X-Git-Url: https://code.communitydata.science/covid19.git/blobdiff_plain/ff96d52cb92966dd0c487e6452aeab70773cf3e6..576d882c04b4cc784cd5a6296cb3c3e5aa596d39:/wikipedia/example_analysis/pageview_example.R

diff --git a/wikipedia/example_analysis/pageview_example.R b/wikipedia/example_analysis/pageview_example.R
new file mode 100644
index 0000000..fb5359a
--- /dev/null
+++ b/wikipedia/example_analysis/pageview_example.R
@@ -0,0 +1,52 @@
+### COVID-19 Digital Observatory
+### 2020-03-28
+### 
+### Minimal example analysis file using pageview data
+
+library(tidyverse)
+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")
+
+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)
+
+
+### 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)
+
+
+