dae.backends.impala package

Submodules

dae.backends.impala.base_query_builder module

class dae.backends.impala.base_query_builder.BaseQueryBuilder(db, variants_table, pedigree_table, variants_schema, table_properties, pedigree_schema, pedigree_df, gene_models=None)[source]

Bases: abc.ABC

A base class for all query builders.

GENE_REGIONS_HEURISTIC_CUTOFF = 20
GENE_REGIONS_HEURISTIC_EXTEND = 20000
MAX_CHILD_NUMBER = 9999
QUOTE = "'"
WHERE = '\n        WHERE\n            {where}\n    '
build_from()[source]
abstract build_group_by()[source]
abstract build_join()[source]
build_limit(limit)[source]
build_select()[source]
build_where(regions=None, genes=None, effect_types=None, family_ids=None, person_ids=None, inheritance=None, roles=None, sexes=None, variant_type=None, real_attr_filter=None, ultra_rare=None, frequency_filter=None, return_reference=None, return_unknown=None, **_kwargs)[source]

Build the where clause of a query.

abstract create_row_deserializer(serializer)[source]
property product
reset_product()[source]

dae.backends.impala.family_variants_query_builder module

class dae.backends.impala.family_variants_query_builder.FamilyVariantsQueryBuilder(db, variants_table, pedigree_table, variants_schema, table_properties, pedigree_schema, pedigree_df, families, gene_models=None, do_join=False)[source]

Bases: dae.backends.impala.base_query_builder.BaseQueryBuilder

Build queries related to family variants.

build_from()[source]
build_group_by()[source]
build_join()[source]
build_where(regions=None, genes=None, effect_types=None, family_ids=None, person_ids=None, inheritance=None, roles=None, sexes=None, variant_type=None, real_attr_filter=None, ultra_rare=None, frequency_filter=None, return_reference=None, return_unknown=None, pedigree_fields=None)[source]

Build the where clause of a query.

create_row_deserializer(serializer)[source]

dae.backends.impala.hdfs_helpers module

class dae.backends.impala.hdfs_helpers.HdfsHelpers(hdfs_host, hdfs_port, replication=None)[source]

Bases: object

Helper methods for working with HDFS.

delete(path, recursive=False)[source]
exists(path)[source]
filesystem()[source]
get(hdfs_filename, local_filename)[source]
property hdfs

Return a file system for working with HDFS.

isdir(hdfs_dirname)[source]
isfile(hdfs_filename)[source]
list_dir(hdfs_dirname)[source]
list_parquet_files(hdfs_dirname, regexp='.*\\.parquet')[source]

List all parquet files in hdfs_dirname.

makedirs(path)[source]

Make all dire alone the path.

mkdir(path)[source]
put(local_filename, hdfs_filename)[source]
put_content(local_path, hdfs_dirname)[source]

Copy local_path to hdfs_dirname.

put_in_directory(local_file, hdfs_dirname)[source]
rename(path, new_path)[source]
tempdir(prefix='', suffix='')[source]

dae.backends.impala.impala_helpers module

class dae.backends.impala.impala_helpers.ImpalaHelpers(impala_hosts, impala_port=21050, pool_size=1)[source]

Bases: object

Helper methods for working with impala.

check_database(dbname)[source]

Check if dbname exists.

check_table(dbname, tablename)[source]

Check if dbname.tablename exists.

connection(timeout: Optional[float] = None)[source]

Create a new connection to the impala host.

create_database(dbname)[source]
drop_database(dbname)[source]
drop_table(dbname, tablename)[source]
get_table_create_statement(db, table)[source]

Get the create statement for table.

import_pedigree_into_db(db, pedigree_table, pedigree_hdfs_file)[source]
import_variants_into_db(db, variants_table, variants_hdfs_dir, partition_description, variants_sample=None, variants_schema=None)[source]

Import variant parquet files in variants_hdfs_dir in impala.

recreate_table(db, table, new_table, new_hdfs_dir)[source]

Recreate a table.

rename_table(db, table, new_table)[source]

Rename db.table to new_table.

dae.backends.impala.impala_query_director module

class dae.backends.impala.impala_query_director.ImpalaQueryDirector(query_builder)[source]

Bases: object

Build a query in the right order.

build_query(regions=None, genes=None, effect_types=None, family_ids=None, person_ids=None, inheritance=None, roles=None, sexes=None, variant_type=None, real_attr_filter=None, ultra_rare=None, frequency_filter=None, return_reference=None, return_unknown=None, limit=None, pedigree_fields=None)[source]

Build a query in the right order.

dae.backends.impala.impala_variants module

class dae.backends.impala.impala_variants.ImpalaQueryRunner(connection_pool, query, deserializer=None)[source]

Bases: dae.backends.query_runners.QueryRunner

Run a query in a separate thread.

connect()[source]

Connect to the connection pool and return the connection.

run()[source]
class dae.backends.impala.impala_variants.ImpalaVariants(impala_helpers, db, variants_table, pedigree_table, gene_models=None)[source]

Bases: object

A backend implementing an impala backend.

