vankesteren

# waveform
library(animation)
library(firatheme) # devtools::install_github(vankesteren/firatheme)

n <- 20
mu <- seq(-5, 5, len = n)
sg <- rgamma(20, 1.5, 0.5)
xx <- seq(-10, 10, len = 1000)
fills <- paste0(firaPalette(n), "88")

vankesteren

# Try-out of Hastie, Tibshirani, & Friedman (ESL, 2009) p.659

# Generate high-dimensional dataset
beta <- -100:100/100
X <- matrix(rnorm(100*201), 100)
y <- X%*%beta + rnorm(100, 0, sqrt(crossprod(beta)))

# Ridge estimates
bhat_ridge <- solve(crossprod(X) + diag(rep(.1, 201)), crossprod(X, y))

vankesteren

#
# Copyright (C) 2018 University of Amsterdam
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 2 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of

vankesteren

view_html <- function(path, height = "maximize") {
    tf <- tempfile(fileext = ".html")
    file.copy(path, tf)
    rstudioapi::viewer(tf, height = height)
}

vankesteren

pcks <- c("ISLR", "tidyverse", "haven", "readxl", "MASS", "glmnet", "splines", 
          "class", "pROC", "rpart", "rpart.plot", "randomForest", "ca", 
          "igraph")

ip <- rownames(installed.packages())

if (!all(pcks %in% ip)) {
  to_install <- pcks[!pcks %in% ip]
  message("Package(s) missing. \n",
          "Please install the following packages: ", 

vankesteren

library(tidyverse)

lights_dat <- read_csv("https://ckan.dataplatform.nl/dataset/83402c68-1c05-4aa5-ab28-2e99d2bc2261/resource/dc10e0ac-351a-49b6-b3db-d0152c29dc02/download/paal-20180906.csv")

pp <- 
  lights_dat %>% 
  filter(latitude > 50) %>% 
  ggplot(aes(x = longitude, y = latitude)) + 
  geom_point(alpha = 0.03, fill = "#FAFAAB", stroke = 0, pch = 21, size = 1.6) +
  geom_point(alpha = 0.8,  fill = "#FAFAAB", stroke = 0, pch = 21, size = 0.2) +

vankesteren

# Use the great rayshader package (www.rayshader.com)
library(rayshader)

# Download data
zip_loc <- tempfile() 
download.file("http://geodata.nationaalgeoregister.nl/ahn1/extract/ahn1_100m/ahn1_100.tif.zip", 
              zip_loc)
local_tif <- raster::raster(unzip(zip_loc, "ahn_100.tif"))
unlink(zip_loc)

vankesteren

# Randomly generate some data
S <- rWishart(1, 10, diag(10))[,,1] / 10
X <- MASS::mvrnorm(100, rep(0, 10), S)
b <- runif(10, -1, 1)
y <- X %*% b + rnorm(100, sd = sqrt(b %*% S %*% b))


# all the interesting regression quantities!
n    <- nrow(X)                       # sample size
p    <- ncol(X)                       # parameters in model matrix

vankesteren

# convolutions
convolve <- function(x, kernel) {
  size  <- length(kernel)
  x_pad <- c(rep(0, size - 1), x)
  out   <- rep(0, length(x))
  for (i in 1:length(x)) {
    out[i] <- x_pad[i:(i + (size - 1))] %*% kernel
  }
  return(out)
}

vankesteren

# Gradient descent with autodiff for linear regression
using Zygote

# Data
X = randn(1000, 10)
b = (1:10)
y = X * b + randn(1000)

# MSE for linear model
function mse(bhat)