davidclarance

WITH customers AS (
  SELECT 'Customer1' AS customer_id UNION ALL
  SELECT 'Customer2' AS customer_id UNION ALL
  SELECT 'Customer3' AS customer_id UNION ALL
  SELECT 'Customer4' AS customer_id
)
SELECT 
  c.customer_id, 
  CONVERT(BIGINT, SUBSTRING(HASHBYTES('MD5', c.customer_id), 1, 5)) % 100 AS assigned_bucket	
FROM customers c;

davidclarance

CREATE TABLE IF NOT EXISTS customers AS
SELECT 'Customer1' AS customer_id UNION ALL
SELECT 'Customer2' AS customer_id UNION ALL
SELECT 'Customer3' AS customer_id UNION ALL
SELECT 'Customer4' AS customer_id;


SELECT 
    c.customer_id,
    ('0x' || md5(c.customer_id)[:10])::int64 % 100 as assigned_bucket

davidclarance

import hashlib

probability_assignments = {"Control": 50, "Variant 1": 30, "Variant 2": 20}

random_customer_ids = ["Customer1", "Customer2", "Customer3", "Customer4"]


def get_hash(customer_id):
    hash_object = hashlib.md5(customer_id.encode())
    return hash_object.hexdigest()[:10]

davidclarance

# Function adapted from https://github.com/AfricaBirdData/ABAP/
# Only pulls presence data

library("tidyverse")
library("purrr")

jsonToTibble <- function(jsonfile) {
  out <- jsonfile %>%
    lapply(function(x) {
      x[sapply(x, is.null)] <- NA

davidclarance

# 0. set up ---------------------------------------------------------------

# libraries
library(rabm)
library(tidyverse)
library(geojsonio)
library(broom)
library(ggplot2)
library(gganimate)

davidclarance

library(tidyverse)

files <- list.files(path = "./data/", pattern = "*.csv")

df <- files %>% 
    map(function(x) {
        read_csv(paste0("./data/", x))
    }) %>%
    reduce(rbind)