This function augments a dataset with predictions and error metrics obtained from a nonlinear dimension reduction (NLDR) model.
Arguments
- df_bin_centroids
Centroid coordinates of hexagonal bins in 2D space.
- df_bin
Centroid coordinates of hexagonal bins in high dimensions.
- training_data
Training data used to fit the model. If NULL, the training data is used (default is NULL).
- type_NLDR
The type of non-linear dimensionality reduction (NLDR) used.
- col_start
The text that begin the column name of the high-dimensional data.
Value
A tibble containing the augmented data with predictions, error metrics, and absolute error metrics.
Examples
df_bin_centroids <- s_curve_obj$s_curve_umap_model_obj$df_bin_centroids
df_bin <- s_curve_obj$s_curve_umap_model_obj$df_bin
augment(highd_data = s_curve_noise_training, model_2d = df_bin_centroids,
model_highd = df_bin)
#> # A tibble: 3,750 × 32
#> ID x1 x2 x3 x4 x5 x6 x7 pred_hb_id
#> <int> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <int>
#> 1 1 -0.120 1.64 -1.99 0.0104 0.0125 0.0923 -1.28e-3 200
#> 2 2 -0.0492 1.51 0.00121 -0.0177 0.00726 -0.0362 -5.35e-3 132
#> 3 3 -0.774 1.30 0.367 -0.00173 0.0156 -0.0962 3.35e-3 102
#> 4 5 -0.478 0.0177 -1.88 0.00848 0.00533 0.0998 6.77e-4 140
#> 5 6 0.818 0.927 -1.58 -0.00318 -0.00980 0.0989 6.96e-3 189
#> 6 7 0.910 1.40 1.42 0.00699 -0.0182 -0.0710 9.66e-3 79
#> 7 9 0.859 1.59 -0.488 -0.0119 0.00421 -0.00440 -5.95e-3 145
#> 8 10 -0.727 1.62 0.314 0.00251 0.0177 -0.0755 -3.69e-3 101
#> 9 11 -0.0400 1.23 0.000801 -0.00489 0.00570 0.0722 -7.89e-3 132
#> 10 12 0.765 0.510 1.64 -0.00641 -0.00941 -0.0708 9.89e-3 35
#> # ℹ 3,740 more rows
#> # ℹ 23 more variables: model_high_d_x1 <dbl>, model_high_d_x2 <dbl>,
#> # model_high_d_x3 <dbl>, model_high_d_x4 <dbl>, model_high_d_x5 <dbl>,
#> # model_high_d_x6 <dbl>, model_high_d_x7 <dbl>, error_square_x1 <dbl>,
#> # error_square_x2 <dbl>, error_square_x3 <dbl>, error_square_x4 <dbl>,
#> # error_square_x5 <dbl>, error_square_x6 <dbl>, error_square_x7 <dbl>,
#> # row_wise_total_error <dbl>, abs_error_x1 <dbl>, abs_error_x2 <dbl>, …