--- a
+++ b/man/generator_fasta_lm.Rd
@@ -0,0 +1,167 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/generator_lm.R
+\name{generator_fasta_lm}
+\alias{generator_fasta_lm}
+\title{Language model generator for fasta/fastq files}
+\usage{
+generator_fasta_lm(
+  path_corpus,
+  format = "fasta",
+  batch_size = 256,
+  maxlen = 250,
+  max_iter = 10000,
+  vocabulary = c("a", "c", "g", "t"),
+  verbose = FALSE,
+  shuffle_file_order = FALSE,
+  step = 1,
+  seed = 1234,
+  shuffle_input = FALSE,
+  file_limit = NULL,
+  path_file_log = NULL,
+  reverse_complement = FALSE,
+  output_format = "target_right",
+  ambiguous_nuc = "zeros",
+  use_quality_score = FALSE,
+  proportion_per_seq = NULL,
+  padding = TRUE,
+  added_label_path = NULL,
+  add_input_as_seq = NULL,
+  skip_amb_nuc = NULL,
+  max_samples = NULL,
+  concat_seq = NULL,
+  target_len = 1,
+  file_filter = NULL,
+  use_coverage = NULL,
+  proportion_entries = NULL,
+  sample_by_file_size = FALSE,
+  n_gram = NULL,
+  n_gram_stride = 1,
+  add_noise = NULL,
+  return_int = FALSE,
+  reshape_xy = NULL
+)
+}
+\arguments{
+\item{path_corpus}{Input directory where fasta files are located or path to single file ending with fasta or fastq
+(as specified in format argument). Can also be a list of directories and/or files.}
+
+\item{format}{File format, either \code{"fasta"} or \code{"fastq"}.}
+
+\item{batch_size}{Number of samples in one batch.}
+
+\item{maxlen}{Length of predictor sequence.}
+
+\item{max_iter}{Stop after \code{max_iter} number of iterations failed to produce a new batch.}
+
+\item{vocabulary}{Vector of allowed characters. Characters outside vocabulary get encoded as specified in \code{ambiguous_nuc}.}
+
+\item{verbose}{Whether to show messages.}
+
+\item{shuffle_file_order}{Logical, whether to go through files randomly or sequentially.}
+
+\item{step}{How often to take a sample.}
+
+\item{seed}{Sets seed for \code{set.seed} function for reproducible results.}
+
+\item{shuffle_input}{Whether to shuffle entries in every fasta/fastq file before extracting samples.}
+
+\item{file_limit}{Integer or \code{NULL}. If integer, use only specified number of randomly sampled files for training. Ignored if greater than number of files in \code{path}.}
+
+\item{path_file_log}{Write name of files to csv file if path is specified.}
+
+\item{reverse_complement}{Boolean, for every new file decide randomly to use original data or its reverse complement.}
+
+\item{output_format}{Determines shape of output tensor for language model.
+Either \code{"target_right"}, \code{"target_middle_lstm"}, \code{"target_middle_cnn"} or \code{"wavenet"}.
+Assume a sequence \code{"AACCGTA"}. Output correspond as follows
+\itemize{
+\item \verb{"target_right": X = "AACCGT", Y = "A"}
+\item \verb{"target_middle_lstm": X = (X_1 = "AAC", X_2 = "ATG"), Y = "C"} (note reversed order of X_2)
+\item \verb{"target_middle_cnn": X = "AACGTA", Y = "C"}
+\item \verb{"wavenet": X = "AACCGT", Y = "ACCGTA"}
+}}
+
+\item{ambiguous_nuc}{How to handle nucleotides outside vocabulary, either \code{"zero"}, \code{"discard"}, \code{"empirical"} or \code{"equal"}.
+\itemize{
+\item If \code{"zero"}, input gets encoded as zero vector.
+\item If \code{"equal"}, input is repetition of \code{1/length(vocabulary)}.
+\item If \code{"discard"}, samples containing nucleotides outside vocabulary get discarded.
+\item If \code{"empirical"}, use nucleotide distribution of current file.
+}}
+
+\item{use_quality_score}{Whether to use fastq quality scores. If TRUE input is not one-hot-encoding but corresponds to probabilities.
+For example (0.97, 0.01, 0.01, 0.01) instead of (1, 0, 0, 0).}
+
+\item{proportion_per_seq}{Numerical value between 0 and 1. Proportion of sequence to take samples from (use random subsequence).}
+
+\item{padding}{Whether to pad sequences too short for one sample with zeros.}
+
+\item{added_label_path}{Path to file with additional input labels. Should be a csv file with one column named "file". Other columns should correspond to labels.}
+
+\item{add_input_as_seq}{Boolean vector specifying for each entry in \code{added_label_path} if rows from csv should be encoded as a sequence or used directly.
