fixed typo in description of view scraper

[covid19.git] / transliterations / analysis / related_searches_example.R

diff --git a/transliterations/analysis/related_searches_example.R b/transliterations/analysis/related_searches_example.R
index 19ddfc76de29de4ebf6bc8b4f79f7ad871ab4a2f..e1197b62796ba05814eda58ea8b93a203cd43df4 100644 (file)
--- a/transliterations/analysis/related_searches_example.R
+++ b/transliterations/analysis/related_searches_example.R
@@ -3,23 +3,31 @@
 ### 
 ### Minimal example analysis file using trending search data
 
 ### 
 ### 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
 ### 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) 
 
                            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,
                                 head, 5)
 
 ## Might cleanup a bit for further analysis or visualization...
 ### Aggregate top 5 search queries by term/day
 top5.per.term.date <- aggregate(query ~ term + date,
                                 data=related.searches.top,
                                 head, 5)
 
 ## Might cleanup a bit for further analysis or visualization...

-top5.per.term.date$date <- asDate(top5.per.term.date$date)
+top5.per.term.date$date <- as.Date(top5.per.term.date$date)

 
 ### Export
 write.table(top5.per.term.date,
 
 ### Export
 write.table(top5.per.term.date,