Update to Standard SQL.

Change-Id: I5e7aeb7994ff0342bd06f8a5c5de91628e5ff4a3
googlegenomics · Nov 8, 2016 · ff4cc44 · ff4cc44
1 parent b048931
commit ff4cc44
Show file tree

Hide file tree

Showing 13 changed files with 145 additions and 152 deletions.
diff --git a/R/README.md b/R/README.md
@@ -3,7 +3,10 @@
  1. If needed, install the [bigrquery](https://github.com/hadley/bigrquery#authentication) package.
 
    ```
-   install.packages("bigrquery")
+    # The currently released version 0.3.0 does not yet have the parameter
+    # to use Standard SQL instead of Legacy SQL, so we install from github.
+    library(devtools)
+    install_github('rstats-db/bigrquery')
    ```
 
  2. From the R prompt set the working directory and run the script:

diff --git a/R/getting-started.R b/R/getting-started.R
@@ -17,15 +17,15 @@ library(bigrquery)
 
 # Provide a table if you want to query your own data
 DisplayAndDispatchQuery <- function(project, queryUri,
-    table="genomics-public-data:platinum_genomes.variants") {
+    table="genomics-public-data.platinum_genomes.variants") {
   # Read in the SQL from a file or URL.
   querySql <- readChar(queryUri, nchars=1e6)
   # Find and replace the table name placeholder with the table name.
-  querySql <- sub("_THE_TABLE_", table, querySql, fixed=TRUE)
+  querySql <- sub("@THE_TABLE", table, querySql, fixed=TRUE)
   # Display the updated SQL.
   cat(querySql)
   # Dispatch the query to BigQuery for execution.
-  query_exec(querySql, project)
+  query_exec(querySql, project, useLegacySql = FALSE)
 }
 
 GettingStarted <- function(project) {

diff --git a/README.md b/README.md
@@ -23,7 +23,7 @@ SELECT
   COUNT(reference_name) AS num_records,
   COUNT(call.call_set_name) AS num_calls
 FROM
-  [genomics-public-data:platinum_genomes.variants]
+  `genomics-public-data.platinum_genomes.variants` v, v.call call
 GROUP BY
   reference_name
 ORDER BY

diff --git a/RMarkdown/README.md b/RMarkdown/README.md
@@ -11,12 +11,12 @@ line by line in R [literate-programming-demo.R](./literate-programming-demo.R)
 
 [literate-programming-demo.md](./literate-programming-demo.md) was created from [literate-programming-demo.Rmd](./literate-programming-demo.Rmd) via
 ```
-require(knitr)
+library(knitr)
 knit("./literate-programming-demo.Rmd")
 ```
 
 [literate-programming-demo.R](./literate-programming-demo.R) was created from [literate-programming-demo.Rmd](./literate-programming-demo.Rmd) via
 ```
-require(knitr)
+library(knitr)
 purl("./literate-programming-demo.Rmd", documentation=1)
 ```
diff --git a/RMarkdown/figure/viz-1.png b/RMarkdown/figure/viz-1.png
diff --git a/RMarkdown/literate-programming-demo.R b/RMarkdown/literate-programming-demo.R
@@ -1,15 +1,14 @@
-
 ## ----one time setup, eval=FALSE------------------------------------------
-## ### To install the bigrquery package
-## install.packages("bigrquery")
-
+## ### To install the bigrquery package.  The currently released version 0.3.0 does not yet
+## ### have the parameter to use Standard SQL instead of Legacy SQL, so we install from github.
+## library(devtools)
+## install_github('rstats-db/bigrquery')
 
 ## ----initialize, message=FALSE, warning=FALSE----------------------------
 library(bigrquery)
 library(ggplot2)
 library(xtable)
 
-
 ## ----eval=FALSE----------------------------------------------------------
 ## ######################[ CHANGE ME ]##################################
 ## # This codelab assumes that the current working directory is where the Rmd file resides.
@@ -19,58 +18,48 @@ library(xtable)
 ## project <- "YOUR-PROJECT-ID"
 ## #####################################################################
 
