Merge pull request #16 from aaronshaw/master

[covid19.git] / wikipedia / example_analysis / pageview_example.R

diff --git a/wikipedia/example_analysis/pageview_example.R b/wikipedia/example_analysis/pageview_example.R
index fb5359aa64c856bec978b1a5bcfc9712de82c907..8d40f00719ad29054c3f3cc841ab2f2c300f16fd 100644 (file)
--- 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=",",