From 40f528f4ffac3e04cb12e02cb8d44831e2c57655 Mon Sep 17 00:00:00 2001 From: aaronshaw Date: Thu, 2 Apr 2020 13:38:32 -0500 Subject: [PATCH] revisions to reflect updated example filename and clean comments in R code --- .../output/top10_views_by_project_date.csv | 20 +++++++++---------- wikipedia/example_analysis/pageview_example.R | 16 ++------------- 2 files changed, 12 insertions(+), 24 deletions(-) diff --git a/wikipedia/example_analysis/output/top10_views_by_project_date.csv b/wikipedia/example_analysis/output/top10_views_by_project_date.csv index ce7eb5e..f497584 100644 --- a/wikipedia/example_analysis/output/top10_views_by_project_date.csv +++ b/wikipedia/example_analysis/output/top10_views_by_project_date.csv @@ -1,11 +1,11 @@ "article","project","timestamp","views" -"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 +"Charles,_Prince_of_Wales","en.wikipedia","2020010100",32880 +"Tom_Hanks","en.wikipedia","2020010100",23586 +"Boris_Johnson","en.wikipedia","2020010100",12974 +"Eurovision_Song_Contest_2020","en.wikipedia","2020010100",7901 +"Mike_Pence","en.wikipedia","2020010100",4088 +"Olga_Kurylenko","en.wikipedia","2020010100",3653 +"WrestleMania_36","en.wikipedia","2020010100",3484 +"World_Health_Organization","en.wikipedia","2020010100",3002 +"Severe_acute_respiratory_syndrome","en.wikipedia","2020010100",2037 +"Centers_for_Disease_Control_and_Prevention","en.wikipedia","2020010100",909 diff --git a/wikipedia/example_analysis/pageview_example.R b/wikipedia/example_analysis/pageview_example.R index fb5359a..8d40f00 100644 --- a/wikipedia/example_analysis/pageview_example.R +++ b/wikipedia/example_analysis/pageview_example.R @@ -9,34 +9,22 @@ library(scales) ### Import and cleanup one datafile from the observatory 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 <- 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$timestamp <- fct_explicit_na(views$timestamp) +views$timestamp <- fct_explicit_na(as.character(views$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=",", -- 2.39.5