TYPE_MAP: Dict[str, Any] = {'bigint': (<class 'int'>, DataType(int64)), 'binary': (<class 'bytes'>, DataType(binary)), 'bool': (<class 'bool'>, DataType(bool)), 'boolean': (<class 'bool'>, DataType(bool)), 'float': (<class 'float'>, DataType(float)), 'float32': (<class 'float'>, DataType(float)), 'float64': (<class 'float'>, DataType(double)), 'int': (<class 'int'>, DataType(int32)), 'int16': (<class 'int'>, DataType(int16)), 'int32': (<class 'int'>, DataType(int32)), 'int64': (<class 'int'>, DataType(int64)), 'int8': (<class 'int'>, DataType(int8)), 'list(float)': (<class 'list'>, ListType(list<item: double>)), 'list(int)': (<class 'list'>, ListType(list<item: int32>)), 'list(str)': (<class 'list'>, ListType(list<item: string>)), 'smallint': (<class 'int'>, DataType(int16)), 'str': (<class 'str'>, DataType(string)), 'string': (<class 'bytes'>, DataType(string)), 'tinyint': (<class 'int'>, DataType(int8))}
build_count_query(regions=None, genes=None, effect_types=None, family_ids=None, person_ids=None, inheritance=None, roles=None, sexes=None, variant_type=None, real_attr_filter=None, ultra_rare=None, return_reference=None, return_unknown=None, limit=None)[source]

Build a query that counts variants.

build_family_variants_query_runner(regions=None, genes=None, effect_types=None, family_ids=None, person_ids=None, inheritance=None, roles=None, sexes=None, variant_type=None, real_attr_filter=None, ultra_rare=None, frequency_filter=None, return_reference=None, return_unknown=None, limit=None, pedigree_fields=None)[source]

Build a query selecting the appropriate family variants.

static build_person_set_collection_query(person_set_collection: dae.person_sets.PersonSetCollection, person_set_collection_query: Tuple[str, Set[str]])[source]

No idea what it does. If you know please edit.

build_summary_variants_query_runner(regions=None, genes=None, effect_types=None, family_ids=None, person_ids=None, inheritance=None, roles=None, sexes=None, variant_type=None, real_attr_filter=None, ultra_rare=None, frequency_filter=None, return_reference=None, return_unknown=None, limit=None)[source]

Build a query selecting the appropriate summary variants.

connection()[source]
property connection_pool
property executor
query_summary_variants(regions=None, genes=None, effect_types=None, family_ids=None, person_ids=None, inheritance=None, roles=None, sexes=None, variant_type=None, real_attr_filter=None, ultra_rare=None, frequency_filter=None, return_reference=None, return_unknown=None, limit=None)[source]

Query summary variants.

query_variants(regions=None, genes=None, effect_types=None, family_ids=None, person_ids=None, inheritance=None, roles=None, sexes=None, variant_type=None, real_attr_filter=None, ultra_rare=None, frequency_filter=None, return_reference=None, return_unknown=None, limit=None, pedigree_fields=None)[source]

Query family variants.

dae.backends.impala.import_commons module

class dae.backends.impala.import_commons.BatchImporter(gpf_instance)[source]

Bases: object

build(argv)[source]
build_cnv_loader(argv)[source]

Build a cnv loader for the provided arguments.

build_context(argv)[source]
build_dae_loader(argv)[source]

Build a dae loader for the provided arguments.

build_denovo_loader(argv)[source]

Build a denovo loader for the provided arguments.

build_familes_loader(argv)[source]

Build a family loader for the provided arguments.

build_genotype_storage(argv)[source]
build_partition_helper(argv)[source]

Create a partition description and partition helper.

build_study_id(argv)[source]

Set an appropriate study id for the provided arguments.

build_vcf_loader(argv)[source]

Build a vcf loader for the provided arguments.

