Homework #3: Manipulating Data
Andrew Zhang
Wednesday, November 05, 2014
Q 3.1 Get Ebola data from the CDC.
The CDC provides data on the recent Ebola Outbreak “http://www.cdc.gov/vhf/ebola/outbreaks/2014-west-africa/case-counts.html”. Read the Ebola outbreak data and store as a nice data frame.
library(XML)## Warning: package 'XML' was built under R version 3.1.2library(ggplot2)## Warning: package 'ggplot2' was built under R version 3.1.2library(dplyr)## Warning: package 'dplyr' was built under R version 3.1.2##
## Attaching package: 'dplyr'
##
## The following object is masked from 'package:stats':
##
## filter
##
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionurl <- 'http://www.cdc.gov/vhf/ebola/outbreaks/2014-west-africa/case-counts.html'
Ebola1 <- readHTMLTable(url)[[1]] #read w/o colClasses
Ebola2 <- readHTMLTable(url)[[2]] #read w/o colClasses
Ebola3 <- readHTMLTable(url)[[3]] #read w/o colClasses
Ebola1.df <- tbl_df(Ebola1)
Ebola2.df <- tbl_df(Ebola2)
Ebola3.df <- tbl_df(Ebola3)
Ebola1.df## Source: local data frame [4 x 4]
##
## Country Total Cases Laboratory-Confirmed Cases Total Deaths
## 1 Guinea 1971 1698 1192
## 2 Liberia 7069 2643 2964
## 3 Sierra Leone 6073 5056 1250
## 4 Total 15113 9397 5406Ebola2.df## Source: local data frame [3 x 4]
##
## Country Total Cases Laboratory-Confirmed Cases Total Deaths
## 1 United States 4 4 1
## 2 Mali 6 5 5
## 3 Total 10 9 6Ebola3.df## Source: local data frame [4 x 4]
##
## Country Total Cases Laboratory-Confirmed Cases Total Deaths
## 1 Nigeria* 20 19 8
## 2 Senegal* 1 1 0
## 3 Spain 1 1 0
## 4 Total 22 21 8Q3.2 Clean up the numbers (no asterisk)
Some numbers in the data above have an asterisk. (19**). Get rid of those ‘stars’
# Ebola2.df and Ebola3.df has "*"
url <- 'http://www.cdc.gov/vhf/ebola/outbreaks/2014-west-africa/case-counts.html'
Ebolal_main <- readHTMLTable(url) #read w/o colClasses
Ebolal_main## $`cases-widespread`
## Country Total Cases Laboratory-Confirmed Cases Total Deaths
## 1 Guinea 1971 1698 1192
## 2 Liberia 7069 2643 2964
## 3 Sierra Leone 6073 5056 1250
## 4 Total 15113 9397 5406
##
## $`cases-travel-associated`
## Country Total Cases Laboratory-Confirmed Cases Total Deaths
## 1 United States 4 4 1
## 2 Mali 6 5 5
## 3 Total 10 9 6
##
## $`cases-localized-transmission`
## Country Total Cases Laboratory-Confirmed Cases Total Deaths
## 1 Nigeria* 20 19 8
## 2 Senegal* 1 1 0
## 3 Spain 1 1 0
## 4 Total 22 21 8# First table is fine
# table 2:
ebola_table2 <- as.data.frame((gsub("\\*", "", as.matrix(Ebolal_main[[2]][,-5]))))
ebola_table2## Country Total Cases Laboratory-Confirmed Cases Total Deaths
## 1 United States 4 4 1
## 2 Mali 6 5 5
## 3 Total 10 9 6# table 3:
ebola_table3 <- as.data.frame((gsub("\\*", "", as.matrix(Ebolal_main[[3]][,-5]))))
ebola_table3## Country Total Cases Laboratory-Confirmed Cases Total Deaths
## 1 Nigeria 20 19 8
## 2 Senegal 1 1 0
## 3 Spain 1 1 0
## 4 Total 22 21 8Q 3.3 Combine the 3 tables in the page into one dataframe.
combined <- rbind(Ebola1.df, ebola_table2, ebola_table3)
combined## Source: local data frame [11 x 4]
##
## Country Total Cases Laboratory-Confirmed Cases Total Deaths
## 1 Guinea 1971 1698 1192
## 2 Liberia 7069 2643 2964
## 3 Sierra Leone 6073 5056 1250
## 4 Total 15113 9397 5406
## 5 United States 4 4 1
## 6 Mali 6 5 5
## 7 Total 10 9 6
## 8 Nigeria 20 19 8
## 9 Senegal 1 1 0
## 10 Spain 1 1 0
## 11 Total 22 21 8Q3.4 Write an R Function
# Q3.5 Reading from Wikipedia:
http://en.wikipedia.org/wiki/List_of_Ebola_outbreaks Find out how many humans have died of Ebola since 1976. . Hint: Consider using readHTMLTable {XML package}. . If a page has multiple tables, and you want the second table, you’d do [[2]]. . If a column name has spaces, you put - Example: df$“Human deaths”
Print the total number of Human deaths from this table.
