## ----include = FALSE----------------------------------------------------------
# Evaluate chunks only where the ducklake DuckDB extension is already
# installed. The probe never downloads anything, so building this vignette
# needs no network access.
ducklake_available <- ducklake::ducklake_extension_available()
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  eval = ducklake_available
)
# Use a unique temp directory for this vignette to avoid conflicts during R CMD check
vignette_temp_dir <- file.path(tempdir(), "time_travel_vignette")
dir.create(vignette_temp_dir, showWarnings = FALSE, recursive = TRUE)
knitr::opts_knit$set(root.dir = vignette_temp_dir)

## ----setup, message=FALSE-----------------------------------------------------
library(ducklake)
library(dplyr)

## ----create-datalake----------------------------------------------------------
# Install the ducklake extension (required once per system)
# The ducklake extension only needs installing once per machine:
# install_ducklake()

# Create or attach to a data lake
attach_ducklake(
  ducklake_name = "time_travel_demo",
  lake_path = vignette_temp_dir
)

# Create initial table with the mtcars dataset
with_transaction(
  create_table(mtcars, "cars"),
  author = "Data Engineer",
  commit_message = "Initial load of mtcars dataset"
)

# Verify the table was created
get_ducklake_table("cars") |>
  select(mpg, cyl, hp, wt) |>
  head()

## ----version1-----------------------------------------------------------------
get_ducklake_table("cars") |>
  summarise(
    n_cars = n(),
    avg_mpg = mean(mpg, na.rm = TRUE),
    avg_hp = mean(hp, na.rm = TRUE)
  )

## ----version2-----------------------------------------------------------------
# Update mpg for high-performance cars (5% reduction)
with_transaction(
  get_ducklake_table("cars") |>
    mutate(mpg = if_else(hp > 200, mpg * 0.95, mpg)) |>
    replace_table("cars"),
  author = "Data Analyst",
  commit_message = "Adjust MPG for high-performance vehicles"
)

# Check the updated averages
get_ducklake_table("cars") |>
  summarise(
    n_cars = n(),
    avg_mpg = mean(mpg, na.rm = TRUE),
    avg_hp = mean(hp, na.rm = TRUE)
  )

## ----version3-----------------------------------------------------------------
with_transaction(
  get_ducklake_table("cars") |>
    mutate(
      efficiency_class = case_when(
        mpg >= 25 ~ "High",
        mpg >= 20 ~ "Medium",
        TRUE ~ "Low"
      )
    ) |>
    replace_table("cars"),
  author = "Data Analyst",
  commit_message = "Add efficiency classification"
)

# View the new classification
get_ducklake_table("cars") |>
  count(efficiency_class) |>
  arrange(desc(n))

## ----version4-----------------------------------------------------------------
with_transaction(
  get_ducklake_table("cars") |>
    mutate(
      efficiency_class = case_when(
        mpg >= 30 ~ "High",
        mpg >= 20 ~ "Medium",
        TRUE ~ "Low"
      )
    ) |>
    replace_table("cars"),
  author = "Senior Analyst",
  commit_message = "Correct efficiency classification thresholds"
)

# View the corrected classification
get_ducklake_table("cars") |>
  count(efficiency_class) |>
  arrange(desc(n))

## ----list-snapshots-----------------------------------------------------------
# View all available versions of the table
snapshots <- list_table_snapshots("cars")
snapshots

## ----query-version2-----------------------------------------------------------
# Get version 2 (after MPG adjustment, before classification)
get_ducklake_table_version("cars", version = 2) |>
  select(mpg, cyl, hp, wt) |>
  head()

# Notice: no efficiency_class column yet

## ----query-version3-----------------------------------------------------------
# Get version 3 (with initial classification)
get_ducklake_table_version("cars", version = 3) |>
  select(mpg, efficiency_class) |>
  count(efficiency_class)

## ----timestamp-query----------------------------------------------------------
# Get the timestamp from version 2
version2_timestamp <- snapshots |>
  filter(schema_version == 2) |>
  pull(snapshot_time)

# Query data as it existed at that time
# Note: Add 1 second to ensure we query AFTER the snapshot was created
get_ducklake_table_asof("cars", version2_timestamp + 1) |>
  summarise(
    avg_mpg = mean(mpg, na.rm = TRUE)
  )

## ----compare-versions---------------------------------------------------------
# Get MPG values from version 1 (original) and version 2 (after adjustment)
original <- get_ducklake_table_version("cars", version = 1) |>
  select(mpg) |>
  collect() |>
  mutate(version = "Original")

adjusted <- get_ducklake_table_version("cars", version = 2) |>
  select(mpg) |>
  collect() |>
  mutate(version = "Adjusted")

# Combine and compare
bind_rows(original, adjusted) |>
  group_by(version) |>
  summarise(
    avg_mpg = mean(mpg, na.rm = TRUE),
    min_mpg = min(mpg),
    max_mpg = max(mpg)
  )

## ----restore-demo-------------------------------------------------------------
# Go back to version 2 (before adding classifications)
restore_table_version("cars", version = 2, author = "Senior Analyst")

# Verify the restoration - efficiency_class column should be gone
get_ducklake_table("cars") |> colnames()

## ----after-restore------------------------------------------------------------
list_table_snapshots("cars")

## ----pinned-attach, eval=FALSE------------------------------------------------
# attach_ducklake(
#   "cars_milestone",
#   lake_path = "~/data/lake",
#   snapshot_version = 2
# )

## ----metadata-----------------------------------------------------------------
# Get detailed snapshot history with all metadata
snapshot_history <- list_table_snapshots("cars")
snapshot_history |>
  select(snapshot_id, snapshot_time, author, commit_message)

## ----all-metadata-------------------------------------------------------------
# View metadata for all tables
all_snapshots <- list_table_snapshots()
all_snapshots |>
  select(snapshot_id, snapshot_time, changes) |>
  head(10)

## ----cleanup, include=FALSE---------------------------------------------------
detach_ducklake("time_travel_demo")