Coerce object to a data frame
Source:R/generics.R, R/assoc.R, R/conc.R, and 5 more
as_data_frame.Rdas_data_frame() is an alternative to as.data.frame(). A number of objects
in mclm can be turned into dataframes with one of these functions.
Usage
as_data_frame(x, row.names = NULL, optional = FALSE, ...)
# S3 method for default
as_data_frame(x, row.names = NULL, optional = FALSE, ...)
# S3 method for assoc_scores
as.data.frame(x, ...)
# S3 method for conc
as.data.frame(x, ...)
# S3 method for fnames
as.data.frame(x, ...)
# S3 method for freqlist
as.data.frame(x, row.names = NULL, optional = FALSE, ...)
# S3 method for details.slma
as.data.frame(x, ...)
# S3 method for slma
as.data.frame(x, ...)
# S3 method for tokens
as.data.frame(x, ...)
# S3 method for types
as.data.frame(x, ...)Arguments
- x
Object to coerce to data.frame.
- row.names
NULLor a character vector giving the rownames for the dataframe.- optional
Logical. If
TRUE, setting rownames and converting column names is optional (seeas.data.frame()).- ...
Additional arguments
Value
Object of class data.frame
Examples
# for an assoc_scores object ---------------------
a <- c(10, 30, 15, 1)
b <- c(200, 1000, 5000, 300)
c <- c(100, 14, 16, 4)
d <- c(300, 5000, 10000, 6000)
types <- c("four", "fictitious", "toy", "examples")
(scores <- assoc_abcd(a, b, c, d, types = types))
#> Association scores (types in list: 4)
#> type a PMI G_signed| b c d dir exp_a DP_rows
#> 1 four 10 -1.921 -45.432| 200 100 300 -1 37.869 -0.202
#> 2 fictitious 30 2.000 56.959|1000 14 5000 1 7.498 0.026
#> 3 toy 15 0.536 2.984|5000 16 10000 1 10.343 0.001
#> 4 examples 1 2.067 1.473| 300 4 6000 1 0.239 0.003
#> <number of extra columns to the right: 7>
#>
as.data.frame(scores)
#> type a b c d dir exp_a DP_rows RR_rows OR
#> 1 four 10 200 100 300 -1 37.8688525 -0.202380952 0.1904762 0.15000
#> 2 fictitious 30 1000 14 5000 1 7.4983455 0.026334032 10.4313454 10.71429
#> 3 toy 15 5000 16 10000 1 10.3429579 0.001393583 1.8723829 1.87500
#> 4 examples 1 300 4 6000 1 0.2386994 0.002656037 4.9867110 5.00000
#> MS Dice PMI chi2_signed G_signed t
#> 1 0.047619048 0.062500000 -1.9210117 -38.158009 -45.431519 -8.8860423
#> 2 0.029126214 0.055865922 2.0003183 81.993003 56.958917 4.1184552
#> 3 0.002991027 0.005945303 0.5363137 3.153303 2.983872 1.2030435
#> 4 0.003322259 0.006535948 2.0667329 2.551819 1.473313 0.7613609
#> p_fisher_1
#> 1 1.000000e+00
#> 2 6.106227e-14
#> 3 5.916695e-02
#> 4 2.170331e-01
as_data_frame(scores)
#> type a b c d dir exp_a DP_rows RR_rows OR
#> 1 four 10 200 100 300 -1 37.8688525 -0.202380952 0.1904762 0.15000
#> 2 fictitious 30 1000 14 5000 1 7.4983455 0.026334032 10.4313454 10.71429
#> 3 toy 15 5000 16 10000 1 10.3429579 0.001393583 1.8723829 1.87500
#> 4 examples 1 300 4 6000 1 0.2386994 0.002656037 4.9867110 5.00000
#> MS Dice PMI chi2_signed G_signed t
#> 1 0.047619048 0.062500000 -1.9210117 -38.158009 -45.431519 -8.8860423
#> 2 0.029126214 0.055865922 2.0003183 81.993003 56.958917 4.1184552
#> 3 0.002991027 0.005945303 0.5363137 3.153303 2.983872 1.2030435
#> 4 0.003322259 0.006535948 2.0667329 2.551819 1.473313 0.7613609
#> p_fisher_1
#> 1 1.000000e+00
#> 2 6.106227e-14
#> 3 5.916695e-02
#> 4 2.170331e-01
# for a conc object ------------------------------
(conc_data <- conc('A very small corpus.', '\\w+', as_text = TRUE))
#> Concordance-based data frame (number of observations: 4)
#> idx left|match |right
#> 1 | A |very small corpus.
#> 2 A| very |small corpus.
#> 3 A very|small |corpus.
#> 4 A very small|corpus|.
#>
#> This data frame has 6 columns:
#> column
#> 1 glob_id
#> 2 id
#> 3 source
#> 4 left
#> 5 match
#> 6 right
as.data.frame(conc_data)
#> glob_id id source left match right
#> 1 1 1 - A very small corpus.
