`deeprvat.preprocessing.preprocess`

Module Contents

`drop_rows`
`ragged_to_matrix`
`process_sparse_gt_file`
`postprocess_sparse_gt`
`write_genotype_file`
`cli`
`add_variant_ids`
`get_file_chromosome`
`parse_file_path_list`
`process_individual_missingness`
`process_sparse_gt`
`combine_genotypes`

deeprvat.preprocessing.preprocess.drop_rows(df: pandas.DataFrame, df_to_drop: pandas.DataFrame) → pandas.DataFrame

deeprvat.preprocessing.preprocess.ragged_to_matrix(rows: List[numpy.ndarray], pad_value: int = -1, max_len: Optional[int] = None) → numpy.ndarray

deeprvat.preprocessing.preprocess.process_sparse_gt_file(file: str, variants: pandas.DataFrame, samples: List[str], calls_to_exclude: pandas.DataFrame = None) → Tuple[List[numpy.ndarray], List[numpy.ndarray]]

deeprvat.preprocessing.preprocess.postprocess_sparse_gt(processed: List[Tuple[List[numpy.ndarray], List[numpy.ndarray]]], result_index: int, n_rows: int) → numpy.ndarray

deeprvat.preprocessing.preprocess.write_genotype_file(f: h5py.File, samples: numpy.ndarray, variant_matrix: numpy.ndarray, genotype_matrix: numpy.ndarray, count_variants: Optional[numpy.ndarray] = None)

deeprvat.preprocessing.preprocess.add_variant_ids(variant_file: str, out_file: str, duplicates_file: str, chromosomes: Optional[str] = None)

deeprvat.preprocessing.preprocess.get_file_chromosome(file, col_names, chrom_field='chrom')

deeprvat.preprocessing.preprocess.parse_file_path_list(file_path_list_path: pathlib.Path)

deeprvat.preprocessing.preprocess.process_individual_missingness(threshold: float, file_paths_list: pathlib.Path, imiss_dir: str, out_file: str)

deeprvat.preprocessing.preprocess.process_sparse_gt(chunksize: int, exclude_variants: List[str], exclude_samples: Optional[str], exclude_calls: Optional[str], chromosomes: Optional[str], skip_sanity_checks: bool, variant_file: str, samples_path: str, sparse_gt: str, out_file: str)

deeprvat.preprocessing.preprocess.combine_genotypes(chunksize: Optional[int], genotype_files: List[str], out_file: str)