--- a
+++ b/man/get_generator.Rd
@@ -0,0 +1,262 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/generators.R
+\name{get_generator}
+\alias{get_generator}
+\title{Wrapper for generator functions}
+\usage{
+get_generator(
+  path = NULL,
+  train_type,
+  batch_size,
+  maxlen,
+  step = NULL,
+  shuffle_file_order = FALSE,
+  vocabulary = c("A", "C", "G", "T"),
+  seed = 1,
+  proportion_entries = NULL,
+  shuffle_input = FALSE,
+  format = "fasta",
+  path_file_log = NULL,
+  reverse_complement = FALSE,
+  n_gram = NULL,
+  n_gram_stride = NULL,
+  output_format = "target_right",
+  ambiguous_nuc = "zero",
+  proportion_per_seq = NULL,
+  skip_amb_nuc = NULL,
+  use_quality_score = FALSE,
+  padding = FALSE,
+  added_label_path = NULL,
+  target_from_csv = NULL,
+  add_input_as_seq = NULL,
+  max_samples = NULL,
+  concat_seq = NULL,
+  target_len = 1,
+  file_filter = NULL,
+  use_coverage = NULL,
+  sample_by_file_size = FALSE,
+  add_noise = NULL,
+  random_sampling = FALSE,
+  set_learning = NULL,
+  file_limit = NULL,
+  reverse_complement_encoding = FALSE,
+  read_data = FALSE,
+  target_split = NULL,
+  path_file_logVal = NULL,
+  model = NULL,
+  vocabulary_label = NULL,
+  masked_lm = NULL,
+  val = FALSE,
+  return_int = FALSE,
+  verbose = TRUE,
+  delete_used_files = FALSE,
+  reshape_xy = NULL
+)
+}
+\arguments{
+\item{path}{Path to training data. If \code{train_type} is \code{label_folder}, should be a vector or list
+where each entry corresponds to a class (list elements can be directories and/or individual files). If \code{train_type} is not \code{label_folder},
+can be a single directory or file or a list of directories and/or files.}
+
+\item{train_type}{Either \code{"lm"}, \code{"lm_rds"}, \code{"masked_lm"} for language model; \code{"label_header"}, \code{"label_folder"}, \code{"label_csv"}, \code{"label_rds"} for classification or \code{"dummy_gen"}.
+\itemize{
+\item Language model is trained to predict character(s) in a sequence. \cr
+\item \code{"label_header"}/\code{"label_folder"}/\code{"label_csv"} are trained to predict a corresponding class given a sequence as input.
+\item If \code{"label_header"}, class will be read from fasta headers.
+\item If \code{"label_folder"}, class will be read from folder, i.e. all files in one folder must belong to the same class.
+\item If \code{"label_csv"}, targets are read from a csv file. This file should have one column named "file". The targets then correspond to entries in that row (except "file"
+column). Example: if we are currently working with a file called "a.fasta" and corresponding label is "label_1", there should be a row in our csv file\tabular{lll}{
+   file \tab label_1 \tab label_2 \cr
+   "a.fasta" \tab 1 \tab 0 \cr
+}
+
+
+\item If \code{"label_rds"}, generator will iterate over set of .rds files containing each a list of input and target tensors. Not implemented for model
+with multiple inputs.
+\item If \code{"lm_rds"}, generator will iterate over set of .rds files and will split tensor according to \code{target_len} argument
+(targets are last \code{target_len} nucleotides of each sequence).
+\item  If \code{"dummy_gen"}, generator creates random data once and repeatedly feeds these to model.
+\item  If \code{"masked_lm"}, generator maskes some parts of the input. See \code{masked_lm} argument for details.
+}}
+
+\item{batch_size}{Number of samples used for one network update.}
+
+\item{maxlen}{Length of predictor sequence.}
+
+\item{step}{Frequency of sampling steps.}
+
+\item{shuffle_file_order}{Boolean, whether to go through files sequentially or shuffle beforehand.}
+
+\item{vocabulary}{Vector of allowed characters. Characters outside vocabulary get encoded as specified in \code{ambiguous_nuc}.}
+
+\item{seed}{Sets seed for reproducible results.}
+
+\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{shuffle_input}{Whether to shuffle entries in file.}
+
+\item{format}{File format, \code{"fasta"}, \code{"fastq"}, \code{"rds"} or \code{"fasta.tar.gz"}, \code{"fastq.tar.gz"} for \code{tar.gz} files.}
+
+\item{path_file_log}{Write name of files used for training 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{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{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{proportion_per_seq}{Numerical value between 0 and 1. Proportion of sequence to take samples from (use random subsequence).}
+
+\item{skip_amb_nuc}{Threshold of ambiguous nucleotides to accept in fasta entry. Complete entry will get discarded otherwise.}
+
+\item{use_quality_score}{Whether to use fastq quality scores. If \code{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{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{target_from_csv}{Path to csv file with target mapping. One column should be called "file" and other entries in row are the targets.}
+
+\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{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{sample_by_file_size}{Sample new file weighted by file size (bigger files more likely).}
+
+\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{random_sampling}{Whether samples should be taken from random positions when using \code{max_samples} argument. If \code{FALSE} random
+samples are taken from a consecutive subsequence.}
+
+\item{set_learning}{When you want to assign one label to set of samples. Only implemented for \code{train_type = "label_folder"}.
