Merge pull request #85 from microsoft/users/mitokic/v0.2-smell-test

v0.1.0 release by the awesome super @mike Tokic

Author: AKannanMSFT

.Rbuildignore

@@ -5,3 +5,8 @@
 ^docs$
 ^pkgdown$
 ^\.github$
+CODE_OF_CONDUCT.md
+SECURITY.md
+SUPPORT.md
+cran-comments.md
+NEWS.md

.github/workflows/R-CMD-check.yaml

@@ -25,8 +25,7 @@ jobs:
           - {os: macOS-latest,   r: 'release'}
 
           - {os: windows-latest, r: 'release'}
-          # Use 3.6 to trigger usage of RTools35
-          - {os: windows-latest, r: '3.6'}
+
 
           # Use older ubuntu to maximise backward compatibility
           - {os: ubuntu-18.04,   r: 'devel', http-user-agent: 'release'}

DESCRIPTION

@@ -1,11 +1,11 @@
 Package: finnts
 Title: Microsoft Finance Time Series Forecasting Framework
-Version: 0.0.0.9000
+Version: 0.1.0
 Authors@R: 
     c(person(given = "Mike",
            family = "Tokic",
            role = c("aut", "cre"),
-           email = "mitokic@microsoft.com", 
+           email = "mftokic@gmail.com", 
            comment = c(ORCID = "0000-0002-7630-7055")), 
       person(given = "Aadharsh",
            family = "Kannan",
@@ -34,13 +34,17 @@ Imports:
     doParallel,
     dplyr,
     earth,
+    foreach,
     generics,
     glmnet,
     gtools,
     hts,
     kernlab,
     lightgbm,
+    lubridate,
+    magrittr,
     matrixcalc,
+    methods,
     modeltime.ensemble,
     modeltime.gluonts,
     modeltime.resample,
@@ -68,11 +72,10 @@ Remotes:
 Suggests: 
     rmarkdown,
     knitr,
+    reactable,
     testthat (>= 3.0.0)
 Config/testthat/edition: 3
 Depends: 
-    R (>= 3.6.0),
-    lubridate,
-    foreach,
+    R (>= 3.6.0), 
     modeltime
 VignetteBuilder: knitr

NAMESPACE

@@ -25,3 +25,10 @@ export(tabnet)
 export(tbats)
 export(theta)
 export(xgboost)
+import(modeltime)
+importFrom(foreach,"%do%")
+importFrom(foreach,"%dopar%")
+importFrom(lubridate,"%m+%")
+importFrom(magrittr,"%>%")
+importFrom(methods,formalArgs)
+importFrom(stats,sd)

NEWS.md

@@ -0,0 +1,4 @@
+
+# finnts 0.1.0
+
+* Initial CRAN Release

R/azure_batch_parallel.R

@@ -22,7 +22,7 @@ get_fcast_parallel_azure <- function(combo_list,
 
   cli::cli_h2("Submitting Tasks to Azure Batch")
 
-  fcst <- foreach(i = combo_list, .combine = 'rbind',
+  fcst <- foreach::foreach(i = combo_list, .combine = 'rbind',
                   .packages = get_export_packages(), 
                   .export = get_transfer_functions(),
                   .options.azure = list(maxTaskRetryCount = 0, 

R/configure_forecast_run.R

@@ -164,7 +164,7 @@ get_date_regex <- function(date_type){
 
 #' Gets the back testing spacing
 #' 
-#' Checks if back_test_spacing is set to auto and gets the right one
+#' Checks if back_test_spacing is set to NULL and gets the right one
 #' 
 #' 
 #' @param back_test_spacing back_test_spacing override
@@ -175,7 +175,7 @@ get_date_regex <- function(date_type){
 get_back_test_spacing <- function(back_test_spacing,
                                        date_type){
 
-  if(back_test_spacing != "auto") {
+  if(!is.null(back_test_spacing)) {
     return(back_test_spacing)
   }
 
@@ -218,7 +218,7 @@ get_back_test_scenario_hist_periods<- function(full_data_tbl,
 
   hist_periods_80 <- floor(historical_periods*0.7) #used with time series CV in multivariate models
 
-  if(back_test_scenarios == "auto") {
+  if(is.null(back_test_scenarios)) {
 
     historical_periods_20 <- floor(historical_periods*0.2)
 

R/forecast_models.R

@@ -259,12 +259,16 @@ construct_forecast_models <- function(full_data_tbl,
     cli::cli_h2("Running Combo: {combo_value}")
 
     # Copy functions into global environment within azure batch
-    if(parallel_processing == "azure_batch") {
-      global_env <- .GlobalEnv
-      export_env <- global_env$azbatchenv$exportenv
-      
-      for(n in ls(export_env , all.names=TRUE)) {
-        assign(n, get(n, export_env), global_env)
+    if(!is.null(parallel_processing)) {
+      if(parallel_processing == "azure_batch") {
+        
+        global_env <- .GlobalEnv
+        export_env <- global_env$azbatchenv$exportenv
+        
+        for(n in ls(export_env , all.names=TRUE)) {
+          assign(n, get(n, export_env), global_env)
+        }
+        
       }
     }
 
@@ -274,13 +278,22 @@ construct_forecast_models <- function(full_data_tbl,
     run_data_full_tbl <- full_data_tbl %>%
       combo_specific_filter(combo_value,
                             combo_variables)
-    
+
     cli::cli_h3("Initial Feature Engineering")
 
