dgbowl_schemas.yadg.dataschema_4_2 package

Bases: BaseModel

metadata: Metadata: Metadata information for yadg.

steps: Sequence[Dummy | BasicCSV | MeasCSV | FlowData | ElectroChem | ChromTrace | ChromData | MassTrace | QFTrace | XPSTrace | XRDTrace]: A sequence of parser steps.

update()

Submodules

dgbowl_schemas.yadg.dataschema_4_2.externaldate module

class dgbowl_schemas.yadg.dataschema_4_2.externaldate.ExternalDateFile(*, file: Content)

Bases: BaseModel

Read external date information from file.

class Content(*, path: str, type: str, match: str | None = None)

Bases: BaseModel

path: str: Path to the external date information file.

type: str: Type of the external date information file.

match: str | None: String to be matched within the file.

file: Content

class dgbowl_schemas.yadg.dataschema_4_2.externaldate.ExternalDateFilename(*, filename: Content)

Bases: BaseModel

Read external date information from the file name.

class Content(*, format: str, len: int)

Bases: BaseModel

format: str: strptime-like format string for processing the date.

len: int: Number of characters from the start of the filename to parse.

filename: Content

class dgbowl_schemas.yadg.dataschema_4_2.externaldate.ExternalDateISOString(*, isostring: str)

Bases: BaseModel

Read a constant external date using an ISO-formatted string.

isostring: str

class dgbowl_schemas.yadg.dataschema_4_2.externaldate.ExternalDateUTSOffset(*, utsoffset: float)

Bases: BaseModel

Read a constant external date using a Unix timestamp offset.

utsoffset: float

class dgbowl_schemas.yadg.dataschema_4_2.externaldate.ExternalDate(*, using: ExternalDateFile | ExternalDateFilename | ExternalDateISOString | ExternalDateUTSOffset, mode: Literal['add', 'replace'] = 'add')

Bases: BaseModel

Supply timestamping information that are external to the processed file.

using: ExternalDateFile | ExternalDateFilename | ExternalDateISOString | ExternalDateUTSOffset: Specification of the external date format.

mode: Literal['add', 'replace']: Whether the external timestamps should be added to or should replace the parsed data.

dgbowl_schemas.yadg.dataschema_4_2.input module

class dgbowl_schemas.yadg.dataschema_4_2.input.Input(*, folders: Sequence[str], prefix: str | None = None, suffix: str | None = None, contains: str | None = None, exclude: str | None = None, encoding: str = 'UTF-8')

Bases: BaseModel

Specification of input files/folders to be processed by the Step.

files: Sequence[str]: Files, or folders to be searched for matching files.

prefix: str | None: Prefix of the filenames to be matched.

suffix: str | None: Suffix of the filenames to be matched.

contains: str | None: A string the matched filenames must contain.

exclude: str | None: A string the matched filenames must not contain.

encoding: str: File encoding.

paths() → List[str]: Returns a list of files to be processed by the Step.

dgbowl_schemas.yadg.dataschema_4_2.metadata module

class dgbowl_schemas.yadg.dataschema_4_2.metadata.Metadata(*, version: Literal['4.2'], provenance: Provenance, timezone: str = 'localtime')

Bases: BaseModel

Metadata, including version and provenance of the DataSchema.

class Provenance(*, type: str, metadata: Mapping[str, Any] | None = None)

Bases: BaseModel

type: str

metadata: Mapping[str, Any] | None

version: Literal['4.2']

provenance: Provenance: Provenance information.

timezone: str: Timezone specification.

Note

This should be set to the timezone where the measurements have been performed, as opposed to the timezone where yadg is being executed, otherwise timezone offsets may not be accounted for correctly.

dgbowl_schemas.yadg.dataschema_4_2.parameters module

class dgbowl_schemas.yadg.dataschema_4_2.parameters.Tol(*, atol: float | None = None, rtol: float | None = None)

Bases: BaseModel

Specification of absolute and relative tolerance/error.

atol: float | None

rtol: float | None

dgbowl_schemas.yadg.dataschema_4_2.step module

class dgbowl_schemas.yadg.dataschema_4_2.step.Dummy(*, parser: Literal['dummy'], input: Input, parameters: Params | None = None, tag: str | None = None, externaldate: ExternalDate | None = None)

Bases: BaseModel

Dummy parser type, useful for testing.

class Params(**extra_data: Any): Bases: BaseModel

parser: Literal['dummy']

input: Input

parameters: Params | None

tag: str | None

externaldate: ExternalDate | None

class dgbowl_schemas.yadg.dataschema_4_2.step.BasicCSV(*, parser: Literal['basiccsv'], input: Input, parameters: Params = None, tag: str | None = None, externaldate: ExternalDate | None = None)

Bases: BaseModel

Customisable tabulated file parser.

Bases: BaseModel

sep: str: Separator of table columns.

strip: str: A str of characters to strip from headers & data.

units: Mapping[str, str] | None: A dict containing column: unit keypairs.

timestamp: Timestamp | TimeDate | UTS | None: Timestamp specification allowing calculation of Unix timestamp for each table row.

sigma: Mapping[str, Tol] | None: External uncertainty specification.

DEPRECATED in DataSchema-4.2

This feature is deprecated as of yadg-4.2 and will stop working in yadg-5.0.

calfile: str | None: Column calibration specification.

