Topic Probabilities per post

Usage

probabilities_segmentr(lda)

Arguments

lda: The LDA object made with fit_LDAs or par_fit_LDAs

Value

List of data frames of probabilities documents belong to topics

Examples

ldas <- SegmentR:::test_data(explore = FALSE)$lda$lda
#> Making DTMs
#> making tuning grid
#> setting up LDAs
probabilities <- purrr::map(
ldas,
probabilities_segmentr
)

probabilities[[1]]
#> # A tibble: 100 × 4
#>    document topic_1 topic_2 topic_3
#>       <dbl>   <dbl>   <dbl>   <dbl>
#>  1        1  0.298    0.476   0.226
#>  2        2  0.244    0.578   0.178
#>  3        3  0.367    0.367   0.267
#>  4        4  0.0208   0.646   0.333
#>  5        5  0.196    0.490   0.314
#>  6        6  0.111    0.361   0.528
#>  7        7  0.574    0.185   0.241
#>  8        8  0.540    0.206   0.254
#>  9        9  0.217    0.417   0.367
#> 10       10  0.406    0.362   0.232
#> # ℹ 90 more rows