{missing} & Angola & -11.2027 & 17.8739 & 0 & $\\dots$ \\\\\n", "\t6 & \\emph{missing} & Antigua and Barbuda & 17.0608 & -61.7964 & 0 & $\\dots$ \\\\\n", "\t7 & \\emph{missing} & Argentina & -38.4161 & -63.6167 & 0 & $\\dots$ \\\\\n", "\t8 & \\emph{missing} & Armenia & 40.0691 & 45.0382 & 0 & $\\dots$ \\\\\n", "\t9 & Australian Capital Territory & Australia & -35.4735 & 149.012 & 0 & $\\dots$ \\\\\n", "\t10 & New South Wales & Australia & -33.8688 & 151.209 & 0 & $\\dots$ \\\\\n", "\t11 & Northern Territory & Australia & -12.4634 & 130.846 & 0 & $\\dots$ \\\\\n", "\t12 & Queensland & Australia & -27.4698 & 153.025 & 0 & $\\dots$ \\\\\n", "\t13 & South Australia & Australia & -34.9285 & 138.601 & 0 & $\\dots$ \\\\\n", "\t14 & Tasmania & Australia & -42.8821 & 147.327 & 0 & $\\dots$ \\\\\n", "\t15 & Victoria & Australia & -37.8136 & 144.963 & 0 & $\\dots$ \\\\\n", "\t16 & Western Australia & Australia & -31.9505 & 115.861 & 0 & $\\dots$ \\\\\n", "\t17 & \\emph{missing} & Austria & 47.5162 & 14.5501 & 0 & $\\dots$ \\\\\n", "\t18 & \\emph{missing} & Azerbaijan & 40.1431 & 47.5769 & 0 & $\\dots$ \\\\\n", "\t19 & \\emph{missing} & Bahamas & 25.0259 & -78.0359 & 0 & $\\dots$ \\\\\n", "\t20 & \\emph{missing} & Bahrain & 26.0275 & 50.55 & 0 & $\\dots$ \\\\\n", "\t21 & \\emph{missing} & Bangladesh & 23.685 & 90.3563 & 0 & $\\dots$ \\\\\n", "\t22 & \\emph{missing} & Barbados & 13.1939 & -59.5432 & 0 & $\\dots$ \\\\\n", "\t23 & \\emph{missing} & Belarus & 53.7098 & 27.9534 & 0 & $\\dots$ \\\\\n", "\t24 & \\emph{missing} & Belgium & 50.8333 & 4.46994 & 0 & $\\dots$ \\\\\n", "\t25 & \\emph{missing} & Belize & 17.1899 & -88.4976 & 0 & $\\dots$ \\\\\n", "\t26 & \\emph{missing} & Benin & 9.3077 & 2.3158 & 0 & $\\dots$ \\\\\n", "\t27 & \\emph{missing} & Bhutan & 27.5142 & 90.4336 & 0 & $\\dots$ \\\\\n", "\t28 & \\emph{missing} & Bolivia & -16.2902 & -63.5887 & 0 & $\\dots$ \\\\\n", "\t29 & \\emph{missing} & Bosnia and Herzegovina & 43.9159 & 17.6791 & 0 & $\\dots$ \\\\\n", "\t30 & \\emph{missing} & Botswana & -22.3285 & 24.6849 & 0 & $\\dots$ \\\\\n", "\t$\\dots$ & $\\dots$ & $\\dots$ & $\\dots$ & $\\dots$ & $\\dots$ & \\\\\n", "\\end{tabular}\n" ], "text/plain": [ "\u001b[1m271×347 DataFrame\u001b[0m\n", "\u001b[1m Row \u001b[0m│\u001b[1m province \u001b[0m\u001b[1m country \u001b[0m\u001b[1m Lat \u001b[0m\u001b[1m Long \u001b[0m\u001b[1m \u001b[0m ⋯\n", "\u001b[1m \u001b[0m│\u001b[90m String? \u001b[0m\u001b[90m String \u001b[0m\u001b[90m Float64? \u001b[0m\u001b[90m Float64? \u001b[0m\u001b[90m \u001b[0m ⋯\n", "─────┼──────────────────────────────────────────────────────────────────────────\n", " 1 │\u001b[90m missing \u001b[0m Afghanistan 33.9391 67.71 ⋯\n", " 2 │\u001b[90m missing \u001b[0m Albania 41.1533 20.1683\n", " 3 │\u001b[90m missing \u001b[0m Algeria 28.0339 1.6596\n", " 4 │\u001b[90m missing \u001b[0m Andorra 42.5063 1.5218\n", " 5 │\u001b[90m missing \u001b[0m Angola -11.2027 17.8739 ⋯\n", " 6 │\u001b[90m missing \u001b[0m Antigua and Barbuda 17.0608 -61.7964\n", " 7 │\u001b[90m missing \u001b[0m Argentina -38.4161 -63.6167\n", " 8 │\u001b[90m missing \u001b[0m Armenia 40.0691 45.0382\n", " 9 │ Australian Capital Territory Australia -35.4735 149.012 ⋯\n", " 10 │ New South Wales Australia -33.8688 151.209\n", " 11 │ Northern Territory Australia -12.4634 130.846\n", " ⋮ │ ⋮ ⋮ ⋮ ⋮ ⋱\n", " 262 │\u001b[90m missing \u001b[0m United Kingdom 55.3781 -3.436\n", " 263 │\u001b[90m missing \u001b[0m Uruguay -32.5228 -55.7658 ⋯\n", " 264 │\u001b[90m missing \u001b[0m Uzbekistan 41.3775 64.5853\n", " 265 │\u001b[90m missing \u001b[0m Vanuatu -15.3767 166.959\n", " 266 │\u001b[90m missing \u001b[0m Venezuela 6.4238 -66.5897\n", " 267 │\u001b[90m missing \u001b[0m Vietnam 14.0583 108.277 ⋯\n", " 268 │\u001b[90m missing \u001b[0m West Bank and Gaza 31.9522 35.2332\n", " 269 │\u001b[90m missing \u001b[0m Yemen 15.5527 48.5164\n", " 270 │\u001b[90m missing \u001b[0m Zambia -13.1339 27.8493\n", " 271 │\u001b[90m missing \u001b[0m Zimbabwe -19.0154 29.1549 ⋯\n", "\u001b[31m 343 columns and 250 rows omitted\u001b[0m" ] }, "execution_count": 16, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data_2 = rename(data, 1 => \"province\", 2 => \"country\")\n", "data_2" ] }, { "cell_type": "code", "execution_count": 17, "metadata": {}, "outputs": [ { "data": { "text/html": [ "

271 rows × 347 columns (omitted printing of 342 columns)

provincecountryLatLong1/22/20
String?StringFloat64?Float64?Int64
1missingAfghanistan33.939167.710
2missingAlbania41.153320.16830
3missingAlgeria28.03391.65960
4missingAndorra42.50631.52180
5missingAngola-11.202717.87390
6missingAntigua and Barbuda17.0608-61.79640
7missingArgentina-38.4161-63.61670
8missingArmenia40.069145.03820
9Australian Capital TerritoryAustralia-35.4735149.0120
10New South WalesAustralia-33.8688151.2090
11Northern TerritoryAustralia-12.4634130.8460
12QueenslandAustralia-27.4698153.0250
13South AustraliaAustralia-34.9285138.6010
14TasmaniaAustralia-42.8821147.3270
15VictoriaAustralia-37.8136144.9630
16Western AustraliaAustralia-31.9505115.8610
17missingAustria47.516214.55010
18missingAzerbaijan40.143147.57690
19missingBahamas25.0259-78.03590
20missingBahrain26.027550.550
21missingBangladesh23.68590.35630
22missingBarbados13.1939-59.54320
23missingBelarus53.709827.95340
24missingBelgium50.83334.469940
25missingBelize17.1899-88.49760
26missingBenin9.30772.31580
27missingBhutan27.514290.43360
28missingBolivia-16.2902-63.58870
29missingBosnia and Herzegovina43.915917.67910
30missingBotswana-22.328524.68490
⋮⋮⋮⋮⋮⋮
" ], "text/latex": [ "\\begin{tabular}{r|cccccc}\n", "\t& province & country & Lat & Long & 1/22/20 & \\\\\n", "\t\\hline\n", "\t& String? & String & Float64? & Float64? & Int64 & \\\\\n", "\t\\hline\n", "\t1 & \\emph{missing} & Afghanistan & 33.9391 & 67.71 & 0 & $\\dots$ \\\\\n", "\t2 & \\emph{missing} & Albania & 41.1533 & 20.1683 & 0 & $\\dots$ \\\\\n", "\t3 & \\emph{missing} & Algeria & 28.0339 & 1.6596 & 0 & $\\dots$ \\\\\n", "\t4 & \\emph{missing} & Andorra & 42.5063 & 1.5218 & 0 & $\\dots$ \\\\\n", "\t5 & \\emph{missing} & Angola & -11.2027 & 17.8739 & 0 & $\\dots$ \\\\\n", "\t6 & \\emph{missing} & Antigua and Barbuda & 17.0608 & -61.7964 & 0 & $\\dots$ \\\\\n", "\t7 & \\emph{missing} & Argentina & -38.4161 & -63.6167 & 0 & $\\dots$ \\\\\n", "\t8 & \\emph{missing} & Armenia & 40.0691 & 45.0382 & 0 & $\\dots$ \\\\\n", "\t9 & Australian Capital Territory & Australia & -35.4735 & 149.012 & 0 & $\\dots$ \\\\\n", "\t10 & New South Wales & Australia & -33.8688 & 151.209 & 0 & $\\dots$ \\\\\n", "\t11 & Northern Territory & Australia & -12.4634 & 130.846 & 0 & $\\dots$ \\\\\n", "\t12 & Queensland & Australia & -27.4698 & 153.025 & 0 & $\\dots$ \\\\\n", "\t13 & South Australia & Australia & -34.9285 & 138.601 & 0 & $\\dots$ \\\\\n", "\t14 & Tasmania & Australia & -42.8821 & 147.327 & 0 & $\\dots$ \\\\\n", "\t15 & Victoria & Australia & -37.8136 & 144.963 & 0 & $\\dots$ \\\\\n", "\t16 & Western Australia & Australia & -31.9505 & 115.861 & 0 & $\\dots$ \\\\\n", "\t17 & \\emph{missing} & Austria & 47.5162 & 14.5501 & 0 & $\\dots$ \\\\\n", "\t18 & \\emph{missing} & Azerbaijan & 40.1431 & 47.5769 & 0 & $\\dots$ \\\\\n", "\t19 & \\emph{missing} & Bahamas & 25.0259 & -78.0359 & 0 & $\\dots$ \\\\\n", "\t20 & \\emph{missing} & Bahrain & 26.0275 & 50.55 & 0 & $\\dots$ \\\\\n", "\t21 & \\emph{missing} & Bangladesh & 23.685 & 90.3563 & 0 & $\\dots$ \\\\\n", "\t22 & \\emph{missing} & Barbados & 13.1939 & -59.5432 & 0 & $\\dots$ \\\\\n", "\t23 & \\emph{missing} & Belarus & 53.7098 & 27.9534 & 0 & $\\dots$ \\\\\n", "\t24 & \\emph{missing} & Belgium & 50.8333 & 4.46994 & 0 & $\\dots$ \\\\\n", "\t25 & \\emph{missing} & Belize & 17.1899 & -88.4976 & 0 & $\\dots$ \\\\\n", "\t26 & \\emph{missing} & Benin & 9.3077 & 2.3158 & 0 & $\\dots$ \\\\\n", "\t27 & \\emph{missing} & Bhutan & 27.5142 & 90.4336 & 0 & $\\dots$ \\\\\n", "\t28 & \\emph{missing} & Bolivia & -16.2902 & -63.5887 & 0 & $\\dots$ \\\\\n", "\t29 & \\emph{missing} & Bosnia and Herzegovina & 43.9159 & 17.6791 & 0 & $\\dots$ \\\\\n", "\t30 & \\emph{missing} & Botswana & -22.3285 & 24.6849 & 0 & $\\dots$ \\\\\n", "\t$\\dots$ & $\\dots$ & $\\dots$ & $\\dots$ & $\\dots$ & $\\dots$ & \\\\\n", "\\end{tabular}\n" ], "text/plain": [ "\u001b[1m271×347 DataFrame\u001b[0m\n", "\u001b[1m Row \u001b[0m│\u001b[1m province \u001b[0m\u001b[1m country \u001b[0m\u001b[1m Lat \u001b[0m\u001b[1m Long \u001b[0m\u001b[1m \u001b[0m ⋯\n", "\u001b[1m \u001b[0m│\u001b[90m String? \u001b[0m\u001b[90m String \u001b[0m\u001b[90m Float64? \u001b[0m\u001b[90m Float64? \u001b[0m\u001b[90m \u001b[0m ⋯\n", "─────┼──────────────────────────────────────────────────────────────────────────\n", " 1 │\u001b[90m missing \u001b[0m Afghanistan 33.9391 67.71 ⋯\n", " 2 │\u001b[90m missing \u001b[0m Albania 41.1533 20.1683\n", " 3 │\u001b[90m missing \u001b[0m Algeria 28.0339 1.6596\n", " 4 │\u001b[90m missing \u001b[0m Andorra 42.5063 1.5218\n", " 5 │\u001b[90m missing \u001b[0m Angola -11.2027 17.8739 ⋯\n", " 6 │\u001b[90m missing \u001b[0m Antigua and Barbuda 17.0608 -61.7964\n", " 7 │\u001b[90m missing \u001b[0m Argentina -38.4161 -63.6167\n", " 8 │\u001b[90m missing \u001b[0m Armenia 40.0691 45.0382\n", " 9 │ Australian Capital Territory Australia -35.4735 149.012 ⋯\n", " 10 │ New South Wales Australia -33.8688 151.209\n", " 11 │ Northern Territory Australia -12.4634 130.846\n", " ⋮ │ ⋮ ⋮ ⋮ ⋮ ⋱\n", " 262 │\u001b[90m missing \u001b[0m United Kingdom 55.3781 -3.436\n", " 263 │\u001b[90m missing \u001b[0m Uruguay -32.5228 -55.7658 ⋯\n", " 264 │\u001b[90m missing \u001b[0m Uzbekistan 41.3775 64.5853\n", " 265 │\u001b[90m missing \u001b[0m Vanuatu -15.3767 166.959\n", " 266 │\u001b[90m missing \u001b[0m Venezuela 6.4238 -66.5897\n", " 267 │\u001b[90m missing \u001b[0m Vietnam 14.0583 108.277 ⋯\n", " 268 │\u001b[90m missing \u001b[0m West Bank and Gaza 31.9522 35.2332\n", " 269 │\u001b[90m missing \u001b[0m Yemen 15.5527 48.5164\n", " 270 │\u001b[90m missing \u001b[0m Zambia -13.1339 27.8493\n", " 271 │\u001b[90m missing \u001b[0m Zimbabwe -19.0154 29.1549 ⋯\n", "\u001b[31m 343 columns and 250 rows omitted\u001b[0m" ] }, "execution_count": 17, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# ! is convention: function *modifies* its argument in place\n", "rename!(data, 1 => \"province\", 2 => \"country\") " ] }, { "cell_type": "code", "execution_count": 18, "metadata": {}, "outputs": [ { "data": { "text/html": [ "

271 rows × 347 columns (omitted printing of 342 columns)

provincecountryLatLong1/22/20
String?StringFloat64?Float64?Int64
1missingAfghanistan33.939167.710
2missingAlbania41.153320.16830
3missingAlgeria28.03391.65960
4missingAndorra42.50631.52180
5missingAngola-11.202717.87390
6missingAntigua and Barbuda17.0608-61.79640
7missingArgentina-38.4161-63.61670
8missingArmenia40.069145.03820
9Australian Capital TerritoryAustralia-35.4735149.0120
10New South WalesAustralia-33.8688151.2090
11Northern TerritoryAustralia-12.4634130.8460
12QueenslandAustralia-27.4698153.0250
13South AustraliaAustralia-34.9285138.6010
14TasmaniaAustralia-42.8821147.3270
15VictoriaAustralia-37.8136144.9630
16Western AustraliaAustralia-31.9505115.8610
17missingAustria47.516214.55010
18missingAzerbaijan40.143147.57690
19missingBahamas25.0259-78.03590
20missingBahrain26.027550.550
21missingBangladesh23.68590.35630
22missingBarbados13.1939-59.54320
23missingBelarus53.709827.95340
24missingBelgium50.83334.469940
25missingBelize17.1899-88.49760
26missingBenin9.30772.31580
27missingBhutan27.514290.43360
28missingBolivia-16.2902-63.58870
29missingBosnia and Herzegovina43.915917.67910
30missingBotswana-22.328524.68490
⋮⋮⋮⋮⋮⋮
" ], "text/latex": [ "\\begin{tabular}{r|cccccc}\n", "\t& province & country & Lat & Long & 1/22/20 & \\\\\n", "\t\\hline\n", "\t& String? & String & Float64? & Float64? & Int64 & \\\\\n", "\t\\hline\n", "\t1 & \\emph{missing} & Afghanistan & 33.9391 & 67.71 & 0 & $\\dots$ \\\\\n", "\t2 & \\emph{missing} & Albania & 41.1533 & 20.1683 & 0 & $\\dots$ \\\\\n", "\t3 & \\emph{missing} & Algeria & 28.0339 & 1.6596 & 0 & $\\dots$ \\\\\n", "\t4 & \\emph{missing} & Andorra & 42.5063 & 1.5218 & 0 & $\\dots$ \\\\\n", "\t5 & \\emph{missing} & Angola & -11.2027 & 17.8739 & 0 & $\\dots$ \\\\\n", "\t6 & \\emph{missing} & Antigua and Barbuda & 17.0608 & -61.7964 & 0 & $\\dots$ \\\\\n", "\t7 & \\emph{missing} & Argentina & -38.4161 & -63.6167 & 0 & $\\dots$ \\\\\n", "\t8 & \\emph{missing} & Armenia & 40.0691 & 45.0382 & 0 & $\\dots$ \\\\\n", "\t9 & Australian Capital Territory & Australia & -35.4735 & 149.012 & 0 & $\\dots$ \\\\\n", "\t10 & New South Wales & Australia & -33.8688 & 151.209 & 0 & $\\dots$ \\\\\n", "\t11 & Northern Territory & Australia & -12.4634 & 130.846 & 0 & $\\dots$ \\\\\n", "\t12 & Queensland & Australia & -27.4698 & 153.025 & 0 & $\\dots$ \\\\\n", "\t13 & South Australia & Australia & -34.9285 & 138.601 & 0 & $\\dots$ \\\\\n", "\t14 & Tasmania & Australia & -42.8821 & 147.327 & 0 & $\\dots$ \\\\\n", "\t15 & Victoria & Australia & -37.8136 & 144.963 & 0 & $\\dots$ \\\\\n", "\t16 & Western Australia & Australia & -31.9505 & 115.861 & 0 & $\\dots$ \\\\\n", "\t17 & \\emph{missing} & Austria & 47.5162 & 14.5501 & 0 & $\\dots$ \\\\\n", "\t18 & \\emph{missing} & Azerbaijan & 40.1431 & 47.5769 & 0 & $\\dots$ \\\\\n", "\t19 & \\emph{missing} & Bahamas & 25.0259 & -78.0359 & 0 & $\\dots$ \\\\\n", "\t20 & \\emph{missing} & Bahrain & 26.0275 & 50.55 & 0 & $\\dots$ \\\\\n", "\t21 & \\emph{missing} & Bangladesh & 23.685 & 90.3563 & 0 & $\\dots$ \\\\\n", "\t22 & \\emph{missing} & Barbados & 13.1939 & -59.5432 & 0 & $\\dots$ \\\\\n", "\t23 & \\emph{missing} & Belarus & 53.7098 & 27.9534 & 0 & $\\dots$ \\\\\n", "\t24 & \\emph{missing} & Belgium & 50.8333 & 