+Input is a list with the following parameters
+\itemize{
+\item \code{samples_per_target}: how many samples to use for one target.
+\item \code{maxlen}: length of one sample.
+\item \code{reshape_mode}: \verb{"time_dist", "multi_input"} or \code{"concat"}.
+\itemize{
+\item
+If \code{reshape_mode} is \code{"multi_input"}, generator will produce \code{samples_per_target} separate inputs, each of length \code{maxlen} (model should have
+\code{samples_per_target} input layers).
+\item If reshape_mode is \code{"time_dist"}, generator will produce a 4D input array. The dimensions correspond to
+\verb{(batch_size, samples_per_target, maxlen, length(vocabulary))}.
+\item If \code{reshape_mode} is \code{"concat"}, generator will concatenate \code{samples_per_target} sequences
+of length \code{maxlen} to one long sequence.
+}
+\item If \code{reshape_mode} is \code{"concat"}, there is an additional \code{buffer_len}
+argument. If \code{buffer_len} is an integer, the subsequences are interspaced with \code{buffer_len} rows. The input length is
+(\code{maxlen} \eqn{*} \code{samples_per_target}) + \code{buffer_len} \eqn{*} (\code{samples_per_target} - 1).
+}}
+
+\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{reverse_complement_encoding}{Whether to use both original sequence and reverse complement as two input sequences.}
+
+\item{read_data}{If \code{TRUE} the first element of output is a list of length 2, each containing one part of paired read. Maxlen should be 2*length of one read.}
+
+\item{target_split}{If target gets read from csv file, list of names to divide target tensor into list of tensors.
+Example: if csv file has header names \verb{"file", "label_1", "label_2", "label_3"} and \code{target_split = list(c("label_1", "label_2"), "label_3")},
+this will divide target matrix to list of length 2, where the first element contains columns named \code{"label_1"} and \code{"label_2"} and the
+second entry contains the column named \code{"label_3"}.}
+
+\item{path_file_logVal}{Path to csv file logging used validation files.}
+
+\item{model}{A keras model.}
+
+\item{vocabulary_label}{Character vector of possible targets. Targets outside \code{vocabulary_label} will get discarded if
+\code{train_type = "label_header"}.}
+
+\item{masked_lm}{If not \code{NULL}, input and target are equal except some parts of the input are masked or random.
+Must be list with the following arguments:
+\itemize{
+\item \code{mask_rate}: Rate of input to mask (rate of input to replace with mask token).
+\item \code{random_rate}: Rate of input to set to random token.
+\item \code{identity_rate}: Rate of input where sample weights are applied but input and output are identical.
+\item \code{include_sw}: Whether to include sample weights.
+\item \code{block_len} (optional): Masked/random/identity regions appear in blocks of size \code{block_len}.
+}}
+
+\item{val}{Logical, call initialized generator "genY" or "genValY" where Y is an integer between 1 and length of directories.}
+
+\item{return_int}{Whether to return integer encoding or one-hot encoding.}
+
+\item{verbose}{Whether to show messages.}
+
+\item{delete_used_files}{Whether to delete file once used. Only applies for rds files.}
+
+\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{
+For a detailed description see the data generator \href{https://deepg.de/articles/data_generator.html}{tutorial}.
+Will choose one of the generators from \code{\link{generator_fasta_lm}},
+\code{\link{generator_fasta_label_folder}}, \code{\link{generator_fasta_label_header_csv}},
+\code{\link{generator_rds}}, \code{\link{generator_random}}, \code{\link{generator_dummy}} or
+\code{\link{generator_fasta_lm}} according to the \code{train_type} and \code{random_sampling}
+arguments.
+}
+\examples{
+\dontshow{if (reticulate::py_module_available("tensorflow")) (if (getRversion() >= "3.4") withAutoprint else force)(\{ # examplesIf}
+# create dummy fasta files
+fasta_path <- tempfile()
+dir.create(fasta_path)
+create_dummy_data(file_path = fasta_path,
+                  num_files = 3,
+                  seq_length = 10,
+                  num_seq = 5,
+                  vocabulary = c("a", "c", "g", "t"))
+
+gen <- get_generator(path = fasta_path,
+                     maxlen = 5, train_type = "lm",
+                     output_format = "target_right",
+                     step = 3, batch_size = 7)
+z <- gen()
+x <- z[[1]]
+y <- z[[2]]
+dim(x)
+dim(y)
+\dontshow{\}) # examplesIf}
+}