sfirke

#!/bin/bash

# Requires the sendemail package being installed on the host machine

# Get container health status
healthy=$(docker inspect -f '{{.State.Health.Status}}' airflow-airflow-scheduler-1)

# Check if healthy
if [[ $healthy != "healthy" ]]; then
  # attempt to restart Airflow - the scheduler will stop if the Azure Postgres DB becomes unavailable due to maintenance

sfirke

# Exploring download counts of a single package
x <- cranlogs::cran_downloads("janitor", from = "2016-10-03", to = "2021-03-12")

library(tidyverse)
library(lubridate)
library(tntpr) # from devtools::install_github("tntp/tntpr")

x$wday <- wday(x$date)
x$weekday <- ifelse(x$wday %in% c(1,7), "Weekend", "Weekday")
x$year <- tntpr::date_to_sy(x$date, as.Date("2016-10-02")) # segments into years using a cutoff date

sfirke

sfirke

import pandas as pd
import solaredge
import time

s = solaredge.Solaredge("YOUR-API-KEY")
site_id = YOUR-SITE-ID

# Edit this date range as you see fit
# If querying at the maximum resolution of 15 minute intervals, the API is limited to queries of a month at a time
# This script queries one day at a time, with a one-second pause per day that is polite but probably not necessary

sfirke

library(pacman)
p_load(tidytext, wordcloud, janeaustenr, dplyr)
data("stop_words")

ppdf <- data.frame(prideprejudice, stringsAsFactors = FALSE)

# create a word cloud
create_word_cloud <- function(dat, col_name, exclude = "", max.words = 50, colors = "#034772", ...){
  col <- deparse(substitute(col_name))
  dat %>% 

sfirke

# I want to remove duplicate mpg rows where cylinder is 4
# Split, tinker with the data.frames by name, bind_rows
library(magrittr)
library(dplyr)

mtcars %>%
  split(., .$cyl == 4) %$%
  bind_rows(`FALSE`,
            `TRUE` %>%
              distinct(mpg, .keep_all = TRUE))

sfirke

# From https://stackoverflow.com/questions/45575971/compile-a-vignette-using-devtoolsbuild-vignette-so-that-md-is-kept-in-the-v
# Usage: render_keep_md("tabyls")

render_keep_md <- function(vignette_name){
  # added the "encoding" argument to get the oe character passed through correctly to the resulting .Md
  rmarkdown::render(paste0("./vignettes/",vignette_name, ".Rmd"), clean=FALSE,  encoding = 'UTF-8')
  files_to_remove = paste0("./vignettes/",vignette_name, c(".html",".knit.md",".utf8.md"))
  lapply(files_to_remove, file.remove)
}

sfirke

# Fix dual-row names: if the first row is not NA or containing the word "response", use the one from the first row
# Note: read your SurveyMonkey .csv with readr::read_csv, not read.csv - otherwise this may not work

library(dplyr)
library(janitor)

fix_SM_dual_row_names <- function(dat){
  current_names <- names(dat)
  row_1 <- unlist(dat[1, ])
  

sfirke

library(ggplot2)
library(dplyr)
library(grid)
library(gridExtra)

add_centered_title <- function(p, text, font_size){
  
  title.grob <- textGrob(
    label = text,
    gp = gpar(fontsize = font_size,

sfirke

Package: janitor
Title: Simple Tools for Examining and Cleaning Dirty Data
Version: 0.3.0.9000
Authors@R: c(person("Sam", "Firke", email = "[email protected]", role = c("aut", "cre")),
    person("Chris", "Haid", email = "[email protected]", role = "ctb"),
    person("Ryan", "Knight", email = "[email protected]", role = "ctb"))
Description: The main janitor functions can: perfectly format data.frame column
    names; provide quick one- and two-variable tabulations (i.e., frequency
    tables and crosstabs); and isolate duplicate records. Other janitor functions
    nicely format the tabulation results. These tabulate-and-report functions