+If a row in your csv file is a sequence this should be \code{TRUE}. For example you may want to add another sequence, say ACCGT. Then this would correspond to 1,2,2,3,4 in
+csv file (if vocabulary = c("A", "C", "G", "T")).  If \code{add_input_as_seq} is \code{TRUE}, 12234 gets one-hot encoded, so added input is a 3D tensor.  If \code{add_input_as_seq} is
+\code{FALSE} this will feed network just raw data (a 2D tensor).}
+
+\item{skip_amb_nuc}{Threshold of ambiguous nucleotides to accept in fasta entry. Complete entry will get discarded otherwise.}
+
+\item{max_samples}{Maximum number of samples to use from one file. If not \code{NULL} and file has more than \code{max_samples} samples, will randomly choose a
+subset of \code{max_samples} samples.}
+
+\item{concat_seq}{Character string or \code{NULL}. If not \code{NULL} all entries from file get concatenated to one sequence with \code{concat_seq} string between them.
+Example: If 1.entry AACC, 2. entry TTTG and \code{concat_seq = "ZZZ"} this becomes AACCZZZTTTG.}
+
+\item{target_len}{Number of nucleotides to predict at once for language model.}
+
+\item{file_filter}{Vector of file names to use from path_corpus.}
+
+\item{use_coverage}{Integer or \code{NULL}. If not \code{NULL}, use coverage as encoding rather than one-hot encoding and normalize.
+Coverage information must be contained in fasta header: there must be a string \code{"cov_n"} in the header, where \code{n} is some integer.}
+
+\item{proportion_entries}{Proportion of fasta entries to keep. For example, if fasta file has 50 entries and \code{proportion_entries = 0.1},
+will randomly select 5 entries.}
+
+\item{sample_by_file_size}{Sample new file weighted by file size (bigger files more likely).}
+
+\item{n_gram}{Integer, encode target not nucleotide wise but combine n nucleotides at once. For example for \verb{n=2, "AA" ->  (1, 0,..., 0),}
+\verb{"AC" ->  (0, 1, 0,..., 0), "TT" -> (0,..., 0, 1)}, where the one-hot vectors have length \code{length(vocabulary)^n}.}
+
+\item{n_gram_stride}{Step size for n-gram encoding. For AACCGGTT with \code{n_gram = 4} and \code{n_gram_stride = 2}, generator encodes
+\verb{(AACC), (CCGG), (GGTT)}; for \code{n_gram_stride = 4} generator encodes \verb{(AACC), (GGTT)}.}
+
+\item{add_noise}{\code{NULL} or list of arguments. If not \code{NULL}, list must contain the following arguments: \code{noise_type} can be \code{"normal"} or \code{"uniform"};
+optional arguments \code{sd} or \code{mean} if noise_type is \code{"normal"} (default is \code{sd=1} and \code{mean=0}) or \verb{min, max} if \code{noise_type} is \code{"uniform"}
+(default is \verb{min=0, max=1}).}
+
+\item{return_int}{Whether to return integer encoding or one-hot encoding.}
+
+\item{reshape_xy}{Can be a list of functions to apply to input and/or target. List elements (containing the reshape functions)
+must be called x for input or y for target and each have arguments called x and y. For example:
+\code{reshape_xy = list(x = function(x, y) {return(x+1)}, y = function(x, y) {return(x+y)})} .
+For rds generator needs to have an additional argument called sw.}
+}
+\value{
+A generator function.
+}
+\description{
+Iterates over folder containing fasta/fastq files and produces encoding of predictor sequences
+and target variables. Will take a sequence of fixed size and use some part of sequence as input and other part as target.
+}
+\examples{
+\dontshow{if (reticulate::py_module_available("tensorflow")) (if (getRversion() >= "3.4") withAutoprint else force)(\{ # examplesIf}
+# create dummy fasta files
+path_input_1 <- tempfile()
+dir.create(path_input_1)
+create_dummy_data(file_path = path_input_1,
+                  num_files = 2,
+                  seq_length = 8,
+                  num_seq = 1,
+                  vocabulary = c("a", "c", "g", "t"))
+
+gen <- generator_fasta_lm(path_corpus = path_input_1, batch_size = 2,
+                                   maxlen = 7)
+z <- gen()
+dim(z[[1]])
+z[[2]]
+\dontshow{\}) # examplesIf}
+}