Merge pull request #9 from aaronshaw/master

minimal analysis example with pageview data

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 (file)
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 (file)
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)
+
+
+