Merge pull request #14 from aaronshaw/aaronshaw-master

pointing at updated data url, adding explicit NA handling to factor, …
This commit is contained in:
Aaron Shaw 2020-04-01 16:58:02 -05:00 committed by GitHub
commit 34f8b9a23e
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 15 additions and 14 deletions

View File

@ -1,11 +1,11 @@
"article","project","timestamp","views" "article","project","timestamp","views"
"201920_coronavirus_pandemic","en.wikipedia","2020032600",1148284 "201920_coronavirus_pandemic","en.wikipedia","2020033100",831879
"2020_coronavirus_pandemic_in_India","en.wikipedia","2020032600",513901 "2020_coronavirus_pandemic_in_India","en.wikipedia","2020033100",323123
"Coronavirus","en.wikipedia","2020032600",397959 "201920_coronavirus_pandemic_by_country_and_territory","en.wikipedia","2020033100",315572
"2020_coronavirus_pandemic_in_the_United_States","en.wikipedia","2020032600",337676 "2020_coronavirus_pandemic_in_the_United_States","en.wikipedia","2020033100",290535
"201920_coronavirus_pandemic_by_country_and_territory","en.wikipedia","2020032600",298603 "Coronavirus_disease_2019","en.wikipedia","2020033100",211391
"2020_coronavirus_pandemic_in_Italy","en.wikipedia","2020032600",297687 "2020_coronavirus_pandemic_in_Italy","en.wikipedia","2020033100",209908
"Coronavirus_disease_2019","en.wikipedia","2020032600",292272 "Coronavirus","en.wikipedia","2020033100",188921
"2020_coronavirus_pandemic_in_Spain","en.wikipedia","2020032600",114732 "USNS_Comfort_(T-AH-20)","en.wikipedia","2020033100",150422
"2020_coronavirus_pandemic_in_the_United_Kingdom","en.wikipedia","2020032600",111856 "USNS_Comfort_(T-AH-20)","en.wikipedia","2020033100",150422
"Anthony_Fauci","en.wikipedia","2020032600",103205 "WrestleMania_36","en.wikipedia","2020033100",137637

1 article project timestamp views
2 2019–20_coronavirus_pandemic en.wikipedia 2020032600 2020033100 1148284 831879
3 2020_coronavirus_pandemic_in_India en.wikipedia 2020032600 2020033100 513901 323123
4 Coronavirus 2019–20_coronavirus_pandemic_by_country_and_territory en.wikipedia 2020032600 2020033100 397959 315572
5 2020_coronavirus_pandemic_in_the_United_States en.wikipedia 2020032600 2020033100 337676 290535
6 2019–20_coronavirus_pandemic_by_country_and_territory Coronavirus_disease_2019 en.wikipedia 2020032600 2020033100 298603 211391
7 2020_coronavirus_pandemic_in_Italy en.wikipedia 2020032600 2020033100 297687 209908
8 Coronavirus_disease_2019 Coronavirus en.wikipedia 2020032600 2020033100 292272 188921
9 2020_coronavirus_pandemic_in_Spain USNS_Comfort_(T-AH-20) en.wikipedia 2020032600 2020033100 114732 150422
10 2020_coronavirus_pandemic_in_the_United_Kingdom USNS_Comfort_(T-AH-20) en.wikipedia 2020032600 2020033100 111856 150422
11 Anthony_Fauci WrestleMania_36 en.wikipedia 2020032600 2020033100 103205 137637

View File

@ -4,13 +4,12 @@
### Minimal example analysis file using pageview data ### Minimal example analysis file using pageview data
library(tidyverse) library(tidyverse)
library(ggplot2)
library(scales) library(scales)
### Import and cleanup data ### Import and cleanup one datafile from the observatory
DataURL <- 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 <- views <-
read.table(DataURL, sep="\t", header=TRUE, stringsAsFactors=FALSE) read.table(DataURL, sep="\t", header=TRUE, stringsAsFactors=FALSE)
@ -30,12 +29,14 @@ views <-
### (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$timestamp <- factor(views$timestamp) views$timestamp <- fct_explicit_na(views$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=",",