── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr 1.1.4 ✔ readr 2.1.5
✔ forcats 1.0.0 ✔ stringr 1.5.1
✔ ggplot2 3.4.4 ✔ tibble 3.2.1
✔ lubridate 1.9.3 ✔ tidyr 1.3.0
✔ purrr 1.0.2
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag() masks stats::lag()
ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
Attaching package: 'tsibble'
The following object is masked from 'package:lubridate':
interval
The following objects are masked from 'package:base':
intersect, setdiff, union
Loading required package: fabletools
library (fable)
library (tsibbledata)
library (fpp3)
library (plotly)
Attaching package: 'plotly'
The following object is masked from 'package:ggplot2':
last_plot
The following object is masked from 'package:stats':
filter
The following object is masked from 'package:graphics':
layout
# A tsibble: 218 x 7 [1Q]
Quarter Beer Tobacco Bricks Cement Electricity Gas
<qtr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 1956 Q1 284 5225 189 465 3923 5
2 1956 Q2 213 5178 204 532 4436 6
3 1956 Q3 227 5297 208 561 4806 7
4 1956 Q4 308 5681 197 570 4418 6
5 1957 Q1 262 5577 187 529 4339 5
6 1957 Q2 228 5651 214 604 4811 7
7 1957 Q3 236 5317 227 603 5259 7
8 1957 Q4 320 6152 222 582 4735 6
9 1958 Q1 272 5758 199 554 4608 5
10 1958 Q2 233 5641 229 620 5196 7
# ℹ 208 more rows
# A tsibble: 15,150 x 9 [1Y]
# Key: Country [263]
Country Code Year GDP Growth CPI Imports Exports Population
<fct> <fct> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 Afghanistan AFG 1960 537777811. NA NA 7.02 4.13 8996351
2 Afghanistan AFG 1961 548888896. NA NA 8.10 4.45 9166764
3 Afghanistan AFG 1962 546666678. NA NA 9.35 4.88 9345868
4 Afghanistan AFG 1963 751111191. NA NA 16.9 9.17 9533954
5 Afghanistan AFG 1964 800000044. NA NA 18.1 8.89 9731361
6 Afghanistan AFG 1965 1006666638. NA NA 21.4 11.3 9938414
7 Afghanistan AFG 1966 1399999967. NA NA 18.6 8.57 10152331
8 Afghanistan AFG 1967 1673333418. NA NA 14.2 6.77 10372630
9 Afghanistan AFG 1968 1373333367. NA NA 15.2 8.90 10604346
10 Afghanistan AFG 1969 1408888922. NA NA 15.0 10.1 10854428
# ℹ 15,140 more rows
gdp <- tidyquant:: tq_get (
x = "NGDPRSAXDCBRQ" ,
get = "economic.data" ,
from = "1997-01-01"
)
Registered S3 method overwritten by 'quantmod':
method from
as.zoo.data.frame zoo
gdp <- gdp |>
mutate (date = yearquarter (date)) |>
as_tsibble (
index = date,
key = symbol
)
gdp_train <- gdp |>
filter_index (. ~ "2020 Q4" )