-
 ## ------------------------------------------------------------------------
 # By default this codelab runs upon the Illumina Platinum Genomes Variants.
 # Change the table here if you wish to run these queries against a different table.
-theTable <- "genomics-public-data:platinum_genomes.variants"
-
+theTable <- "genomics-public-data.platinum_genomes.variants"
 
 ## ------------------------------------------------------------------------
 DisplayAndDispatchQuery <- function(queryUri) {
   # Read in the SQL from a file or URL.
   querySql <- readChar(queryUri, nchars=1e6)
   # Find and replace the table name placeholder with our table name.
-  querySql <- sub("_THE_TABLE_", theTable, querySql, fixed=TRUE)
+  querySql <- sub("@THE_TABLE", theTable, querySql, fixed=TRUE)
   # Display the updated SQL.
   cat(querySql)
   # Dispatch the query to BigQuery for execution.
-  query_exec(querySql, project)
+  query_exec(querySql, project, useLegacySql = FALSE)
 }
 
-
 ## ----comment=NA----------------------------------------------------------
 result <- DisplayAndDispatchQuery("../sql/sample-variant-counts-for-brca1.sql")
 
-
 ## ----result, comment=NA--------------------------------------------------
 head(result)
 summary(result)
 str(result)
 
-
 ## ----viz, fig.align="center", fig.width=10-------------------------------
 ggplot(result, aes(x=call_set_name, y=variant_count)) +
   geom_bar(stat="identity") + coord_flip() +
   ggtitle("Count of Variants Per Sample")
 
-
 ## ----comment=NA----------------------------------------------------------
 result <- DisplayAndDispatchQuery("../sql/variant-level-data-for-brca1.sql")
 
-
 ## ----echo=FALSE, message=FALSE, warning=FALSE, comment=NA, results="asis"----
 print(xtable(head(result)), type="html", include.rownames=F)
 
-
 ## ----comment=NA----------------------------------------------------------
 result <- DisplayAndDispatchQuery("../sql/sample-level-data-for-brca1.sql")
 
-
 ## ----echo=FALSE, message=FALSE, warning=FALSE, comment=NA, results="asis"----
 print(xtable(head(result)), type="html", include.rownames=F)
 
-
 ## ----provenance, comment=NA----------------------------------------------
 sessionInfo()
 
diff --git a/RMarkdown/literate-programming-demo.Rmd b/RMarkdown/literate-programming-demo.Rmd
@@ -29,8 +29,10 @@ Now let's proceed with a specific example of [literate programming](http://en.wi
 If you have not used the [bigrquery](https://github.com/hadley/bigrquery) package previously, you will likely need to do something like the following to get it installed:
 
 ```{r one time setup, eval=FALSE}
-### To install the bigrquery package
-install.packages("bigrquery")
+### To install the bigrquery package.  The currently released version 0.3.0 does not yet
+### have the parameter to use Standard SQL instead of Legacy SQL, so we install from github.
+library(devtools)
+install_github('rstats-db/bigrquery')
 ```
 
 Next we will load our needed packages into our session:
@@ -54,7 +56,7 @@ project <- "YOUR-PROJECT-ID"
 ```{r}
 # By default this codelab runs upon the Illumina Platinum Genomes Variants.
 # Change the table here if you wish to run these queries against a different table.
-theTable <- "genomics-public-data:platinum_genomes.variants"
+theTable <- "genomics-public-data.platinum_genomes.variants"
 ```
 
 
@@ -64,11 +66,11 @@ DisplayAndDispatchQuery <- function(queryUri) {
   # Read in the SQL from a file or URL.
   querySql <- readChar(queryUri, nchars=1e6)
   # Find and replace the table name placeholder with our table name.
-  querySql <- sub("_THE_TABLE_", theTable, querySql, fixed=TRUE)
+  querySql <- sub("@THE_TABLE", theTable, querySql, fixed=TRUE)
   # Display the updated SQL.
   cat(querySql)
   # Dispatch the query to BigQuery for execution.
-  query_exec(querySql, project)
+  query_exec(querySql, project, useLegacySql = FALSE)
 }
 ```