revisions to reflect updated example filename and clean comments in R code

This commit is contained in:
aaronshaw 2020-04-02 13:38:32 -05:00
parent ba21acdf37
commit 40f528f4ff
2 changed files with 12 additions and 24 deletions

View File

@ -1,11 +1,11 @@
"article","project","timestamp","views" "article","project","timestamp","views"
"201920_coronavirus_pandemic","en.wikipedia","2020033100",831879 "Charles,_Prince_of_Wales","en.wikipedia","2020010100",32880
"2020_coronavirus_pandemic_in_India","en.wikipedia","2020033100",323123 "Tom_Hanks","en.wikipedia","2020010100",23586
"201920_coronavirus_pandemic_by_country_and_territory","en.wikipedia","2020033100",315572 "Boris_Johnson","en.wikipedia","2020010100",12974
"2020_coronavirus_pandemic_in_the_United_States","en.wikipedia","2020033100",290535 "Eurovision_Song_Contest_2020","en.wikipedia","2020010100",7901
"Coronavirus_disease_2019","en.wikipedia","2020033100",211391 "Mike_Pence","en.wikipedia","2020010100",4088
"2020_coronavirus_pandemic_in_Italy","en.wikipedia","2020033100",209908 "Olga_Kurylenko","en.wikipedia","2020010100",3653
"Coronavirus","en.wikipedia","2020033100",188921 "WrestleMania_36","en.wikipedia","2020010100",3484
"USNS_Comfort_(T-AH-20)","en.wikipedia","2020033100",150422 "World_Health_Organization","en.wikipedia","2020010100",3002
"USNS_Comfort_(T-AH-20)","en.wikipedia","2020033100",150422 "Severe_acute_respiratory_syndrome","en.wikipedia","2020010100",2037
"WrestleMania_36","en.wikipedia","2020033100",137637 "Centers_for_Disease_Control_and_Prevention","en.wikipedia","2020010100",909

1 article project timestamp views
2 2019–20_coronavirus_pandemic Charles,_Prince_of_Wales en.wikipedia 2020033100 2020010100 831879 32880
3 2020_coronavirus_pandemic_in_India Tom_Hanks en.wikipedia 2020033100 2020010100 323123 23586
4 2019–20_coronavirus_pandemic_by_country_and_territory Boris_Johnson en.wikipedia 2020033100 2020010100 315572 12974
5 2020_coronavirus_pandemic_in_the_United_States Eurovision_Song_Contest_2020 en.wikipedia 2020033100 2020010100 290535 7901
6 Coronavirus_disease_2019 Mike_Pence en.wikipedia 2020033100 2020010100 211391 4088
7 2020_coronavirus_pandemic_in_Italy Olga_Kurylenko en.wikipedia 2020033100 2020010100 209908 3653
8 Coronavirus WrestleMania_36 en.wikipedia 2020033100 2020010100 188921 3484
9 USNS_Comfort_(T-AH-20) World_Health_Organization en.wikipedia 2020033100 2020010100 150422 3002
10 USNS_Comfort_(T-AH-20) Severe_acute_respiratory_syndrome en.wikipedia 2020033100 2020010100 150422 2037
11 WrestleMania_36 Centers_for_Disease_Control_and_Prevention en.wikipedia 2020033100 2020010100 137637 909

View File

@ -9,34 +9,22 @@ library(scales)
### Import and cleanup one datafile from the observatory ### Import and cleanup one datafile from the observatory
DataURL <- DataURL <-
url("https://covid19.communitydata.science/datasets/wikipedia/digobs_covid19-wikipedia-enwiki_dailyviews-20200401.tsv") url("https://covid19.communitydata.science/datasets/wikipedia/digobs_covid19-wikipedia-enwiki_dailyviews-20200101.tsv")
views <- views <-
read.table(DataURL, sep="\t", header=TRUE, stringsAsFactors=FALSE) read.table(DataURL, sep="\t", header=TRUE, stringsAsFactors=FALSE)
### Alternatively, uncomment and run if working locally with full git
### tree
###
### Identify data source directory and file
## DataDir <- ("../data/")
## DataFile <- ("dailyviews2020032600.tsv")
## related.searches.top <- read.table(paste(DataDir,DataFile, sep=""),
## sep="\t", header=TRUE,
## stringsAsFactors=FALSE)
### Cleanup and do the grouping with functions from the Tidyverse ### Cleanup and do the grouping with functions from the Tidyverse
### (see https://www.tidyverse.org for more info) ### (see https://www.tidyverse.org for more info)
views <- views[,c("article", "project", "timestamp", "views")] views <- views[,c("article", "project", "timestamp", "views")]
views$timestamp <- fct_explicit_na(views$timestamp) views$timestamp <- fct_explicit_na(as.character(views$timestamp))
### Sorts and groups at the same time ### Sorts and groups at the same time
views.by.proj.date <- arrange(group_by(views, project, timestamp), views.by.proj.date <- arrange(group_by(views, project, timestamp),
desc(views)) desc(views))
### Export just the top 10 by pageviews ### Export just the top 10 by pageviews
write.table(head(views.by.proj.date, 10), write.table(head(views.by.proj.date, 10),
file="output/top10_views_by_project_date.csv", sep=",", file="output/top10_views_by_project_date.csv", sep=",",