default_params_doc: This function does nothing. It is intended to inherit is...
In richelbilderbeek/gcaer: Interface to GCAE

default_params_doc

R Documentation

This function does nothing. It is intended to inherit is parameters' documentation.

Description

This function does nothing. It is intended to inherit is parameters' documentation.

Usage

default_params_doc(
  analyse_epochs,
  args,
  base_input_filename,
  base_output_filename,
  base_phenotype_value,
  bed_filename,
  bim_filename,
  csv_filename,
  csv_filename_for_nmse,
  data,
  datadir,
  data_opts_id,
  epoch,
  epochs,
  estimated_values,
  evaluate_filenames,
  evaluate_results,
  example_filename,
  fam_filename,
  file_extension,
  folder_name,
  gcae_experiment_params,
  gcae_experiment_params_filename,
  gcae_experiment_results,
  gcae_folder,
  gcae_input_data,
  gcae_input_filenames,
  gcae_options,
  gcae_options_filename,
  gcae_setup,
  gcae_setup_filename,
  gcae_version,
  gcaer_folder,
  genotype_concordances_filename,
  genotype_concordances_table,
  gif_filename,
  github_repo_branch_name,
  github_repo_url,
  labels_filename,
  labels_table,
  log_filename,
  losses_from_project_filename,
  losses_from_train_t_filename,
  losses_from_train_t_table,
  losses_from_train_v_filename,
  losses_from_train_v_table,
  metric,
  metrics,
  model,
  model_filename,
  model_id,
  n_neurons,
  nmse_in_time_filename,
  nmse_in_time_table,
  ormr_folder_name,
  os,
  out,
  phe_filename,
  plink_options,
  pheno_model_filename,
  pheno_model_id,
  phenotype_predictions_filename,
  phenotype_predictions_table,
  png_filename,
  project_filenames,
  python_bin_path,
  python_version,
  r_squared_in_time_filename,
  r_squared_in_time_table,
  resume_from,
  save_interval,
  score_per_pop_filename,
  score_per_pop_table,
  scores_filename,
  scores_table,
  superpops,
  train_filenames,
  train_times_table,
  train_opts_id,
  train_times_filename,
  trainedmodeldir,
  trainedmodelname,
  true_values,
  unique_id,
  url,
  verbose
)

