Created
May 2, 2019 21:58
-
-
Save gomesfellipe/ea0e9b41d811a5e014aa4c7b57c283db to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Codigo inspirado neste post: | |
# https://www.business-science.io/code-tools/2017/10/24/demo_week_timetk.html | |
# Testando se o ajuste funciona para a serie AirPassenger | |
# Nao sei ate que ponto este metodo esta correto... Vamos estudar! | |
library(tsibble) | |
library(lubridate) | |
library(dplyr) | |
library(timetk) # Toolkit for working with time series in R | |
library(tidyquant) # Loads tidyverse, financial pkgs, used to get data | |
# Obtendo serie: | |
serie <- AirPassengers | |
# Serie no formato "tidy" | |
serie <- | |
serie %>% | |
as_tsibble() %>% | |
mutate(date = as.Date(index)) %>% | |
as_tibble() %>% | |
select(-index) | |
# Removendo ultimos 6 valores para teste: | |
actuals_tbl <- tail(serie, 6) | |
serie <- serie %>% .[1:(nrow(.)-6),] | |
# Plot Serie | |
serie %>% | |
ggplot(aes(date, value)) + | |
geom_line(col = palette_light()[1]) + | |
geom_point(col = palette_light()[1]) + | |
geom_ma(ma_fun = SMA, n = 12, size = 1) + | |
theme_tq() + | |
scale_x_date(date_breaks = "1 year", date_labels = "%Y") + | |
labs(title = "Airpassenger") | |
# Obtendo variaveis de calendario: | |
serie <- | |
serie %>% | |
tk_augment_timeseries_signature() | |
# linear regression model used, but can use any model | |
fit_lm <- lm(value ~ ., data = select(serie, -one_of(c("date", "diff")))) | |
# Resultado do modelo: | |
summary(fit_lm) | |
# Retrieves the timestamp information | |
serie_idx <- | |
serie %>% | |
tk_index() | |
tail(serie_idx) | |
# Make future index | |
future_idx <- | |
serie_idx %>% | |
tk_make_future_timeseries(n_future = 6) | |
future_idx | |
new_data_tbl <- | |
future_idx %>% | |
tk_get_timeseries_signature() | |
new_data_tbl | |
# Make predictions | |
pred <- predict(fit_lm, newdata = select(new_data_tbl, -one_of(c("index", "diff")))) | |
predictions_tbl <- tibble( | |
date = future_idx, | |
value = pred | |
) | |
predictions_tbl | |
actuals_tbl | |
# Plot da previsao + valores reais: | |
serie %>% | |
ggplot(aes(x = date, y = value)) + | |
# Training data | |
geom_line(color = palette_light()[[1]]) + | |
geom_point(color = palette_light()[[1]]) + | |
# Predictions | |
geom_line(aes(y = value), color = palette_light()[[2]], data = predictions_tbl) + | |
geom_point(aes(y = value), color = palette_light()[[2]], data = predictions_tbl) + | |
# Actuals | |
geom_line(color = palette_light()[[1]], data = actuals_tbl) + | |
geom_point(color = palette_light()[[1]], data = actuals_tbl) + | |
# Aesthetics | |
theme_tq() + | |
labs(title = "AirPassenger: Time Series Machine Learning", | |
subtitle = "Using basic multivariate linear regression can yield accurate results") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment