CRAN Package Check Results for Package shapr

Last updated on 2025-10-30 09:50:02 CET.

Flavor	Version	Tinstall	Tcheck	Ttotal	Status	Flags
r-devel-linux-x86_64-debian-clang	1.0.5	84.07	441.61	525.68	OK
r-devel-linux-x86_64-debian-gcc	1.0.5	47.42	310.43	357.85	OK
r-devel-linux-x86_64-fedora-clang	1.0.5	154.00	707.02	861.02	OK
r-devel-linux-x86_64-fedora-gcc	1.0.5	150.00	690.56	840.56	OK
r-devel-windows-x86_64	1.0.5	96.00	357.00	453.00	ERROR
r-patched-linux-x86_64	1.0.5	86.80	420.09	506.89	OK
r-release-linux-x86_64	1.0.5	80.65	419.96	500.61	OK
r-release-macos-arm64	1.0.5	28.00	178.00	206.00	OK
r-release-macos-x86_64	1.0.5	38.00	370.00	408.00	WARN
r-release-windows-x86_64	1.0.5	97.00	374.00	471.00	ERROR
r-oldrel-macos-arm64	1.0.5	27.00	169.00	196.00	NOTE
r-oldrel-macos-x86_64	1.0.5	36.00	323.00	359.00	NOTE
r-oldrel-windows-x86_64	1.0.5	113.00	498.00	611.00	ERROR

Check Details

Version: 1.0.5
Check: tests
Result: ERROR Running 'testthat.R' [193s] Running the tests in 'tests/testthat.R' failed. Complete output: > # CRAN OMP THREAD LIMIT > Sys.setenv("OMP_THREAD_LIMIT" = 1) > > library(testthat) > library(shapr) Attaching package: 'shapr' The following object is masked from 'package:testthat': setup > > test_check("shapr") -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: gaussian * Procedure: Non-iterative * Number of Monte Carlo integration samples: 5 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: gaussian * Procedure: Non-iterative * Number of Monte Carlo integration samples: 5 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain_forecast()` ---------------------------------------- i Feature names extracted from the model contain `NA`. Consistency checks between model and data are therefore disabled. i `max_n_coalitions` is `NULL` or larger than `2^n_features = 128`, and is therefore set to `2^n_features = 128`. -- Explanation overview -- * Model class: <Arima> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 7 * Number of observations to explain: 2 -- Main computation started -- i Using 128 of 128 coalitions. -- Starting `shapr::explain_forecast()` ---------------------------------------- i Feature names extracted from the model contain `NA`. Consistency checks between model and data are therefore disabled. i `max_n_coalitions` is `NULL` or larger than `2^n_features = 64`, and is therefore set to `2^n_features = 64`. -- Explanation overview -- * Model class: <Arima> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 6 * Number of observations to explain: 2 -- Main computation started -- i Using 64 of 64 coalitions. -- Starting `shapr::explain_forecast()` ---------------------------------------- i Feature names extracted from the model contain `NA`. Consistency checks between model and data are therefore disabled. i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <Arima> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 2 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain_forecast()` ---------------------------------------- i Feature names extracted from the model contain `NA`. Consistency checks between model and data are therefore disabled. i `max_n_coalitions` is `NULL` or larger than `2^n_groups = 4`, and is therefore set to `2^n_groups = 4`. -- Explanation overview -- * Model class: <Arima> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of group-wise Shapley values: 2 * Number of observations to explain: 2 -- Main computation started -- i Using 4 of 4 coalitions. -- Starting `shapr::explain_forecast()` ---------------------------------------- i Feature names extracted from the model contain `NA`. Consistency checks between model and data are therefore disabled. i `max_n_coalitions` is `NULL` or larger than `2^n_groups = 4`, and is therefore set to `2^n_groups = 4`. -- Explanation overview -- * Model class: <Arima> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of group-wise Shapley values: 2 * Number of observations to explain: 2 -- Main computation started -- i Using 4 of 4 coalitions. -- Starting `shapr::explain_forecast()` ---------------------------------------- i Feature names extracted from the model contain `NA`. Consistency checks between model and data are therefore disabled. i `max_n_coalitions` is `NULL` or larger than `2^n_groups = 4`, and is therefore set to `2^n_groups = 4`. -- Explanation overview -- * Model class: <Arima> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of group-wise Shapley values: 2 * Number of observations to explain: 2 -- Main computation started -- i Using 4 of 4 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: independence * Procedure: Iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Iterative computation started -- -- Iteration 1 ----------------------------------------------------------------- i Using 6 of 32 coalitions, 6 new. -- Iteration 2 ----------------------------------------------------------------- i Using 8 of 32 coalitions, 2 new. -- Iteration 3 ----------------------------------------------------------------- i Using 10 of 32 coalitions, 2 new. -- Iteration 4 ----------------------------------------------------------------- i Using 12 of 32 coalitions, 2 new. -- Iteration 5 ----------------------------------------------------------------- i Using 14 of 32 coalitions, 2 new. -- Iteration 6 ----------------------------------------------------------------- i Using 16 of 32 coalitions, 2 new. -- Iteration 7 ----------------------------------------------------------------- i Using 18 of 32 coalitions, 2 new. -- Iteration 8 ----------------------------------------------------------------- i Using 20 of 32 coalitions, 2 new. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: gaussian * Procedure: Iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Iterative computation started -- -- Iteration 1 ----------------------------------------------------------------- i Using 6 of 32 coalitions, 6 new. -- Iteration 2 ----------------------------------------------------------------- i Using 8 of 32 coalitions, 2 new. -- Iteration 3 ----------------------------------------------------------------- i Using 12 of 32 coalitions, 4 new. -- Iteration 4 ----------------------------------------------------------------- i Using 16 of 32 coalitions, 4 new. -- Iteration 5 ----------------------------------------------------------------- i Using 18 of 32 coalitions, 2 new. -- Iteration 6 ----------------------------------------------------------------- i Using 22 of 32 coalitions, 4 new. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_groups = 32`, and is therefore set to `2^n_groups = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: gaussian * Procedure: Iterative * Number of Monte Carlo integration samples: 1000 * Number of group-wise Shapley values: 5 * Feature groups: Solar.R: {"Solar.R"}; Wind: {"Wind"}; Temp: {"Temp"}; Month: {"Month"}; Day: {"Day"} * Number of observations to explain: 3 -- Iterative computation started -- -- Iteration 1 ----------------------------------------------------------------- i Using 6 of 32 coalitions, 6 new. -- Iteration 2 ----------------------------------------------------------------- i Using 8 of 32 coalitions, 2 new. -- Iteration 3 ----------------------------------------------------------------- i Using 12 of 32 coalitions, 4 new. -- Iteration 4 ----------------------------------------------------------------- i Using 16 of 32 coalitions, 4 new. -- Iteration 5 ----------------------------------------------------------------- i Using 18 of 32 coalitions, 2 new. -- Iteration 6 ----------------------------------------------------------------- i Using 22 of 32 coalitions, 4 new. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: ctree * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: ctree * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: ctree * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 10 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: ctree * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of group-wise Shapley values: 3 * Feature groups: A: {"Solar.R", "Wind"}; B: {"Temp", "Month_factor"}; C: {"Day"} * Number of observations to explain: 3 -- Main computation started -- i Using 6 of 8 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: ctree * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: ctree * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: gaussian * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` at 2025-10-14 19:49:49 -------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: gaussian * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 * Computations (temporary) saved at: 'D:\temp\2025_10_14_01_50_00_4128\RtmpApJbpN\shapr_obj_108507f967355.rds' -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: independence, empirical, gaussian, and copula * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: independence, empirical, gaussian, and copula * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: independence, empirical, gaussian, and copula * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: gaussian, gaussian, gaussian, and gaussian * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: independence, empirical, independence, and empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: independence, empirical, independence, and empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: vaeac * Procedure: Non-iterative * Number of Monte Carlo integration samples: 10 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. Flavor: r-devel-windows-x86_64

Version: 1.0.5
Check: Rd files
Result: WARN additional_regression_setup.Rd: Sections \title, and \name must exist and be unique in Rd files aicc_full_cpp.Rd: Sections \title, and \name must exist and be unique in Rd files aicc_full_single_cpp.Rd: Sections \title, and \name must exist and be unique in Rd files append_vS_list.Rd: Sections \title, and \name must exist and be unique in Rd files categorical_to_one_hot_layer.Rd: Sections \title, and \name must exist and be unique in Rd files check_categorical_valid_MCsamp.Rd: Sections \title, and \name must exist and be unique in Rd files check_convergence.Rd: Sections \title, and \name must exist and be unique in Rd files check_groups.Rd: Sections \title, and \name must exist and be unique in Rd files check_verbose.Rd: Sections \title, and \name must exist and be unique in Rd files cli_compute_vS.Rd: Sections \title, and \name must exist and be unique in Rd files cli_iter.Rd: Sections \title, and \name must exist and be unique in Rd files cli_startup.Rd: Sections \title, and \name must exist and be unique in Rd files cli_topline.Rd: Sections \title, and \name must exist and be unique in Rd files coalition_matrix_cpp.Rd: Sections \title, and \name must exist and be unique in Rd files Error writing to connection: No space left on device compute_estimates.Rd: Sections \title, and \name must exist and be unique in Rd files compute_shapley.Rd: Sections \title, and \name must exist and be unique in Rd files compute_time.Rd: Sections \title, and \name must exist and be unique in Rd files compute_vS.Rd: Sections \title, and \name must exist and be unique in Rd files convert_feature_name_to_idx.Rd: Sections \title, and \name must exist and be unique in Rd files correction_matrix_cpp.Rd: Sections \title, and \name must exist and be unique in Rd files Error writing to connection: No space left on device create_ctree.Rd: Sections \title, and \name must exist and be unique in Rd files create_marginal_data_cat.Rd: Sections \title, and \name must exist and be unique in Rd files create_marginal_data_gaussian.Rd: Sections \title, and \name must exist and be unique in Rd files create_marginal_data_training.Rd: Sections \title, and \name must exist and be unique in Rd files default_doc_export.Rd: Sections \title, and \name must exist and be unique in Rd files default_doc_internal.Rd: Sections \title, and \name must exist and be unique in Rd files exact_coalition_table.Rd: Sections \title, and \name must exist and be unique in Rd files Error writing to connection: No space left on device Error writing to connection: No space left on device finalize_explanation.Rd: Sections \title, and \name must exist and be unique in Rd files format_convergence_info.Rd: Sections \title, and \name must exist and be unique in Rd files format_info_basic.Rd: Sections \title, and \name must exist and be unique in Rd files Warning in for (i in seq_along(specs)) { : closing unused connection 6 () Warning in for (i in seq_along(specs)) { : closing unused connection 5 () Warning in for (i in seq_along(specs)) { : closing unused connection 4 () Warning in for (i in seq_along(specs)) { : closing unused connection 3 () format_info_extra.Rd: Sections \title, and \name must exist and be unique in Rd files format_round.Rd: Sections \title, and \name must exist and be unique in Rd files format_shapley_info.Rd: Sections \title, and \name must exist and be unique in Rd files gauss_cat_loss.Rd: Sections \title, and \name must exist and be unique in Rd files gauss_cat_parameters.Rd: Sections \title, and \name must exist and be unique in Rd files gauss_cat_sampler_most_likely.Rd: Sections \title, and \name must exist and be unique in Rd files gauss_cat_sampler_random.Rd: Sections \title, and \name must exist and be unique in Rd files gaussian_transform.Rd: Sections \title, and \name must exist and be unique in Rd files gaussian_transform_separate.Rd: Sections \title, and \name must exist and be unique in Rd files get_S_causal_steps.Rd: Sections \title, and \name must exist and be unique in Rd files get_cov_mat.Rd: Sections \title, and \name must exist and be unique in Rd files get_data_forecast.Rd: Sections \title, and \name must exist and be unique in Rd files get_data_specs.Rd: Sections \title, and \name must exist and be unique in Rd files Error writing to connection: No space left on device get_extra_parameters.Rd: Sections \title, and \name must exist and be unique in Rd files get_feature_specs.Rd: Sections \title, and \name must exist and be unique in Rd files get_iterative_args_default.Rd: Sections \title, and \name must exist and be unique in Rd files get_max_n_coalitions_causal.Rd: Sections \title, and \name must exist and be unique in Rd files get_model_specs.Rd: Sections \title, and \name must exist and be unique in Rd files get_mu_vec.Rd: Sections \title, and \name must exist and be unique in Rd files get_nice_time.Rd: Sections \title, and \name must exist and be unique in Rd files get_output_args_default.Rd: Sections \title, and \name must exist and be unique in Rd files get_predict_model.Rd: Sections \title, and \name must exist and be unique in Rd files Error writing to connection: No space left on device get_supported_approaches.Rd: Sections \title, and \name must exist and be unique in Rd files get_supported_models.Rd: Sections \title, and \name must exist and be unique in Rd files get_valid_causal_coalitions.Rd: Sections \title, and \name must exist and be unique in Rd files group_forecast_setup.Rd: Sections \title, and \name must exist and be unique in Rd files hat_matrix_cpp.Rd: Sections \title, and \name must exist and be unique in Rd files inv_gaussian_transform_cpp.Rd: Sections \title, and \name must exist and be unique in Rd files lag_data.Rd: Sections \title, and \name must exist and be unique in Rd files mahalanobis_distance_cpp.Rd: Sections \title, and \name must exist and be unique in Rd files mcar_mask_generator.Rd: Sections \title, and \name must exist and be unique in Rd files memory_layer.Rd: Sections \title, and \name must exist and be unique in Rd files model_checker.Rd: Sections \title, and \name must exist and be unique in Rd files num_str.Rd: Sections \title, and \name must exist and be unique in Rd files observation_impute.Rd: Sections \title, and \name must exist and be unique in Rd files observation_impute_cpp.Rd: Sections \title, and \name must exist and be unique in Rd files paired_sampler.Rd: Sections \title, and \name must exist and be unique in Rd files Error writing to connection: No space left on device Error writing to connection: No space left on device Error writing to connection: No space left on device Error writing to connection: No space left on device Error writing to connection: No space left on device Error writing to connection: No space left on device prepare_data.Rd: Sections \title, and \name must exist and be unique in Rd files prepare_data_causal.Rd: Sections \title, and \name must exist and be unique in Rd files prepare_data_copula_cpp.Rd: Sections \title, and \name must exist and be unique in Rd files prepare_data_copula_cpp_caus.Rd: Sections \title, and \name must exist and be unique in Rd files prepare_data_gaussian_cpp.Rd: Sections \title, and \name must exist and be unique in Rd files prepare_data_gaussian_cpp_caus.Rd: Sections \title, and \name must exist and be unique in Rd files prepare_data_single_coalition.Rd: Sections \title, and \name must exist and be unique in Rd files prepare_next_iteration.Rd: Sections \title, and \name must exist and be unique in Rd files print.shapr.Rd: Sections \title, and \name must exist and be unique in Rd files print_iter.Rd: Sections \title, and \name must exist and be unique in Rd files process_factor_data.Rd: Sections \title, and \name must exist and be unique in Rd files quantile_type7_cpp.Rd: Sections \title, and \name must exist and be unique in Rd files reg_forecast_setup.Rd: Sections \title, and \name must exist and be unique in Rd files regression.check_namespaces.Rd: Sections \title, and \name must exist and be unique in Rd files regression.check_parameters.Rd: Sections \title, and \name must exist and be unique in Rd files regression.check_recipe_func.Rd: Sections \title, and \name must exist and be unique in Rd files regression.check_sur_n_comb.Rd: Sections \title, and \name must exist and be unique in Rd files regression.check_vfold_cv_para.Rd: Sections \title, and \name must exist and be unique in Rd files regression.cv_message.Rd: Sections \title, and \name must exist and be unique in Rd files regression.get_string_to_R.Rd: Sections \title, and \name must exist and be unique in Rd files Warning in for (block in blocks) { : closing unused connection 10 () Warning in for (block in blocks) { : closing unused connection 9 () Warning in for (block in blocks) { : closing unused connection 8 () Warning in for (block in blocks) { : closing unused connection 7 () Warning in for (block in blocks) { : closing unused connection 6 () Warning in for (block in blocks) { : closing unused connection 5 () Warning in for (block in blocks) { : closing unused connection 4 () Warning in for (block in blocks) { : closing unused connection 3 () round_manual.Rd: Sections \title, and \name must exist and be unique in Rd files rss_cpp.Rd: Sections \title, and \name must exist and be unique in Rd files Error writing to connection: No space left on device sample_coalitions_cpp_str_paired.Rd: Sections \title, and \name must exist and be unique in Rd files sample_combinations.Rd: Sections \title, and \name must exist and be unique in Rd files sample_ctree.Rd: Sections \title, and \name must exist and be unique in Rd files save_results.Rd: Sections \title, and \name must exist and be unique in Rd files Error writing to connection: No space left on device Error writing to connection: No space left on device shapley_setup.Rd: Sections \title, and \name must exist and be unique in Rd files shapley_weights.Rd: Sections \title, and \name must exist and be unique in Rd files shapr-package.Rd: Sections \title, and \name must exist and be unique in Rd files skip_connection.Rd: Sections \title, and \name must exist and be unique in Rd files specified_masks_mask_generator.Rd: Sections \title, and \name must exist and be unique in Rd files specified_prob_mask_generator.Rd: Sections \title, and \name must exist and be unique in Rd files summary.shapr.Rd: Sections \title, and \name must exist and be unique in Rd files test_predict_model.Rd: Sections \title, and \name must exist and be unique in Rd files testing_cleanup.Rd: Sections \title, and \name must exist and be unique in Rd files Error writing to connection: No space left on device vaeac_categorical_parse_params.Rd: Sections \title, and \name must exist and be unique in Rd files vaeac_check_activation_func.Rd: Sections \title, and \name must exist and be unique in Rd files vaeac_check_cuda.Rd: Sections \title, and \name must exist and be unique in Rd files vaeac_check_epoch_values.Rd: Sections \title, and \name must exist and be unique in Rd files vaeac_check_extra_named_list.Rd: Sections \title, and \name must exist and be unique in Rd files vaeac_check_logicals.Rd: Sections \title, and \name must exist and be unique in Rd files vaeac_check_mask_gen.Rd: Sections \title, and \name must exist and be unique in Rd files vaeac_check_masking_ratio.Rd: Sections \title, and \name must exist and be unique in Rd files Error writing to connection: No space left on device vaeac_check_positive_integers.Rd: Sections \title, and \name must exist and be unique in Rd files vaeac_check_positive_numerics.Rd: Sections \title, and \name must exist and be unique in Rd files vaeac_check_probabilities.Rd: Sections \title, and \name must exist and be unique in Rd files vaeac_check_save_names.Rd: Sections \title, and \name must exist and be unique in Rd files vaeac_check_save_parameters.Rd: Sections \title, and \name must exist and be unique in Rd files vaeac_check_which_vaeac_model.Rd: Sections \title, and \name must exist and be unique in Rd files vaeac_check_x_colnames.Rd: Sections \title, and \name must exist and be unique in Rd files vaeac_compute_normalization.Rd: Sections \title, and \name must exist and be unique in Rd files vaeac_dataset.Rd: Sections \title, and \name must