4.46994 & 0 & $\\dots$ \\\\\n", "\t25 & \\emph{missing} & Belize & 17.1899 & -88.4976 & 0 & $\\dots$ \\\\\n", "\t26 & \\emph{missing} & Benin & 9.3077 & 2.3158 & 0 & $\\dots$ \\\\\n", "\t27 & \\emph{missing} & Bhutan & 27.5142 & 90.4336 & 0 & $\\dots$ \\\\\n", "\t28 & \\emph{missing} & Bolivia & -16.2902 & -63.5887 & 0 & $\\dots$ \\\\\n", "\t29 & \\emph{missing} & Bosnia and Herzegovina & 43.9159 & 17.6791 & 0 & $\\dots$ \\\\\n", "\t30 & \\emph{missing} & Botswana & -22.3285 & 24.6849 & 0 & $\\dots$ \\\\\n", "\t$\\dots$ & $\\dots$ & $\\dots$ & $\\dots$ & $\\dots$ & $\\dots$ & \\\\\n", "\\end{tabular}\n" ], "text/plain": [ "\u001b[1m271×347 DataFrame\u001b[0m\n", "\u001b[1m Row \u001b[0m│\u001b[1m province \u001b[0m\u001b[1m country \u001b[0m\u001b[1m Lat \u001b[0m\u001b[1m Long \u001b[0m\u001b[1m \u001b[0m ⋯\n", "\u001b[1m \u001b[0m│\u001b[90m String? \u001b[0m\u001b[90m String \u001b[0m\u001b[90m Float64? \u001b[0m\u001b[90m Float64? \u001b[0m\u001b[90m \u001b[0m ⋯\n", "─────┼──────────────────────────────────────────────────────────────────────────\n", " 1 │\u001b[90m missing \u001b[0m Afghanistan 33.9391 67.71 ⋯\n", " 2 │\u001b[90m missing \u001b[0m Albania 41.1533 20.1683\n", " 3 │\u001b[90m missing \u001b[0m Algeria 28.0339 1.6596\n", " 4 │\u001b[90m missing \u001b[0m Andorra 42.5063 1.5218\n", " 5 │\u001b[90m missing \u001b[0m Angola -11.2027 17.8739 ⋯\n", " 6 │\u001b[90m missing \u001b[0m Antigua and Barbuda 17.0608 -61.7964\n", " 7 │\u001b[90m missing \u001b[0m Argentina -38.4161 -63.6167\n", " 8 │\u001b[90m missing \u001b[0m Armenia 40.0691 45.0382\n", " 9 │ Australian Capital Territory Australia -35.4735 149.012 ⋯\n", " 10 │ New South Wales Australia -33.8688 151.209\n", " 11 │ Northern Territory Australia -12.4634 130.846\n", " ⋮ │ ⋮ ⋮ ⋮ ⋮ ⋱\n", " 262 │\u001b[90m missing \u001b[0m United Kingdom 55.3781 -3.436\n", " 263 │\u001b[90m missing \u001b[0m Uruguay -32.5228 -55.7658 ⋯\n", " 264 │\u001b[90m missing \u001b[0m Uzbekistan 41.3775 64.5853\n", " 265 │\u001b[90m missing \u001b[0m Vanuatu -15.3767 166.959\n", " 266 │\u001b[90m missing \u001b[0m Venezuela 6.4238 -66.5897\n", " 267 │\u001b[90m missing \u001b[0m Vietnam 14.0583 108.277 ⋯\n", " 268 │\u001b[90m missing \u001b[0m West Bank and Gaza 31.9522 35.2332\n", " 269 │\u001b[90m missing \u001b[0m Yemen 15.5527 48.5164\n", " 270 │\u001b[90m missing \u001b[0m Zambia -13.1339 27.8493\n", " 271 │\u001b[90m missing \u001b[0m Zimbabwe -19.0154 29.1549 ⋯\n", "\u001b[31m 343 columns and 250 rows omitted\u001b[0m" ] }, "execution_count": 18, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data" ] }, { "cell_type": "code", "execution_count": 19, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "search: \u001b[0m\u001b[1mr\u001b[22m\u001b[0m\u001b[1me\u001b[22m\u001b[0m\u001b[1mn\u001b[22m\u001b[0m\u001b[1ma\u001b[22m\u001b[0m\u001b[1mm\u001b[22m\u001b[0m\u001b[1me\u001b[22m \u001b[0m\u001b[1mr\u001b[22m\u001b[0m\u001b[1me\u001b[22m\u001b[0m\u001b[1mn\u001b[22m\u001b[0m\u001b[1ma\u001b[22m\u001b[0m\u001b[1mm\u001b[22m\u001b[0m\u001b[1me\u001b[22m! p\u001b[0m\u001b[1mr\u001b[22mop\u001b[0m\u001b[1me\u001b[22mrty\u001b[0m\u001b[1mn\u001b[22m\u001b[0m\u001b[1ma\u001b[22m\u001b[0m\u001b[1mm\u001b[22m\u001b[0m\u001b[1me\u001b[22ms\n", "\n" ] }, { "data": { "text/latex": [ "\\begin{verbatim}\n", "rename(df::AbstractDataFrame, vals::AbstractVector{Symbol};\n", " makeunique::Bool=false)\n", "rename(df::AbstractDataFrame, vals::AbstractVector{<:AbstractString};\n", " makeunique::Bool=false)\n", "rename(df::AbstractDataFrame, (from => to)::Pair...)\n", "rename(df::AbstractDataFrame, d::AbstractDict)\n", "rename(df::AbstractDataFrame, d::AbstractVector{<:Pair})\n", "rename(f::Function, df::AbstractDataFrame)\n", "\\end{verbatim}\n", "Create a new data frame that is a copy of \\texttt{df} with changed column names. Each name is changed at most once. Permutation of names is allowed.\n", "\n", "\\section{Arguments}\n", "\\begin{itemize}\n", "\\item \\texttt{df} : the \\texttt{AbstractDataFrame}; if it is a \\texttt{SubDataFrame} then renaming is only allowed if it was created using \\texttt{:} as a column selector.\n", "\n", "\n", "\\item \\texttt{d} : an \\texttt{AbstractDict} or an \\texttt{AbstractVector} of \\texttt{Pair}s that maps the original names or column numbers to new names\n", "\n", "\n", "\\item \\texttt{f} : a function which for each column takes the old name as a \\texttt{String} and returns the new name that gets converted to a \\texttt{Symbol}\n", "\n", "\n", "\\item \\texttt{vals} : new column names as a vector of \\texttt{Symbol}s or \\texttt{AbstractString}s of the same length as the number of columns in \\texttt{df}\n", "\n", "\n", "\\item \\texttt{makeunique} : if \\texttt{false} (the default), an error will be raised if duplicate names are found; if \\texttt{true}, duplicate names will be suffixed with \\texttt{\\_i} (\\texttt{i} starting at 1 for the first duplicate).\n", "\n", "\\end{itemize}\n", "If pairs are passed to \\texttt{rename} (as positional arguments or in a dictionary or a vector) then:\n", "\n", "\\begin{itemize}\n", "\\item \\texttt{from} value can be a \\texttt{Symbol}, an \\texttt{AbstractString} or an \\texttt{Integer};\n", "\n", "\n", "\\item \\texttt{to} value can be a \\texttt{Symbol} or an \\texttt{AbstractString}.\n", "\n", "\\end{itemize}\n", "Mixing symbols and strings in \\texttt{to} and \\texttt{from} is not allowed.\n", "\n", "See also: \\href{@ref}{\\texttt{rename!}}\n", "\n", "\\section{Examples}\n", "\\begin{verbatim}\n", "julia> df = DataFrame(i = 1, x = 2, y = 3)\n", "1×3 DataFrame\n", " Row │ i x y\n", " │ Int64 Int64 Int64\n", "─────┼─────────────────────\n", " 1 │ 1 2 3\n", "\n", "julia> rename(df, :i => :A, :x => :X)\n", "1×3 DataFrame\n", " Row │ A X y\n", " │ Int64 Int64 Int64\n", "─────┼─────────────────────\n", " 1 │ 1 2 3\n", "\n", "julia> rename(df, :x => :y, :y => :x)\n", "1×3 DataFrame\n", " Row │ i y x\n", " │ Int64 Int64 Int64\n", "─────┼─────────────────────\n", " 1 │ 1 2 3\n", "\n", "julia> rename(df, [1 => :A, 2 => :X])\n", "1×3 DataFrame\n", " Row │ A X y\n", " │ Int64 Int64 Int64\n", "─────┼─────────────────────\n", " 1 │ 1 2 3\n", "\n", "julia> rename(df, Dict(\"i\" => \"A\", \"x\" => \"X\"))\n", "1×3 DataFrame\n", " Row │ A X y\n", " │ Int64 Int64 Int64\n", "─────┼─────────────────────\n", " 1 │ 1 2 3\n", "\n", "julia> rename(uppercase, df)\n", "1×3 DataFrame\n", " Row │ I X Y\n", " │ Int64 Int64 Int64\n", "─────┼─────────────────────\n", " 1 │ 1 2 3\n", "\\end{verbatim}\n" ], "text/markdown": [ "```\n", "rename(df::AbstractDataFrame, vals::AbstractVector{Symbol};\n", " makeunique::Bool=false)\n", "rename(df::AbstractDataFrame, vals::AbstractVector{<:AbstractString};\n", " makeunique::Bool=false)\n", "rename(df::AbstractDataFrame, (from => to)::Pair...)