#> 2 2 2 - A very small corpus.
#> 3 3 3 - A very small corpus.
#> 4 4 4 - A very small corpus .
# for an fnames object ---------------------------
cwd_fnames <- as_fnames(c('file1', 'file2'))
as.data.frame(cwd_fnames)
#> filename
#> 1 file1
#> 2 file2
# for a freqlist, types or tokens object ---------
toy_corpus <- "Once upon a time there was a tiny toy corpus.
It consisted of three sentences. And it lived happily ever after."
(flist <- freqlist(toy_corpus, as_text = TRUE))
#> Frequency list (types in list: 19, tokens in list: 21)
#> rank type abs_freq nrm_freq
#> ---- --------- -------- --------
#> 1 a 2 952.381
#> 2 it 2 952.381
#> 3 after 1 476.190
#> 4 and 1 476.190
#> 5 consisted 1 476.190
#> 6 corpus 1 476.190
#> 7 ever 1 476.190
#> 8 happily 1 476.190
#> 9 lived 1 476.190
#> 10 of 1 476.190
#> 11 once 1 476.190
#> 12 sentences 1 476.190
#> 13 there 1 476.190
#> 14 three 1 476.190
#> 15 time 1 476.190
#> 16 tiny 1 476.190
#> 17 toy 1 476.190
#> 18 upon 1 476.190
#> 19 was 1 476.190
as.data.frame(flist)
#> rank type abs_freq nrm_freq
#> 1 1 a 2 952.3810
#> 2 2 it 2 952.3810
#> 3 3 after 1 476.1905
#> 4 4 and 1 476.1905
#> 5 5 consisted 1 476.1905
#> 6 6 corpus 1 476.1905
#> 7 7 ever 1 476.1905
#> 8 8 happily 1 476.1905
#> 9 9 lived 1 476.1905
#> 10 10 of 1 476.1905
#> 11 11 once 1 476.1905
#> 12 12 sentences 1 476.1905
#> 13 13 there 1 476.1905
#> 14 14 three 1 476.1905
#> 15 15 time 1 476.1905
#> 16 16 tiny 1 476.1905
#> 17 17 toy 1 476.1905
#> 18 18 upon 1 476.1905
#> 19 19 was 1 476.1905
(flist2 <- keep_re(flist, "^..?$"))
#> Frequency list (types in list: 3, tokens in list: 5)
#> <total number of tokens: 21>
#> rank orig_rank type abs_freq nrm_freq
#> ---- --------- ---- -------- --------
#> 1 1 a 2 952.381
#> 2 2 it 2 952.381
#> 3 10 of 1 476.190
as.data.frame
#> function (x, row.names = NULL, optional = FALSE, ...)
#> {
#> if (is.null(x))
#> return(as.data.frame(list()))
#> UseMethod("as.data.frame")
#> }
#> <bytecode: 0x561fc4f60440>
#> <environment: namespace:base>
(toks <- tokenize(toy_corpus))
#> Token sequence of length 21
#> idx token
#> --- ---------
#> 1 once
#> 2 upon
#> 3 a
#> 4 time
#> 5 there
#> 6 was
#> 7 a
#> 8 tiny
#> 9 toy
#> 10 corpus
#> 11 it
#> 12 consisted
#> 13 of
#> 14 three
#> 15 sentences
#> 16 and
#> 17 it
#> 18 lived
#> 19 happily
#> 20 ever
#> ...
#>
as.data.frame(toks)
#> token
#> 1 once
#> 2 upon
#> 3 a
#> 4 time
#> 5 there
#> 6 was
#> 7 a
#> 8 tiny
#> 9 toy
#> 10 corpus
#> 11 it
#> 12 consisted
#> 13 of
#> 14 three
#> 15 sentences
#> 16 and
#> 17 it
#> 18 lived
#> 19 happily
#> 20 ever
#> 21 after
(toks <- tokenize(toy_corpus))
#> Token sequence of length 21
#> idx token
#> --- ---------
#> 1 once
#> 2 upon
#> 3 a
#> 4 time
#> 5 there
#> 6 was
#> 7 a
#> 8 tiny
#> 9 toy
#> 10 corpus
#> 11 it
#> 12 consisted
#> 13 of
#> 14 three
#> 15 sentences
#> 16 and
#> 17 it
#> 18 lived
#> 19 happily
#> 20 ever
#> ...
#>
as.data.frame(toks)
#> token
#> 1 once
#> 2 upon
#> 3 a
#> 4 time
#> 5 there
#> 6 was
#> 7 a
#> 8 tiny
#> 9 toy
#> 10 corpus
#> 11 it
#> 12 consisted
#> 13 of
#> 14 three
#> 15 sentences
#> 16 and
#> 17 it
#> 18 lived
#> 19 happily
#> 20 ever
#> 21 after