"article","project","timestamp","views"
- "2019–20_coronavirus_pandemic","en.wikipedia","2020032600",1148284
- "2020_coronavirus_pandemic_in_India","en.wikipedia","2020032600",513901
- "Coronavirus","en.wikipedia","2020032600",397959
- "2020_coronavirus_pandemic_in_the_United_States","en.wikipedia","2020032600",337676
- "2019–20_coronavirus_pandemic_by_country_and_territory","en.wikipedia","2020032600",298603
- "2020_coronavirus_pandemic_in_Italy","en.wikipedia","2020032600",297687
- "Coronavirus_disease_2019","en.wikipedia","2020032600",292272
- "2020_coronavirus_pandemic_in_Spain","en.wikipedia","2020032600",114732
- "2020_coronavirus_pandemic_in_the_United_Kingdom","en.wikipedia","2020032600",111856
- "Anthony_Fauci","en.wikipedia","2020032600",103205
+ "2019–20_coronavirus_pandemic","en.wikipedia","2020033100",831879
+ "2020_coronavirus_pandemic_in_India","en.wikipedia","2020033100",323123
+ "2019–20_coronavirus_pandemic_by_country_and_territory","en.wikipedia","2020033100",315572
+ "2020_coronavirus_pandemic_in_the_United_States","en.wikipedia","2020033100",290535
+ "Coronavirus_disease_2019","en.wikipedia","2020033100",211391
+ "2020_coronavirus_pandemic_in_Italy","en.wikipedia","2020033100",209908
+ "Coronavirus","en.wikipedia","2020033100",188921
+ "USNS_Comfort_(T-AH-20)","en.wikipedia","2020033100",150422
+ "USNS_Comfort_(T-AH-20)","en.wikipedia","2020033100",150422
+ "WrestleMania_36","en.wikipedia","2020033100",137637
### Minimal example analysis file using pageview data
library(tidyverse)
- library(ggplot2)
library(scales)
- ### Import and cleanup data
+ ### Import and cleanup one datafile from the observatory
DataURL <-
- url("https://github.com/CommunityDataScienceCollective/COVID-19_Digital_Observatory/raw/master/wikipedia_views/data/dailyviews2020032600.tsv")
+ url("https://covid19.communitydata.science/datasets/wikipedia/digobs_covid19-wikipedia-enwiki_dailyviews-20200401.tsv")
views <-
read.table(DataURL, sep="\t", header=TRUE, stringsAsFactors=FALSE)
### (see https://www.tidyverse.org for more info)
views <- views[,c("article", "project", "timestamp", "views")]
- views$timestamp <- factor(views$timestamp)
+ views$timestamp <- fct_explicit_na(views$timestamp)
+
### Sorts and groups at the same time
views.by.proj.date <- arrange(group_by(views, project, timestamp),
desc(views))
+
### Export just the top 10 by pageviews
write.table(head(views.by.proj.date, 10),
file="output/top10_views_by_project_date.csv", sep=",",