\n", "rename(df::AbstractDataFrame, d::AbstractDict)\n", "rename(df::AbstractDataFrame, d::AbstractVector{<:Pair})\n", "rename(f::Function, df::AbstractDataFrame)\n", "```\n", "\n", "Create a new data frame that is a copy of `df` with changed column names. Each name is changed at most once. Permutation of names is allowed.\n", "\n", "# Arguments\n", "\n", " * `df` : the `AbstractDataFrame`; if it is a `SubDataFrame` then renaming is only allowed if it was created using `:` as a column selector.\n", " * `d` : an `AbstractDict` or an `AbstractVector` of `Pair`s that maps the original names or column numbers to new names\n", " * `f` : a function which for each column takes the old name as a `String` and returns the new name that gets converted to a `Symbol`\n", " * `vals` : new column names as a vector of `Symbol`s or `AbstractString`s of the same length as the number of columns in `df`\n", " * `makeunique` : if `false` (the default), an error will be raised if duplicate names are found; if `true`, duplicate names will be suffixed with `_i` (`i` starting at 1 for the first duplicate).\n", "\n", "If pairs are passed to `rename` (as positional arguments or in a dictionary or a vector) then:\n", "\n", " * `from` value can be a `Symbol`, an `AbstractString` or an `Integer`;\n", " * `to` value can be a `Symbol` or an `AbstractString`.\n", "\n", "Mixing symbols and strings in `to` and `from` is not allowed.\n", "\n", "See also: [`rename!`](@ref)\n", "\n", "# Examples\n", "\n", "```julia\n", "julia> df = DataFrame(i = 1, x = 2, y = 3)\n", "1×3 DataFrame\n", " Row │ i x y\n", " │ Int64 Int64 Int64\n", "─────┼─────────────────────\n", " 1 │ 1 2 3\n", "\n", "julia> rename(df, :i => :A, :x => :X)\n", "1×3 DataFrame\n", " Row │ A X y\n", " │ Int64 Int64 Int64\n", "─────┼─────────────────────\n", " 1 │ 1 2 3\n", "\n", "julia> rename(df, :x => :y, :y => :x)\n", "1×3 DataFrame\n", " Row │ i y x\n", " │ Int64 Int64 Int64\n", "─────┼─────────────────────\n", " 1 │ 1 2 3\n", "\n", "julia> rename(df, [1 => :A, 2 => :X])\n", "1×3 DataFrame\n", " Row │ A X y\n", " │ Int64 Int64 Int64\n", "─────┼─────────────────────\n", " 1 │ 1 2 3\n", "\n", "julia> rename(df, Dict(\"i\" => \"A\", \"x\" => \"X\"))\n", "1×3 DataFrame\n", " Row │ A X y\n", " │ Int64 Int64 Int64\n", "─────┼─────────────────────\n", " 1 │ 1 2 3\n", "\n", "julia> rename(uppercase, df)\n", "1×3 DataFrame\n", " Row │ I X Y\n", " │ Int64 Int64 Int64\n", "─────┼─────────────────────\n", " 1 │ 1 2 3\n", "```\n" ], "text/plain": [ "\u001b[36m rename(df::AbstractDataFrame, vals::AbstractVector{Symbol};\u001b[39m\n", "\u001b[36m makeunique::Bool=false)\u001b[39m\n", "\u001b[36m rename(df::AbstractDataFrame, vals::AbstractVector{<:AbstractString};\u001b[39m\n", "\u001b[36m makeunique::Bool=false)\u001b[39m\n", "\u001b[36m rename(df::AbstractDataFrame, (from => to)::Pair...)\u001b[39m\n", "\u001b[36m rename(df::AbstractDataFrame, d::AbstractDict)\u001b[39m\n", "\u001b[36m rename(df::AbstractDataFrame, d::AbstractVector{<:Pair})\u001b[39m\n", "\u001b[36m rename(f::Function, df::AbstractDataFrame)\u001b[39m\n", "\n", " Create a new data frame that is a copy of \u001b[36mdf\u001b[39m with changed column names. Each\n", " name is changed at most once. Permutation of names is allowed.\n", "\n", "\u001b[1m Arguments\u001b[22m\n", "\u001b[1m ≡≡≡≡≡≡≡≡≡≡≡\u001b[22m\n", "\n", " • \u001b[36mdf\u001b[39m : the \u001b[36mAbstractDataFrame\u001b[39m; if it is a \u001b[36mSubDataFrame\u001b[39m then renaming\n", " is only allowed if it was created using \u001b[36m:\u001b[39m as a column selector.\n", "\n", " • \u001b[36md\u001b[39m : an \u001b[36mAbstractDict\u001b[39m or an \u001b[36mAbstractVector\u001b[39m of \u001b[36mPair\u001b[39ms that maps the\n", " original names or column numbers to new names\n", "\n", " • \u001b[36mf\u001b[39m : a function which for each column takes the old name as a\n", " \u001b[36mString\u001b[39m and returns the new name that gets converted to a \u001b[36mSymbol\u001b[39m\n", "\n", " • \u001b[36mvals\u001b[39m : new column names as a vector of \u001b[36mSymbol\u001b[39ms or \u001b[36mAbstractString\u001b[39ms\n", " of the same length as the number of columns in \u001b[36mdf\u001b[39m\n", "\n", " • \u001b[36mmakeunique\u001b[39m : if \u001b[36mfalse\u001b[39m (the default), an error will be raised if\n", " duplicate names are found; if \u001b[36mtrue\u001b[39m, duplicate names will be\n", " suffixed with \u001b[36m_i\u001b[39m (\u001b[36mi\u001b[39m starting at 1 for the first duplicate).\n", "\n", " If pairs are passed to \u001b[36mrename\u001b[39m (as positional arguments or in a dictionary or\n", " a vector) then:\n", "\n", " • \u001b[36mfrom\u001b[39m value can be a \u001b[36mSymbol\u001b[39m, an \u001b[36mAbstractString\u001b[39m or an \u001b[36mInteger\u001b[39m;\n", "\n", " • \u001b[36mto\u001b[39m value can be a \u001b[36mSymbol\u001b[39m or an \u001b[36mAbstractString\u001b[39m.\n", "\n", " Mixing symbols and strings in \u001b[36mto\u001b[39m and \u001b[36mfrom\u001b[39m is not allowed.\n", "\n", " See also: \u001b[36mrename!\u001b[39m\n", "\n", "\u001b[1m Examples\u001b[22m\n", "\u001b[1m ≡≡≡≡≡≡≡≡≡≡\u001b[22m\n", "\n", "\u001b[36m julia> df = DataFrame(i = 1, x = 2, y = 3)\u001b[39m\n", "\u001b[36m 1×3 DataFrame\u001b[39m\n", "\u001b[36m Row │ i x y\u001b[39m\n", "\u001b[36m │ Int64 Int64 Int64\u001b[39m\n", "\u001b[36m ─────┼─────────────────────\u001b[39m\n", "\u001b[36m 1 │ 1 2 3\u001b[39m\n", "\u001b[36m \u001b[39m\n", "\u001b[36m julia> rename(df, :i => :A, :x => :X)\u001b[39m\n", "\u001b[36m 1×3 DataFrame\u001b[39m\n", "\u001b[36m Row │ A X y\u001b[39m\n", "\u001b[36m │ Int64 Int64 Int64\u001b[39m\n", "\u001b[36m ─────┼─────────────────────\u001b[39m\n", "\u001b[36m 1 │ 1 2 3\u001b[39m\n", "\u001b[36m \u001b[39m\n", "\u001b[36m julia> rename(df, :x => :y, :y => :x)\u001b[39m\n", "\u001b[36m 1×3 DataFrame\u001b[39m\n", "\u001b[36m Row │ i y x\u001b[39m\n", "\u001b[36m │ Int64 Int64 Int64\u001b[39m\n", "\u001b[36m ─────┼─────────────────────\u001b[39m\n", "\u001b[36m 1 │ 1 2 3\u001b[39m\n", "\u001b[36m \u001b[39m\n", "\u001b[36m julia> rename(df, [1 => :A, 2 => :X])\u001b[39m\n", "\u001b[36m 1×3 DataFrame\u001b[39m\n", "\u001b[36m Row │ A X y\u001b[39m\n", "\u001b[36m │ Int64 Int64 Int64\u001b[39m\n", "\u001b[36m ─────┼─────────────────────\u001b[39m\n", "\u001b[36m 1 │ 1 2 3\u001b[39m\n", "\u001b[36m \u001b[39m\n", "\u001b[36m julia> rename(df, Dict(\"i\" => \"A\", \"x\" => \"X\"))\u001b[39m\n", "\u001b[36m 1×3 DataFrame\u001b[39m\n", "\u001b[36m Row │ A X y\u001b[39m\n", "\u001b[36m │ Int64 Int64 Int64\u001b[39m\n", "\u001b[36m ─────┼─────────────────────\u001b[39m\n", "\u001b[36m 1 │ 1 2 3\u001b[39m\n", "\u001b[36m \u001b[39m\n", "\u001b[36m julia> rename(uppercase, df)\u001b[39m\n", "\u001b[36m 1×3 DataFrame\u001b[39m\n", "\u001b[36m Row │ I X Y\u001b[39m\n", "\u001b[36m │ Int64 Int64 Int64\u001b[39m\n", "\u001b[36m ─────┼─────────────────────\u001b[39m\n", "\u001b[36m 1 │ 1 2 3\u001b[39m" ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" } ], "source": [ "?rename" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Interact.jl: Simple interactive visualizations" ] }, { "cell_type": "code", "execution_count": 20, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "\u001b[32m\u001b[1m Resolving\u001b[22m\u001b[39m package versions...