dae.backends.storage package

Submodules

dae.backends.storage.filesystem_genotype_storage module

class dae.backends.storage.filesystem_genotype_storage.FilesystemGenotypeStorage(storage_config, section_id)[source]

Bases: dae.backends.storage.genotype_storage.GenotypeStorage

A storage that uses the filesystem as its backend.

build_backend(study_config, genome, gene_models)[source]
get_data_dir(*path)[source]
is_filestorage()[source]

Deprecated since version pending: remove from the API

simple_study_import(study_id, families_loader=None, variant_loaders=None, study_config=None, **kwargs)[source]

Handle import of simple studies.

dae.backends.storage.genotype_storage module

class dae.backends.storage.genotype_storage.GenotypeStorage(storage_config, storage_id)[source]

Bases: abc.ABC

Base class for genotype storages.

abstract build_backend(study_config, genome, gene_models)[source]
property id

Deprecated since version switch: to using storage_id

is_filestorage()[source]

Deprecated since version pending: remove from the API

is_impala()[source]

Deprecated since version pending: remove from the API

abstract simple_study_import(study_id, families_loader=None, variant_loaders=None, study_config=None, **kwargs)[source]

Handle import of simple studies.

dae.backends.storage.genotype_storage_factory module

class dae.backends.storage.genotype_storage_factory.GenotypeStorageFactory(dae_config)[source]

Bases: object

Create the correct Genotype Storage.

get_default_genotype_storage()[source]
get_genotype_storage(genotype_storage_id)[source]

Create and return a genotype storage with id genotype_storage_id.

get_genotype_storage_ids()[source]

dae.backends.storage.impala_genotype_storage module

class dae.backends.storage.impala_genotype_storage.ImpalaGenotypeStorage(storage_config, section_id)[source]

Bases: dae.backends.storage.genotype_storage.GenotypeStorage

Defines Apache Impala genotype storage.

build_backend(study_config, genome, gene_models)[source]
default_hdfs_study_path(study_id)[source]
default_pedigree_hdfs_filename(study_id)[source]
default_variants_hdfs_dirname(study_id)[source]
full_hdfs_path(hdfs_path)[source]
get_db()[source]
property hdfs_helpers

Create and return an HDFS helpers object.

hdfs_upload_dataset(study_id, variants_dir, pedigree_file, partition_description)[source]

Upload a variants dir and pedigree file to hdfs.

property impala_helpers
impala_import_dataset(study_id, pedigree_hdfs_file, variants_hdfs_dir, partition_description, variants_sample=None, variants_schema=None)[source]

Create pedigree and variant tables for a study.

impala_load_dataset(study_id, variants_dir, pedigree_file)[source]

Load a study data into impala genotype storage.

is_impala()[source]

Deprecated since version pending: remove from the API

property rsync_helpers
simple_study_import(study_id, families_loader=None, variant_loaders=None, study_config=None, output='.', include_reference=False, **kwargs)[source]

Handle import of simple studies.

classmethod study_tables(study_config)[source]

Return variants and pedigree tables names for a study.

dae.backends.storage.schema2_genotype_storage module

class dae.backends.storage.schema2_genotype_storage.HdfsStudyLayout(pedigree_file: str, summary_variant_dir: str, family_variant_dir: str, summary_sample: str, family_sample: str, meta_file: str)[source]

Bases: object

family_sample: str
family_variant_dir: str
meta_file: str
pedigree_file: str
summary_sample: str
summary_variant_dir: str
class dae.backends.storage.schema2_genotype_storage.Schema2GenotypeStorage(storage_config, section_id)[source]

Bases: dae.backends.storage.genotype_storage.GenotypeStorage

A genotype storing implementing the new schema2.

build_backend(study_config, genome, gene_models)[source]
property hdfs_helpers

Return the hdfs helper used to interact with hdfs.

hdfs_upload_dataset(study_id, variants_dir, pedigree_file, meta_file, partition_description) dae.backends.storage.schema2_genotype_storage.HdfsStudyLayout[source]

Upload local data to hdfs.

property impala_helpers
import_dataset(study_id, hdfs_study_layout: dae.backends.storage.schema2_genotype_storage.HdfsStudyLayout, partition_description)[source]

Load a dataset from HDFS into impala.

is_filestorage()[source]

Deprecated since version pending: remove from the API

is_impala()[source]

Deprecated since version pending: remove from the API

simple_study_import(study_id, families_loader=None, variant_loaders=None, study_config=None, **kwargs)[source]

Handle import of simple studies.

Module contents