From: Kaylea Champion Date: Sun, 29 Mar 2020 18:39:32 +0000 (-0700) Subject: Merge pull request #7 from kayleachampion/master X-Git-Url: https://code.communitydata.science/covid19.git/commitdiff_plain/a86c3a97eec2b5e6d2e2762518d83879f1cfec45?hp=317c32cdb5b5c6eb923a242b645023876d14fee8 Merge pull request #7 from kayleachampion/master cleanup with merge --- diff --git a/transliterations/analysis/output/top5_queries_per_term_per_date.csv b/transliterations/analysis/output/top5_queries_per_term_per_date.csv index 5ce1aa7..83b5aff 100644 --- a/transliterations/analysis/output/top5_queries_per_term_per_date.csv +++ b/transliterations/analysis/output/top5_queries_per_term_per_date.csv @@ -1,6 +1,11 @@ "term","date","query.1","query.2","query.3","query.4","query.5" -"coronavirus","2020-03-27",coronavirus update,corona,coronavirus symptoms,news coronavirus,coronavirus cases -"covid-19","2020-03-27",covid-19 coronavirus,coronavirus,covid,covid-19 cases,covid 19 -"covid-19 pandemic","2020-03-27",coronavirus,covid-19 coronavirus pandemic,coronavirus pandemic,who,is covid-19 a pandemic -"covid19","2020-03-27",covid,covid 19,coronavirus covid19,coronavirus,covid19 cases -"sars-cov-2","2020-03-27",coronavirus,coronavirus sars-cov-2,covid-19,covid-19 sars-cov-2,sars +"coronavirus",2020-03-27,coronavirus update,corona,coronavirus symptoms,news coronavirus,coronavirus cases +"covid-19",2020-03-27,covid-19 coronavirus,coronavirus,covid,covid-19 cases,covid 19 +"covid-19 pandemic",2020-03-27,coronavirus,covid-19 coronavirus pandemic,coronavirus pandemic,who,is covid-19 a pandemic +"covid19",2020-03-27,covid,covid 19,coronavirus covid19,coronavirus,covid19 cases +"sars-cov-2",2020-03-27,coronavirus,coronavirus sars-cov-2,covid-19,covid-19 sars-cov-2,sars +"coronavirus",2020-03-28,coronavirus update,corona,coronavirus symptoms,news coronavirus,coronavirus cases +"covid-19",2020-03-28,coronavirus,coronavirus covid-19,covid,covid-19 cases,covid 19 +"covid-19 pandemic",2020-03-28,coronavirus pandemic,coronavirus,covid-19 coronavirus pandemic,is covid-19 a pandemic,who pandemic +"covid19",2020-03-28,covid,covid 19,coronavirus covid19,coronavirus,covid19 cases +"sars-cov-2",2020-03-28,coronavirus sars-cov-2,coronavirus,sars-cov-2 covid-19,covid-19,sars diff --git a/transliterations/analysis/related_searches_example.R b/transliterations/analysis/related_searches_example.R index 2576d4a..e1197b6 100644 --- a/transliterations/analysis/related_searches_example.R +++ b/transliterations/analysis/related_searches_example.R @@ -3,16 +3,24 @@ ### ### Minimal example analysis file using trending search data -### Identify data source directory and file -DataDir <- ("../data/output/") -DataFile <- ("related_searches_top.csv") - ### Import and cleanup data -related.searches.top <- read.table(paste(DataDir,DataFile, - sep=""), + +DataURL <- + url("https://github.com/CommunityDataScienceCollective/COVID-19_Digital_Observatory/blob/master/transliterations/data/output/related_searches_top.csv") + +related.searches.top <- read.table(DataURL, sep=",", header=TRUE, stringsAsFactors=FALSE) +### Alternatively, uncomment and run if working locally with full git tree +### Identify data source directory and file +## DataDir <- ("../data/output/") +## DataFile <- ("related_searches_top.csv") + +## related.searches.top <- read.table(paste(DataDir,DataFile, sep=""), +## sep=",", header=TRUE, +## stringsAsFactors=FALSE) + ### Aggregate top 5 search queries by term/day top5.per.term.date <- aggregate(query ~ term + date, data=related.searches.top, diff --git a/wikipedia_views/analysis/output/top10_views_by_project_date.csv b/wikipedia_views/analysis/output/top10_views_by_project_date.csv new file mode 100644 index 0000000..796af10 --- /dev/null +++ b/wikipedia_views/analysis/output/top10_views_by_project_date.csv @@ -0,0 +1,11 @@ +"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 diff --git a/wikipedia_views/analysis/pageview_example.R b/wikipedia_views/analysis/pageview_example.R new file mode 100644 index 0000000..8a7aba3 --- /dev/null +++ b/wikipedia_views/analysis/pageview_example.R @@ -0,0 +1,51 @@ +### COVID-19 Digital Observatory +### 2020-03-28 +### +### Minimal example analysis file using pageview data + +library(tidyverse) +library(ggplot2) +library(scales) + +### Import and cleanup data + +DataURL <- + url("https://github.com/CommunityDataScienceCollective/COVID-19_Digital_Observatory/raw/master/wikipedia_views/data/dailyviews2020032600.tsv") + +views <- + 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 +### (see https://www.tidyverse.org for more info) + +views <- views[,c("article", "project", "timestamp", "views")] +views$timestamp <- factor(views$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=",", + row.names=FALSE) + +### A simple visualization +p <- ggplot(data=views.by.proj.date, aes(views)) + +## Density plot with log-transformed axis +p + geom_density() + scale_x_log10(labels=comma) + + +