xgboost model speed ups

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: finnts
 Title: Microsoft Finance Time Series Forecasting Framework
-Version: 0.5.0
+Version: 0.5.0.9001
 Authors@R: 
     c(person(given = "Mike",
            family = "Tokic",

NEWS.md

@@ -1,3 +1,10 @@
+# finnts 0.5.9001 (development version)
+
+## Improvements
+
+-   Shortened global model list to just xgboost
+-   Faster xgboost model training for larger datasets 
+
 # finnts 0.5.0
 
 ## Improvements

R/models.R

@@ -57,7 +57,7 @@ list_r2_models <- function() {
 #' @return list of models
 #' @noRd
 list_global_models <- function() {
-  list <- c("cubist", "glmnet", "mars", "svm-poly", "svm-rbf", "xgboost")
+  list <- c("xgboost")
 
   return(list)
 }
@@ -69,7 +69,8 @@ list_global_models <- function() {
 #' @noRd
 list_multivariate_models <- function() {
   list <- c(
-    list_global_models(), "arima-boost", "arimax", "prophet-boost", "prophet-xregs",
+    "cubist", "glmnet", "mars", "svm-poly", "svm-rbf", "xgboost", 
+    "arima-boost", "arimax", "prophet-boost", "prophet-xregs",
     "nnetar-xregs"
   )
 

R/train_models.R

@@ -419,6 +419,13 @@ train_models <- function(run_info,
           dplyr::select(Model_Workflow)
 
         workflow <- workflow$Model_Workflow[[1]]
+        
+        if (nrow(prep_data) > 500 & model == "xgboost") {
+          # update xgboost model to use 'hist' tree method to speed up training
+          workflow <- workflows::update_model(workflow,
+                                              workflows::extract_spec_parsnip(workflow) %>%
+                                                parsnip::set_args(tree_method = "hist"))
+        }
 
         if (feature_selection & model %in% fs_model_list) {
           # update model workflow to only use features from feature selection process

