Update parallelization episode

episodes/branch.Rmd

@@ -1,6 +1,6 @@
 ---
 title: 'Branching'
-teaching: 10
+teaching: 30
 exercises: 2
 ---
 
@@ -152,7 +152,7 @@ Before moving on, let's define another **custom function** function: `model_glan
 You will need to write custom functions frequently when using `targets`, so it's good to get used to it!
 
 As the name `model_glance()` suggests (it is good to write functions with names that indicate their purpose), this will build a model then immediately run `glance()` on it.
-The reason for doing so is that we get a **dataframe as a result**, which as previously mentioned is very helpful for branching, as we will see in the next section.
+The reason for doing so is that we get a **dataframe as a result**, which is very helpful for branching, as we will see in the next section.
 Save this in `R/functions.R`:
 
 ```{r}
@@ -310,14 +310,42 @@ Add the step to the workflow:
 
 ```{r}
 #| label = "example-model-augment-show",
-#| code = readLines("files/plans/plan_8.R")[2:35],
+#| code = readLines("files/plans/plan_7.R")[2:36],
 #| eval = FALSE
 ```
 
 ::::::::::::::::::::::::::::::::::
 
 :::::::::::::::::::::::::::::::::::::
 
+### Further simplify the workflow
+
+You may have noticed that we can further simplify the workflow: there is no need to have separate `penguins_data` and `penguins_data_grouped` dataframes.
+In general it is best to keep the number of named objects as small as possible to make it easier to reason about your code.
+Let's combine the cleaning and grouping step into a single command:
+
+```{r}
+#| label = "example-model-show-8",
+#| eval = FALSE,
+#| code = readLines("files/plans/plan_8.R")[2:35]
+```
+
+And run it once more:
+
+```{r}
+#| label: example-model-show-8
+#| echo: false
+pushd(plan_6_dir)
+# simulate already running the plan once
+write_example_plan("plan_7.R")
+tar_make(reporter = "silent")
+# run version of plan that uses `model_glance_orig()` (doesn't include species
+# names in output)
+write_example_plan("plan_8.R")
+tar_make()
+popd()
+```
+
 ::::::::::::::::::::::::::::::::::::: {.callout}
 
 ## Best practices for branching

episodes/files/plans/plan_10.R

@@ -16,27 +16,26 @@ tar_plan(
     path_to_file("penguins_raw.csv"),
     read_csv(!!.x, show_col_types = FALSE)
   ),
-  # Clean data
-  penguins_data = clean_penguin_data(penguins_data_raw),
-  # Build models
-  models = list(
-    combined_model = lm(
-      bill_depth_mm ~ bill_length_mm, data = penguins_data),
-    species_model = lm(
-      bill_depth_mm ~ bill_length_mm + species, data = penguins_data),
-    interaction_model = lm(
-      bill_depth_mm ~ bill_length_mm * species, data = penguins_data)
+  # Clean and group data
+  tar_group_by(
+    penguins_data,
+    clean_penguin_data(penguins_data_raw),
+    species
   ),
-  # Get model summaries
+  # Get summary of combined model with all species together
+  combined_summary = model_glance(penguins_data),
+  # Get summary of one model per species
   tar_target(
-    model_summaries,
-    glance_with_mod_name_slow(models),
-    pattern = map(models)
+    species_summary,
+    model_glance_slow(penguins_data),
+    pattern = map(penguins_data)
   ),
-  # Get model predictions
+  # Get predictions of combined model with all species together
+  combined_predictions = model_glance_slow(penguins_data),
+  # Get predictions of one model per species
   tar_target(
-    model_predictions,
-    augment_with_mod_name_slow(models),
-    pattern = map(models)
+    species_predictions,
+    model_augment_slow(penguins_data),
+    pattern = map(penguins_data)
   )
 )

episodes/files/plans/plan_6c.R

@@ -0,0 +1,34 @@
+options(tidyverse.quiet = TRUE)
+source("R/functions.R")
+source("R/packages.R")
+
+tar_plan(
+  # Load raw data
+  tar_file_read(
+    penguins_data_raw,
+    path_to_file("penguins_raw.csv"),
+    read_csv(!!.x, show_col_types = FALSE)
+  ),
+  # Clean and group data
+  tar_group_by(
+    penguins_data,
+    clean_penguin_data(penguins_data_raw),
+    species
+  ),
+  # Get summary of combined model with all species together
+  combined_summary = model_glance(penguins_data),
+  # Get summary of one model per species
+  tar_target(
+    species_summary,
+    model_glance(penguins_data),
+    pattern = map(penguins_data)
+  ),
+  # Get predictions of combined model with all species together
+  combined_predictions = model_glance(penguins_data),
+  # Get predictions of one model per species
+  tar_target(
+    species_predictions,
+    model_augment(penguins_data),
+    pattern = map(penguins_data)
+  )
+)

episodes/files/plans/plan_7.R

@@ -11,19 +11,26 @@ tar_plan(
   ),
   # Clean data
   penguins_data = clean_penguin_data(penguins_data_raw),
-  # Build models
-  models = list(
-    combined_model = lm(
-      bill_depth_mm ~ bill_length_mm, data = penguins_data),
-    species_model = lm(
-      bill_depth_mm ~ bill_length_mm + species, data = penguins_data),
-    interaction_model = lm(
-      bill_depth_mm ~ bill_length_mm * species, data = penguins_data)
+  # Group data