gdp_train
# A tsibble: 96 x 3 [1Q]
# Key: symbol [1]
symbol date price
<chr> <qtr> <dbl>
1 NGDPRSAXDCBRQ 1997 Q1 183938.
2 NGDPRSAXDCBRQ 1997 Q2 185608.
3 NGDPRSAXDCBRQ 1997 Q3 187566.
4 NGDPRSAXDCBRQ 1997 Q4 189084
5 NGDPRSAXDCBRQ 1998 Q1 185663.
6 NGDPRSAXDCBRQ 1998 Q2 188338.
7 NGDPRSAXDCBRQ 1998 Q3 188495.
8 NGDPRSAXDCBRQ 1998 Q4 186331.
9 NGDPRSAXDCBRQ 1999 Q1 186906
10 NGDPRSAXDCBRQ 1999 Q2 187512.
# ℹ 86 more rows
p <- gdp_train |>
autoplot (price) +
labs (
title = "Time series plot of the Real GDP for Mexico" ,
y = "GDP"
)
ggplotly (p, dynamicTicks = TRUE ) |>
rangeslider ()
gdp_train |>
gg_season (price) |>
ggplotly ()
gdp_train |>
model (stl = STL (price, robust = TRUE )) |>
components () |>
autoplot () |>
ggplotly ()
gdp_train |>
autoplot (log (price)) +
ggtitle ("Log of the Real GDP of Brazil" )
gdp_train |>
model (stl = STL (log (price) ~ season (window = "periodic" ), robust = TRUE )) |>
components () |>
autoplot () |>
ggplotly ()
gdp_fit <- gdp_train |>
model (
snaive = SNAIVE (log (price)),
drift = RW (log (price) ~ drift ())
)
gdp_fit |>
select (snaive) |>
gg_tsresiduals () +
ggtitle ("Residuals Diagnostics for the Seasonal Naïve Model" )
Warning: Removed 4 rows containing missing values (`geom_line()`).
Warning: Removed 4 rows containing missing values (`geom_point()`).
Warning: Removed 4 rows containing non-finite values (`stat_bin()`).
gdp_fit |>
select (drift) |>
gg_tsresiduals () +
ggtitle ("Residuals Diagnostics for the Drift Model" )
Warning: Removed 1 row containing missing values (`geom_line()`).
Warning: Removed 1 rows containing missing values (`geom_point()`).
Warning: Removed 1 rows containing non-finite values (`stat_bin()`).
gdp_fit |>
augment () |>
features (.innov, ljung_box, lag = 24 , dof = 0 )
# A tibble: 2 × 4
symbol .model lb_stat lb_pvalue
<chr> <chr> <dbl> <dbl>
1 NGDPRSAXDCBRQ drift 7.84 0.999
2 NGDPRSAXDCBRQ snaive 139. 0
gdp_train_accu <- accuracy (gdp_fit) |>
arrange (MAPE)
gdp_train_accu |>
select (symbol: .type, MAPE, RMSE, MAE, MASE)
# A tibble: 2 × 7
symbol .model .type MAPE RMSE MAE MASE
<chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl>
1 NGDPRSAXDCBRQ drift Training 1.10 4793. 2851. 0.366
2 NGDPRSAXDCBRQ snaive Training 3.02 9724. 7786. 1
gdp_fit_dcmp <- gdp_train |>
model (
stlf = decomposition_model (
STL (log (price) ~ season (window = "periodic" ), robust = TRUE ),
RW (season_adjust ~ drift ())
)
)
gdp_fit_dcmp
# A mable: 1 x 2
# Key: symbol [1]
symbol stlf
<chr> <model>
1 NGDPRSAXDCBRQ <STL decomposition model>
gdp_fit <- gdp_fit |>
left_join (gdp_fit_dcmp)
Joining with `by = join_by(symbol)`
gdp_fit |>
accuracy () |>
select (symbol: .type, MAPE, RMSE, MAE, MASE) |>
arrange (MAPE)
# A tibble: 3 × 7
symbol .model .type MAPE RMSE MAE MASE
<chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl>
1 NGDPRSAXDCBRQ drift Training 1.10 4793. 2851. 0.366
2 NGDPRSAXDCBRQ stlf Training 1.12 4886. 2920. 0.375
3 NGDPRSAXDCBRQ snaive Training 3.02 9724. 7786. 1
gdp_fit |>
select (stlf) |>
gg_tsresiduals ()
Warning: Removed 4 rows containing missing values (`geom_line()`).
Warning: Removed 4 rows containing missing values (`geom_point()`).
Warning: Removed 4 rows containing non-finite values (`stat_bin()`).
gdp_fit |>
augment () |>
features (.innov, ljung_box)
# A tibble: 3 × 4
symbol .model lb_stat lb_pvalue
<chr> <chr> <dbl> <dbl>
1 NGDPRSAXDCBRQ drift 0.232 6.30e- 1
2 NGDPRSAXDCBRQ snaive 58.3 2.20e-14
3 NGDPRSAXDCBRQ stlf 0.202 6.53e- 1
gdp_fc <- gdp_fit |>
forecast (h = 6 )
