thisisnic

# Detect invalid timezones

all_names <- tzdb::tzdb_names()

bad_names <- c(
  all_names[startsWith(all_names, "US/")],
  all_names[!stringr::str_detect(all_names, "/")]
)

all_names[map_lgl(all_names, ~!.x %in% bad_names)]

thisisnic

library(arrow)
#> Some features are not enabled in this build of Arrow. Run `arrow_info()` for more information.
#> 
#> Attaching package: 'arrow'
#> The following object is masked from 'package:utils':
#> 
#>     timestamp
library(dplyr)
#> 

thisisnic

library(arrow)
#> Some features are not enabled in this build of Arrow. Run `arrow_info()` for more information.
#> 
#> Attaching package: 'arrow'
#> The following object is masked from 'package:utils':
#> 
#>     timestamp
library(dplyr)
#> 

thisisnic

``` r
library(arrow)
library(dplyr)
library(stringr)

tf <- tempfile()

# values to save - note the space after the final new line
dodgy_vals <- "x,y\n0,1\n ,4"
cat(dodgy_vals)

thisisnic

# query details copied from https://github.com/voltrondata-labs/arrowbench/blob/main/R/tpch-queries.R
query_results <- lineitem_db %>%
      select(l_shipdate, l_returnflag, l_linestatus, l_quantity,
           l_extendedprice, l_discount, l_tax) %>%
    # kludge, should be: filter(l_shipdate <= "1998-12-01" - interval x day) %>%
    # where x is between 60 and 120, 90 is the only one that will validate.
    filter(l_shipdate <= as.Date("1998-09-02")) %>%
    select(l_returnflag, l_linestatus, l_quantity, l_extendedprice, l_discount, l_tax) %>%
    group_by(l_returnflag, l_linestatus) %>%
    summarise(

thisisnic

---
title: "Apache Arrow R Questions on Stack Overflow"
format: html
---

```{r}
#| label: load-packages-and-code
#| include: false
library(httr)
library(dplyr)

thisisnic

#!/bin/bash
set -e

SOURCE_DIR='<path_to_project_root_goes_here>'

# Find all .R files which have been staged via git add
FILES_TO_STYLE=$(git diff --name-only --staged | grep "\.R")

for FILE in ${FILES_TO_STYLE[@]}
do

thisisnic

# checkout the branch you're working on
git checkout my-branch

# fetch all branches from the upstream repo
git fetch upstream

# rebase your changes on top of the upstream master branch
git rebase upstream/master

# force push your changes to your branch

thisisnic

Instructions condensed from https://stackoverflow.com/questions/62613253/downloading-all-jupyter-notebooks-from-coursera-tar-size-exeeding-100mb

# Click on the 'jupyter' logo in any notebook for that course to be taken to the working directory that jupyter is running on.

# Click "new" (on the right) and then "terminal" and run the following commands

# navigate to parent directory
cd ..

# compress all your notebooks and other associated files

thisisnic

library(shinyjqui)
library(shiny)

show_columns <- c('column a','column b','column c','column d','column e','column f','column g','column h','column i','column j','column k','column l','column m','column n','column o','column p')
hidden_columns <- c('column q','column r','column s','column t','column u','column v','column w','column x','column y','column z')

ui <- fluidPage(

  column(
    width = 12,