[R-package] fix warnings in demos (#4569)

* [R-package] fix warnings in demos

* Apply suggestions from code review

Co-authored-by: Nikita Titov <[email protected]>

* fix additional params issues in multiclass and categorical_feature examples

* Update R-package/demo/multiclass.R

Co-authored-by: Nikita Titov <[email protected]>

Co-authored-by: Nikita Titov <[email protected]>

.gitignore

@@ -326,7 +326,7 @@ coverage.xml
 .hypothesis/
 **/coverage.html
 **/coverage.html.zip
-R-package/tests/testthat/Rplots.pdf
+**/Rplots.pdf
 
 # Translations
 *.mo
@@ -427,6 +427,7 @@ miktex*.zip
 *.def
 
 # Files created by examples and tests
+*.buffer
 **/lgb-Dataset.data
 **/lgb.Dataset.data
 **/model.txt

R-package/demo/basic_walkthrough.R

@@ -12,29 +12,33 @@ test <- agaricus.test
 class(train$label)
 class(train$data)
 
+# Set parameters for model training
+train_params <- list(
+    num_leaves = 4L
+    , learning_rate = 1.0
+    , objective = "binary"
+    , nthread = 2L
+)
+
 #--------------------Basic Training using lightgbm----------------
 # This is the basic usage of lightgbm you can put matrix in data field
 # Note: we are putting in sparse matrix here, lightgbm naturally handles sparse input
 # Use sparse matrix when your feature is sparse (e.g. when you are using one-hot encoding vector)
 print("Training lightgbm with sparseMatrix")
 bst <- lightgbm(
     data = train$data
+    , params = train_params
     , label = train$label
-    , num_leaves = 4L
-    , learning_rate = 1.0
     , nrounds = 2L
-    , objective = "binary"
 )
 
 # Alternatively, you can put in dense matrix, i.e. basic R-matrix
 print("Training lightgbm with Matrix")
 bst <- lightgbm(
     data = as.matrix(train$data)
+    , params = train_params
     , label = train$label
-    , num_leaves = 4L
-    , learning_rate = 1.0
     , nrounds = 2L
-    , objective = "binary"
 )
 
 # You can also put in lgb.Dataset object, which stores label, data and other meta datas needed for advanced features
@@ -45,42 +49,32 @@ dtrain <- lgb.Dataset(
 )
 bst <- lightgbm(
     data = dtrain
-    , num_leaves = 4L
-    , learning_rate = 1.0
+    , params = train_params
     , nrounds = 2L
-    , objective = "binary"
 )
 
 # Verbose = 0,1,2
 print("Train lightgbm with verbose 0, no message")
 bst <- lightgbm(
     data = dtrain
-    , num_leaves = 4L
-    , learning_rate = 1.0
+    , params = train_params
     , nrounds = 2L
-    , objective = "binary"
     , verbose = 0L
 )
 
 print("Train lightgbm with verbose 1, print evaluation metric")
 bst <- lightgbm(
     data = dtrain
-    , num_leaves = 4L
-    , learning_rate = 1.0
+    , params = train_params
     , nrounds = 2L
-    , nthread = 2L
-    , objective = "binary"
     , verbose = 1L
 )
 
 print("Train lightgbm with verbose 2, also print information about tree")
 bst <- lightgbm(
     data = dtrain
-    , num_leaves = 4L
-    , learning_rate = 1.0
+    , params = train_params
     , nrounds = 2L
-    , nthread = 2L
-    , objective = "binary"
     , verbose = 2L
 )
 
@@ -126,25 +120,19 @@ valids <- list(train = dtrain, test = dtest)
 print("Train lightgbm using lgb.train with valids")
 bst <- lgb.train(
     data = dtrain
-    , num_leaves = 4L
-    , learning_rate = 1.0
+    , params = train_params
     , nrounds = 2L
     , valids = valids
-    , nthread = 2L
-    , objective = "binary"
 )
 
