hannesdatta

# Function scans global environment for occurence of regular expression (`regex`), 
# and saves all objects in `filename`.
save_by_regex <- function(regex, filename) {
  lscall = ls(envir=.GlobalEnv)
  stuff_to_save = grep(regex, lscall, value=T)
  if (length(stuff_to_save)>0) {
    cat('saving...\n')
    cat(paste0('(', paste0(stuff_to_save, collapse=', '), ')\n'))
    save(list=stuff_to_save , file = filename)
    cat('...done.\n') } else {

hannesdatta

# Code snippet to compare the outcome of different regressions
# - showing regression results in a publication-ready table
# - conducting a statistical test for differences in coefficients using the delta method

## Let's generate some data
set.seed(1234) # initialize random number generator
y= runif(1000)
x1= runif(1000)
x2= runif(1000)
x3= runif(1000)

hannesdatta

#' Draw from variance-covariance matrix, given correlation rho (buggy!)
#'
#' The purpose of this function is to generate draws from
#' the variance-covariance matrix, given a specific correlation structure.
#' In particular, a four-dimensional correlation structure is drawn, in which
#' the first dimension (sales) is correlated with the remaining 3 dimensions
#' (marketing mix instruments) with *rho*, and the correlations among the 3 dimensions
#' (marketing mix instruments) is zero (or about zero).
#'
#' @param rho Correlation between the first dimension, and the remaining three dimensions

hannesdatta

################################
# FIND AND INSTALL R PACKAGES  #
#                              #
#                              #
# Searches source code for     #
# references to packages,      #
# and installs all             #
# uninstalled packages.        #
#                              #
# Put this script in the       #

hannesdatta

# Load packages
library(dplyr)
library(tidyverse)
library(writexl)

#########
# Input #
#########

## Open data

hannesdatta

# Load packages
library(tidyverse)
library(reshape2)

# DOWNLOAD DATA 

## Function to download data and save as CSV
download_data <- function(url, filename){
  download.file(url = url, destfile = paste0(filename, ".csv"))
}

hannesdatta

library(data.table)

time = 1:200
stores = c('ah', 'jumbo', 'super')
panelists = paste0('id', 1:1000)

store_id = rep(stores, each=length(time))
time_id = rep(time, length(stores))
year = floor(time_id/52)+1
  

hannesdatta

# HOW TO MANAGE MEMORY ISSUES IN R?

# A common problem of data- and computation-intensive projects
# in R is memory management.

# Suppose you would like to estimate a series of models,
# but estimating all of them would exceed your available
# memory.
#
# One solution could be to have individual R scripts

hannesdatta

# Looping
for (i in 1:10) {
  print(i)
}

# Using looping with return values (i.e., to "save" stuff to carry on working)
results = lapply(1:10, function(x) x*2)

# Demo to download all of Europe's listing data to R
library(googledrive)

hannesdatta

# Cleanup, wiping the (sub)directories output/temp/audit

wipe: 
	R -e "unlink('../../gen/data-preparation/output/*.*')"
	R -e "unlink('../../gen/data-preparation/temp/*.*')"
	R -e "unlink('../../gen/data-preparation/audit/*.*')"