gdp_fc
# A fable: 18 x 5 [1Q]
# Key: symbol, .model [3]
symbol .model date price .mean
<chr> <chr> <qtr> <dist> <dbl>
1 NGDPRSAXDCBRQ snaive 2021 Q1 t(N(13, 0.0014)) 297054.
2 NGDPRSAXDCBRQ snaive 2021 Q2 t(N(13, 0.0014)) 270458.
3 NGDPRSAXDCBRQ snaive 2021 Q3 t(N(13, 0.0014)) 292060.
4 NGDPRSAXDCBRQ snaive 2021 Q4 t(N(13, 0.0014)) 302765.
5 NGDPRSAXDCBRQ snaive 2022 Q1 t(N(13, 0.0029)) 297266.
6 NGDPRSAXDCBRQ snaive 2022 Q2 t(N(13, 0.0029)) 270651.
7 NGDPRSAXDCBRQ drift 2021 Q1 t(N(13, 0.00031)) 304186.
8 NGDPRSAXDCBRQ drift 2021 Q2 t(N(13, 0.00063)) 305832.
9 NGDPRSAXDCBRQ drift 2021 Q3 t(N(13, 0.00095)) 307487.
10 NGDPRSAXDCBRQ drift 2021 Q4 t(N(13, 0.0013)) 309153.
11 NGDPRSAXDCBRQ drift 2022 Q1 t(N(13, 0.0016)) 310829.
12 NGDPRSAXDCBRQ drift 2022 Q2 t(N(13, 0.002)) 312515.
13 NGDPRSAXDCBRQ stlf 2021 Q1 t(N(13, 0.00031)) 304309.
14 NGDPRSAXDCBRQ stlf 2021 Q2 t(N(13, 0.00063)) 305936.
15 NGDPRSAXDCBRQ stlf 2021 Q3 t(N(13, 0.00096)) 307197.
16 NGDPRSAXDCBRQ stlf 2021 Q4 t(N(13, 0.0013)) 309160.
17 NGDPRSAXDCBRQ stlf 2022 Q1 t(N(13, 0.0016)) 310962.
18 NGDPRSAXDCBRQ stlf 2022 Q2 t(N(13, 0.002)) 312628.
gdp_fc |>
autoplot (gdp) +
facet_wrap (~ .model, ncol = 1 )
gdp_fc |>
filter (.model == "stlf" ) |>
autoplot (gdp)
gdp_fc |>
accuracy (gdp) |>
select (.model: .type, MAPE, RMSE, MAE, MASE) |>
arrange (MAPE)
# A tibble: 3 × 7
.model symbol .type MAPE RMSE MAE MASE
<chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl>
1 stlf NGDPRSAXDCBRQ Test 0.602 1969. 1845. 0.237
2 drift NGDPRSAXDCBRQ Test 0.617 2046. 1892. 0.243
3 snaive NGDPRSAXDCBRQ Test 6.20 23818. 19134. 2.46
gdp_fit2 <- gdp |>
model (
stlf = decomposition_model (
STL (log (price) ~ season (window = "periodic" ), robust = TRUE ),
RW (season_adjust ~ drift ())
)
)
gdp_fit2
# A mable: 1 x 2
# Key: symbol [1]
symbol stlf
<chr> <model>
1 NGDPRSAXDCBRQ <STL decomposition model>
gdp_fc_fut <- gdp_fit2 |>
forecast (h = "3 years" )
