This function calculates the average values of high-dimensional data within each hexagonal bin.
Arguments
- .data
A data frame containing the high-dimensional data and 2D embeddings.
- column_start_text
The text that begin the column name of the high-D data
Examples
training_data <- s_curve_noise_training
num_bins_x <- 4
shape_value <- 1.833091
hexbin_data_object <- extract_hexbin_centroids(nldr_df = s_curve_noise_umap,
num_bins = num_bins_x, shape_val = shape_value)
df_bin_centroids <- hexbin_data_object$hexdf_data
UMAP_data_with_hb_id <- s_curve_noise_umap |> dplyr::mutate(hb_id = hexbin_data_object$hb_data@cID)
df_all <- dplyr::bind_cols(training_data |> dplyr::select(-ID), UMAP_data_with_hb_id)
avg_highD_data(df_all)
#> # A tibble: 16 × 8
#> hb_id x1 x2 x3 x4 x5 x6 x7
#> <int> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 1 -0.987 1.38 -1.16 0.00156 0.0112 -0.0293 0.00135
#> 2 2 -0.455 1.70 -1.84 0.00791 -0.00110 0.000331 -0.00257
#> 3 6 -0.340 0.428 -1.89 0.000996 -0.000543 -0.0536 -0.00196
#> 4 7 0.632 1.31 -1.72 0.0103 -0.0111 0.00934 0.00106
#> 5 11 -0.175 0.0562 -1.98 0.00204 -0.00179 0.0112 -0.00111
#> 6 12 0.572 0.0605 -1.76 0.00273 0.0107 0.0308 -0.00430
#> 7 13 0.980 0.552 -1.04 0.00143 -0.00296 0.0207 0.00641
#> 8 17 0.713 0.406 -0.298 -0.0133 0.0127 -0.0697 -0.00924
#> 9 18 0.737 1.35 -0.365 -0.000748 0.00380 0.0346 0.00109
#> 10 24 -0.0687 1.09 0.0180 0.0105 0.00131 -0.00516 0.00346
#> 11 28 -0.506 1.92 0.138 0.0159 -0.0149 -0.0841 0.00453
#> 12 29 -0.890 1.13 0.641 -0.00525 0.000260 0.0278 0.0000386
#> 13 38 -0.613 1.69 1.79 0.0119 -0.00418 -0.000519 -0.00251
#> 14 39 -0.210 0.584 1.88 -0.00330 0.00214 -0.00493 -0.000651
#> 15 44 0.536 1.67 1.71 0.00257 0.00381 -0.0135 0.000988
#> 16 45 0.807 0.611 1.48 -0.00346 0.00550 -0.00259 -0.00372