exist and be unique in Rd files vaeac_extend_batch.Rd: Sections \title, and \name must exist and be unique in Rd files vaeac_get_current_save_state.Rd: Sections \title, and \name must exist and be unique in Rd files Error writing to connection: No space left on device vaeac_get_evaluation_criteria.Rd: Sections \title, and \name must exist and be unique in Rd files Error writing to connection: No space left on device vaeac_get_full_state_list.Rd: Sections \title, and \name must exist and be unique in Rd files vaeac_get_mask_generator_name.Rd: Sections \title, and \name must exist and be unique in Rd files vaeac_get_model_from_checkp.Rd: Sections \title, and \name must exist and be unique in Rd files vaeac_get_n_decimals.Rd: Sections \title, and \name must exist and be unique in Rd files vaeac_get_optimizer.Rd: Sections \title, and \name must exist and be unique in Rd files vaeac_get_save_file_names.Rd: Sections \title, and \name must exist and be unique in Rd files vaeac_get_val_iwae.Rd: Sections \title, and \name must exist and be unique in Rd files vaeac_get_x_explain_extended.Rd: Sections \title, and \name must exist and be unique in Rd files vaeac_impute_missing_entries.Rd: Sections \title, and \name must exist and be unique in Rd files vaeac_kl_normal_normal.Rd: Sections \title, and \name must exist and be unique in Rd files vaeac_normal_parse_params.Rd: Sections \title, and \name must exist and be unique in Rd files vaeac_normalize_data.Rd: Sections \title, and \name must exist and be unique in Rd files vaeac_postprocess_data.Rd: Sections \title, and \name must exist and be unique in Rd files vaeac_preprocess_data.Rd: Sections \title, and \name must exist and be unique in Rd files vaeac_print_train_summary.Rd: Sections \title, and \name must exist and be unique in Rd files vaeac_save_state.Rd: Sections \title, and \name must exist and be unique in Rd files Error writing to connection: No space left on device Error writing to connection: No space left on device vaeac_train_model_continue.Rd: Sections \title, and \name must exist and be unique in Rd files vaeac_update_para_locations.Rd: Sections \title, and \name must exist and be unique in Rd files vaeac_update_pretrained_model.Rd: Sections \title, and \name must exist and be unique in Rd files weight_matrix.Rd: Sections \title, and \name must exist and be unique in Rd files weight_matrix_cpp.Rd: Sections \title, and \name must exist and be unique in Rd files problems found in ‘additional_regression_setup.Rd’, ‘aicc_full_cpp.Rd’, ‘aicc_full_single_cpp.Rd’, ‘append_vS_list.Rd’, ‘categorical_to_one_hot_layer.Rd’, ‘check_categorical_valid_MCsamp.Rd’, ‘check_convergence.Rd’, ‘check_groups.Rd’, ‘check_verbose.Rd’, ‘cli_compute_vS.Rd’, ‘cli_iter.Rd’, ‘cli_startup.Rd’, ‘cli_topline.Rd’, ‘coalition_matrix_cpp.Rd’, ‘compute_MSEv_eval_crit.Rd’, ‘compute_estimates.Rd’, ‘compute_shapley.Rd’, ‘compute_time.Rd’, ‘compute_vS.Rd’, ‘convert_feature_name_to_idx.Rd’, ‘correction_matrix_cpp.Rd’, ‘create_coalition_table.Rd’, ‘create_ctree.Rd’, ‘create_marginal_data_cat.Rd’, ‘create_marginal_data_gaussian.Rd’, ‘create_marginal_data_training.Rd’, ‘default_doc_export.Rd’, ‘default_doc_internal.Rd’, ‘exact_coalition_table.Rd’, ‘explain.Rd’, ‘explain_forecast.Rd’, ‘finalize_explanation.Rd’, ‘format_convergence_info.Rd’, ‘format_info_basic.Rd’, ‘format_info_extra.Rd’, ‘format_round.Rd’, ‘format_shapley_info.Rd’, ‘gauss_cat_loss.Rd’, ‘gauss_cat_parameters.Rd’, ‘gauss_cat_sampler_most_likely.Rd’, ‘gauss_cat_sampler_random.Rd’, ‘gaussian_transform.Rd’, ‘gaussian_transform_separate.Rd’, ‘get_S_causal_steps.Rd’, ‘get_cov_mat.Rd’, ‘get_data_forecast.Rd’, ‘get_data_specs.Rd’, ‘get_extra_comp_args_default.Rd’, ‘get_extra_parameters.Rd’, ‘get_feature_specs.Rd’, ‘get_iterative_args_default.Rd’, ‘get_max_n_coalitions_causal.Rd’, ‘get_model_specs.Rd’, ‘get_mu_vec.Rd’, ‘get_nice_time.Rd’, ‘get_output_args_default.Rd’, ‘get_predict_model.Rd’, ‘get_results.Rd’, ‘get_supported_approaches.Rd’, ‘get_supported_models.Rd’, ‘get_valid_causal_coalitions.Rd’, ‘group_forecast_setup.Rd’, ‘hat_matrix_cpp.Rd’, ‘inv_gaussian_transform_cpp.Rd’, ‘lag_data.Rd’, ‘mahalanobis_distance_cpp.Rd’, ‘mcar_mask_generator.Rd’, ‘memory_layer.Rd’, ‘model_checker.Rd’, ‘num_str.Rd’, ‘observation_impute.Rd’, ‘observation_impute_cpp.Rd’, ‘paired_sampler.Rd’, ‘plot.shapr.Rd’, ‘plot_MSEv_eval_crit.Rd’, ‘plot_SV_several_approaches.Rd’, ‘plot_vaeac_eval_crit.Rd’, ‘plot_vaeac_imputed_ggpairs.Rd’, ‘predict_model.Rd’, ‘prepare_data.Rd’, ‘prepare_data_causal.Rd’, ‘prepare_data_copula_cpp.Rd’, ‘prepare_data_copula_cpp_caus.Rd’, ‘prepare_data_gaussian_cpp.Rd’, ‘prepare_data_gaussian_cpp_caus.Rd’, ‘prepare_data_single_coalition.Rd’, ‘prepare_next_iteration.Rd’, ‘print.shapr.Rd’, ‘print_iter.Rd’, ‘process_factor_data.Rd’, ‘quantile_type7_cpp.Rd’, ‘reg_forecast_setup.Rd’, ‘regression.check_namespaces.Rd’, ‘regression.check_parameters.Rd’, ‘regression.check_recipe_func.Rd’, ‘regression.check_sur_n_comb.Rd’, ‘regression.check_vfold_cv_para.Rd’, ‘regression.cv_message.Rd’, ‘regression.get_string_to_R.Rd’, ‘round_manual.Rd’, ‘rss_cpp.Rd’, ‘sample_coalition_table.Rd’, ‘sample_coalitions_cpp_str_paired.Rd’, ‘sample_combinations.Rd’, ‘sample_ctree.Rd’, ‘save_results.Rd’, ‘setup.Rd’, ‘setup_approach.Rd’, ‘shapley_setup.Rd’, ‘shapley_weights.Rd’, ‘shapr-package.Rd’, ‘skip_connection.Rd’, ‘specified_masks_mask_generator.Rd’, ‘specified_prob_mask_generator.Rd’, ‘summary.shapr.Rd’, ‘test_predict_model.Rd’, ‘testing_cleanup.Rd’, ‘vaeac.Rd’, ‘vaeac_categorical_parse_params.Rd’, ‘vaeac_check_activation_func.Rd’, ‘vaeac_check_cuda.Rd’, ‘vaeac_check_epoch_values.Rd’, ‘vaeac_check_extra_named_list.Rd’, ‘vaeac_check_logicals.Rd’, ‘vaeac_check_mask_gen.Rd’, ‘vaeac_check_masking_ratio.Rd’, ‘vaeac_check_parameters.Rd’, ‘vaeac_check_positive_integers.Rd’, ‘vaeac_check_positive_numerics.Rd’, ‘vaeac_check_probabilities.Rd’, ‘vaeac_check_save_names.Rd’, ‘vaeac_check_save_parameters.Rd’, ‘vaeac_check_which_vaeac_model.Rd’, ‘vaeac_check_x_colnames.Rd’, ‘vaeac_compute_normalization.Rd’, ‘vaeac_dataset.Rd’, ‘vaeac_extend_batch.Rd’, ‘vaeac_get_current_save_state.Rd’, ‘vaeac_get_data_objects.Rd’, ‘vaeac_get_evaluation_criteria.Rd’, ‘vaeac_get_extra_para_default.Rd’, ‘vaeac_get_full_state_list.Rd’, ‘vaeac_get_mask_generator_name.Rd’, ‘vaeac_get_model_from_checkp.Rd’, ‘vaeac_get_n_decimals.Rd’, ‘vaeac_get_optimizer.Rd’, ‘vaeac_get_save_file_names.Rd’, ‘vaeac_get_val_iwae.Rd’, ‘vaeac_get_x_explain_extended.Rd’, ‘vaeac_impute_missing_entries.Rd’, ‘vaeac_kl_normal_normal.Rd’, ‘vaeac_normal_parse_params.Rd’, ‘vaeac_normalize_data.Rd’, ‘vaeac_postprocess_data.Rd’, ‘vaeac_preprocess_data.Rd’, ‘vaeac_print_train_summary.Rd’, ‘vaeac_save_state.Rd’, ‘vaeac_train_model.Rd’, ‘vaeac_train_model_auxiliary.Rd’, ‘vaeac_train_model_continue.Rd’, ‘vaeac_update_para_locations.Rd’, ‘vaeac_update_pretrained_model.Rd’, ‘weight_matrix.Rd’, ‘weight_matrix_cpp.Rd’ Flavor: r-release-macos-x86_64

Version: 1.0.5
Check: tests