gdp_fc_fut
# A fable: 12 x 5 [1Q]
# Key: symbol, .model [1]
symbol .model date price .mean
<chr> <chr> <qtr> <dist> <dbl>
1 NGDPRSAXDCBRQ stlf 2023 Q4 t(N(13, 0.00028)) 327224.
2 NGDPRSAXDCBRQ stlf 2024 Q1 t(N(13, 0.00057)) 329471.
3 NGDPRSAXDCBRQ stlf 2024 Q2 t(N(13, 0.00087)) 331257.
4 NGDPRSAXDCBRQ stlf 2024 Q3 t(N(13, 0.0012)) 332607.
5 NGDPRSAXDCBRQ stlf 2024 Q4 t(N(13, 0.0015)) 334560.
6 NGDPRSAXDCBRQ stlf 2025 Q1 t(N(13, 0.0018)) 336861.
7 NGDPRSAXDCBRQ stlf 2025 Q2 t(N(13, 0.0021)) 338691.
8 NGDPRSAXDCBRQ stlf 2025 Q3 t(N(13, 0.0024)) 340075.
9 NGDPRSAXDCBRQ stlf 2025 Q4 t(N(13, 0.0027)) 342075.
10 NGDPRSAXDCBRQ stlf 2026 Q1 t(N(13, 0.0031)) 344432.
11 NGDPRSAXDCBRQ stlf 2026 Q2 t(N(13, 0.0034)) 346306.
12 NGDPRSAXDCBRQ stlf 2026 Q3 t(N(13, 0.0038)) 347726.
gdp_fc_fut |>
autoplot (gdp)
cement <- aus_production |>
select (Cement)
recent_production <- cement %>% filter (year (Quarter) >= 1985 )
cement_train <- recent_production %>% filter (year (Quarter) <= 2003 )
cement_train
# A tsibble: 76 x 2 [1Q]
Cement Quarter
<dbl> <qtr>
1 1251 1985 Q1
2 1456 1985 Q2
3 1631 1985 Q3
4 1555 1985 Q4
5 1375 1986 Q1
6 1546 1986 Q2
7 1568 1986 Q3
8 1561 1986 Q4
9 1332 1987 Q1
10 1458 1987 Q2
# ℹ 66 more rows
c <- cement_train |>
autoplot (Cement)
ggplotly (c, dynamicTicks = TRUE ) |>
rangeslider ()
cement_train |>
gg_season (Cement) |>
ggplotly ()
cement_train|>
model (stl = STL (Cement, robust = TRUE )) |>
components () |>
autoplot () |>
ggplotly ()
cement_fit <- cement_train |>
model (
snaive = SNAIVE (Cement),
naive = NAIVE (Cement),
drift = RW (Cement ~ drift ()),
stlf = decomposition_model (
STL (Cement ~ season (window = "periodic" ), robust = TRUE ),
RW (season_adjust ~ drift ())
),
ets_MAdA = ETS (Cement ~ error ("M" ) + trend ("Ad" ) + season ("A" )),
ets_ANM = ETS (Cement ~ error ("A" ) + trend ("N" ) + season ("M" )),
ets_AAdN = ETS (Cement ~ error ("A" ) + trend ("Ad" ) + season ("N" )),
stl_ets_A = decomposition_model (
STL (Cement, robust= TRUE ),
ETS (season_year ~ error ("A" ) + trend ("N" ) + season ("M" )),
ETS (season_adjust ~ error ("A" ) + trend ("N" ) + season ("A" ))
),
stl_ets_M = decomposition_model (
STL (Cement, robust= TRUE ),
ETS (season_year ~ error ("A" ) + trend ("N" ) + season ("A" )),
ETS (season_adjust ~ error ("A" ) + trend ("Ad" ) + season ("M" ))
)
)
cement_fit |>
select (snaive) |>
gg_tsresiduals () +
ggtitle ("Residuals Diagnostics for the Seasonal Naïve Model" )
Warning: Removed 4 rows containing missing values (`geom_line()`).
Warning: Removed 4 rows containing missing values (`geom_point()`).
Warning: Removed 4 rows containing non-finite values (`stat_bin()`).
cement_fit |>
select (drift) |>
gg_tsresiduals () +
ggtitle ("Residuals Diagnostics for the Drift Model" )
Warning: Removed 1 row containing missing values (`geom_line()`).
Warning: Removed 1 rows containing missing values (`geom_point()`).
Warning: Removed 1 rows containing non-finite values (`stat_bin()`).
cement_fit |>
select (stlf) |>
gg_tsresiduals () +
ggtitle ("Residuals Diagnostics for the stlf Model" )
Warning: Removed 4 rows containing missing values (`geom_line()`).
Warning: Removed 4 rows containing missing values (`geom_point()`).
Warning: Removed 4 rows containing non-finite values (`stat_bin()`).
