config package

Submodules

config.config module

class config.config.TextConfig(mean_length: int, standard_deviation: int)

Bases: object

Configuration for generated text length distribution.

mean_length

Average length of generated text.

Type:

int

standard_deviation

Standard deviation for text length.

Type:

int

mean_length: int

standard_deviation: int

__init__(mean_length: int, standard_deviation: int) → None

class config.config.RunType(*values)

Bases: Enum

Execution mode of the data generation pipeline.

PRODUCTION = 'PRODUCTION'

DEVELOPMENT = 'DEVELOPMENT'

class config.config.Config(release_information: ReleaseInformation, number_of_tickets: int, number_translation_nodes: int, graph_runs_per_batch: int, text_config: TextConfig, assistants: dict[AssistantName, Assistant], run_type: RunType = RunType.DEVELOPMENT, time_zone: ZoneInfo = zoneinfo.ZoneInfo(key='Europe/Berlin'))

Bases: object

Holds all configuration parameters for a dataset generation run.

release_information

Metadata about this release.

Type:

ReleaseInformation

number_of_tickets

Total synthetic tickets to generate.

Type:

int

number_translation_nodes

How many translation steps per ticket.

Type:

int

graph_runs_per_batch

Number of graph executions per batch.

Type:

int

text_config

Settings for text length variation.

Type:

TextConfig

assistants

Mapping of assistant roles.

Type:

dict[AssistantName, Assistant]

run_type

Whether this is a production or development run.

Type:

RunType

time_zone

Time zone for timestamps; default Europe/Berlin.

Type:

ZoneInfo

release_information: ReleaseInformation

number_of_tickets: int

number_translation_nodes: int

graph_runs_per_batch: int

text_config: TextConfig

assistants: dict[AssistantName, Assistant]

run_type: RunType = 'DEVELOPMENT'

time_zone: ZoneInfo = zoneinfo.ZoneInfo(key='Europe/Berlin')

property output_file: Path

Get the output file path for this release.

Returns:

Path where generated dataset will be saved.

Return type:

Path

property run_information: RunInformation

Construct run metrics for reporting and logging.

Returns:

Object summarizing batch and ticket counts.

Return type:

RunInformation

__init__(release_information: ReleaseInformation, number_of_tickets: int, number_translation_nodes: int, graph_runs_per_batch: int, text_config: TextConfig, assistants: dict[AssistantName, Assistant], run_type: RunType = RunType.DEVELOPMENT, time_zone: ZoneInfo = zoneinfo.ZoneInfo(key='Europe/Berlin')) → None

config.run_information module

class config.run_information.RunInformation(number_of_tickets: int, number_translation_nodes: int, graph_runs_per_batch: int)

Bases: object

Holds parameters and derived metrics for a run of the dataset generator.

number_of_tickets

Total number of tickets to generate.

Type:

int

number_translation_nodes

Number of translation nodes per ticket.

Type:

int

graph_runs_per_batch

Number of graph executions in each batch.

Type:

int

number_of_tickets: int

number_translation_nodes: int

graph_runs_per_batch: int

property graph_ticket_runs: int

Calculate how many ticket graphs will be run.

Returns:

The number of ticket-graph runs (tickets divided by translation nodes).

Return type:

int

property amount_batches: int

Calculate how many batches are required.

Returns:

Total batches, computed as (tickets / batch size) / translation nodes.

Return type:

int

__init__(number_of_tickets: int, number_translation_nodes: int, graph_runs_per_batch: int) → None

config.version module

class config.version.VersionType(*values)

Bases: Enum

SemVer part types and their index in the version tuple.

MAJOR

Major version index 0.

Type:

VersionType

MINOR

Minor version index 1.

Type:

VersionType

PATCH

Patch version index 2.

Type:

VersionType

MAJOR = 0

MINOR = 1

PATCH = 2

__init__(part_index: int)

Store the index corresponding to this version part.

class config.version.VersionTag(*values)

Bases: Enum

Optional tags appended to version strings.

TEST

“test” tag.

Type:

VersionTag

PROD

“prod” tag.

Type:

VersionTag

TEST = 'test'

PROD = 'prod'

class config.version.Version(version_parts: tuple[int, int, int], version_tag: VersionTag | None = None)

Bases: object

Semantic version representation with optional tag.

version_parts

(major, minor, patch).

Type:

tuple[int, int, int]

version_tag

Optional tag to append.

Type:

VersionTag | None

VERSION_SPLIT = '.'

VERSION_FILE_SPLIT = '_'

VERSION_FILE_PREFIX = 'v'

VERSION_LIMIT = 100

VERSION_PARTS = 3

version_parts: tuple[int, int, int]

version_tag: VersionTag | None = None

static from_string(version_string: str) → Version

Parse a dotted version string into a Version, padding missing parts with zero.

with_tag(version_tag: VersionTag) → Version

Return a new Version with the given tag.

as_file_version() → str

Generate the file-friendly version string, e.g. ‘1_2_3-test’.

is_to_high() → bool

Check if any version part exceeds the limit.

next_version(version_type: VersionType) → Version

Increment the specified part and return a new Version.

__init__(version_parts: tuple[int, int, int], version_tag: VersionTag | None = None) → None

class config.version.ReleaseInformation(version: Version, output_dir: Path, file_prefix: str = 'ticket-dataset-', file_extension: str = '.json', release_type: VersionType = VersionType.PATCH)

Bases: object

Holds metadata for a release and computes output file paths.

version

Semantic version.

Type:

Version

output_dir

Directory to write the file.

Type:

Path

file_prefix

Prefix for the output filename.

Type:

str

file_extension

Extension for the output filename.

Type:

str

release_type

Which part to bump next.

Type:

VersionType

version: Version

output_dir: Path

file_prefix: str = 'ticket-dataset-'

file_extension: str = '.json'

release_type: VersionType = 2

get_output_file() → Path

Compose the full output file Path for this release.

exists() → bool

Check if the output file already exists.

get_next_existing() → Self

Recursively find the next non-existing release, raising if limit exceeded.

property next_version: Self

Return a new ReleaseInformation with its version bumped.

__init__(version: Version, output_dir: Path, file_prefix: str = 'ticket-dataset-', file_extension: str = '.json', release_type: VersionType = VersionType.PATCH) → None

config.version_test module

config.version_test.test_version_from_string(version_string, expected)

config.version_test.test_version_with_tag(tag)

config.version_test.test_version_as_file_version(parts, tag, expected)

config.version_test.test_version_next_version(initial, version_type, expected)

config.version_test.test_release_information_get_output_file(mock_exists)

config.version_test.test_release_information_get_next_existing(mock_exists)

config.version_test.test_release_information_exists(mock_exists)

config.version_test.test_release_information_next_version(release_type, expected)

Module contents