+    # Run all recipes
+    if(is.null(recipes_to_run)) {
+      run_all_recipes_override <- FALSE
+    } else if(recipes_to_run == "all") {
+      run_all_recipes_override <- TRUE
+    } else {
+      run_all_recipes_override <- FALSE
+    }
+    
     # recipe 1: standard feature engineering
     run_data_full_recipe_1 <- NULL
 
-    if(is.null(recipes_to_run) | "R1" %in% recipes_to_run | sum(recipes_to_run == "all") == 1) {
+    if(is.null(recipes_to_run) | "R1" %in% recipes_to_run | run_all_recipes_override) {
 
       run_data_full_recipe_1 <- run_data_full_tbl %>%
         multivariate_prep_recipe_1(external_regressors = external_regressors,
@@ -301,7 +314,7 @@ construct_forecast_models <- function(full_data_tbl,
     # recipe 2: custom horizon specific feature engineering
     run_data_full_recipe_2 <- NULL
 
-    if((is.null(recipes_to_run) & date_type %in% c("month", "quarter", "year")) | "R2" %in% recipes_to_run | sum(recipes_to_run == "all") == 1) {
+    if((is.null(recipes_to_run) & date_type %in% c("month", "quarter", "year")) | "R2" %in% recipes_to_run | run_all_recipes_override) {
 
       run_data_full_recipe_2 <- run_data_full_tbl %>%
         multivariate_prep_recipe_2(external_regressors = external_regressors,
@@ -332,7 +345,7 @@ construct_forecast_models <- function(full_data_tbl,
     combined_models_recipe_2 <- modeltime::modeltime_table()
 
     # parallel processing
-    if(run_model_parallel==TRUE & parallel_processing!="local_machine") {
+    if(run_model_parallel == TRUE) {
       parallel_args <- init_parallel_within(parallel_processing, num_cores)
     }
 
@@ -353,12 +366,17 @@ construct_forecast_models <- function(full_data_tbl,
     models_to_go_over <- names(model_list)
 
     # PCA
-    if(sum(pca == TRUE) == 1 | (combo_value == "All-Data" & is.null(pca)) | (is.null(pca) & date_type %in% c("day", "week"))) {
+    if((combo_value == "All-Data" & is.null(pca)) | (is.null(pca) & date_type %in% c("day", "week"))) {
+      run_pca <- TRUE
+    } else if(is.null(pca)) {
+      run_pca <- FALSE
+    } else if(pca == TRUE) {
       run_pca <- TRUE
     } else {
       run_pca <- FALSE
     }
-
+    
+    # train each model
     for(model_name in models_to_go_over){
 
       model_fn <- as.character(model_list[model_name])
@@ -390,15 +408,15 @@ construct_forecast_models <- function(full_data_tbl,
         try(combined_models_recipe_1 <- modeltime::add_modeltime_model(combined_models_recipe_1,
                                                                        mdl_called,
                                                                        location = "top") %>%
-              update_model_description(1, model_name),
+              modeltime::update_model_description(1, model_name),
             silent = TRUE)
 
       }else{
 
 
         freq_val <- frequency
 
-        if(((model_name %in% r1_models) | (model_name %in% r2_models)) & (is.null(recipes_to_run) | sum(recipes_to_run == "all") == 1 | "R1" %in% recipes_to_run)){
+        if(((model_name %in% r1_models) | (model_name %in% r2_models)) & (is.null(recipes_to_run) | run_all_recipes_override | "R1" %in% recipes_to_run)){
 
           add_name <- paste0(model_name,"-R1",model_name_suffix)
           if(model_name %in% deep_nn_models){
@@ -422,12 +440,12 @@ construct_forecast_models <- function(full_data_tbl,
             try(combined_models_recipe_1 <- modeltime::add_modeltime_model(combined_models_recipe_1,
                                                                            mdl_called,
                                                                            location = "top") %>%
-                  update_model_description(1, add_name),
+                  modeltime::update_model_description(1, add_name),
                 silent = TRUE)
 
         }
 
-        if(model_name %in% r2_models & ("R2" %in% recipes_to_run | sum(recipes_to_run == "all") == 1 | (is.null(recipes_to_run) & date_type %in% c("month", "quarter", "year")))){
+        if(model_name %in% r2_models & ("R2" %in% recipes_to_run | run_all_recipes_override | (is.null(recipes_to_run) & date_type %in% c("month", "quarter", "year")))){
 
           add_name <- paste0(model_name,"-R2",model_name_suffix)
           try(mdl_called <- invoke_forecast_function(fn_to_invoke =  model_fn,
@@ -446,7 +464,7 @@ construct_forecast_models <- function(full_data_tbl,
           try(combined_models_recipe_2 <- modeltime::add_modeltime_model(combined_models_recipe_2,
                                                                          mdl_called,
                                                                          location = "top") %>%
-                update_model_description(1, add_name),
+                modeltime::update_model_description(1, add_name),
               silent = TRUE)
         }
 
@@ -651,7 +669,7 @@ construct_forecast_models <- function(full_data_tbl,
         try(combined_ensemble_models <- modeltime::add_modeltime_model(combined_ensemble_models,
                                                                        mdl_ensemble,
                                                                        location = "top") %>%
-              update_model_description(1, add_name),
+              modeltime::update_model_description(1, add_name),
             silent = TRUE)
       }
 
@@ -746,7 +764,7 @@ construct_forecast_models <- function(full_data_tbl,
     }
 
     #stop parallel processing
-    if(run_model_parallel==TRUE & parallel_processing!="local_machine"){
+    if(run_model_parallel==TRUE){
       exit_parallel_within(parallel_args)
     }