绘制回测 Workflow_Set 数据

Question

我正在尝试查看此模型相对于之前的实际收盘价的表现。我使用的是 workflow_set 模型，提取预测没有问题。我在下面提供了一个可重现的例子。我希望能够绘制实际情况，以及经过回测的趋势线和预测。

tickers <- "TSLA"

first.date <- Sys.Date() - 3000
last.date <- Sys.Date()
freq.data <- "daily"


stocks <- BatchGetSymbols::BatchGetSymbols(tickers = tickers,
                                           first.date = first.date,
                                           last.date = last.date,
                                           freq.data = freq.data ,
                                           do.cache = FALSE,
                                           thresh.bad.data = 0) 

stocks <- stocks %>% as.data.frame() %>% select(Date = df.tickers.ref.date, Close = df.tickers.price.close) 

time_val_split <- 
  stocks %>%
  sliding_period(
    Date,
    period = "day",
    every = 52)

data_extended <- stocks %>%
  future_frame(
    .length_out = 60,
    .bind_data  = TRUE
  ) %>%
  ungroup()

train_tbl <- data_extended %>% drop_na() 

future_tbl <- data_extended %>% filter(is.na(Close))

base_rec <- recipe(Close ~ Date, train_tbl) %>%
  step_timeseries_signature(Date) %>%
  step_rm(matches("(.xts$)|(.iso$)|(.lbl)|(hour)|(minute)|(second)|(am.pm)|(mweek)|(qday)|(week2)|(week3)|(week4)")) %>%
  step_dummy(all_nominal(), one_hot = TRUE) %>%
  step_normalize(all_numeric_predictors()) %>%
  step_scale(all_numeric_predictors()) %>%
  step_rm(Date)
 
cubist_spec <- 
  cubist_rules(committees = tune(),
               neighbors = tune()) %>% 
  set_engine("Cubist") 

rf_spec <- 
  rand_forest(mtry = tune(), 
              min_n = tune(),
              trees = 1000) %>% 
  set_engine("ranger") %>% 
  set_mode("regression")

base <- 
  workflow_set(
    preproc = list(base_date = base_rec),
    models = list(
      cubist_base = cubist_spec,
      cart_base = cart_spec
    ))

all_workflows <- 
  bind_rows(
    base
  )

cores <- parallel::detectCores(logical = FALSE)
clusters <- parallel::makePSOCKcluster(cores)
doParallel::registerDoParallel(clusters)

wflwset_tune_results <- 
  all_workflows %>%
  workflow_map(
    fn = "tune_race_anova",
    seed = 1,
    resamples = time_val_split,
    grid = 2,
    verbose = TRUE)

doParallel::stopImplicitCluster()

best_for_each_mod <- wflwset_tune_results %>%
  rank_results(select_best = TRUE) %>% 
  filter(.metric == "rmse") %>%
  select(wflow_id, .config, mean, preprocessor, model)

b_mod <- best_for_each_mod %>%
  arrange(mean) %>%
  head(1) %>%
  select(wflow_id) %>% as.character()


best_param <- wflwset_tune_results %>% extract_workflow_set_result(id = b_mod) %>% select_best(metric = "rmse") 

# Finalize model with best param
best_finalized <- wflwset_tune_results %>%
  extract_workflow(b_mod) %>%
  finalize_workflow(best_param) %>%
  fit(train_tbl)

此时模型已经训练完毕，但我似乎无法弄清楚如何运行它与先前的实际情况相比较。我的目标是将支持的结果与下面的预测结合起来。

prediction_tbl <- best_finalized %>%
  predict(new_data = future_tbl) %>%
  bind_cols(future_tbl) %>%
  select(.pred, Date) %>%
  mutate(type = "prediction") %>%
  rename(Close = .pred)

 train_tbl %>% mutate(type = "actual") %>% rbind(prediction_tbl) %>%
  ggplot(aes(Date, Close, color = type)) +
  geom_line(size = 2)

Answer 1

根据您的评论，我建议在将 future_tbl 绑定到您的预测后使用 pivot_longer()。这使您可以将所有内容都放在一个管道中，而不必创建两个单独的数据框然后将它们绑定在一起。这是一个根据 mpg 绘制预测值和实际值的示例。希望这对您有所帮助！

library(tidymodels)
#> Registered S3 method overwritten by 'tune':
#>   method                   from   
#>   required_pkgs.model_spec parsnip

# split data
set.seed(123)
mtcars <- as_tibble(mtcars)
cars_split <- initial_split(mtcars)
cars_train <- training(cars_split)
cars_test <- testing(cars_split)

# plot truth & prediction against another variable
workflow() %>%
  add_model(linear_reg() %>% set_engine("lm")) %>%
  add_recipe(recipe(qsec ~ ., data = cars_train)) %>%
  fit(cars_train) %>%
  predict(cars_test) %>%
  bind_cols(cars_test) %>%
  pivot_longer(cols = c(.pred, qsec),
               names_to = "comparison",
               values_to = "value") %>%
  ggplot(aes(x = mpg,
             y = value,
             color = comparison)) +
  geom_point(alpha = 0.75)

^{由 reprex package (v2.0.1)}

于 2021-11-18 创建

绘制回测 Workflow_Set 数据

Plotting Backtested Workflow_Set data

r

workflow

tidymodels