Result: ERROR Running 'testthat.R' [210s] Running the tests in 'tests/testthat.R' failed. Complete output: > # CRAN OMP THREAD LIMIT > Sys.setenv("OMP_THREAD_LIMIT" = 1) > > library(testthat) > library(shapr) Attaching package: 'shapr' The following object is masked from 'package:testthat': setup > > test_check("shapr") -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: gaussian * Procedure: Non-iterative * Number of Monte Carlo integration samples: 5 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: gaussian * Procedure: Non-iterative * Number of Monte Carlo integration samples: 5 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain_forecast()` ---------------------------------------- i Feature names extracted from the model contain `NA`. Consistency checks between model and data are therefore disabled. i `max_n_coalitions` is `NULL` or larger than `2^n_features = 128`, and is therefore set to `2^n_features = 128`. -- Explanation overview -- * Model class: <Arima> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 7 * Number of observations to explain: 2 -- Main computation started -- i Using 128 of 128 coalitions. -- Starting `shapr::explain_forecast()` ---------------------------------------- i Feature names extracted from the model contain `NA`. Consistency checks between model and data are therefore disabled. i `max_n_coalitions` is `NULL` or larger than `2^n_features = 64`, and is therefore set to `2^n_features = 64`. -- Explanation overview -- * Model class: <Arima> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 6 * Number of observations to explain: 2 -- Main computation started -- i Using 64 of 64 coalitions. -- Starting `shapr::explain_forecast()` ---------------------------------------- i Feature names extracted from the model contain `NA`. Consistency checks between model and data are therefore disabled. i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <Arima> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 2 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain_forecast()` ---------------------------------------- i Feature names extracted from the model contain `NA`. Consistency checks between model and data are therefore disabled. i `max_n_coalitions` is `NULL` or larger than `2^n_groups = 4`, and is therefore set to `2^n_groups = 4`. -- Explanation overview -- * Model class: <Arima> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of group-wise Shapley values: 2 * Number of observations to explain: 2 -- Main computation started -- i Using 4 of 4 coalitions. -- Starting `shapr::explain_forecast()` ---------------------------------------- i Feature names extracted from the model contain `NA`. Consistency checks between model and data are therefore disabled. i `max_n_coalitions` is `NULL` or larger than `2^n_groups = 4`, and is therefore set to `2^n_groups = 4`. -- Explanation overview -- * Model class: <Arima> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of group-wise Shapley values: 2 * Number of observations to explain: 2 -- Main computation started -- i Using 4 of 4 coalitions. -- Starting `shapr::explain_forecast()` ---------------------------------------- i Feature names extracted from the model contain `NA`. Consistency checks between model and data are therefore disabled. i `max_n_coalitions` is `NULL` or larger than `2^n_groups = 4`, and is therefore set to `2^n_groups = 4`. -- Explanation overview -- * Model class: <Arima> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of group-wise Shapley values: 2 * Number of observations to explain: 2 -- Main computation started -- i Using 4 of 4 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: independence * Procedure: Iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Iterative computation started -- -- Iteration 1 ----------------------------------------------------------------- i Using 6 of 32 coalitions, 6 new. -- Iteration 2 ----------------------------------------------------------------- i Using 8 of 32 coalitions, 2 new. -- Iteration 3 ----------------------------------------------------------------- i Using 10 of 32 coalitions, 2 new. -- Iteration 4 ----------------------------------------------------------------- i Using 12 of 32 coalitions, 2 new. -- Iteration 5 ----------------------------------------------------------------- i Using 14 of 32 coalitions, 2 new. -- Iteration 6 ----------------------------------------------------------------- i Using 16 of 32 coalitions, 2 new. -- Iteration 7 ----------------------------------------------------------------- i Using 18 of 32 coalitions, 2 new. -- Iteration 8 ----------------------------------------------------------------- i Using 20 of 32 coalitions, 2 new. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: gaussian * Procedure: Iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Iterative computation started -- -- Iteration 1 ----------------------------------------------------------------- i Using 6 of 32 coalitions, 6 new. -- Iteration 2 ----------------------------------------------------------------- i Using 8 of 32 coalitions, 2 new. -- Iteration 3 ----------------------------------------------------------------- i Using 12 of 32 coalitions, 4 new. -- Iteration 4 ----------------------------------------------------------------- i Using 16 of 32 coalitions, 4 new. -- Iteration 5 ----------------------------------------------------------------- i Using 18 of 32 coalitions, 2 new. -- Iteration 6 ----------------------------------------------------------------- i Using 22 of 32 coalitions, 4 new. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_groups = 32`, and is therefore set to `2^n_groups = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: gaussian * Procedure: Iterative * Number of Monte Carlo integration samples: 1000 * Number of group-wise Shapley values: 5 * Feature groups: Solar.R: {"Solar.R"}; Wind: {"Wind"}; Temp: {"Temp"}; Month: {"Month"}; Day: {"Day"} * Number of observations to explain: 3 -- Iterative computation started -- -- Iteration 1 ----------------------------------------------------------------- i Using 6 of 32 coalitions, 6 new. -- Iteration 2 ----------------------------------------------------------------- i Using 8 of 32 coalitions, 2 new. -- Iteration 3 ----------------------------------------------------------------- i Using 12 of 32 coalitions, 4 new. -- Iteration 4 ----------------------------------------------------------------- i Using 16 of 32 coalitions, 4 new. -- Iteration 5 ----------------------------------------------------------------- i Using 18 of 32 coalitions, 2 new. -- Iteration 6 ----------------------------------------------------------------- i Using 22 of 32 coalitions, 4 new. