library(tidyverse) # data science
library(fpp3) # ts
library(plotly) # interactive plots
library(patchwork) # handling many plots in one figure
library(tidyquant) # financial analisys and downloading dataClase 1
?aus_accommodationstarting httpd help server ... doneaus_accommodation# A tsibble: 592 x 5 [1Q]
# Key: State [8]
Date State Takings Occupancy CPI
<qtr> <chr> <dbl> <dbl> <dbl>
1 1998 Q1 Australian Capital Territory 24.3 65 67
2 1998 Q2 Australian Capital Territory 22.3 59 67.4
3 1998 Q3 Australian Capital Territory 22.5 58 67.5
4 1998 Q4 Australian Capital Territory 24.4 59 67.8
5 1999 Q1 Australian Capital Territory 23.7 58 67.8
6 1999 Q2 Australian Capital Territory 25.4 61 68.1
7 1999 Q3 Australian Capital Territory 28.2 66 68.7
8 1999 Q4 Australian Capital Territory 25.8 60 69.1
9 2000 Q1 Australian Capital Territory 27.3 60.9 69.7
10 2000 Q2 Australian Capital Territory 30.1 64.7 70.2
# ℹ 582 more rows592 filas, 5 columnas, Key:State(8) son 8 estados, osea, 8 series de tiempo
aus_accommodation |>
distinct(State)# A tibble: 8 × 1
State
<chr>
1 Australian Capital Territory
2 New South Wales
3 Northern Territory
4 Queensland
5 South Australia
6 Tasmania
7 Victoria
8 Western Australia tasmania <- aus_accommodation |>
filter(State == "Tasmania") |>
# select(Date, Takings, Occupancy) option 1
# select(Date, Takings:Occupnacy)
select(-c(State, CPI)) |>
mutate(
'Año unión N°1'=1
) |>
janitor::clean_names()
tasmania# A tsibble: 74 x 4 [1Q]
date takings occupancy ano_union_n_1
<qtr> <dbl> <dbl> <dbl>
1 1998 Q1 28.7 67 1
2 1998 Q2 19.0 45 1
3 1998 Q3 16.1 39 1
4 1998 Q4 25.9 56 1
5 1999 Q1 28.4 66 1
6 1999 Q2 20.1 48 1
7 1999 Q3 17.3 41 1
8 1999 Q4 24.3 56 1
9 2000 Q1 30.0 66.2 1
10 2000 Q2 21.7 49.7 1
# ℹ 64 more rowstasmania |>
autoplot(takings, color='#2E79E8', size=2)
we see that the Takings have an upward trend, yearly seasonality, and an increasing variance. We can try using a log transformation
p <- tasmania |>
autoplot(log(takings), color='#2E79E8', size=1)+
geom_point()
ggplotly(p, dynamicTicks = TRUE) |>
rangeslider()tasmania |>
gg_season(log(takings)) # para ver la seasonality
tasmania |>
gg_subseries(log(takings))
tasmania |>
gg_tsdisplay(log(takings), plot_type="auto")
stocks <- c('AAPL','GOOGL','TSLA','MSFT')
stocks_data <- tq_get(
x = stocks,
get = "stock.prices",
from = "2010-01-01",
to = "2024-01-25"
)
stocks_data <- stocks_data |>
as_tsibble(index = date, key = symbol)
stocks_data# A tsibble: 14,030 x 8 [1D]
# Key: symbol [4]
symbol date open high low close volume adjusted
<chr> <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 AAPL 2010-01-04 7.62 7.66 7.59 7.64 493729600 6.48
2 AAPL 2010-01-05 7.66 7.70 7.62 7.66 601904800 6.49
3 AAPL 2010-01-06 7.66 7.69 7.53 7.53 552160000 6.39
4 AAPL 2010-01-07 7.56 7.57 7.47 7.52 477131200 6.38
5 AAPL 2010-01-08 7.51 7.57 7.47 7.57 447610800 6.42
6 AAPL 2010-01-11 7.60 7.61 7.44 7.50 462229600 6.36
7 AAPL 2010-01-12 7.47 7.49 7.37 7.42 594459600 6.29
8 AAPL 2010-01-13 7.42 7.53 7.29 7.52 605892000 6.38
9 AAPL 2010-01-14 7.50 7.52 7.47 7.48 432894000 6.34
10 AAPL 2010-01-15 7.53 7.56 7.35 7.35 594067600 6.23
# ℹ 14,020 more rowsstocks_data |>
ggplot(aes(x = date, y = close, color = symbol))+
geom_line()
stocks_data |>
ggplot(aes(x = date, open = open, high = high, low = low, close = close))+
geom_candlestick()+
facet_wrap(~ symbol, ncol = 2)
stocks2 <- 'AAPL'
stocks_data2 <- tq_get(
x = stocks2,
get = "stock.prices",
from = "2010-01-01",
to = "2024-01-30"
)
stocks_data2 <- stocks_data2 |>
as_tsibble(index = date, key = symbol)
stocks_data2 |>
ggplot(aes(x = date, open = open, high = high, low = low, close = close))+
geom_candlestick()+
facet_wrap(~ symbol, ncol = 2)
Cedasticidad
- Homocedasticidad para varianza constante
- Heterocedasticidad para varianza variable
Componentes
- Estacionalidad: Es una periodicidad fija.
- Ciclos: No se sabe con exactitud cuando va a ser la siguiente