simonthompson99

# batch renames files with hyphens to underscores
for i in `ls *-*`
do
NEW=`echo $i|tr '-' '_'`
git mv $i $NEW
done

# or do sed on the filename with multiple options
for i in `ls *.sql`
do

simonthompson99

# run three times a day (between 9am and 4pm), Mon - Fri
H H(9-16)/3 * * 1-5

simonthompson99

-- pg dump of a specific schema from metrics db on index
pg_dump metrics -h 10.1.24.39 -p 5433 -U cdt_user -n <schema_name> > <out>.sql

-- select a random percentage of rows of table
select * from my_table tablesample bernoulli(<percentage in numbers, e.g. 10>)
-- or to select random rows in query
select * from query order by random() limit 100

-- useful aggregate functions to use with GROUP BY
string_agg(<field>, ';') /* equivalent to R's paste(<field>, collapse = ";") */

simonthompson99

# open up current file (useful for opening markdowns in chrome)
:!open %

# search across folder tree for test
# From within buffer at top most level of folder tree to search
:grep '<searchstring>' **/*.<fileending to search> or grep -R <searchstring> . to recursievely search all files in project
:copen to open the quickfix list, and :ccl to close it
:cn to go to the next on the quickfix list
:cp to go to the previous
# OR

simonthompson99

# rename repository
# change name on remote repo, copy ssh url from the clone button on main page
mv <old folder> <new folder>
git remote set-url origin git@github.com:genomicsengland/<new repo name>

# compare local copy of file to remote
git fetch origin
git diff origin/master -- <path to file>

# list all branches

simonthompson99

#-- convert pdf into single page png images with p01 numbering
for file in *.pdf; do
    echo 'converting $file'
    convert -density 400 -colorspace sRGB $file -scene 1 -alpha off ${file%.pdf}_p%02d.png;
done

simonthompson99

-- on query
pg_dump -h 10.1.24.39 -p 5433 --schema <schema-name> <db_name> > ~/scratch/<dump_file>.sql
 
-- local
cd ~/scratch
scp sthompson@10.1.24.38:~/scratch/<dump_file>.sql .
sed -i .bak 's/OWNER TO cdt_user;/OWNER TO simon;/g' <dump_file>.sql
psql -d <target_db> -h localhost -p 5432 -U simon < <dump_file>.sql

simonthompson99

#-- get latest rds file from filelisting with datestamps
get_latest_rds <- function(d, kw){
    ls <- list.files(d, pattern = "*.rds", full.names = T)
    f <- sort(ls[grepl(kw, ls)], decreasing = T)[1]
    d <- readRDS(f)
    cat(paste("Fetched", f, "--", nrow(d), "rows", ncol(d), "columns\n"))
    return(d)
}

simonthompson99

#-- convert df to tibble
tbl <- tbl_df(df)

#-- aggregate by multiple groups
d <- df %>% filter(<filter_conditional>) %>%
    group_by(<grouping_variable1>, ...) %>%
    summarise(<out_var> = <out_var_function_call>,...)

#-- get crosstabs table and replace low counts
tab_ldp <- d %>%

simonthompson99

1. download old .tar.gz from the package archive
2. run R CMD INSTALL .tar.gz or to get the dependencies installed run install.packages(".tar.gz", repos = NULL, type = "source")