## ----setup, include=FALSE-----------------------------------------------------
knitr::opts_chunk$set(collapse = TRUE, comment = "#>",
  fig.width = 7, fig.height = 5)
library(stream)
set.seed(1000)

## ----benchmark----------------------------------------------------------------
stream <- DSD_Benchmark(1)
stream

## ----snapshots, fig.height=7--------------------------------------------------
old_par <- par(mfrow = c(2, 2))
for (i in seq_len(4)) {
  plot(stream, n = 250, xlim = c(0, 1), ylim = c(0, 1),
    main = paste("Starting at point", 1 + (i - 1) * 1650))
  arrows(0.15, 0.85, 0.85, 0.15, col = "gray70", lwd = 2)
  arrows(0.15, 0.15, 0.85, 0.85, col = "gray70", lwd = 2)
  if (i < 4) invisible(get_points(stream, n = 1400))
}
par(old_par)

## ----static-pitfall-----------------------------------------------------------
set.seed(0)
stream <- DSD_Memory(DSD_Benchmark(1), n = 5000)

model <- DSC_DBSTREAM(r = 0.05, lambda = 0.01)
update(model, stream, n = 1000)

# new points right after the training data
evaluate_static(model, stream, n = 200,
  measure = c("purity", "crand"), type = "macro", assign = "micro")

# points from late in the stream; the model has not seen the movement
invisible(get_points(stream, n = 3000))
evaluate_static(model, stream, n = 200,
  measure = c("purity", "crand"), type = "macro", assign = "micro")

## ----fixed-stream-------------------------------------------------------------
set.seed(0)
stream <- DSD_Memory(DSD_Benchmark(1), n = 5000)

## ----models-------------------------------------------------------------------
algorithms <- list(
  "Sample + k-means" = DSC_TwoStage(
    micro = DSC_Sample(k = 100, biased = TRUE),
    macro = DSC_Kmeans(k = 2)),
  "Window + k-means" = DSC_TwoStage(
    micro = DSC_Window(horizon = 100, lambda = 0.01),
    macro = DSC_Kmeans(k = 2)),
  "D-Stream" = DSC_DStream(gridsize = 0.1, lambda = 0.01),
  "DBSTREAM" = DSC_DBSTREAM(r = 0.05, lambda = 0.01)
)

## ----evaluation---------------------------------------------------------------
evaluation <- lapply(algorithms, function(model) {
  reset_stream(stream)
  evaluate_stream(model, stream, horizon = 100, n = 5000,
    measure = c("purity", "crand"), type = "macro", assign = "micro")
})
head(evaluation[["DBSTREAM"]])

## ----score-trajectories-------------------------------------------------------
position <- evaluation[[1]][, "points"]
scores <- sapply(evaluation, function(x) x[, "cRand"])

matplot(position, scores, type = "l", lwd = 1,
  xlab = "Points processed", ylab = "Adjusted Rand index")
legend("bottomleft", legend = names(algorithms),
  col = seq_along(algorithms), lty = seq_along(algorithms), cex = 0.8)

## ----score-distributions------------------------------------------------------
boxplot(scores, las = 2, cex.axis = 0.8, ylab = "Adjusted Rand index")
colMeans(scores)

## ----purity-------------------------------------------------------------------
purity <- sapply(evaluation, function(x) x[, "purity"])
colMeans(purity)

## ----lambda-------------------------------------------------------------------
lambdas <- c(0, 0.001, 0.01, 0.1)
lambda_eval <- lapply(lambdas, function(l) {
  reset_stream(stream)
  evaluate_stream(DSC_DBSTREAM(r = 0.05, lambda = l), stream,
    horizon = 100, n = 5000,
    measure = "crand", type = "macro", assign = "micro")
})
lambda_scores <- sapply(lambda_eval, function(x) x[, "cRand"])
colnames(lambda_scores) <- paste("lambda =", lambdas)

matplot(position, lambda_scores, type = "l", lwd = 1,
  xlab = "Points processed", ylab = "Adjusted Rand index")
legend("bottomleft", legend = colnames(lambda_scores),
  col = seq_along(lambdas), lty = seq_along(lambdas), cex = 0.8)
colMeans(lambda_scores, na.rm = TRUE)

## ----moving-animation, eval=knitr::is_html_output() && requireNamespace("gifski", quietly=TRUE) && requireNamespace("animation", quietly=TRUE), fig.show='animate', animation.hook='gifski', interval=0.1, aniopts='loop', dev='png', fig.width=6.4, fig.height=6.8, dpi=100, fig.retina=1, fig.alt='DBSTREAM following two moving clusters'----
set.seed(1000)
animation_stream <- DSD_Benchmark(1)
animation_model <- DSC_DBSTREAM(r = 0.05, lambda = 0.01)

res <- animate_cluster(animation_model, 
                       animation_stream,
                       measure = "cRand",
                       horizon = 100, 
                       n = 5000, 
                       wait = 0,  # for use in a notebook
                       plot.args = list(xlim = c(0, 1), 
                                        ylim = c(0, 1), 
                                        type = "both"))