classmethod cli_arguments_parser(gpf_instance)[source]
property families
generate_instructions(argv)[source]
generate_study_config(argv)[source]
static main(argv=['-b', 'html', '-d', '_build/doctrees', '.', '_build/html'], gpf_instance=None)[source]
class dae.backends.impala.import_commons.DatasetHelpers(gpf_instance=None)[source]

Bases: object

A collection of helper methods for working with datasets.

check_dataset_hdfs_directories(genotype_storage, dataset_id)[source]
check_dataset_impala_tables(dataset_id)[source]
check_dataset_rename_hdfs_directory(old_id, new_id)[source]
dataset_drop_impala_tables(dataset_id, dry_run=None)[source]
dataset_recreate_impala_tables(old_id, new_id, dry_run=None)[source]
dataset_remove_hdfs_directory(dataset_id, dry_run=None)[source]

Delete the HDFS directory for a dataset with id dataset_id.

dataset_rename_hdfs_directory(old_id, new_id, dry_run=None)[source]

Rename two directories in HDFS.

disable_study_config(dataset_id, dry_run=None)[source]
find_genotype_data_config(dataset_id)[source]
find_genotype_data_config_file(dataset_id)[source]
get_genotype_storage(dataset_id)[source]
is_impala_genotype_storage(dataset_id)[source]
remove_study_config(dataset_id)[source]
rename_study_config(dataset_id, new_id, config_content, dry_run=None)[source]
class dae.backends.impala.import_commons.MakefileGenerator[source]

Bases: object

Generate a Makefile which when executed imports a study.

TEMPLATE = <Template memory:7fc43a1bf940>
static generate(context)[source]
class dae.backends.impala.import_commons.MakefilePartitionHelper(partition_descriptor, genome, add_chrom_prefix=None, del_chrom_prefix=None)[source]

Bases: object

bucket_index(region_bin)[source]

Return bucket index for a region bin.

build_target_chromosomes(target_chromosomes)[source]
generate_chrom_targets(target_chrom)[source]

Split the target chrom into regions according to part desc.

generate_variants_targets(target_chromosomes, mode=None)[source]

Generate variants targets.

region_bins_count(chrom)[source]
class dae.backends.impala.import_commons.SnakefileGenerator[source]

Bases: object

Generate a Snakefile which when executed imports a study.

TEMPLATE = <Template memory:7fc43a1c2730>
static generate(context)[source]
class dae.backends.impala.import_commons.SnakefileKubernetesGenerator[source]

Bases: object

Generate a Snakefile which when executed imports a study using k8s.

TEMPLATE = <Template memory:7fc43a20e640>
static generate(context)[source]
class dae.backends.impala.import_commons.Variants2ParquetTool[source]

Bases: object

Tool that stores variants in a parquet file(s).

BUCKET_INDEX_DEFAULT = 1000
VARIANTS_FREQUENCIES: bool = False
VARIANTS_LOADER_CLASS: Any = None
VARIANTS_TOOL: Optional[str] = None
classmethod cli_arguments_parser(gpf_instance)[source]
classmethod main(argv=['-b', 'html', '-d', '_build/doctrees', '.', '_build/html'], gpf_instance=None)[source]
classmethod run(argv, gpf_instance=None)[source]
dae.backends.impala.import_commons.construct_import_annotation_pipeline(gpf_instance, annotation_configfile=None)[source]

Construct the import annotation pipeline.

dae.backends.impala.import_commons.construct_import_effect_annotator(gpf_instance)[source]

Construct the import effect annotator.

dae.backends.impala.import_commons.save_study_config(dae_config, study_id, study_config, force=False)[source]

Save the study config to a file.

dae.backends.impala.parquet_io module

Provides Apache Parquet storage of genotype data.

class dae.backends.impala.parquet_io.ContinuousParquetFileWriter(filepath, variant_loader, filesystem=None, rows=100000)[source]

Bases: object

Class that writes to a output parquet file.

This class automatically writes to a given parquet file when supplied enough data. Automatically dumps leftover data when closing into the file

append_allele(allele, variant_data, extra_attributes_data, summary_vectors)[source]

Append the data for an entire variant to the buffer.

