iangow

Fast Portfolio Sorts Revisited

library(tidyverse)
library(dtplyr)
library(data.table)
library(bench)
library(DBI)

iangow

Fast Portfolio Sorts with DuckDB/parquet

Load a few packages. Here farr provides system_time().

library(tidyverse)
library(DBI)
library(farr)

iangow

---
title: "Alternative text for figures"
author: Ian D. Gow
date: 2024-04-25
date-format: "D MMMM YYYY"
bibliography: book.bib
format: docx
---

```{r}

iangow

library(stringr)
library(dplyr)

path = getwd()

file_list <-
  tibble(full_path = list.files(path, full.names = TRUE)) |>
  filter(str_detect(full_path, "\\.(qmd)$"))

get_libraries <- function(file) {

iangow

Authors,Author(s) ID,Title,Year,Source title,Volume,Issue,Art. No.,Page start,Page end,Page count,Cited by,DOI,Link,Document Type,Publication Stage,Open Access,Source,EID
"Biehl, H., Bleibtreu, C., Stefani, U.","58793833200;57200334948;54582932500;","The real effects of financial reporting: Evidence and suggestions for future research",2024,"Journal of International Accounting, Auditing and Taxation","54",,"100594","","",,,"10.1016/j.intaccaudtax.2023.100594","https://www.scopus.com/inward/record.uri?eid=2-s2.0-85181527482&doi=10.1016%2fj.intaccaudtax.2023.100594&partnerID=40&md5=34a90aa58abcb7c16af7d1555a2b3bb4",Article,"Final","All Open Access, Hybrid Gold",Scopus,2-s2.0-85181527482
"Collins, D.W., Nguyen, N.Q., Nguyen, T.T.","7403253898;57219198785;57212090956;","Manager sentiment and conditional conservatism",2024,"Journal of Business Finance and Accounting",,,,"","",,,"10.1111/jbfa.12780","https://www.scopus.com/inward/record.uri?eid=2-s2.0-85182461797&doi=10.1111%2fjbfa.12780&partnerID=40&md5=98353953fa

iangow

library(tidyverse)
library(readabs)

raw_abs <- read_abs("5601.0")

candidate_series <-
  raw_abs %>%
  filter(str_detect(series, "Owner occupier"),
         str_detect(series, "External refinancing"),
         str_detect(series, "New loan commitments"),

iangow

Sys.setenv(PGHOST= "wrds-pgdata.wharton.upenn.edu",
           PGPORT= 9737L,
           PGDATABASE = "wrds",
           PGUSER = "iangow")

library(dplyr, warn.conflicts = FALSE)
library(DBI)

db <- dbConnect(RPostgres::Postgres())

iangow

library(dplyr, warn.conflicts = FALSE)
library(DBI)
set.seed(1)
make_dat <- function(nrow=1, ncol=5) {
  df <- 
    cbind.data.frame(name=stringi::stri_rand_strings(n=nrow, length=3), 
                     matrix(data=sample(c(T, F), nrow*ncol, T), ncol=ncol))
  names(df) <- c("name", paste0("v_", 1:ncol))
  df

iangow

See StackOverflow for the original question.

library(data.table)
library(dplyr, warn.conflicts = FALSE)
library(tidyr)
library(DBI)

# Make the data
fruits_tbl <- tibble(fruit_name = c('orange', 'apple',

iangow

install.packages(
  'tidypolars', 
  repos = c('https://etiennebacher.r-universe.dev', getOption("repos"))
)

library(tidypolars)
library(polars)
library(collapse, warn.conflicts = FALSE)
library(dplyr, warn.conflicts = FALSE)
library(DBI)