### 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=",",