|
a |
|
b/man/create_dummy_data.Rd |
|
|
1 |
% Generated by roxygen2: do not edit by hand |
|
|
2 |
% Please edit documentation in R/write_dummy_data.R |
|
|
3 |
\name{create_dummy_data} |
|
|
4 |
\alias{create_dummy_data} |
|
|
5 |
\title{Write random sequences to fasta file} |
|
|
6 |
\usage{ |
|
|
7 |
create_dummy_data( |
|
|
8 |
file_path, |
|
|
9 |
num_files, |
|
|
10 |
header = "header", |
|
|
11 |
seq_length, |
|
|
12 |
num_seq, |
|
|
13 |
fasta_name_start = "file", |
|
|
14 |
write_to_file_path = FALSE, |
|
|
15 |
prob = NULL, |
|
|
16 |
vocabulary = c("a", "c", "g", "t") |
|
|
17 |
) |
|
|
18 |
} |
|
|
19 |
\arguments{ |
|
|
20 |
\item{file_path}{Output directory; can also be a file name but only possible if \code{write_to_file_path = TRUE} and |
|
|
21 |
\code{num_files = 1}).} |
|
|
22 |
|
|
|
23 |
\item{num_files}{Number of files to create.} |
|
|
24 |
|
|
|
25 |
\item{header}{Fasta header name.} |
|
|
26 |
|
|
|
27 |
\item{seq_length}{Length of one sequence. If vector longer than 1, will randomly sample from that vector.} |
|
|
28 |
|
|
|
29 |
\item{num_seq}{Number of sequences per file.} |
|
|
30 |
|
|
|
31 |
\item{fasta_name_start}{Beginning string of file name. Output files are named fasta_name_start + _i.fasta where i is an integer index.} |
|
|
32 |
|
|
|
33 |
\item{write_to_file_path}{Whether to write output directly to \code{file_path}, i.e. file_path is not a directory.} |
|
|
34 |
|
|
|
35 |
\item{prob}{Probability of each character in the \code{vocabulary} to be sampled. If \code{NULL} each character has same probability.} |
|
|
36 |
|
|
|
37 |
\item{vocabulary}{Set of characters to sample sequences from.} |
|
|
38 |
} |
|
|
39 |
\value{ |
|
|
40 |
None. Writes data to files. |
|
|
41 |
} |
|
|
42 |
\description{ |
|
|
43 |
Create random sequences from predefined vocabulary and write to fasta file. |
|
|
44 |
} |
|
|
45 |
\examples{ |
|
|
46 |
path_output <- tempfile() |
|
|
47 |
dir.create(path_output) |
|
|
48 |
create_dummy_data(file_path = path_output, |
|
|
49 |
num_files = 3, |
|
|
50 |
seq_length = 11, |
|
|
51 |
num_seq = 5, |
|
|
52 |
vocabulary = c("a", "c", "g", "t")) |
|
|
53 |
list.files(path_output) |
|
|
54 |
|
|
|
55 |
} |