cement_fit |>
select (ets_MAdA) |>
gg_tsresiduals () +
ggtitle ("Residuals Diagnostics for the ets_ANA Model" )
cement_fit |>
select (ets_ANM) |>
gg_tsresiduals () +
ggtitle ("Residuals Diagnostics for the ets_AAdA Model" )
cement_fit |>
select (ets_AAdN) |>
gg_tsresiduals () +
ggtitle ("Residuals Diagnostics for the ets_MAdM Model" )
cement_fit |>
select (stl_ets_A) |>
gg_tsresiduals () +
ggtitle ("Residuals Diagnostics for the stl_ets_A Model" )
cement_fit |>
select (stl_ets_M) |>
gg_tsresiduals () +
ggtitle ("Residuals Diagnostics for the stl_ets_M Model" )
cement_fit |>
augment () |>
features (.innov, ljung_box, lag = 30 , dof = 0 )
# A tibble: 9 × 3
.model lb_stat lb_pvalue
<chr> <dbl> <dbl>
1 drift 239. 0
2 ets_AAdN 204. 0
3 ets_ANM 41.2 0.0841
4 ets_MAdA 49.8 0.0130
5 naive 239. 0
6 snaive 252. 0
7 stl_ets_A 33.2 0.316
8 stl_ets_M 49.2 0.0149
9 stlf 44.3 0.0446
cement_train_accu <- accuracy (cement_fit) |>
arrange (MAPE)
cement_train_accu |>
select (.model, .type, MAPE, RMSE, MAE, MASE)
# A tibble: 9 × 6
.model .type MAPE RMSE MAE MASE
<chr> <chr> <dbl> <dbl> <dbl> <dbl>
1 stl_ets_M Training 4.28 94.4 72.9 0.505
2 ets_MAdA Training 4.36 96.0 74.1 0.513
3 stlf Training 4.36 101. 75.3 0.522
4 ets_ANM Training 4.45 97.5 75.5 0.523
5 stl_ets_A Training 5.70 134. 92.0 0.638
6 ets_AAdN Training 7.36 151. 122. 0.846
7 drift Training 8.09 166. 135. 0.934
8 naive Training 8.17 166. 137. 0.946
9 snaive Training 8.45 170. 144. 1
cement_fc <- cement_fit |>
forecast (h= "7 years" )
cement_fc
# A fable: 252 x 4 [1Q]
# Key: .model [9]
.model Quarter Cement .mean
<chr> <qtr> <dist> <dbl>
1 snaive 2004 Q1 N(1831, 28963) 1831
2 snaive 2004 Q2 N(1892, 28963) 1892
3 snaive 2004 Q3 N(2227, 28963) 2227
4 snaive 2004 Q4 N(2090, 28963) 2090
5 snaive 2005 Q1 N(1831, 57926) 1831
6 snaive 2005 Q2 N(1892, 57926) 1892
7 snaive 2005 Q3 N(2227, 57926) 2227
8 snaive 2005 Q4 N(2090, 57926) 2090
9 snaive 2006 Q1 N(1831, 86890) 1831
10 snaive 2006 Q2 N(1892, 86890) 1892
# ℹ 242 more rows
cement_fc |>
autoplot (cement|> filter_index ("1995 Q1" ~ .), size = 2 ) +
facet_wrap (~ .model, ncol = 3 ) +
theme (legend.position = "none" )
cement_fc |>
accuracy (cement) |>
select (.model: .type, MAPE, RMSE, MAE, MASE) |>
arrange (MAPE)
Warning: The future dataset is incomplete, incomplete out-of-sample data will be treated as missing.
2 observations are missing between 2010 Q3 and 2010 Q4
# A tibble: 9 × 6
.model .type MAPE RMSE MAE MASE
<chr> <chr> <dbl> <dbl> <dbl> <dbl>
1 stlf Test 7.23 202. 170. 1.77
2 drift Test 7.64 207. 173. 1.79
3 stl_ets_M Test 9.07 254. 216. 2.24
4 ets_MAdA Test 9.39 261. 223. 2.32
5 ets_AAdN Test 9.41 259. 222. 2.31
6 naive Test 9.91 273. 234. 2.44
7 ets_ANM Test 10.8 285. 253. 2.63
8 snaive Test 11.9 323. 279. 2.90
9 stl_ets_A Test 12.4 352. 288. 2.99
cement_fit_fut <- cement_train |>
model (
ets_ANM = ETS (Cement ~ error ("A" ) + trend ("N" ) + season ("M" ))
)
cement_fc_fut <- cement_fit_fut |>
forecast (h = "6 years" )
cement_fc_fut |>
autoplot (cement_train)
En este caso el modelo que se utiliza es el de ets_ANM debido a que es el mejor modelo que no rechaza la hipotesis. El modelo utiliza un error aditivo, no muestra tendencia y tiene estacionalidad multiplicativa. Este modelo es el 7mo que mejor se ajusta, sin embargo se utiliza este, ya que los 6 anteriores son rechazados, ya que su P-value es menor a 0.05. El error MAPE del modelo es de 10.80, por lo que se dice que aunque es el mejor modelo, cuenta con un error muy grande.