 # We can change evaluation metrics, or use multiple evaluation metrics
 print("Train lightgbm using lgb.train with valids, watch logloss and error")
 bst <- lgb.train(
     data = dtrain
-    , num_leaves = 4L
-    , learning_rate = 1.0
+    , params = train_params
     , nrounds = 2L
     , valids = valids
     , eval = c("binary_error", "binary_logloss")
-    , nthread = 2L
-    , objective = "binary"
 )
 
 # lgb.Dataset can also be saved using lgb.Dataset.save
@@ -154,12 +142,9 @@ lgb.Dataset.save(dtrain, "dtrain.buffer")
 dtrain2 <- lgb.Dataset("dtrain.buffer")
 bst <- lgb.train(
     data = dtrain2
-    , num_leaves = 4L
-    , learning_rate = 1.0
+    , params = train_params
     , nrounds = 2L
     , valids = valids
-    , nthread = 2L
-    , objective = "binary"
 )
 
 # information can be extracted from lgb.Dataset using getinfo

R-package/demo/categorical_features_rules.R

@@ -85,7 +85,6 @@ params <- list(
     , metric = "l2"
     , min_data = 1L
     , learning_rate = 0.1
-    , min_data = 0L
     , min_hessian = 1.0
     , max_depth = 2L
 )

R-package/demo/early_stopping.R

@@ -46,7 +46,7 @@ bst <- lgb.train(
   , dtrain
   , num_round
   , valids
-  , objective = logregobj
+  , obj = logregobj
   , eval = evalerror
   , early_stopping_round = 3L
 )

R-package/demo/leaf_stability.R

@@ -85,18 +85,21 @@ test <- agaricus.test
 dtest <- lgb.Dataset.create.valid(dtrain, test$data, label = test$label)
 
 # setup parameters and we train a model
-params <- list(objective = "regression", metric = "l2")
+params <- list(
+  objective = "regression"
+  , metric = "l2"
+  , min_data = 1L
+  , learning_rate = 0.1
+  , bagging_fraction = 0.1
+  , bagging_freq = 1L
+  , bagging_seed = 1L
+)
 valids <- list(test = dtest)
 model <- lgb.train(
     params
     , dtrain
     , 50L
     , valids
-    , min_data = 1L
-    , learning_rate = 0.1
-    , bagging_fraction = 0.1
-    , bagging_freq = 1L
-    , bagging_seed = 1L
 )
 
 # We create a data.frame with the following structure:
@@ -141,13 +144,17 @@ table(new_data$binned)
 .depth_density_plot(df = new_data)
 
 # Now, let's show with other parameters
+params <- list(
+  objective = "regression"
+  , metric = "l2"
+  , min_data = 1L
+  , learning_rate = 1.0
+)
 model2 <- lgb.train(
     params
     , dtrain
     , 100L
     , valids
-    , min_data = 1L
-    , learning_rate = 1.0
 )
 
 # We create the data structure, but for model2
@@ -193,13 +200,17 @@ table(new_data2$binned)
 .depth_density_plot(df = new_data2)
 
 # Now, try with very severe overfitting
+params <- list(
+  objective = "regression"
+  , metric = "l2"
+  , min_data = 1L
+  , learning_rate = 1.0
+)
 model3 <- lgb.train(
     params
     , dtrain
     , 1000L
     , valids
-    , min_data = 1L
-    , learning_rate = 1.0
 )
 
 # We create the data structure, but for model3

R-package/demo/multiclass.R

@@ -18,14 +18,18 @@ dtest <- lgb.Dataset.create.valid(dtrain, data = test[, 1L:4L], label = test[, 5
 valids <- list(test = dtest)
 
 # Method 1 of training
-params <- list(objective = "multiclass", metric = "multi_error", num_class = 3L)
+params <- list(
+    objective = "multiclass"
+    , metric = "multi_error"
+    , num_class = 3L
+    , min_data = 1L
+    , learning_rate = 1.0
+)
 model <- lgb.train(
     params
     , dtrain
     , 100L
     , valids
-    , min_data = 1L
-    , learning_rate = 1.0
     , early_stopping_rounds = 10L
 )
 
@@ -34,17 +38,19 @@ model <- lgb.train(
 my_preds <- predict(model, test[, 1L:4L])
 
 # Method 2 of training, identical
+params <- list(
+    min_data = 1L
+    , learning_rate = 1.0
+    , objective = "multiclass"
+    , metric = "multi_error"
+    , num_class = 3L
+)
 model <- lgb.train(
-    list()
+    params
     , dtrain
     , 100L
     , valids
-    , min_data = 1L
-    , learning_rate = 1.0
     , early_stopping_rounds = 10L
-    , objective = "multiclass"
-    , metric = "multi_error"
-    , num_class = 3L
 )
 
 # We can predict on test data, identical

R-package/demo/multiclass_custom_objective.R

@@ -20,18 +20,20 @@ valids <- list(train = dtrain, test = dtest)
 # Method 1 of training with built-in multiclass objective
 # Note: need to turn off boost from average to match custom objective
 # (https://github.com/microsoft/LightGBM/issues/1846)
+params <- list(
+    min_data = 1L
+    , learning_rate = 1.0
+    , num_class = 3L
+    , boost_from_average = FALSE
+    , metric = "multi_logloss"
+)
 model_builtin <- lgb.train(
-    list()
+    params
     , dtrain
-    , boost_from_average = FALSE
     , 100L
     , valids
-    , min_data = 1L
-    , learning_rate = 1.0
     , early_stopping_rounds = 10L
-    , objective = "multiclass"
-    , metric = "multi_logloss"
-    , num_class = 3L
+    , obj = "multiclass"
 )
 
 preds_builtin <- predict(model_builtin, test[, 1L:4L], rawscore = TRUE, reshape = TRUE)
@@ -92,17 +94,19 @@ custom_multiclass_metric <- function(preds, dtrain) {
     ))
 }
 
+params <- list(
+    min_data = 1L
+    , learning_rate = 1.0
+    , num_class = 3L
+)
 model_custom <- lgb.train(
-    list()
+    params
     , dtrain
     , 100L
     , valids
-    , min_data = 1L
-    , learning_rate = 1.0
     , early_stopping_rounds = 10L
-    , objective = custom_multiclass_obj
+    , obj = custom_multiclass_obj
     , eval = custom_multiclass_metric
-    , num_class = 3L
 )
 
 preds_custom <- predict(model_custom, test[, 1L:4L], rawscore = TRUE, reshape = TRUE)

R-package/demo/weight_param.R

@@ -34,14 +34,14 @@ params <- list(
     , num_leaves = 7L
     , max_depth = 3L
     , nthread = 1L
+    , min_data = 1L
+    , learning_rate = 1.0
 )
 model <- lgb.train(
     params
     , dtrain
     , 50L
     , valids
-    , min_data = 1L
-    , learning_rate = 1.0
     , early_stopping_rounds = 10L
 )
 weight_loss <- as.numeric(model$record_evals$test$l2$eval)
@@ -58,14 +58,14 @@ params <- list(
     , num_leaves = 7L
     , max_depth = 3L
     , nthread = 1L
+    , min_data = 1L
+    , learning_rate = 1.0
 )
 model <- lgb.train(
     params
     , dtrain
     , 50L
     , valids
-    , min_data = 1L
-    , learning_rate = 1.0
     , early_stopping_rounds = 10L
 )
 small_weight_loss <- as.numeric(model$record_evals$test$l2$eval)
@@ -94,14 +94,14 @@ params <- list(
     , num_leaves = 7L
     , max_depth = 3L
     , nthread = 1L
+    , min_data = 1L
+    , learning_rate = 1.0
 )
 model <- lgb.train(
     params
     , dtrain
     , 50L
     , valids
-    , min_data = 1L
-    , learning_rate = 1.0
     , early_stopping_rounds = 10L
 )
 large_weight_loss <- as.numeric(model$record_evals$test$l2$eval)