Parameters

attributes (list) – List of key-value tuples containing the data

build_table()[source]
close()[source]
data_reset()[source]
size()[source]
class dae.backends.impala.parquet_io.NoPartitionDescriptor(root_dirname='')[source]

Bases: dae.backends.impala.parquet_io.PartitionDescriptor

Defines class for missing partition description.

build_impala_partitions()[source]
property chromosomes
static generate_file_access_glob()[source]

Generate a glob for accessing parquet files in the partition.

has_partitions()[source]
property region_length
variant_filename(family_allele)[source]
static variants_filename_basedir(filename)[source]

Extract the variants basedir from filename.

write_partition_configuration()[source]
class dae.backends.impala.parquet_io.ParquetManager[source]

Bases: object

Provide function for producing variants and pedigree parquet files.

static build_parquet_filenames(prefix, study_id=None, bucket_index=0, suffix=None)[source]

Build parquet filenames.

static families_to_parquet(families, pedigree_filename)[source]
static variants_to_parquet(variants_loader, partition_descriptor, bucket_index=1, rows=100000, include_reference=False)[source]

Read variants from variant_loader and store them in parquet.

class dae.backends.impala.parquet_io.ParquetPartitionDescriptor(chromosomes, region_length, family_bin_size=0, coding_effect_types=None, rare_boundary=0, root_dirname='')[source]

Bases: dae.backends.impala.parquet_io.PartitionDescriptor

Defines partition description used for parquet datasets.

add_family_bins_to_families(families)[source]
build_impala_partitions()[source]
property chromosomes
property coding_effect_types
property family_bin_size
static from_config(config_path, root_dirname='')[source]

Create a partition description from the provided config file.

static from_dict(config, root_dirname='') dae.backends.impala.parquet_io.ParquetPartitionDescriptor[source]

Create a paritition description from the provided config.

generate_file_access_glob()[source]

Return a glob for accessing every parquet file in the partition.

has_partitions()[source]
property rare_boundary
property region_length
variant_filename(family_allele)[source]
variants_filename_basedir(filename)[source]

Return the basedir of the variant file.

write_partition_configuration()[source]
class dae.backends.impala.parquet_io.PartitionDescriptor[source]

Bases: object

Abstract class for partition description.

build_impala_partitions()[source]
property chromosomes
has_partitions()[source]
property region_length
variant_filename(family_allele)[source]
write_partition_configuration()[source]
class dae.backends.impala.parquet_io.VariantsParquetWriter(variants_loader, partition_descriptor, bucket_index=None, rows=100000, include_reference=True)[source]

Bases: object

Provide functions for storing variants into parquet dataset.

write_dataset()[source]

Write the variants, parittion description and schema.

write_schema()[source]

Write the schema to a separate file.

dae.backends.impala.parquet_io.add_missing_parquet_fields(pps, ped_df)[source]

Add missing parquet fields.

dae.backends.impala.parquet_io.pedigree_parquet_schema()[source]

Return the schema for pedigree parquet file.

dae.backends.impala.parquet_io.save_ped_df_to_parquet(ped_df, filename, filesystem=None)[source]

Convert pdf_df from a dataframe to parquet and store it in filename.

dae.backends.impala.rsync_helpers module

class dae.backends.impala.rsync_helpers.RsyncHelpers(remote)[source]

Bases: object

A class containing helper funcs for working with rsync.

clear_remote(remote_subdir)[source]

Clear the remote directory.

copy_to_local(local_path, remote_subdir=None, exclude=None)[source]
copy_to_remote(local_path, remote_subdir=None, exclude=None, clear_remote=True)[source]

Copy from a local dir to a remote one.

hosturl()[source]

dae.backends.impala.serializers module

class dae.backends.impala.serializers.AlleleParquetSerializer(annotation_schema, extra_attributes=None)[source]

Bases: object

Serialize a bunch of alleles.

