Time Series 001

Time Series 001

### Source: https://cran.r-project.org/web/packages/forecastML/vignettes/grouped_forecast.html
library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(DT)
library(ggplot2)
library(forecastML)
library(xgboost)

## 
## Attaching package: 'xgboost'

## The following object is masked from 'package:dplyr':
## 
##     slice

data("data_buoy_gaps", package = "forecastML")

DT::datatable(head(data_buoy_gaps), options = list(scrollX = TRUE))

data <- forecastML::fill_gaps(data_buoy_gaps, date_col = 1, frequency = '1 day', 
                              groups = 'buoy_id', static_features = c('lat', 'lon'))

print(list(paste0("The original dataset with gaps in data collection is ", nrow(data_buoy_gaps), " rows."), 
           paste0("The modified dataset with no gaps in data collection from fill_gaps() is ", nrow(data), " rows.")))

## [[1]]
## [1] "The original dataset with gaps in data collection is 23646 rows."
## 
## [[2]]
## [1] "The modified dataset with no gaps in data collection from fill_gaps() is 31225 rows."

DT::datatable(head(data), options = list(scrollX = TRUE))

data$day <- lubridate::mday(data$date)
data$year <- lubridate::year(data$date)

p <- ggplot(data, aes(x = date, y = wind_spd, color = ordered(buoy_id), group = year))
p <- p + geom_line()
p <- p + facet_wrap(~ ordered(buoy_id), scales = "fixed")
p <- p + theme_bw() + theme(
  legend.position = "none"
) + xlab(NULL)
p

## Warning: Removed 848 rows containing missing values (geom_path).

outcome_col <- 1  # The column position of our 'wind_spd' outcome.

horizons <- c(1, 7, 30)  # Forecast 1, 1:7, and 1:30 days into the future.

lookback <- c(1:30, 360:370)  # Features from 1 to 30 days in the past and annually.

dates <- data$date  # Grouped time series forecasting requires dates.
data$date <- NULL  # Dates, however, don't need to be in the input data.

frequency <- "1 day"  # A string that works in base::seq(..., by = "frequency").

dynamic_features <- c("day", "year")  # Features that change through time but which we will not lag.

groups <- "buoy_id"  # 1 forecast for each group or buoy.

static_features <- c("lat", "lon")  # Features that do not change through time.

type <- "train"  # Create a model-training dataset.

data_train <- forecastML::create_lagged_df(data, type = type, outcome_col = outcome_col,
                                           horizons = horizons, lookback = lookback,
                                           dates = dates, frequency = frequency,
                                           dynamic_features = dynamic_features,
                                           groups = groups, static_features = static_features, 
                                           use_future = FALSE)

print(paste0("The class of `data_train` is ", class(data_train)))

## [1] "The class of `data_train` is grouped_lagged_df"
## [2] "The class of `data_train` is lagged_df"        
## [3] "The class of `data_train` is list"

DT::datatable(head(data_train$horizon_1), options = list(scrollX = TRUE))

p <- plot(data_train)  # plot.lagged_df() returns a ggplot object.
p <- p + geom_tile(NULL)  # Remove the gray border for a cleaner plot.
p

windows <- forecastML::create_windows(data_train, window_length = 365, skip = 730,
                                      include_partial_window = FALSE)

p <- plot(windows, data_train) + theme(legend.position = "none")
p

## Warning: Removed 4977 rows containing missing values (geom_path).

## Warning: Removed 11872 rows containing missing values (geom_point).

p <- plot(windows, data_train, group_filter = "buoy_id == 1") + 
  theme(legend.position = "none")

## Warning in min(data_plot[, 1], na.rm = TRUE): no non-missing arguments to
## min; returning Inf

## Warning in max(data_plot[, 1], na.rm = TRUE): no non-missing arguments to
## max; returning -Inf

## Warning in min(data_plot[, 1], na.rm = TRUE): no non-missing arguments to
## min; returning Inf

## Warning: Factor `ggplot_color_group` contains implicit NA, consider using
## `forcats::fct_explicit_na`

p

## Warning: Removed 3 rows containing missing values (geom_label).