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: ctree * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: ctree * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: ctree * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 10 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: ctree * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of group-wise Shapley values: 3 * Feature groups: A: {"Solar.R", "Wind"}; B: {"Temp", "Month_factor"}; C: {"Day"} * Number of observations to explain: 3 -- Main computation started -- i Using 6 of 8 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: ctree * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: ctree * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: gaussian * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` at 2025-10-26 14:41:03 -------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: gaussian * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 * Computations (temporary) saved at: 'D:\temp\2025_10_26_01_50_00_14777\RtmpMjlaMQ\shapr_obj_b8a079154a9b.rds' -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: independence, empirical, gaussian, and copula * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: independence, empirical, gaussian, and copula * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: independence, empirical, gaussian, and copula * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: gaussian, gaussian, gaussian, and gaussian * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: independence, empirical, independence, and empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: independence, empirical, independence, and empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: vaeac * Procedure: Non-iterative * Number of Monte Carlo integration samples: 10 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: vaeac * Procedure: Non-iterative * Number of Monte Carlo integration samples: 10 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: gaussian * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_groups = 32`, and is therefore set to `2^n_groups = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: gaussian * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of group-wise Shapley values: 5 * Feature groups: Solar.R: {"Solar.R"}; Wind: {"Wind"}; Temp: {"Temp"}; Month: {"Month"}; Day: {"Day"} * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: independence * Procedure: Non-iterative * Number of Monte Carlo integration samples: 50 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 18 of 32 coalitions. -- Convergence info v Iterative Shapley value estimation stopped at 18 coalitions after 1 iterations, due to: Maximum number of iterations (1) reached! Maximum number of coalitions (18) reached! Final estimated Shapley values (sd) explain_id none Solar.R Wind Temp Month <int> <char> <char> <char> <char> <char> 1: 1 42.44 (0) -3.39 (0.80) 7.95 (0.62) 14.86 (3.27) -4.63 (2.39) 2: 2 42.44 (0) 3.08 (0.62) -3.56 (0.36) -4.64 (0.97) -6.03 (1.03) 3: 3 42.44 (0) 3.73 (0.60) -18.90 (0.68) -1.04 (1.40) -3.56 (1.36) Day <char> 1: -2.20 (2.47) 2: -2.74 (0.96) 3: 2.20 (0.96) -- Starting `shapr::explain()` ------------------------------------------------- -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: independence * Procedure: Non-iterative * Number of Monte Carlo integration samples: 50 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 20 of 32 coalitions. -- Convergence info v Iterative Shapley value estimation stopped at 20 coalitions after 1 iterations, due to: Maximum number of iterations (1) reached! Maximum number of coalitions (20) reached! Final estimated Shapley values (sd) explain_id none Solar.R Wind Temp Month <int> <char> <char> <char> <char> <char> 1: 1 42.44 (0) -4.33 (0.59) 7.52 (0.79) 17.47 (0.29) -5.01 (0.72) 2: 2 42.44 (0) 2.87 (0.55) -4.41 (0.35) -4.71 (0.16) -4.97 (0.50) 3: 3 42.44 (0) 3.35 (0.18) -18.35 (0.16) -1.83 (0.06) -2.82 (0.21) Day <char> 1: -3.06 (0.29) 2: -2.67 (0.16) 3: 2.08 (0.06) [ FAIL 2 | WARN 1 | SKIP 56 | PASS 48 ] ══ Skipped tests (56) ══════════════════════════════════════════════════════════ • On CRAN (56): 'test-asymmetric-causal-output.R:14:1', 'test-asymmetric-causal-setup.R:4:3', 'test-asymmetric-causal-setup.R:232:3', 'test-asymmetric-causal-setup.R:256:3', 'test-asymmetric-causal-setup.R:321:3', 'test-forecast-output.R:2:1', 'test-forecast-setup.R:7:3', 'test-forecast-setup.R:36:3', 'test-forecast-setup.R:114:3', 'test-forecast-setup.R:139:3', 'test-forecast-setup.R:166:3', 'test-forecast-setup.R:228:3', 'test-forecast-setup.R:302:3', 'test-forecast-setup.R:352:3', 'test-forecast-setup.R:448:3', 'test-forecast-setup.R:521:3', 'test-iterative-output.R:1:1', 'test-iterative-setup.R:79:3', 'test-iterative-setup.R:313:3', 'test-iterative-setup.R:398:3', 'test-plot.R:1:1', 'test-regression-output.R:1:1', 'test-regression-setup.R:11:3', 'test-regression-setup.R:49:3', 'test-regression-setup.R:177:3', 'test-regression-setup.R:235:3', 'test-regression-setup.R:297:3', 'test-regression-setup.R:338:3', 'test-regular-output.R:1:1', 'test-regular-setup.R:5:3', 'test-regular-setup.R:38:3', 'test-regular-setup.R:121:3', 'test-regular-setup.R:243:3', 'test-regular-setup.R:262:3', 'test-regular-setup.R:320:3', 'test-regular-setup.R:397:3', 'test-regular-setup.R:558:3', 'test-regular-setup.R:681:3', 'test-regular-setup.R:797:3', 'test-regular-setup.R:818:3', 'test-regular-setup.R:876:3', 'test-regular-setup.R:934:3', 'test-regular-setup.R:1040:3', 'test-regular-setup.R:1152:3', 'test-regular-setup.R:1225:3', 'test-regular-setup.R:1269:3', 'test-regular-setup.R:1794:3', 'test-regular-setup.R:1829:3', 'test-regular-setup.R:1852:3', 'test-semi-deterministic-output.R:1:1', 'test-semi-deterministic-setup.R:2:3', 'test-semi-deterministic-setup.R:23:3', 'test-semi-deterministic-setup.R:48:3', 'test-semi-deterministic-setup.R:97:3', 'test-semi-deterministic-setup.R:126:3', 'test-summary.R:1:1' ══ Failed tests ════════════════════════════════════════════════════════════════ ── Error ('test-regular-setup.R:1632:3'): vaeac_set_seed_works ───────────────── <std::runtime_error/C++Error/error/condition> Error in `cpp_torch_manual_seed(as.character(seed))`: Lantern is not loaded. Please use `install_torch()` to install additional dependencies. Backtrace: ▆ 1. └─shapr::explain(...) at test-regular-setup.R:1632:3 2. ├─shapr::setup_approach(internal, model = model, predict_model = predict_model) 3. └─shapr:::setup_approach.vaeac(internal, model = model, predict_model = predict_model) 4. ├─base::do.call(vaeac_train_model, c(vaeac_all_parameters, list(x_train = internal$data$x_train))) 5. └─shapr (local) `<fn>`(...) 6. └─torch::torch_manual_seed(seed) 7. └─torch:::cpp_torch_manual_seed(as.character(seed)) ── Error ('test-regular-setup.R:1678:3'): vaeac_pretreained_vaeac_model ──────── <std::runtime_error/C++Error/error/condition> Error in `cpp_torch_manual_seed(as.character(seed))`: Lantern is not loaded. Please use `install_torch()` to install additional dependencies. Backtrace: ▆ 1. └─shapr::explain(...) at test-regular-setup.R:1678:3 2. ├─shapr::setup_approach(internal, model = model, predict_model = predict_model) 3. └─shapr:::setup_approach.vaeac(internal, model = model, predict_model = predict_model) 4. ├─base::do.call(vaeac_train_model, c(vaeac_all_parameters, list(x_train = internal$data$x_train))) 5. └─shapr (local) `<fn>`(...) 6. └─torch::torch_manual_seed(seed) 7. └─torch:::cpp_torch_manual_seed(as.character(seed)) [ FAIL 2 | WARN 1 | SKIP 56 | PASS 48 ] Error: Test failures Execution halted Flavor: r-release-windows-x86_64

Version: 1.0.5
Check: installed package size
Result: NOTE installed size is 8.6Mb sub-directories of 1Mb or more: doc 3.3Mb libs 4.1Mb Flavors: r-oldrel-macos-arm64, r-oldrel-macos-x86_64, r-oldrel-windows-x86_64

Version: 1.0.5
Check: tests