ALLELE_CREATION_PROPERTIES = ['chromosome', 'position', 'end_position', 'variant_type', 'reference', 'alternative', 'allele_index', 'summary_index', 'transmission_type', 'family_id', 'gt', 'best_state', 'genetic_model', 'variant_in_roles', 'variant_in_sexes', 'inheritance_in_members', 'variant_in_members']
ALLELE_PROP_GETTERS = {'effect_details_details': <function AlleleParquetSerializer.<lambda>>, 'effect_details_transcript_ids': <function AlleleParquetSerializer.<lambda>>, 'effect_gene_genes': <function AlleleParquetSerializer.<lambda>>, 'effect_gene_types': <function AlleleParquetSerializer.<lambda>>, 'effect_type': <function AlleleParquetSerializer.<lambda>>}
BASE_SCHEMA_FIELDS = [pyarrow.Field<bucket_index: int32>, pyarrow.Field<summary_variant_index: int64>, pyarrow.Field<allele_index: int8>, pyarrow.Field<chrom: string>, pyarrow.Field<position: int32>, pyarrow.Field<end_position: int32>, pyarrow.Field<reference: string>, pyarrow.Field<alternative: string>, pyarrow.Field<variant_type: int8>, pyarrow.Field<transmission_type: int8>, pyarrow.Field<alternatives_data: string>, pyarrow.Field<effect_type: string>, pyarrow.Field<effect_gene: string>, pyarrow.Field<effect_data: string>, pyarrow.Field<family_variant_index: int64>, pyarrow.Field<family_id: string>, pyarrow.Field<is_denovo: bool>, pyarrow.Field<variant_sexes: int8>, pyarrow.Field<variant_roles: int32>, pyarrow.Field<variant_inheritance: int16>, pyarrow.Field<variant_in_member: string>, pyarrow.Field<genotype_data: string>, pyarrow.Field<best_state_data: string>, pyarrow.Field<genetic_model_data: int8>, pyarrow.Field<inheritance_data: string>, pyarrow.Field<af_parents_called_count: int32>, pyarrow.Field<af_parents_called_percent: float>, pyarrow.Field<af_allele_count: int32>, pyarrow.Field<af_allele_freq: float>, pyarrow.Field<frequency_data: string>, pyarrow.Field<genomic_scores_data: string>]
BASE_SEARCHABLE_PROPERTIES_TYPES = {'allele_index': DataType(int32), 'bucket_index': DataType(int32), 'chromosome': DataType(string), 'effect_gene_symbols': DataType(string), 'effect_types': DataType(string), 'end_position': DataType(int32), 'family_id': DataType(string), 'family_index': DataType(int32), 'inheritance_in_members': DataType(int16), 'is_denovo': DataType(int8), 'position': DataType(int32), 'reference': DataType(string), 'summary_index': DataType(int32), 'transmission_type': DataType(int8), 'variant_in_members': DataType(string), 'variant_in_roles': DataType(int32), 'variant_in_sexes': DataType(int8), 'variant_type': DataType(int8)}
ENUM_PROPERTIES = {'inheritance_in_members': <enum 'Inheritance'>, 'transmission_type': <enum 'TransmissionType'>, 'variant_in_roles': <enum 'Role'>, 'variant_in_sexes': <enum 'Sex'>, 'variant_type': <enum 'Type'>}
FAMILY_SEARCHABLE_PROPERTIES_TYPES = {'family_id': DataType(string), 'family_index': DataType(int32), 'inheritance_in_members': DataType(int16), 'is_denovo': DataType(int8), 'variant_in_members': DataType(string), 'variant_in_roles': DataType(int32), 'variant_in_sexes': DataType(int8)}
GENOMIC_SCORES_SCHEMA_CLEAN_UP = ['worst_effect', 'family_bin', 'rare', 'genomic_scores_data', 'frequency_bin', 'coding', 'position_bin', 'chrome_bin', 'coding2', 'region_bin', 'coding_bin', 'effect_data', 'genotype_data', 'inheritance_data', 'genomic_scores_data', 'variant_sexes', 'alternatives_data', 'chrom', 'best_state_data', 'summary_variant_index', 'effect_type', 'effect_gene', 'effect_genes', 'effect_gene_genes', 'effect_gene_types', 'effect_details_details', 'effect_details_transcript_ids', 'effect_details', 'variant_inheritance', 'variant_in_member', 'variant_roles', 'genetic_model_data', 'frequency_data', 'alternative', 'variant_data', 'family_variant_index']
LIST_TO_ROW_PROPERTIES_LISTS = [['effect_types', 'effect_gene_symbols'], ['variant_in_members']]
PRODUCT_PROPERTIES_LIST = ['effect_types', 'effect_gene_symbols', 'variant_in_members']
SUMMARY_SEARCHABLE_PROPERTIES_TYPES = {'allele_index': DataType(int32), 'bucket_index': DataType(int32), 'chromosome': DataType(string), 'effect_gene_symbols': DataType(string), 'effect_types': DataType(string), 'end_position': DataType(int32), 'position': DataType(int32), 'reference': DataType(string), 'summary_index': DataType(int32), 'transmission_type': DataType(int8), 'variant_type': DataType(int8)}
property allele_batch_header

Return the names of the properties in an allele batch.

build_allele_batch_dict(allele, variant_data, extra_attributes_data, summary_vectors)[source]