+  tar_group_by(
+    penguins_data_grouped,
+    penguins_data,
+    species
   ),
-  # Get model summaries
+  # Get summary of combined model with all species together
+  combined_summary = model_glance(penguins_data),
+  # Get summary of one model per species
   tar_target(
-    model_summaries,
-    glance_with_mod_name(models),
-    pattern = map(models)
+    species_summary,
+    model_glance(penguins_data_grouped),
+    pattern = map(penguins_data_grouped)
+  ),
+  # Get predictions of combined model with all species together
+  combined_predictions = model_glance(penguins_data_grouped),
+  # Get predictions of one model per species
+  tar_target(
+    species_predictions,
+    model_augment(penguins_data_grouped),
+    pattern = map(penguins_data_grouped)
   )
 )

episodes/files/plans/plan_8.R

@@ -9,27 +9,26 @@ tar_plan(
     path_to_file("penguins_raw.csv"),
     read_csv(!!.x, show_col_types = FALSE)
   ),
-  # Clean data
-  penguins_data = clean_penguin_data(penguins_data_raw),
-  # Build models
-  models = list(
-    combined_model = lm(
-      bill_depth_mm ~ bill_length_mm, data = penguins_data),
-    species_model = lm(
-      bill_depth_mm ~ bill_length_mm + species, data = penguins_data),
-    interaction_model = lm(
-      bill_depth_mm ~ bill_length_mm * species, data = penguins_data)
+  # Clean and group data
+  tar_group_by(
+    penguins_data,
+    clean_penguin_data(penguins_data_raw),
+    species
   ),
-  # Get model summaries
+  # Get summary of combined model with all species together
+  combined_summary = model_glance(penguins_data),
+  # Get summary of one model per species
   tar_target(
-    model_summaries,
-    glance_with_mod_name(models),
-    pattern = map(models)
+    species_summary,
+    model_glance(penguins_data),
+    pattern = map(penguins_data)
   ),
-  # Get model predictions
+  # Get predictions of combined model with all species together
+  combined_predictions = model_glance(penguins_data),
+  # Get predictions of one model per species
   tar_target(
-    model_predictions,
-    augment_with_mod_name(models),
-    pattern = map(models)
+    species_predictions,
+    model_augment(penguins_data),
+    pattern = map(penguins_data)
   )
 )

episodes/files/plans/plan_9.R

@@ -16,27 +16,26 @@ tar_plan(
     path_to_file("penguins_raw.csv"),
     read_csv(!!.x, show_col_types = FALSE)
   ),
-  # Clean data
-  penguins_data = clean_penguin_data(penguins_data_raw),
-  # Build models
-  models = list(
-    combined_model = lm(
-      bill_depth_mm ~ bill_length_mm, data = penguins_data),
-    species_model = lm(
-      bill_depth_mm ~ bill_length_mm + species, data = penguins_data),
-    interaction_model = lm(
-      bill_depth_mm ~ bill_length_mm * species, data = penguins_data)
+  # Clean and group data
+  tar_group_by(
+    penguins_data,
+    clean_penguin_data(penguins_data_raw),
+    species
   ),
-  # Get model summaries
+  # Get summary of combined model with all species together
+  combined_summary = model_glance(penguins_data),
+  # Get summary of one model per species
   tar_target(
-    model_summaries,
-    glance_with_mod_name(models),
-    pattern = map(models)
+    species_summary,
+    model_glance(penguins_data),
+    pattern = map(penguins_data)
   ),
-  # Get model predictions
+  # Get predictions of combined model with all species together
+  combined_predictions = model_glance(penguins_data),
+  # Get predictions of one model per species
   tar_target(
-    model_predictions,
-    augment_with_mod_name(models),
-    pattern = map(models)
+    species_predictions,
+    model_augment(penguins_data),
+    pattern = map(penguins_data)
   )
 )

episodes/files/tar_functions/model_augment.R

@@ -1,4 +1,4 @@
-model_glance <- function(penguins_data) {
+model_augment <- function(penguins_data) {
   # Make model
   model <- lm(
     bill_depth_mm ~ bill_length_mm,

episodes/files/tar_functions/model_augment_slow.R

@@ -0,0 +1,17 @@
+model_augment_slow <- function(penguins_data) {
+  Sys.sleep(4)
+  # Make model
+  model <- lm(
+    bill_depth_mm ~ bill_length_mm,
+    data = penguins_data)
+  # Get species name
+  species_name <- unique(penguins_data$species)
+  # If this is the combined dataset with multiple
+  # species, changed name to 'combined'
+  if (length(species_name) > 1) {
+    species_name <- "combined"
+  }
+  # Get model summary and add species name
+  augment(model) |>
+    mutate(species = species_name, .before = 1)
+}

episodes/files/tar_functions/model_glance_slow.R

@@ -0,0 +1,17 @@
+model_glance_slow <- function(penguins_data) {
+  Sys.sleep(4)
+  # Make model
+  model <- lm(
+    bill_depth_mm ~ bill_length_mm,
+    data = penguins_data)
+  # Get species name
+  species_name <- unique(penguins_data$species)
+  # If this is the combined dataset with multiple
+  # species, changed name to 'combined'
+  if (length(species_name) > 1) {
+    species_name <- "combined"
+  }
+  # Get model summary and add species name
+  glance(model) |>
+    mutate(species = species_name, .before = 1)
+}