Result: ERROR Running 'testthat.R' [305s] Running the tests in 'tests/testthat.R' failed. Complete output: > # CRAN OMP THREAD LIMIT > Sys.setenv("OMP_THREAD_LIMIT" = 1) > > library(testthat) > library(shapr) Attaching package: 'shapr' The following object is masked from 'package:testthat': setup > > test_check("shapr") -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: gaussian * Procedure: Non-iterative * Number of Monte Carlo integration samples: 5 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: gaussian * Procedure: Non-iterative * Number of Monte Carlo integration samples: 5 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain_forecast()` ---------------------------------------- i Feature names extracted from the model contain `NA`. Consistency checks between model and data are therefore disabled. i `max_n_coalitions` is `NULL` or larger than `2^n_features = 128`, and is therefore set to `2^n_features = 128`. -- Explanation overview -- * Model class: <Arima> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 7 * Number of observations to explain: 2 -- Main computation started -- i Using 128 of 128 coalitions. -- Starting `shapr::explain_forecast()` ---------------------------------------- i Feature names extracted from the model contain `NA`. Consistency checks between model and data are therefore disabled. i `max_n_coalitions` is `NULL` or larger than `2^n_features = 64`, and is therefore set to `2^n_features = 64`. -- Explanation overview -- * Model class: <Arima> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 6 * Number of observations to explain: 2 -- Main computation started -- i Using 64 of 64 coalitions. -- Starting `shapr::explain_forecast()` ---------------------------------------- i Feature names extracted from the model contain `NA`. Consistency checks between model and data are therefore disabled. i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <Arima> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 2 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain_forecast()` ---------------------------------------- i Feature names extracted from the model contain `NA`. Consistency checks between model and data are therefore disabled. i `max_n_coalitions` is `NULL` or larger than `2^n_groups = 4`, and is therefore set to `2^n_groups = 4`. -- Explanation overview -- * Model class: <Arima> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of group-wise Shapley values: 2 * Number of observations to explain: 2 -- Main computation started -- i Using 4 of 4 coalitions. -- Starting `shapr::explain_forecast()` ---------------------------------------- i Feature names extracted from the model contain `NA`. Consistency checks between model and data are therefore disabled. i `max_n_coalitions` is `NULL` or larger than `2^n_groups = 4`, and is therefore set to `2^n_groups = 4`. -- Explanation overview -- * Model class: <Arima> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of group-wise Shapley values: 2 * Number of observations to explain: 2 -- Main computation started -- i Using 4 of 4 coalitions. -- Starting `shapr::explain_forecast()` ---------------------------------------- i Feature names extracted from the model contain `NA`. Consistency checks between model and data are therefore disabled. i `max_n_coalitions` is `NULL` or larger than `2^n_groups = 4`, and is therefore set to `2^n_groups = 4`. -- Explanation overview -- * Model class: <Arima> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of group-wise Shapley values: 2 * Number of observations to explain: 2 -- Main computation started -- i Using 4 of 4 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: independence * Procedure: Iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Iterative computation started -- -- Iteration 1 ----------------------------------------------------------------- i Using 6 of 32 coalitions, 6 new. -- Iteration 2 ----------------------------------------------------------------- i Using 8 of 32 coalitions, 2 new. -- Iteration 3 ----------------------------------------------------------------- i Using 10 of 32 coalitions, 2 new. -- Iteration 4 ----------------------------------------------------------------- i Using 12 of 32 coalitions, 2 new. -- Iteration 5 ----------------------------------------------------------------- i Using 14 of 32 coalitions, 2 new. -- Iteration 6 ----------------------------------------------------------------- i Using 16 of 32 coalitions, 2 new. -- Iteration 7 ----------------------------------------------------------------- i Using 18 of 32 coalitions, 2 new. -- Iteration 8 ----------------------------------------------------------------- i Using 20 of 32 coalitions, 2 new. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: gaussian * Procedure: Iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Iterative computation started -- -- Iteration 1 ----------------------------------------------------------------- i Using 6 of 32 coalitions, 6 new. -- Iteration 2 ----------------------------------------------------------------- i Using 8 of 32 coalitions, 2 new. -- Iteration 3 ----------------------------------------------------------------- i Using 12 of 32 coalitions, 4 new. -- Iteration 4 ----------------------------------------------------------------- i Using 16 of 32 coalitions, 4 new. -- Iteration 5 ----------------------------------------------------------------- i Using 18 of 32 coalitions, 2 new. -- Iteration 6 ----------------------------------------------------------------- i Using 22 of 32 coalitions, 4 new. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_groups = 32`, and is therefore set to `2^n_groups = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: gaussian * Procedure: Iterative * Number of Monte Carlo integration samples: 1000 * Number of group-wise Shapley values: 5 * Feature groups: Solar.R: {"Solar.R"}; Wind: {"Wind"}; Temp: {"Temp"}; Month: {"Month"}; Day: {"Day"} * Number of observations to explain: 3 -- Iterative computation started -- -- Iteration 1 ----------------------------------------------------------------- i Using 6 of 32 coalitions, 6 new. -- Iteration 2 ----------------------------------------------------------------- i Using 8 of 32 coalitions, 2 new. -- Iteration 3 ----------------------------------------------------------------- i Using 12 of 32 coalitions, 4 new. -- Iteration 4 ----------------------------------------------------------------- i Using 16 of 32 coalitions, 4 new. -- Iteration 5 ----------------------------------------------------------------- i Using 18 of 32 coalitions, 2 new. -- Iteration 6 ----------------------------------------------------------------- i Using 22 of 32 coalitions, 4 new. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: ctree * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: ctree * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: ctree * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 10 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: ctree * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of group-wise Shapley values: 3 * Feature groups: A: {"Solar.R", "Wind"}; B: {"Temp", "Month_factor"}; C: {"Day"} * Number of observations to explain: 3 -- Main computation started -- i Using 6 of 8 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: ctree * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: ctree * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: gaussian * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` at 2025-10-22 01:43:53 -------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: gaussian * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 * Computations (temporary) saved at: 'D:\temp\2025_10_21_12_46_10_10564\RtmpSOCZ2O\shapr_obj_779425f428bb.rds' -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: independence, empirical, gaussian, and copula * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: independence, empirical, gaussian, and copula * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: independence, empirical, gaussian, and copula * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: gaussian, gaussian, gaussian, and gaussian * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: independence, empirical, independence, and empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: independence, empirical, independence, and empirical * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: vaeac * Procedure: Non-iterative * Number of Monte Carlo integration samples: 10 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: vaeac * Procedure: Non-iterative * Number of Monte Carlo integration samples: 10 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_features = 32`, and is therefore set to `2^n_features = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: gaussian * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- i `max_n_coalitions` is `NULL` or larger than `2^n_groups = 32`, and is therefore set to `2^n_groups = 32`. -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: gaussian * Procedure: Non-iterative * Number of Monte Carlo integration samples: 1000 * Number of group-wise Shapley values: 5 * Feature groups: Solar.R: {"Solar.R"}; Wind: {"Wind"}; Temp: {"Temp"}; Month: {"Month"}; Day: {"Day"} * Number of observations to explain: 3 -- Main computation started -- i Using 32 of 32 coalitions. -- Starting `shapr::explain()` ------------------------------------------------- -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: independence * Procedure: Non-iterative * Number of Monte Carlo integration samples: 50 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 18 of 32 coalitions. -- Convergence info v Iterative Shapley value estimation stopped at 18 coalitions after 1 iterations, due to: Maximum number of iterations (1) reached! Maximum number of coalitions (18) reached! Final estimated Shapley values (sd) explain_id none Solar.R Wind Temp Month <int> <char> <char> <char> <char> <char> 1: 1 42.44 (0) -3.39 (0.80) 7.95 (0.62) 14.86 (3.27) -4.63 (2.39) 2: 2 42.44 (0) 3.08 (0.62) -3.56 (0.36) -4.64 (0.97) -6.03 (1.03) 3: 3 42.44 (0) 3.73 (0.60) -18.90 (0.68) -1.04 (1.40) -3.56 (1.36) Day <char> 1: -2.20 (2.47) 2: -2.74 (0.96) 3: 2.20 (0.96) -- Starting `shapr::explain()` ------------------------------------------------- -- Explanation overview -- * Model class: <lm> * v(S) estimation class: Monte Carlo integration * Approach: independence * Procedure: Non-iterative * Number of Monte Carlo integration samples: 50 * Number of feature-wise Shapley values: 5 * Number of observations to explain: 3 -- Main computation started -- i Using 20 of 32 coalitions. -- Convergence info v Iterative Shapley value estimation stopped at 20 coalitions after 1 iterations, due to: Maximum number of iterations (1) reached! Maximum number of coalitions (20) reached! Final estimated Shapley values (sd) explain_id none Solar.R Wind Temp Month <int> <char> <char> <char> <char> <char> 1: 1 42.44 (0) -4.33 (0.59) 7.52 (0.79) 17.47 (0.29) -5.01 (0.72) 2: 2 42.44 (0) 2.87 (0.55) -4.41 (0.35) -4.71 (0.16) -4.97 (0.50) 3: 3 42.44 (0) 3.35 (0.18) -18.35 (0.16) -1.83 (0.06) -2.82 (0.21) Day <char> 1: -3.06 (0.29) 2: -2.67 (0.16) 3: 2.08 (0.06) [ FAIL 2 | WARN 1 | SKIP 56 | PASS 48 ] ══ Skipped tests (56) ══════════════════════════════════════════════════════════ • On CRAN (56): 'test-asymmetric-causal-output.R:14:1', 'test-asymmetric-causal-setup.R:4:3', 'test-asymmetric-causal-setup.R:232:3', 'test-asymmetric-causal-setup.R:256:3', 'test-asymmetric-causal-setup.R:321:3', 'test-forecast-output.R:2:1', 'test-forecast-setup.R:7:3', 'test-forecast-setup.R:36:3', 'test-forecast-setup.R:114:3', 'test-forecast-setup.R:139:3', 'test-forecast-setup.R:166:3', 'test-forecast-setup.R:228:3', 'test-forecast-setup.R:302:3', 'test-forecast-setup.R:352:3', 'test-forecast-setup.R:448:3', 'test-forecast-setup.R:521:3', 'test-iterative-output.R:1:1', 'test-iterative-setup.R:79:3', 'test-iterative-setup.R:313:3', 'test-iterative-setup.R:398:3', 'test-plot.R:1:1', 'test-regression-output.R:1:1', 'test-regression-setup.R:11:3', 'test-regression-setup.R:49:3', 'test-regression-setup.R:177:3', 'test-regression-setup.R:235:3', 'test-regression-setup.R:297:3', 'test-regression-setup.R:338:3', 'test-regular-output.R:1:1', 'test-regular-setup.R:5:3', 'test-regular-setup.R:38:3', 'test-regular-setup.R:121:3', 'test-regular-setup.R:243:3', 'test-regular-setup.R:262:3', 'test-regular-setup.R:320:3', 'test-regular-setup.R:397:3', 'test-regular-setup.R:558:3', 'test-regular-setup.R:681:3', 'test-regular-setup.R:797:3', 'test-regular-setup.R:818:3', 'test-regular-setup.R:876:3', 'test-regular-setup.R:934:3', 'test-regular-setup.R:1040:3', 'test-regular-setup.R:1152:3', 'test-regular-setup.R:1225:3', 'test-regular-setup.R:1269:3', 'test-regular-setup.R:1794:3', 'test-regular-setup.R:1829:3', 'test-regular-setup.R:1852:3', 'test-semi-deterministic-output.R:1:1', 'test-semi-deterministic-setup.R:2:3', 'test-semi-deterministic-setup.R:23:3', 'test-semi-deterministic-setup.R:48:3', 'test-semi-deterministic-setup.R:97:3', 'test-semi-deterministic-setup.R:126:3', 'test-summary.R:1:1' ══ Failed tests ════════════════════════════════════════════════════════════════ ── Error ('test-regular-setup.R:1632:3'): vaeac_set_seed_works ───────────────── <std::runtime_error/C++Error/error/condition> Error in `cpp_torch_manual_seed(as.character(seed))`: Lantern is not loaded. Please use `install_torch()` to install additional dependencies. Backtrace: ▆ 1. └─shapr::explain(...) at test-regular-setup.R:1632:3 2. ├─shapr::setup_approach(internal, model = model, predict_model = predict_model) 3. └─shapr:::setup_approach.vaeac(internal, model = model, predict_model = predict_model) 4. ├─base::do.call(vaeac_train_model, c(vaeac_all_parameters, list(x_train = internal$data$x_train))) 5. └─shapr (local) `<fn>`(...) 6. └─torch::torch_manual_seed(seed) 7. └─torch:::cpp_torch_manual_seed(as.character(seed)) ── Error ('test-regular-setup.R:1678:3'): vaeac_pretreained_vaeac_model ──────── <std::runtime_error/C++Error/error/condition> Error in `cpp_torch_manual_seed(as.character(seed))`: Lantern is not loaded. Please use `install_torch()` to install additional dependencies. Backtrace: ▆ 1. └─shapr::explain(...) at test-regular-setup.R:1678:3 2. ├─shapr::setup_approach(internal, model = model, predict_model = predict_model) 3. └─shapr:::setup_approach.vaeac(internal, model = model, predict_model = predict_model) 4. ├─base::do.call(vaeac_train_model, c(vaeac_all_parameters, list(x_train = internal$data$x_train))) 5. └─shapr (local) `<fn>`(...) 6. └─torch::torch_manual_seed(seed) 7. └─torch:::cpp_torch_manual_seed(as.character(seed)) [ FAIL 2 | WARN 1 | SKIP 56 | PASS 48 ] Error: Test failures Execution halted Flavor: r-oldrel-windows-x86_64