\n", "\u001b[32m\u001b[1m Updating\u001b[22m\u001b[39m `C:\\Users\\kcsgo\\.julia\\environments\\v1.4\\Project.toml`\n", "\u001b[90m [no changes]\u001b[39m\n", "\u001b[32m\u001b[1m Updating\u001b[22m\u001b[39m `C:\\Users\\kcsgo\\.julia\\environments\\v1.4\\Manifest.toml`\n", "\u001b[90m [no changes]\u001b[39m\n" ] } ], "source": [ "Pkg.add(\"Interact\")" ] }, { "cell_type": "code", "execution_count": 21, "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", " Unable to load WebIO. Please make sure WebIO works for your Jupyter client.\n", " For troubleshooting, please see \n", " the WebIO/IJulia documentation.\n", " \n", "

\n" ], "text/plain": [ "HTML{String}(\"\\n\\n Unable to load WebIO. Please make sure WebIO works for your Jupyter client.\\n For troubleshooting, please see \\n the WebIO/IJulia documentation.\\n \\n

\\n\")" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "using Interact" ] }, { "cell_type": "code", "execution_count": 22, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "i = 1\n", "i = 2\n", "i = 3\n", "i = 4\n", "i = 5\n", "i = 6\n", "i = 7\n", "i = 8\n", "i = 9\n", "i = 10\n" ] } ], "source": [ "for i in 1:10\n", " @show i\n", "end" ] }, { "cell_type": "code", "execution_count": 23, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "UnitRange{Int64}" ] }, "execution_count": 23, "metadata": {}, "output_type": "execute_result" } ], "source": [ "typeof(1:10)" ] }, { "cell_type": "code", "execution_count": 24, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "10-element Array{Int64,1}:\n", " 1\n", " 2\n", " 3\n", " 4\n", " 5\n", " 6\n", " 7\n", " 8\n", " 9\n", " 10" ] }, "execution_count": 24, "metadata": {}, "output_type": "execute_result" } ], "source": [ "collect(1:10)" ] }, { "cell_type": "code", "execution_count": 25, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "i = 1\n", "i = 2\n", "i = 3\n", "i = 4\n", "i = 5\n", "i = 6\n", "i = 7\n", "i = 8\n", "i = 9\n", "i = 10\n" ] } ], "source": [ "for i in 1:10\n", " println(\"i = \", i)\n", "end" ] }, { "cell_type": "code", "execution_count": 31, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "4-element Array{String,1}:\n", " \"Albania\"\n", " \"Algeria\"\n", " \"Andorra\"\n", " \"Angola\"" ] }, "execution_count": 31, "metadata": {}, "output_type": "execute_result" } ], "source": [ "countries = data[2:5, 2]" ] }, { "cell_type": "code", "execution_count": 32, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "271-element Array{String,1}:\n", " \"Afghanistan\"\n", " \"Albania\"\n", " \"Algeria\"\n", " \"Andorra\"\n", " \"Angola\"\n", " \"Antigua and Barbuda\"\n", " \"Argentina\"\n", " \"Armenia\"\n", " \"Australia\"\n", " \"Australia\"\n", " \"Australia\"\n", " \"Australia\"\n", " \"Australia\"\n", " ⋮\n", " \"United Kingdom\"\n", " \"United Kingdom\"\n", " \"United Kingdom\"\n", " \"Uruguay\"\n", " \"Uzbekistan\"\n", " \"Vanuatu\"\n", " \"Venezuela\"\n", " \"Vietnam\"\n", " \"West Bank and Gaza\"\n", " \"Yemen\"\n", " \"Zambia\"\n", " \"Zimbabwe\"" ] }, "execution_count": 32, "metadata": {}, "output_type": "execute_result" } ], "source": [ "countries = data[1:end, 2]" ] }, { "cell_type": "code", "execution_count": 33, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "271-element Array{String,1}:\n", " \"Afghanistan\"\n", " \"Albania\"\n", " \"Algeria\"\n", " \"Andorra\"\n", " \"Angola\"\n", " \"Antigua and Barbuda\"\n", " \"Argentina\"\n", " \"Armenia\"\n", " \"Australia\"\n", " \"Australia\"\n", " \"Australia\"\n", " \"Australia\"\n", " \"Australia\"\n", " ⋮\n", " \"United Kingdom\"\n", " \"United Kingdom\"\n", " \"United Kingdom\"\n", " \"Uruguay\"\n", " \"Uzbekistan\"\n", " \"Vanuatu\"\n", " \"Venezuela\"\n", " \"Vietnam\"\n", " \"West Bank and Gaza\"\n", " \"Yemen\"\n", " \"Zambia\"\n", " \"Zimbabwe\"" ] }, "execution_count": 33, "metadata": {}, "output_type": "execute_result" } ], "source": [ "countries = collect(data[:, 2])" ] }, { "cell_type": "code", "execution_count": 34, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "191-element Array{String,1}:\n", " \"Afghanistan\"\n", " \"Albania\"\n", " \"Algeria\"\n", " \"Andorra\"\n", " \"Angola\"\n", " \"Antigua and Barbuda\"\n", " \"Argentina\"\n", " \"Armenia\"\n", " \"Australia\"\n", " \"Austria\"\n", " \"Azerbaijan\"\n", " \"Bahamas\"\n", " \"Bahrain\"\n", " ⋮\n", " \"Ukraine\"\n", " \"United Arab Emirates\"\n", " \"United Kingdom\"\n", " \"Uruguay\"\n", " \"Uzbekistan\"\n", " \"Vanuatu\"\n", " \"Venezuela\"\n", " \"Vietnam\"\n", " \"West Bank and Gaza\"\n", " \"Yemen\"\n", " \"Zambia\"\n", " \"Zimbabwe\"" ] }, "execution_count": 34, "metadata": {}, "output_type": "execute_result" } ], "source": [ "unique_countries = unique(countries)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "> Note: Julia has 1-based indexing: indices of vectors start at 1, not 0" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Extract data and plot" ] }, { "cell_type": "code", "execution_count": 36, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "true" ] }, "execution_count": 36, "metadata": {}, "output_type": "execute_result" } ], "source": [ "startswith(\"United\", \"U\")" ] }, { "cell_type": "code", "execution_count": 37, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "false" ] }, "execution_count": 37, "metadata": {}, "output_type": "execute_result" } ], "source": [ "startswith(\"David\", \"U\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Array comprehension:" ] }, { "cell_type": "code", "execution_count": 38, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "271-element Array{Bool,1}:\n", " 0\n", " 0\n", " 0\n", " 0\n", " 0\n", " 0\n", " 0\n", " 0\n", " 0\n", " 0\n", " 0\n", " 0\n", " 0\n", " ⋮\n", " 1\n", " 1\n", " 1\n", " 1\n", " 1\n", " 0\n", " 0\n", " 0\n", " 0\n", " 0\n", " 0\n", " 0" ] }, "execution_count": 38, "metadata": {}, "output_type": "execute_result" } ], "source": [ "U_countries = [startswith(country, \"U\") for country in countries]" ] }, { "cell_type": "code", "execution_count": 40, "metadata": {}, "outputs": [ { "data": { "text/html": [ "

17 rows × 347 columns (omitted printing of 342 columns)

provincecountryLatLong1/22/20
String?StringFloat64?Float64?Int64
1missingUS40.0-100.01
2missingUganda1.3733332.29030
3missingUkraine48.379431.16560
4missingUnited Arab Emirates23.424153.84780
5AnguillaUnited Kingdom18.2206-63.06860
6BermudaUnited Kingdom32.3078-64.75050
7British Virgin IslandsUnited Kingdom18.4207-64.640
8Cayman IslandsUnited Kingdom19.3133-81.25460
