tvladeck

korresp_som <- trainSOM(a, scaling = "chi2", type = "korresp", dimension = c(2,2))

row_num <- korresp_som$parameters$the.grid$dim[[1]]
col_num <- korresp_som$parameters$the.grid$dim[[2]]

korresp_clusters <- 
  korresp_som$clustering %>% 
  as.data.frame %>% 
  set_colnames(c("cluster")) %>% 
  mutate(entity = rownames(.)) %>% 

tvladeck

# normalize sequences
tx_sample <-
  tx_sample %>%
  mutate(
    order_date = order_date - first_date
  )
  
# create TraMineRextras object
tx_seq <- seqecreate(
  id = tx_sample$customer_id,

tvladeck

library(corrplot)

playstation_data <- matrix(0, nrow = 6, ncol = 5)
rownames(playstation_data) <- c("Connoisseurs", "Connectors", "Rivals", "Indulgers", "Escapers", "Dabblers")
colnames(playstation_data) <- c("Periphery", "Hit", "Mid-Core", "Core", "Occasionals")

playstation_data[1, ] <- c(10, 5, 3, 101, 18)
playstation_data[2, ] <- c(38, 10, 72, 18, 68)
playstation_data[3, ] <- c(10, 110, 22, 28, 15) 
playstation_data[4, ] <- c(80, 10, 9, 44, 70)

tvladeck

# draw from an exponential distribution with mean 90
payment_failures  <- rexp(1000, rate = 1/90)

# number of payment failures after 90 days
pf_90 <- (payment_failures < 90) %>% sum

# number of payment failures after 60 days (assuming same distribution)
pf_60 <- (payment_failures < 60) %>% sum

# number of 90 day payment failures observed relative to 60 day payment failures

tvladeck

# We simulate draws from two different timing distributions representing different processes
payment_failures  <- rexp(1000, rate = 1/90)
intentional_churn <- rexp(1000, rate = 1/120)

### proportion of payment failures to intentional churn at 90 day cutoff

pf_90 <- (payment_failures < 90) %>% sum
if_90 <- (intentional_churn < 90) %>% sum 

pf_90 / (if_90 + pf_90)

tvladeck

set.seed(20180226)
block_mining_times <- rpois(1000, 10) # lambda = 10
max_time <- sum(block_mining_times)
cumulative_times <- cumsum(block_mining_times)

rand_times <- runif(1000, min = 0, max = max_time)

deltas_between_blocks <- 
  rand_times %>% 
  sapply(function(t){

tvladeck

cat orders_2018-05-01.csv | head | sed -e 's/,,/, ,/g' | column -s, -t | less -#5 -N -S

tvladeck

library(foreach)
library(doParallel)
library(tidyverse)
library(magrittr)

registerDoParallel(40)

runs <- 100

N_test <- c(250, 300, 350, 400, 500, 600) # sample in each group

tvladeck

library(ca)
library(ggplot2)
library(ggrepel)
library(stringr)
library(scales)
library(magrittr)
library(factoextra)

repel_ca_from_table <- 
  function(

tvladeck

library(RColorBrewer)
library(fields) #to use designer.colors
library(reshape2)
library(dplyr)


gradient_heatmap <- 
  function(
    df, 
    num_percentiles = 10,