Build a batch of allele data in the form of a dict.

build_searchable_vectors_summary(summary_variant)[source]

Build searchable vectors summary.

describe_blob_schema()[source]
deserialize_allele(stream)[source]

Read an allele from the input stream.

deserialize_family_variant(main_blob, family, extra_blob=None)[source]

Read a family variant from the input stream.

deserialize_summary_variant(main_blob, extra_blob=None)[source]

Read a summary variant from the input stream.

classmethod produce_base_schema()[source]
property schema

Lazy construct and return the schema.

property searchable_properties
property searchable_properties_family
property searchable_properties_summary
serialize_extra_attributes(variant)[source]

Serialize a variant’s extra attributes.

serialize_family_variant(variant_alleles, summary_blobs, scores_blobs)[source]

Serialize a family variant.

serialize_scores_data(alleles)[source]

Serialize scores data.

serialize_summary_data(alleles)[source]

Serialize summary data and return a list of blobs.

static write_property(stream, value, serializer)[source]
class dae.backends.impala.serializers.Serializer(serialize, deserialize, type)

Bases: tuple

deserialize

Alias for field number 1

serialize

Alias for field number 0

type

Alias for field number 2

dae.backends.impala.serializers.read_best_state(stream)[source]

Read best state from the stream.

dae.backends.impala.serializers.read_float(stream)[source]
dae.backends.impala.serializers.read_genetic_model(stream)[source]
dae.backends.impala.serializers.read_genotype(stream)[source]

Read a genotype from the stream.

dae.backends.impala.serializers.read_in_roles(stream)[source]

Read a list of Roles from the stream.

dae.backends.impala.serializers.read_in_sexes(stream) list[Optional[dae.variants.attributes.Sex]][source]

Read a list of sexes from the stream.

dae.backends.impala.serializers.read_inheritance(stream)[source]

Read a list of Inheritances from the stream.

dae.backends.impala.serializers.read_int32(stream)[source]
dae.backends.impala.serializers.read_int8(stream)[source]
dae.backends.impala.serializers.read_int8_signed(stream)[source]
dae.backends.impala.serializers.read_string(stream)[source]
dae.backends.impala.serializers.read_string_list(stream) list[Optional[str]][source]

Read a list of strings from the stream.

dae.backends.impala.serializers.read_transmission_type(stream)[source]
dae.backends.impala.serializers.read_variant_type(stream)[source]
dae.backends.impala.serializers.write_best_state(stream, best_state)[source]

Write best state to the stream.

dae.backends.impala.serializers.write_big_enum(stream, enum)[source]
dae.backends.impala.serializers.write_big_enum_list(stream, the_list)[source]

Write a list of big enums (more than 128 states) to the stream.

dae.backends.impala.serializers.write_effects(stream, allele)[source]

Write allele’s effect data to the stream.

dae.backends.impala.serializers.write_enum(stream, enum)[source]
dae.backends.impala.serializers.write_enum_list(stream, the_list)[source]

Write a list of enums to the stream.

dae.backends.impala.serializers.write_float(stream, num)[source]
dae.backends.impala.serializers.write_genotype(stream, genotype)[source]

Write genotype data to the stream.

dae.backends.impala.serializers.write_int32(stream, num)[source]
dae.backends.impala.serializers.write_int8(stream, num)[source]
dae.backends.impala.serializers.write_int8_signed(stream, num)[source]
dae.backends.impala.serializers.write_string(stream, string)[source]
dae.backends.impala.serializers.write_string_list(stream, the_list: list[Optional[str]])[source]

Write a list of strings to the stream.

dae.backends.impala.summary_variants_query_builder module

class dae.backends.impala.summary_variants_query_builder.SummaryVariantsQueryBuilder(db, variants_table, pedigree_table, variants_schema, table_properties, pedigree_schema, pedigree_df, gene_models=None, summary_variants_table=None)[source]

Bases: dae.backends.impala.base_query_builder.BaseQueryBuilder

Build queries related to summary variants.

build_from()[source]
build_group_by()[source]
build_join()[source]
build_where(regions=None, genes=None, effect_types=None, family_ids=None, person_ids=None, inheritance=None, roles=None, sexes=None, variant_type=None, real_attr_filter=None, ultra_rare=None, frequency_filter=None, return_reference=None, return_unknown=None, **_kwargs)[source]

Build the where clause of a query.

create_row_deserializer(serializer)[source]

Module contents