Arguments

`analyse_epochs`	the epochs to analyse, e.g. `c(1, 2, 3)`, as checked by check_analyse_epochs
`args`	arguments for the `GCAE` executable
`base_input_filename`	the base of the filenames that are used as input for `GCAE`/`GCAE2`
`base_output_filename`	the base of the filenames that are used as output for `GCAE`/`GCAE2`
`base_phenotype_value`	the base phenotypic value for an additive trait, i.e. the phenotypic value for homozygotes of the common allele
`bed_filename`	name of a PLINK genotypes (`.bed`) file, as can be read using read_plink_bed_file
`bim_filename`	name of a PLINK `.bim` file as can be read using read_plink_bim_file
`csv_filename`	name of the comma-seperated (`.csv`) file to be produced, as checked by check_csv_filename
`csv_filename_for_nmse`	name for the comma-seperated file (as checked by check_csv_filename) to store the normalized mean square error compared to the identity line
`data`	file prefix, not including path, of the data files. The data files must be in EIGENSTRAT or PLINK binary (`.bed`, `.bim`, `.fam`) format)
`datadir`	directory where sample data is stored. If not absolute: assumed relative to `⁠GenoCAE/⁠` directory. A valid `datadir` ends with a slash (`/`) and does not start with a full stop (`.`), as to mimic the `GCAE` interface
`data_opts_id`	data options id, corresponding to a file data_opts/data_opts_id.json The data options affect how data is input to the model.
`epoch`	the epoch, as checked by check_epoch
`epochs`	number of epochs, as checked by check_epochs
`estimated_values`	estimated values
`evaluate_filenames`	names of the files returned by gcae_evaluate
`evaluate_results`	the results of a call to parse_evaluate_filenames, as checked by check_evaluate_results
`example_filename`	name of the example file
`fam_filename`	name of a PLINK `.fam` file as can be read using read_plink_fam_file
`file_extension`	a file extension, for example `.R` or `.csv`.
`folder_name`	name of a folder, as checked by check_folder_name
`gcae_experiment_params`	parameters to run a full `GCAE` experimenr (i.e. call do_gcae_experiment), as created by create_gcae_experiment_params and checked by check_gcae_experiment_params
`gcae_experiment_params_filename`	name of the file to save/read `gcae_experiment_params` to/from, using read_gcae_experiment_params_file and save_gcae_experiment_params
`gcae_experiment_results`	the results of a call to do_gcae_experiment, as checked by check_gcae_experiment_results
`gcae_folder`	folder where `GCAE` is installed
`gcae_input_data`	in-memory data that can be used as input for `GCAE`. Use linkread_gcae_input_files to read it from files, use check_gcae_input_data to check it for validity.
`gcae_input_filenames`	the GCAE input filenames, in the form of a list with the following elements: `bed_filename`: path to a `.bed` file, as can be read by read_plink_bed_file `bim_filename`: path to a `.bim` file, as can be read by read_plink_bim_file `fam_filename`: path to a `.fam` file, as can be read by read_plink_fam_file `phe_filename`: path to a `.phe` file, as can be read by read_plink_phe_file `labels_filename`: path to a `.csv` file as can be read by read_labels_file
`gcae_options`	options to run GCAE, as created by create_gcae_options
`gcae_options_filename`	name of a file to save/load a `gcae_options` to/from
`gcae_setup`	GCAE model setup, as created by create_gcae_setup, read from file by read_gcae_setup_file, checked by check_gcae_setup, and saved to file by save_gcae_setup.
`gcae_setup_filename`	name of a file to save/load a `gcae_setup` to/from
`gcae_version`	version of GCAE, e.g. `"1.0"` Use get_gcae_version to get the `GCAE` version.
`gcaer_folder`	name of the folder where gcaer stores its temporary files
`genotype_concordances_filename`	path to the `genotype_concordances.csv` file
`genotype_concordances_table`	genotype concordances in time, as can be checked by check_genotype_concordances_table
`gif_filename`	name of a GIF file, as checked by check_gif_filename
`github_repo_branch_name`	name of the `git` branch, e.g `master` or `Pheno`. Use get_default_github_repo_branch_name for the default value
`github_repo_url`	URL of the GitHub repository, e.g. `⁠https://github.com/kausmees/GenoCAE⁠` or `⁠https://github.com/cnettel/GenoCAE⁠` or `⁠https://github.com/richelbilderbeek/GenoCAE⁠`. Use get_default_github_repo_url for the default value
`labels_filename`	path to a `.csv` file containing super- and -population labels, as can be read by read_labels_file
`labels_table`	a table containing super- and -population labels, as can be read by read_labels_file. Note that `GCAE` does not use column names, `gcaer` adds these for convenience
`log_filename`	name of a `GCAE` `.log` file
`losses_from_project_filename`	path to the `losses_from_project.csv` file
`losses_from_train_t_filename`	path to the `losses_from_train_t.csv` file
`losses_from_train_t_table`	losses from training, measured in the training step, as can be checked by check_losses_from_train_t_table
`losses_from_train_v_filename`	path to the `losses_from_train_v.csv` file
`losses_from_train_v_table`	losses from training, measured in the validation step, as can be checked by check_losses_from_train_v_table
`metric`	the metric, as checked by check_metric. Use `""` to indicate not to use a clusting metric
`metrics`	the metrics, as checked by check_metrics. Use `""` to indicate not to use a clusting metric
`model`	the `GCAE` architecture, as checked by check_model. Use read_model_file to read a `GCAE` architecture from file. Use save_model to save the `model` to a JSON file. Use plot_model to plot the `model`. Use save_model_plot to save a plot of the `model` to file.
`model_filename`	name of a file that stores a `GCAE` architecture, as checked by check_model_filename. Use read_model_file to read a `GCAE` architecture from that file.
`model_id`	model id, corresponding to a file models/model_id.json
`n_neurons`	the number of neurons, as checked by check_n_neurons
`nmse_in_time_filename`	name of the file for the normalized mean squared error in time.
`nmse_in_time_table`	normalized mean squared error in time, as can be checked by check_nmse_in_time_table
`ormr_folder_name`	folder where the link[ormr]ormr R package installs the Python packages
`os`	name of the operating system, as returned by app_dir
`out`	the base filename of the output files. This parameter is named after the `GCAE` `--out` flag
`phe_filename`	name of a PLINK phenotype (`.phe`) file as can be read using read_plink_phe_file
`plink_options`	PLINK options, as created by create_plink_options
`pheno_model_filename`	name of a file that stores the phenotype prediction `GCAE` architecture, as checked by check_pheno_model_filename. Use read_pheno_model_file to read a `GCAE` pehnotype prediction architecture from that file.
`pheno_model_id`	phenotype model ID, as checked by check_pheno_model_id
`phenotype_predictions_filename`	name of a file for phenotype predictions
`phenotype_predictions_table`	a table of phenotype predictions, with a true and estimated value for all individuals at a certain epoch
`png_filename`	name of the `PNG` file to be produced, as checked by check_png_filename
`project_filenames`	path to the files as created (and returned) by gcae_project
`python_bin_path`	path to a `python` binary/executable
`python_version`	the Python version
`r_squared_in_time_filename`	name of the file for the `r_squared` in time.
`r_squared_in_time_table`	`r_squared` in time, as can be checked by check_r_squared_in_time_table
`resume_from`	the epoch to resume from, as checked by check_resume_from
`save_interval`	epoch intervals at which to save state of model, and at which to calculate the valid loss
`score_per_pop_filename`	name of a file containing the evaluation scores from the dimensionality reduction
`score_per_pop_table`	table that contains the dimensionality reduction scores per population
`scores_filename`	name of the files for F1 scores through time
`scores_table`	table that contains the dimensionality reduction scores
`superpops`	path to the `superpops` file, which contains the labels table and can be read using read_labels_file. This argument is named after the GCAE `--superpops` CLI flag.
`train_filenames`	path to the files as created (and returned) by gcae_train
`train_times_table`	a table with training time per epoch, as can be checked with check_train_times_table
`train_opts_id`	train options id, corresponding to a file train_opts/train_opts_id.json
`train_times_filename`	path to the `train_times.csv` file
`trainedmodeldir`	name of the folder to save the trained model to. A valid `trainedmodeldir` ends with a slash (`/`) as to mimic the `GCAE` interface
`trainedmodelname`	name of the trained model, which is `ae_out` by default
`true_values`	the true/known values
`unique_id`	the unique identifier of a setting
`url`	`GCAE` download URL
`verbose`	the verbosity of a function. Set to TRUE for more output. Use check_verbose to detect if this argument is valid.

Note

This is an internal function, so it should be marked with @noRd. This is not done, as this will disallow all functions to find the documentation parameters