iangow

Setting Up a Python Environment for Quarto + Jupyter Using uv and .venv

This guide explains how to:

1. Install uv
2. Create a project with pyproject.toml
3. Use a project-local .venv
4. Add dependencies to the project
5. Sync the environment
6. Register the environment as a Jupyter kernel

iangow

library(dplyr, warn.conflicts = FALSE)
library(tidyr)
library(wrds)
#> ── Checking WRDS credentials ───────────────────────────────────── wrds 0.0.1 ──
#> ✔ Credentials found for user iangow
library(farr, warn.conflicts = FALSE)

db <- wrds_connect()

iangow

library(readxl)
library(httr2)
library(tidyverse)

# Define file URL and destination path
url <- "https://www.jobsandskills.gov.au/sites/default/files/2024-12/occupation_profiles_data_-_november_2024.xlsx"
destfile <- "occupation_profiles_data.xlsx"

# Create request with headers

iangow

Setting up the ODBC driver on MacOS

The following instructions improve on those here by avoiding the need to:

a. Compile the Homebrew binary itself
b. Set the path for the Homebrew binary

Steps

1. Install HomeBrew using the .pkg file available here.

iangow

libname home '.';

PROC SQL;        
  CREATE TABLE crsp_dates AS
  SELECT date, intnx('MONTH', date, 0, 'BEGINNING') AS month format=yymmdd10.
  FROM crsp.msi
  ORDER BY date;
QUIT;

DATA crsp_dates;

iangow

libname home '.';

PROC SQL;        
  CREATE TABLE crsp_dates AS
  SELECT date, intnx('MONTH', date, 0, 'BEGINNING') AS month format=yymmdd10.
  FROM crsp.msi
  ORDER BY date;
QUIT;

DATA crsp_dates;

iangow

library(farr)
library(tidyverse)

original <- read_csv("~/Downloads/WalkerDataCodeMar2021/original.csv")

original |>
  group_by(fyear) |>
  summarize(auc = auc(prob, aaer), .groups = "drop") |>
  mutate(avg_auc = mean(auc))

iangow

install.packages(c("formatR", "markdown", "tinytex", "downlit", "xml2"))

iangow

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

db <- dbConnect(duckdb::duckdb())

dbExecute(db, "ATTACH '' AS pg (TYPE POSTGRES);")

dbExecute(db, "COPY pg.crsp.dsf FROM '/Users/iangow/Library/CloudStorage/Dropbox/pq_data/crsp/dsf.parquet'")

create_view <- function(conn, table, schema = "", 

iangow

library(httr2)         # request(), req_*(), resp_body_html()
library(rvest)         # html_elements(), html_table()
library(tidyverse)

extract_team_ids <- function(link_text) {
  matches <- str_match(link_text, '<a href="teams/(.*)_idx.html">(.*)</a>')
  team_id <- matches[, 2]
  team_name <- matches[, 3]
  tibble(team_id, team_name)
}