# 1: get the table using "readHTMLTable":
url2 <- 'http://en.wikipedia.org/wiki/List_of_Ebola_outbreaks'
ebola_wiki <- readHTMLTable(url2,colClasses= c('character', 'character', 'character' , 'character','character','character','character'))
Sum_human_deaths <- sum(as.numeric(gsub(",","",ebola_wiki[[2]]$"Human deaths")))## Warning: NAs introduced by coercionSum_human_deaths## [1] NAQ 3.6 dplyr
Take the readymade dataset airquality
Q: Calculate the average Ozone levels for each month in the data.
(Make sure you avoid the NA values!)
library(dplyr)
summary(airquality)## Ozone Solar.R Wind Temp
## Min. : 1.00 Min. : 7.0 Min. : 1.700 Min. :56.00
## 1st Qu.: 18.00 1st Qu.:115.8 1st Qu.: 7.400 1st Qu.:72.00
## Median : 31.50 Median :205.0 Median : 9.700 Median :79.00
## Mean : 42.13 Mean :185.9 Mean : 9.958 Mean :77.88
## 3rd Qu.: 63.25 3rd Qu.:258.8 3rd Qu.:11.500 3rd Qu.:85.00
## Max. :168.00 Max. :334.0 Max. :20.700 Max. :97.00
## NA's :37 NA's :7
## Month Day
## Min. :5.000 Min. : 1.0
## 1st Qu.:6.000 1st Qu.: 8.0
## Median :7.000 Median :16.0
## Mean :6.993 Mean :15.8
## 3rd Qu.:8.000 3rd Qu.:23.0
## Max. :9.000 Max. :31.0
## names(airquality)## [1] "Ozone" "Solar.R" "Wind" "Temp" "Month" "Day"head(airquality)## Ozone Solar.R Wind Temp Month Day
## 1 41 190 7.4 67 5 1
## 2 36 118 8.0 72 5 2
## 3 12 149 12.6 74 5 3
## 4 18 313 11.5 62 5 4
## 5 NA NA 14.3 56 5 5
## 6 28 NA 14.9 66 5 6# Method 1:
df1 <- aggregate(airquality, by=list(airquality$Month), FUN=mean, na.rm=TRUE)
df1 %>%
select( Month, Ozone)## Month Ozone
## 1 5 23.61538
## 2 6 29.44444
## 3 7 59.11538
## 4 8 59.96154
## 5 9 31.44828# Method 2 (This one does not seem to think about the NA values)
aggregate(data=airquality, Ozone~Month, mean) ## Month Ozone
## 1 5 23.61538
## 2 6 29.44444
## 3 7 59.11538
## 4 8 59.96154
## 5 9 31.44828# Why this one does not require "na.rm=TURE"??
# Ploting:
aggregate(data=airquality, Ozone~Month, mean) %>%
with(barplot(Ozone, main="AVG Ozone by Month"))
# Method 3:
# 1. Check row 10 for Ozone with NA:
airquality[10, ]## Ozone Solar.R Wind Temp Month Day
## 10 NA 194 8.6 69 5 10# 2. Get rid of NA for Ozon:
airquality_new <- airquality[!is.na(airquality$Ozone) , ]
airquality_new## Ozone Solar.R Wind Temp Month Day
## 1 41 190 7.4 67 5 1
## 2 36 118 8.0 72 5 2
## 3 12 149 12.6 74 5 3
## 4 18 313 11.5 62 5 4
## 6 28 NA 14.9 66 5 6
## 7 23 299 8.6 65 5 7
## 8 19 99 13.8 59 5 8
## 9 8 19 20.1 61 5 9
## 11 7 NA 6.9 74 5 11
## 12 16 256 9.7 69 5 12
## 13 11 290 9.2 66 5 13
## 14 14 274 10.9 68 5 14
## 15 18 65 13.2 58 5 15
## 16 14 334 11.5 64 5 16
## 17 34 307 12.0 66 5 17
## 18 6 78 18.4 57 5 18
## 19 30 322 11.5 68 5 19
## 20 11 44 9.7 62 5 20
## 21 1 8 9.7 59 5 21
## 22 11 320 16.6 73 5 22
## 23 4 25 9.7 61 5 23
## 24 32 92 12.0 61 5 24
## 28 23 13 12.0 67 5 28
## 29 45 252 14.9 81 5 29
## 30 115 223 5.7 79 5 30
## 31 37 279 7.4 76 5 31
## 38 29 127 9.7 82 6 7
## 40 71 291 13.8 90 6 9
## 41 39 323 11.5 87 6 10
## 44 23 148 8.0 82 6 13
## 47 21 191 14.9 77 6 16
## 48 37 284 20.7 72 6 17