9Channel IslandsUnited Kingdom49.3723-2.36440
10Falkland Islands (Malvinas)United Kingdom-51.7963-59.52360
11GibraltarUnited Kingdom36.1408-5.35360
12Isle of ManUnited Kingdom54.2361-4.54810
13MontserratUnited Kingdom16.7425-62.18740
14Turks and Caicos IslandsUnited Kingdom21.694-71.79790
15missingUnited Kingdom55.3781-3.4360
16missingUruguay-32.5228-55.76580
17missingUzbekistan41.377564.58530
" ], "text/latex": [ "\\begin{tabular}{r|cccccc}\n", "\t& province & country & Lat & Long & 1/22/20 & \\\\\n", "\t\\hline\n", "\t& String? & String & Float64? & Float64? & Int64 & \\\\\n", "\t\\hline\n", "\t1 & \\emph{missing} & US & 40.0 & -100.0 & 1 & $\\dots$ \\\\\n", "\t2 & \\emph{missing} & Uganda & 1.37333 & 32.2903 & 0 & $\\dots$ \\\\\n", "\t3 & \\emph{missing} & Ukraine & 48.3794 & 31.1656 & 0 & $\\dots$ \\\\\n", "\t4 & \\emph{missing} & United Arab Emirates & 23.4241 & 53.8478 & 0 & $\\dots$ \\\\\n", "\t5 & Anguilla & United Kingdom & 18.2206 & -63.0686 & 0 & $\\dots$ \\\\\n", "\t6 & Bermuda & United Kingdom & 32.3078 & -64.7505 & 0 & $\\dots$ \\\\\n", "\t7 & British Virgin Islands & United Kingdom & 18.4207 & -64.64 & 0 & $\\dots$ \\\\\n", "\t8 & Cayman Islands & United Kingdom & 19.3133 & -81.2546 & 0 & $\\dots$ \\\\\n", "\t9 & Channel Islands & United Kingdom & 49.3723 & -2.3644 & 0 & $\\dots$ \\\\\n", "\t10 & Falkland Islands (Malvinas) & United Kingdom & -51.7963 & -59.5236 & 0 & $\\dots$ \\\\\n", "\t11 & Gibraltar & United Kingdom & 36.1408 & -5.3536 & 0 & $\\dots$ \\\\\n", "\t12 & Isle of Man & United Kingdom & 54.2361 & -4.5481 & 0 & $\\dots$ \\\\\n", "\t13 & Montserrat & United Kingdom & 16.7425 & -62.1874 & 0 & $\\dots$ \\\\\n", "\t14 & Turks and Caicos Islands & United Kingdom & 21.694 & -71.7979 & 0 & $\\dots$ \\\\\n", "\t15 & \\emph{missing} & United Kingdom & 55.3781 & -3.436 & 0 & $\\dots$ \\\\\n", "\t16 & \\emph{missing} & Uruguay & -32.5228 & -55.7658 & 0 & $\\dots$ \\\\\n", "\t17 & \\emph{missing} & Uzbekistan & 41.3775 & 64.5853 & 0 & $\\dots$ \\\\\n", "\\end{tabular}\n" ], "text/plain": [ "\u001b[1m17×347 DataFrame\u001b[0m\n", "\u001b[1m Row \u001b[0m│\u001b[1m province \u001b[0m\u001b[1m country \u001b[0m\u001b[1m Lat \u001b[0m\u001b[1m Long \u001b[0m ⋯\n", "\u001b[1m \u001b[0m│\u001b[90m String? \u001b[0m\u001b[90m String \u001b[0m\u001b[90m Float64? \u001b[0m\u001b[90m Float64? \u001b[0m ⋯\n", "─────┼──────────────────────────────────────────────────────────────────────────\n", " 1 │\u001b[90m missing \u001b[0m US 40.0 -100.0 ⋯\n", " 2 │\u001b[90m missing \u001b[0m Uganda 1.37333 32.2903\n", " 3 │\u001b[90m missing \u001b[0m Ukraine 48.3794 31.1656\n", " 4 │\u001b[90m missing \u001b[0m United Arab Emirates 23.4241 53.8478\n", " 5 │ Anguilla United Kingdom 18.2206 -63.0686 ⋯\n", " 6 │ Bermuda United Kingdom 32.3078 -64.7505\n", " 7 │ British Virgin Islands United Kingdom 18.4207 -64.64\n", " 8 │ Cayman Islands United Kingdom 19.3133 -81.2546\n", " 9 │ Channel Islands United Kingdom 49.3723 -2.3644 ⋯\n", " 10 │ Falkland Islands (Malvinas) United Kingdom -51.7963 -59.5236\n", " 11 │ Gibraltar United Kingdom 36.1408 -5.3536\n", " 12 │ Isle of Man United Kingdom 54.2361 -4.5481\n", " 13 │ Montserrat United Kingdom 16.7425 -62.1874 ⋯\n", " 14 │ Turks and Caicos Islands United Kingdom 21.694 -71.7979\n", " 15 │\u001b[90m missing \u001b[0m United Kingdom 55.3781 -3.436\n", " 16 │\u001b[90m missing \u001b[0m Uruguay -32.5228 -55.7658\n", " 17 │\u001b[90m missing \u001b[0m Uzbekistan 41.3775 64.5853 ⋯\n", "\u001b[31m 343 columns omitted\u001b[0m" ] }, "execution_count": 40, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data[U_countries, :]" ] }, { "cell_type": "code", "execution_count": 41, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "271-element BitArray{1}:\n", " 0\n", " 0\n", " 0\n", " 0\n", " 0\n", " 0\n", " 0\n", " 0\n", " 0\n", " 0\n", " 0\n", " 0\n", " 0\n", " ⋮\n", " 0\n", " 0\n", " 0\n", " 0\n", " 0\n", " 0\n", " 0\n", " 0\n", " 0\n", " 0\n", " 0\n", " 0" ] }, "execution_count": 41, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# . is \"broadcasting\": apply operation to each element of a vector\n", "countries .== \"US\" " ] }, { "cell_type": "code", "execution_count": 42, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "248" ] }, "execution_count": 42, "metadata": {}, "output_type": "execute_result" } ], "source": [ "US_row = findfirst(countries .== \"US\")" ] }, { "cell_type": "code", "execution_count": 43, "metadata": {}, "outputs": [ { "data": { "text/html": [ "

DataFrameRow (347 columns)

provincecountryLatLong1/22/201/23/201/24/201/25/201/26/20
String?StringFloat64?Float64?Int64Int64Int64Int64Int64
248missingUS40.0-100.011225
" ], "text/latex": [ "\\begin{tabular}{r|cccccccccc}\n", "\t& province & country & Lat & Long & 1/22/20 & 1/23/20 & 1/24/20 & 1/25/20 & 1/26/20 & \\\\\n", "\t\\hline\n", "\t& String? & String & Float64? & Float64? & Int64 & Int64 & Int64 & Int64 & Int64 & \\\\\n", "\t\\hline\n", "\t248 & \\emph{missing} & US & 40.0 & -100.0 & 1 & 1 & 2 & 2 & 5 & $\\dots$ \\\\\n", "\\end{tabular}\n" ], "text/plain": [ "\u001b[1mDataFrameRow\u001b[0m\n", "\u001b[1m Row \u001b[0m│\u001b[1m province \u001b[0m\u001b[1m country \u001b[0m\u001b[1m Lat \u001b[0m\u001b[1m Long \u001b[0m\u001b[1m 1/22/20 \u001b[0m\u001b[1m 1/23/20 \u001b[0m\u001b[1m 1/24/20 \u001b[0m\u001b[1m 1/25/\u001b[0m ⋯\n", "\u001b[1m \u001b[0m│\u001b[90m String? \u001b[0m\u001b[90m String \u001b[0m\u001b[90m Float64? \u001b[0m\u001b[90m Float64? \u001b[0m\u001b[90m Int64 \u001b[0m\u001b[90m Int64 \u001b[0m\u001b[90m Int64 \u001b[0m\u001b[90m Int64\u001b[0m ⋯\n", "─────┼──────────────────────────────────────────────────────────────────────────\n", " 248 │\u001b[90m missing \u001b[0m US 40.0 -100.0 1 1 2 ⋯\n", "\u001b[31m 340 columns omitted\u001b[0m" ] }, "execution_count": 43, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data[US_row, :]" ] }, { "cell_type": "code", "execution_count": 46, "metadata": {}, "outputs": [ { "data": { "text/html": [ "

DataFrameRow (347 columns)

provincecountryLatLong1/22/201/23/201/24/201/25/201/26/20
String?StringFloat64?Float64?Int64Int64Int64Int64Int64
248missingUS40.0-100.011225
" ], "text/latex": [ "\\begin{tabular}{r|cccccccccc}\n", "\t& province & country & Lat & Long & 1/22/20 & 1/23/20 & 1/24/20 & 1/25/20 & 1/26/20 & \\\\\n", "\t\\hline\n", "\t& String? & String & Float64? & Float64? & Int64 & Int64 & Int64 & Int64 & Int64 & \\\\\n", "\t\\hline\n", "\t248 & \\emph{missing} & US & 40.0 & -100.0 & 1 & 1 & 2 & 2 & 5 & $\\dots$ \\\\\n", "\\end{tabular}\n" ], "text/plain": [ "\u001b[1mDataFrameRow\u001b[0m\n", "\u001b[1m Row \u001b[0m│\u001b[1m province \u001b[0m\u001b[1m country \u001b[0m\u001b[1m Lat \u001b[0m\u001b[1m Long \u001b[0m\u001b[1m 1/22/20 \u001b[0m\u001b[1m 1/23/20 \u001b[0m\u001b[1m 1/24/20 \u001b[0m\u001b[1m 1/25/\u001b[0m ⋯\n", "\u001b[1m \u001b[0m│\u001b[90m String? \u001b[0m\u001b[90m String \u001b[0m\u001b[90m Float64? \u001b[0m\u001b[90m Float64? \u001b[0m\u001b[90m Int64 \u001b[0m\u001b[90m Int64 \u001b[0m\u001b[90m Int64 \u001b[0m\u001b[90m Int64\u001b[0m ⋯\n", "─────┼──────────────────────────────────────────────────────────────────────────\n", " 248 │\u001b[90m missing \u001b[0m US 40.0 -100.0 1 1 2 ⋯\n", "\u001b[31m 340 columns omitted\u001b[0m" ] }, "execution_count": 46, "metadata": {}, "output_type": "execute_result" } ], "source": [ "UC_data_row = data[US_row, :]" ] }, { "cell_type": "code", "execution_count": 47, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "343-element Array{Int64,1}:\n", " 1\n", " 1\n", " 2\n", " 2\n", " 5\n", " 5\n", " 5\n", " 6\n", " 6\n", " 8\n", " 8\n", " 8\n", " 11\n", " ⋮\n", " 17468841\n", " 17665284\n", " 17853731\n", " 18045048\n", " 18239758\n", " 18466484\n", " 18665343\n", " 18765529\n", " 18992126\n", " 19142603\n", " 19309281\n", " 19510836" ] }, "execution_count": 47, "metadata": {}, "output_type": "execute_result" } ], "source": [ "US_data = convert(Vector, UC_data_row[5:end])" ] }, { "cell_type": "code", "execution_count": 49, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "\u001b[32m\u001b[1m Resolving\u001b[22m\u001b[39m package versions...\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m libfdk_aac_jll ── v0.1.6+4\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m EarCut_jll ────── v2.1.5+1\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m x265_jll ──────── v3.0.0+3\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m Showoff ───────── v0.3.2\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m RecipesPipeline ─ v0.1.13\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m Contour ───────── v0.5.7\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m StaticArrays ──── v1.0.1\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m Plots ─────────── v1.6.12\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m FreeType2_jll ─── v2.10.1+5\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m Bzip2_jll ─────── v1.0.6+5\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m LAME_jll ──────── v3.100.0+3\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m OpenSSL_jll ───── v1.1.1+6\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m Grisu ─────────── v1.0.0\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m libass_jll ────── v0.14.0+4\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m libvorbis_jll ─── v1.3.6+6\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m LaTeXStrings ──── v1.2.0\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m IterTools ─────── v1.3.0\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m Opus_jll ──────── v1.3.1+3\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m Adapt ─────────── v2.3.0\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m LibVPX_jll ────── v1.9.0+1\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m GeometryTypes ─── v0.8.4\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m FFMPEG_jll ────── v4.3.1+4\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m PlotUtils ─────── v1.0.8\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m FFMPEG ────────── v0.4.0\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m Ogg_jll ───────── v1.3.4+2\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m RecipesBase ───── v1.1.1\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m Zlib_jll ──────── v1.2.11+18\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m GR ────────────── v0.49.1\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m Latexify ──────── v0.14.7\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m GeometryBasics ── v0.3.5\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m StatsBase ─────── v0.33.2\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m NaNMath ───────── v0.3.5\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m x264_jll ──────── v2020.7.14+2\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m FriBidi_jll ───── v1.0.5+6\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m PlotThemes ────── v2.0.0\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m StructArrays ──── v0.4.4\n", "\u001b[32m\u001b[1m Installed\u001b[22m\u001b[39m ColorSchemes ──── v3.10.2\n", "\u001b[32m\u001b[1m Updating\u001b[22m\u001b[39m `C:\\Users\\kcsgo\\.julia\\environments\\v1.4\\Project.toml`\n", " \u001b[90m [91a5bcdd]\u001b[39m\u001b[92m + Plots v1.6.12\u001b[39m\n", "\u001b[32m\u001b[1m Updating\u001b[22m\u001b[39m `C:\\Users\\kcsgo\\.julia\\environments\\v1.4\\Manifest.toml`\n", " \u001b[90m [79e6a3ab]\u001b[39m\u001b[92m + Adapt v2.3.0\u001b[39m\n", " \u001b[90m [6e34b625]\u001b[39m\u001b[92m + Bzip2_jll v1.0.6+5\u001b[39m\n", " \u001b[90m [35d6a980]\u001b[39m\u001b[92m + ColorSchemes v3.10.2\u001b[39m\n", " \u001b[90m [d38c429a]\u001b[39m\u001b[92m + Contour v0.5.7\u001b[39m\n", " \u001b[90m [5ae413db]\u001b[39m\u001b[92m + EarCut_jll v2.1.5+1\u001b[39m\n", " \u001b[90m [c87230d0]\u001b[39m\u001b[92m + FFMPEG v0.4.0\u001b[39m\n", " \u001b[90m [b22a6f82]\u001b[39m\u001b[92m + FFMPEG_jll v4.3.1+4\u001b[39m\n", " \u001b[90m [d7e528f0]\u001b[39m\u001b[92m + FreeType2_jll v2.10.1+5\u001b[39m\n", " \u001b[90m [559328eb]\u001b[39m\u001b[92m + FriBidi_jll v1.0.5+6\u001b[39m\n", " \u001b[90m [28b8d3ca]\u001b[39m\u001b[92m + GR v0.49.1\u001b[39m\n", " \u001b[90m [5c1252a2]\u001b[39m\u001b[92m + GeometryBasics v0.3.5\u001b[39m\n", " \u001b[90m [4d00f742]\u001b[39m\u001b[92m + GeometryTypes v0.8.4\u001b[39m\n", " \u001b[90m [42e2da0e]\u001b[39m\u001b[92m + Grisu v1.0.0\u001b[39m\n", " \u001b[90m [c8e1da08]\u001b[39m\u001b[92m + IterTools v1.3.0\u001b[39m\n", " \u001b[90m [c1c5ebd0]\u001b[39m\u001b[92m + LAME_jll v3.100.0+3\u001b[39m\n", " \u001b[90m [b964fa9f]\u001b[39m\u001b[92m + LaTeXStrings v1.2.0\u001b[39m\n", " \u001b[90m [23fbe1c1]\u001b[39m\u001b[92m + Latexify v0.14.7\u001b[39m\n", " \u001b[90m [dd192d2f]\u001b[39m\u001b[92m + LibVPX_jll v1.9.0+1\u001b[39m\n", " \u001b[90m [77ba4419]\u001b[39m\u001b[92m + NaNMath v0.3.5\u001b[39m\n", " \u001b[90m [e7412a2a]\u001b[39m\u001b[92m + Ogg_jll v1.3.4+2\u001b[39m\n", " \u001b[90m [458c3c95]\u001b[39m\u001b[92m + OpenSSL_jll v1.1.1+6\u001b[39m\n", " \u001b[90m [91d4177d]\u001b[39m\u001b[92m + Opus_jll v1.3.1+3\u001b[39m\n", " \u001b[90m [ccf2f8ad]\u001b[39m\u001b[92m + PlotThemes v2.0.0\u001b[39m\n", " \u001b[90m [995b91a9]\u001b[39m\u001b[92m + PlotUtils v1.0.8\u001b[39m\n", " \u001b[90m [91a5bcdd]\u001b[39m\u001b[92m + Plots v1.6.12\u001b[39m\n", " \u001b[90m [3cdcf5f2]\u001b[39m\u001b[92m + RecipesBase v1.1.1\u001b[39m\n", " \u001b[90m [01d81517]\u001b[39m\u001b[92m + RecipesPipeline v0.1.13\u001b[39m\n", " \u001b[90m [992d4aef]\u001b[39m\u001b[92m + Showoff v0.3.2\u001b[39m\n", " \u001b[90m [90137ffa]\u001b[39m\u001b[92m + StaticArrays v1.0.1\u001b[39m\n", " \u001b[90m [2913bbd2]\u001b[39m\u001b[92m + StatsBase v0.33.2\u001b[39m\n", " \u001b[90m [09ab397b]\u001b[39m\u001b[92m + StructArrays v0.4.4\u001b[39m\n", " \u001b[90m [83775a58]\u001b[39m\u001b[92m + Zlib_jll v1.2.11+18\u001b[39m\n", " \u001b[90m [0ac62f75]\u001b[39m\u001b[92m + libass_jll v0.14.0+4\u001b[39m\n", " \u001b[90m [f638f0a6]\u001b[39m\u001b[92m + libfdk_aac_jll v0.1.6+4\u001b[39m\n", " \u001b[90m [f27f6e37]\u001b[39m\u001b[92m + libvorbis_jll v1.3.6+6\u001b[39m\n", " \u001b[90m [1270edf5]\u001b[39m\u001b[92m + x264_jll v2020.7.14+2\u001b[39m\n", " \u001b[90m [dfaa095f]\u001b[39m\u001b[92m + x265_jll v3.0.0+3\u001b[39m\n", "\u001b[32m\u001b[1m Building\u001b[22m\u001b[39m GR → `C:\\Users\\kcsgo\\.julia\\packages\\GR\\cRdXQ\\deps\\build.log`\n" ] } ], "source": [ "Pkg.add(\"Plots\")" ] }, { "cell_type": "code", "execution_count": 50, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "┌ Info: Precompiling Plots [91a5bcdd-55d7-5caf-9e0b-520d859cae80]\n", "└ @ Base loading.jl:1260\n" ] } ], "source": [ "using Plots" ] }, { "cell_type": "code", "execution_count": 51, "metadata": {}, "outputs": [ { "data": { "image/svg+xml": [ "\n", "\n", "\n", " \n", " \n", " \n", "\n", "\n", "\n", " \n", " \n", " \n", "\n", "\n", "\n", " \n", " \n", " \n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n" ] }, "execution_count": 51, "metadata": {}, "output_type": "execute_result" } ], "source": [ "plot(US_data)" ] }, { "cell_type": "code", "execution_count": 52, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "347-element Array{String,1}:\n", " \"province\"\n", " \"country\"\n", " \"Lat\"\n", " \"Long\"\n", " \"1/22/20\"\n", " \"1/23/20\"\n", " \"1/24/20\"\n", " \"1/25/20\"\n", " \"1/26/20\"\n", " \"1/27/20\"\n", " \"1/28/20\"\n", " \"1/29/20\"\n", " \"1/30/20\"\n", " ⋮\n", " \"12/18/20\"\n", " \"12/19/20\"\n", " \"12/20/20\"\n", " \"12/21/20\"\n", " \"12/22/20\"\n", " \"12/23/20\"\n", " \"12/24/20\"\n", " \"12/25/20\"\n", " \"12/26/20\"\n", " \"12/27/20\"\n", " \"12/28/20\"\n", " \"12/29/20\"" ] }, "execution_count": 52, "metadata": {}, "output_type": "execute_result" } ], "source": [ "col_names = names(data)" ] }, { "cell_type": "code", "execution_count": 58, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "343-element Array{String,1}:\n", " \"1/22/20\"\n", " \"1/23/20\"\n", " \"1/24/20\"\n", " \"1/25/20\"\n", " \"1/26/20\"\n", " \"1/27/20\"\n", " \"1/28/20\"\n", " \"1/29/20\"\n", " \"1/30/20\"\n", " \"1/31/20\"\n", " \"2/1/20\"\n", " \"2/2/20\"\n", " \"2/3/20\"\n", " ⋮\n", " \"12/18/20\"\n", " \"12/19/20\"\n", " \"12/20/20\"\n", " \"12/21/20\"\n", " \"12/22/20\"\n", " \"12/23/20\"\n", " \"12/24/20\"\n", " \"12/25/20\"\n", " \"12/26/20\"\n", " \"12/27/20\"\n", " \"12/28/20\"\n", " \"12/29/20\"" ] }, "execution_count": 58, "metadata": {}, "output_type": "execute_result" } ], "source": [ "date_strings = String.(names(data))[5:end]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Parse: convert string representation into a Julia object" ] }, { "cell_type": "code", "execution_count": 59, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "\"1/22/20\"" ] }, "execution_count": 59, "metadata": {}, "output_type": "execute_result" } ], "source": [ "date_strings[1]" ] }, { "cell_type": "code", "execution_count": 56, "metadata": {}, "outputs": [], "source": [ "using Dates" ] }, { "cell_type": "code", "execution_count": 57, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "dateformat\"d/m/Y\"" ] }, "execution_count": 57, "metadata": {}, "output_type": "execute_result" } ], "source": [ "format = Dates.DateFormat(\"d/m/Y\")" ] }, { "cell_type": "code", "execution_count": 60, "metadata": {}, "outputs": [ { "ename": "ArgumentError", "evalue": "ArgumentError: Month: 22 out of range (1:12)", "output_type": "error", "traceback": [ "ArgumentError: Month: 22 out of range (1:12)", "", "Stacktrace:", " [1] Date(::Int64, ::Int64, ::Int64) at D:\\buildbot\\worker\\package_win64\\build\\usr\\share\\julia\\stdlib\\v1.4\\Dates\\src\\types.jl:223", " [2] parse(::Type{Date}, ::String, ::DateFormat{Symbol(\"d/m/Y\"),Tuple{Dates.DatePart{'d'},Dates.Delim{Char,1},Dates.DatePart{'m'},Dates.Delim{Char,1},Dates.DatePart{'Y'}}}) at D:\\buildbot\\worker\\package_win64\\build\\usr\\share\\julia\\stdlib\\v1.4\\Dates\\src\\parse.jl:285", " [3] top-level scope at In[60]:1" ] } ], "source": [ "parse(Date, date_strings[1], format)" ] }, { "cell_type": "code", "execution_count": 62, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "2020-01-22" ] }, "execution_count": 62, "metadata": {}, "output_type": "execute_result" } ], "source": [ "format = Dates.DateFormat(\"m/d/Y\")\n", "parse(Date, date_strings[1], format) + Year(2000)" ] }, { "cell_type": "code", "execution_count": 63, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "343-element Array{Date,1}:\n", " 2020-01-22\n", " 2020-01-23\n", " 2020-01-24\n", " 2020-01-25\n", " 2020-01-26\n", " 2020-01-27\n", " 2020-01-28\n", " 2020-01-29\n", " 2020-01-30\n", " 2020-01-31\n", " 2020-02-01\n", " 2020-02-02\n", " 2020-02-03\n", " ⋮\n", " 2020-12-18\n", " 2020-12-19\n", " 2020-12-20\n", " 2020-12-21\n", " 2020-12-22\n", " 2020-12-23\n", " 2020-12-24\n", " 2020-12-25\n", " 2020-12-26\n", " 2020-12-27\n", " 2020-12-28\n", " 2020-12-29" ] }, "execution_count": 63, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dates = parse.(Date, date_strings, format) + Year(2000)" ] }, { "cell_type": "code", "execution_count": 67, "metadata": {}, "outputs": [ { "data": { "image/svg+xml": [ "\n", "\n", "\n", " \n", " \n", " \n", "\n", "\n", "\n", " \n", " \n", " \n", "\n", "\n", "\n", " \n", " \n", " \n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n" ] }, "execution_count": 67, "metadata": {}, "output_type": "execute_result" } ], "source": [ "plot(dates, US_data, xticks=dates[1:5:end], xrotation=45, leg=:topleft, \n", " label=\"US data\", m=:o)\n", "\n", "xlabel!(\"date\")\n", "ylabel!(\"confirmed cases in US\")\n", "title!(\"US confirmed COVID-19 cases\")" ] }, { "cell_type": "code", "execution_count": 68, "metadata": {}, "outputs": [ { "data": { "image/svg+xml": [ "\n", "\n", "\n", " \n", " \n", " \n", "\n", "\n", "\n", " \n", " \n", " \n", "\n", "\n", "\n", " \n", " \n", " \n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n" ] }, "execution_count": 68, "metadata": {}, "output_type": "execute_result" } ], "source": [ "plot(dates, US_data, xticks=dates[1:5:end], xrotation=45, leg=:topleft, \n", " label=\"US data\", m=:o,\n", " yscale=:log10)\n", "\n", "xlabel!(\"date\")\n", "ylabel!(\"confirmed cases in US\")\n", "title!(\"US confirmed COVID-19 cases\")" ] } ], "metadata": { "kernelspec": { "display_name": "Julia 1.4.1", "language": "julia", "name": "julia-1.4" }, "language_info": { "file_extension": ".jl", "mimetype": "application/julia", "name": "julia", "version": "1.4.1" } }, "nbformat": 4, "nbformat_minor": 4 }