vignettes/models-used-in-finnts.Rmd

@@ -23,11 +23,11 @@ reactable::reactable(
     rbind(data.frame(Model = "arima", Type = "univariate, local", Underlying.Package = "modeltime, forecast", Description = "Regression model that is based on finding relationships between lagged values of the target variable you are trying to forecast.")) %>%
     rbind(data.frame(Model = "arima-boost", Type = "multivariate, local", Underlying.Package = "modeltime, forecast, xgboost", Description = "Arima model (refer to arima) that models the trend compoent of target variable, then uses xgboost model (refer to xgboost) to train on the remaining residuals.")) %>%
     rbind(data.frame(Model = "arimax", Type = "multivariate, local", Underlying.Package = "modeltime, forecast", Description = "ARIMA model that incorporates external regressors and other engineered features.")) %>%
-    rbind(data.frame(Model = "cubist", Type = "multivariate, local, global, ensemble", Underlying.Package = "rules", Description = "Hybrid of tree based and linear regression approach. Many decision trees are built, but regression coefficients are used at each terminal node instead of averging values in other tree based approaches.")) %>%
+    rbind(data.frame(Model = "cubist", Type = "multivariate, local, ensemble", Underlying.Package = "rules", Description = "Hybrid of tree based and linear regression approach. Many decision trees are built, but regression coefficients are used at each terminal node instead of averging values in other tree based approaches.")) %>%
     rbind(data.frame(Model = "croston", Type = "univariate, local", Underlying.Package = "modeltime, forecast", Description = "Useful for intermittent demand forecasting, aka when there are a lot of periods of zero values. Involves simple exponential smoothing on non-zero values of target variable and another application of seasonal exponential smoothing on periods between non-zero elements of the target variable. Refer to ets for more details on exponential smoothing.")) %>%
     rbind(data.frame(Model = "ets", Type = "univariate, local", Underlying.Package = "modeltime, forecast", Description = "Forecasts produced using exponential smoothing methods are weighted averages of past observations, with the weights decaying exponentially as the observations get older. Exponential smoothing models try to forecast the components of a time series which can be broken down in to error, trend, and seasonality. These components can be forecasted separately then either added or multiplied together to get the final forecast output.")) %>%
-    rbind(data.frame(Model = "glmnet", Type = "multivariate, local, global, ensemble", Underlying.Package = "parsnip, glmnet", Description = "Linear regression (line of best fit) with regularization to help prevent overfitting and built in variable selection.")) %>%
-    rbind(data.frame(Model = "mars", Type = "multivariate, local, global", Underlying.Package = "parsnip, earth", Description = "An extension to linear regression that captures nonlinearities and interactions between variables.")) %>%
+    rbind(data.frame(Model = "glmnet", Type = "multivariate, local, ensemble", Underlying.Package = "parsnip, glmnet", Description = "Linear regression (line of best fit) with regularization to help prevent overfitting and built in variable selection.")) %>%
+    rbind(data.frame(Model = "mars", Type = "multivariate, local", Underlying.Package = "parsnip, earth", Description = "An extension to linear regression that captures nonlinearities and interactions between variables.")) %>%
     rbind(data.frame(Model = "meanf", Type = "univariate, local", Underlying.Package = "modeltime, forecast", Description = "Simple average of previous year of target variable values.")) %>%
     rbind(data.frame(Model = "nnetar", Type = "univariate, local", Underlying.Package = "modeltime, forecast", Description = "A neural network autoregression model is a traditional feed forward neural network (sometimes called an perceptron) that is fed by lagged values of the historical data set (similar to ARIMA).")) %>%
     rbind(data.frame(Model = "nnetar-xregs", Type = "multivariate, local", Underlying.Package = "modeltime, forecast", Description = "Same approach as nnetar but can incorporate other features in addition to the target variable, like external regressors and date features.")) %>%
@@ -37,8 +37,8 @@ reactable::reactable(
     rbind(data.frame(Model = "snaive", Type = "univariate, local", Underlying.Package = "modeltime, forecast", Description = "Simple model that takes the value from the same period in the previous year.")) %>%
     rbind(data.frame(Model = "stlm-arima", Type = "univariate, local", Underlying.Package = "modeltime, forecast", Description = "Applies an STL decomposition (breaks out target variable into seasonal, trend, and error/residual/remainder components), models the seasonally adjusted data, reseasonalizes, and returns the forecasts. An arima model (refer to arima) is used in forecasting the seasonaly adjusted data.")) %>%
     rbind(data.frame(Model = "stlm-ets", Type = "univariate, local", Underlying.Package = "modeltime, forecast", Description = "Applies an STL decomposition (breaks out target variable into seasonal, trend, and error/residual/remainder components), models the seasonally adjusted data, reseasonalizes, and returns the forecasts. An ets model (refer to ets) is used in forecasting the seasonaly adjusted data.")) %>%
-    rbind(data.frame(Model = "svm-poly", Type = "multivariate, local, global, ensemble", Underlying.Package = "parsnip, kernlab", Description = "Uses a nonlinear function, specifically a polynomial function, to create a regression line of the target variable.")) %>%
-    rbind(data.frame(Model = "svm-rbf", Type = "multivariate, local, global, ensemble", Underlying.Package = "parsnip, kernlab", Description = "Uses a nonlinear function, specifically a radial basis function, to create a regression line of the target variable.")) %>%
+    rbind(data.frame(Model = "svm-poly", Type = "multivariate, local, ensemble", Underlying.Package = "parsnip, kernlab", Description = "Uses a nonlinear function, specifically a polynomial function, to create a regression line of the target variable.")) %>%
+    rbind(data.frame(Model = "svm-rbf", Type = "multivariate, local, ensemble", Underlying.Package = "parsnip, kernlab", Description = "Uses a nonlinear function, specifically a radial basis function, to create a regression line of the target variable.")) %>%
     rbind(data.frame(Model = "tbats", Type = "univariate, local", Underlying.Package = "modeltime, forecast", Description = "A spin off of the traditional ets model (refer to ets), with some additional components to capture multiple seasonalities.")) %>%
     rbind(data.frame(Model = "theta", Type = "univariate, local", Underlying.Package = "modeltime, forecast", Description = "Theta is similar to exponential smoothing (refer to ets) but with another component called drift. Adding drift to exponential smoothing allows the forecast to increase or decrease over time, where the amount of change over time (called the drift) is set to be the average change seen within the historical data.")) %>%
     rbind(data.frame(Model = "xgboost", Type = "multivariate, local, global, ensemble", Underlying.Package = "parsnip, xgboost", Description = "Builds many decision trees (similar to random forests), but predictions that are initially inaccurate are applied more weight in subsequent training rounds to increase accuracy across all predictions.")),