## 49 20 37 9.2 65 6 18
## 50 12 120 11.5 73 6 19
## 51 13 137 10.3 76 6 20
## 62 135 269 4.1 84 7 1
## 63 49 248 9.2 85 7 2
## 64 32 236 9.2 81 7 3
## 66 64 175 4.6 83 7 5
## 67 40 314 10.9 83 7 6
## 68 77 276 5.1 88 7 7
## 69 97 267 6.3 92 7 8
## 70 97 272 5.7 92 7 9
## 71 85 175 7.4 89 7 10
## 73 10 264 14.3 73 7 12
## 74 27 175 14.9 81 7 13
## 76 7 48 14.3 80 7 15
## 77 48 260 6.9 81 7 16
## 78 35 274 10.3 82 7 17
## 79 61 285 6.3 84 7 18
## 80 79 187 5.1 87 7 19
## 81 63 220 11.5 85 7 20
## 82 16 7 6.9 74 7 21
## 85 80 294 8.6 86 7 24
## 86 108 223 8.0 85 7 25
## 87 20 81 8.6 82 7 26
## 88 52 82 12.0 86 7 27
## 89 82 213 7.4 88 7 28
## 90 50 275 7.4 86 7 29
## 91 64 253 7.4 83 7 30
## 92 59 254 9.2 81 7 31
## 93 39 83 6.9 81 8 1
## 94 9 24 13.8 81 8 2
## 95 16 77 7.4 82 8 3
## 96 78 NA 6.9 86 8 4
## 97 35 NA 7.4 85 8 5
## 98 66 NA 4.6 87 8 6
## 99 122 255 4.0 89 8 7
## 100 89 229 10.3 90 8 8
## 101 110 207 8.0 90 8 9
## 104 44 192 11.5 86 8 12
## 105 28 273 11.5 82 8 13
## 106 65 157 9.7 80 8 14
## 108 22 71 10.3 77 8 16
## 109 59 51 6.3 79 8 17
## 110 23 115 7.4 76 8 18
## 111 31 244 10.9 78 8 19
## 112 44 190 10.3 78 8 20
## 113 21 259 15.5 77 8 21
## 114 9 36 14.3 72 8 22
## 116 45 212 9.7 79 8 24
## 117 168 238 3.4 81 8 25
## 118 73 215 8.0 86 8 26
## 120 76 203 9.7 97 8 28
## 121 118 225 2.3 94 8 29
## 122 84 237 6.3 96 8 30
## 123 85 188 6.3 94 8 31
## 124 96 167 6.9 91 9 1
## 125 78 197 5.1 92 9 2
## 126 73 183 2.8 93 9 3
## 127 91 189 4.6 93 9 4
## 128 47 95 7.4 87 9 5
## 129 32 92 15.5 84 9 6
## 130 20 252 10.9 80 9 7
## 131 23 220 10.3 78 9 8
## 132 21 230 10.9 75 9 9
## 133 24 259 9.7 73 9 10
## 134 44 236 14.9 81 9 11
## 135 21 259 15.5 76 9 12
## 136 28 238 6.3 77 9 13
## 137 9 24 10.9 71 9 14
## 138 13 112 11.5 71 9 15
## 139 46 237 6.9 78 9 16
## 140 18 224 13.8 67 9 17
## 141 13 27 10.3 76 9 18
## 142 24 238 10.3 68 9 19
## 143 16 201 8.0 82 9 20
## 144 13 238 12.6 64 9 21
## 145 23 14 9.2 71 9 22
## 146 36 139 10.3 81 9 23
## 147 7 49 10.3 69 9 24
## 148 14 20 16.6 63 9 25
## 149 30 193 6.9 70 9 26
## 151 14 191 14.3 75 9 28
## 152 18 131 8.0 76 9 29
## 153 20 223 11.5 68 9 30# 3. Verify:
head(airquality, 10)## Ozone Solar.R Wind Temp Month Day
## 1 41 190 7.4 67 5 1
## 2 36 118 8.0 72 5 2
## 3 12 149 12.6 74 5 3
## 4 18 313 11.5 62 5 4
## 5 NA NA 14.3 56 5 5
## 6 28 NA 14.9 66 5 6
## 7 23 299 8.6 65 5 7
## 8 19 99 13.8 59 5 8
## 9 8 19 20.1 61 5 9
## 10 NA 194 8.6 69 5 10head(airquality_new, 10)## Ozone Solar.R Wind Temp Month Day
## 1 41 190 7.4 67 5 1
## 2 36 118 8.0 72 5 2
## 3 12 149 12.6 74 5 3
## 4 18 313 11.5 62 5 4
## 6 28 NA 14.9 66 5 6
## 7 23 299 8.6 65 5 7
## 8 19 99 13.8 59 5 8
## 9 8 19 20.1 61 5 9
## 11 7 NA 6.9 74 5 11
## 12 16 256 9.7 69 5 12# Run the code, this time, I did not include the "na.rm=TRUE"
df1 <- aggregate(airquality_new, by=list(airquality_new$Month), FUN=mean)
df1 %>%
select( Month, Ozone)## Month Ozone
## 1 5 23.61538
## 2 6 29.44444
## 3 7 59.11538
## 4 8 59.96154
## 5 9 31.44828# The result is the same as method 1