DEPRECATED in DataSchema-4.2

This feature is deprecated as of yadg-4.2 and will stop working in yadg-5.0.

convert: Any | None: Column renaming specification.

DEPRECATED in DataSchema-4.2

This feature is deprecated as of yadg-4.2 and will stop working in yadg-5.0.

parser: Literal['basiccsv']

input: Input

parameters: Params

tag: str | None

externaldate: ExternalDate | None

class dgbowl_schemas.yadg.dataschema_4_2.step.MeasCSV(*, parser: Literal['meascsv'], input: Input, parameters: Params = None, tag: str | None = None, externaldate: ExternalDate | None = None)

Bases: BaseModel

Legacy file parser for measurement.csv files from FHI.

Note

This parser is deprecated, and the BasicCSV parser should be used instead.

class Params(*, timestamp: Timestamp | TimeDate | UTS = Timestamp(timestamp=TimestampSpec(index=0, format='%Y-%m-%d-%H-%M-%S')), calfile: str | None = None, convert: Any | None = None)

Bases: BaseModel

timestamp: Timestamp | TimeDate | UTS

calfile: str | None: Column calibration specification.

DEPRECATED in DataSchema-4.2

This feature is deprecated as of yadg-4.2 and will stop working in yadg-5.0.

convert: Any | None: Column renaming specification.

DEPRECATED in DataSchema-4.2

This feature is deprecated as of yadg-4.2 and will stop working in yadg-5.0.

parser: Literal['meascsv']

input: Input

parameters: Params

tag: str | None

externaldate: ExternalDate | None

class dgbowl_schemas.yadg.dataschema_4_2.step.FlowData(*, parser: Literal['flowdata'], input: Input, parameters: Params = None, tag: str | None = None, externaldate: ExternalDate | None = None)

Bases: BaseModel

Parser for flow controller/meter data.

class Params(*, filetype: Literal['drycal.csv', 'drycal.rtf', 'drycal.txt'] = 'drycal.csv', calfile: str | None = None, convert: Any | None = None)

Bases: BaseModel

filetype: Literal['drycal.csv', 'drycal.rtf', 'drycal.txt']

calfile: str | None: Column calibration specification.

DEPRECATED in DataSchema-4.2

This feature is deprecated as of yadg-4.2 and will stop working in yadg-5.0.

convert: Any | None: Column renaming specification.

DEPRECATED in DataSchema-4.2

This feature is deprecated as of yadg-4.2 and will stop working in yadg-5.0.

parser: Literal['flowdata']

input: Input

parameters: Params

tag: str | None

externaldate: ExternalDate | None

class dgbowl_schemas.yadg.dataschema_4_2.step.ElectroChem(*, parser: Literal['electrochem'], input: Input, parameters: Params = None, tag: str | None = None, externaldate: ExternalDate | None = None)

Bases: BaseModel

Parser for electrochemistry files.

class Params(*, filetype: Literal['eclab.mpt', 'eclab.mpr', 'tomato.json'] = 'eclab.mpr', transpose: bool = True)

Bases: BaseModel

filetype: Literal['eclab.mpt', 'eclab.mpr', 'tomato.json']

transpose: bool: Transpose impedance data into traces (default) or keep as timesteps.

class Input(*, folders: Sequence[str], prefix: str | None = None, suffix: str | None = None, contains: str | None = None, exclude: str | None = None, encoding: str = 'windows-1252')

Bases: Input

encoding: str: File encoding.

parser: Literal['electrochem']

input: Input

parameters: Params

tag: str | None

externaldate: ExternalDate | None

class dgbowl_schemas.yadg.dataschema_4_2.step.ChromTrace(*, parser: Literal['chromtrace'], input: Input, parameters: Params = None, tag: str | None = None, externaldate: ExternalDate | None = None)

Bases: BaseModel

Parser for raw chromatography traces.

Note

For parsing processed (integrated) chromatographic data, use the ChromData parser.

class Params(*, filetype: Literal['ezchrom.asc', 'fusion.json', 'fusion.zip', 'agilent.ch', 'agilent.dx', 'agilent.csv'] = 'ezchrom.asc', calfile: str | None = None, species: Any | None = None, detectors: Any | None = None)

Bases: BaseModel

filetype: Literal['ezchrom.asc', 'fusion.json', 'fusion.zip', 'agilent.ch', 'agilent.dx', 'agilent.csv']

calfile: str | None: Species calibration specification.

DEPRECATED in DataSchema-4.2

This feature is deprecated as of yadg-4.2 and will stop working in yadg-5.0.

species: Any | None: Species information as a dict.

DEPRECATED in DataSchema-4.2

This feature is deprecated as of yadg-4.2 and will stop working in yadg-5.0.

detectors: Any | None: Detector integration parameters as a dict.

DEPRECATED in DataSchema-4.2

This feature is deprecated as of yadg-4.2 and will stop working in yadg-5.0.

parser: Literal['chromtrace']

input: Input

parameters: Params

tag: str | None

externaldate: ExternalDate | None

class dgbowl_schemas.yadg.dataschema_4_2.step.ChromData(*, parser: Literal['chromdata'], input: Input, parameters: Params = None, tag: str | None = None, externaldate: ExternalDate | None = None)

Bases: BaseModel

Parser for processed chromatography data.

class Params(*, filetype: Literal['fusion.json', 'fusion.zip', 'fusion.csv', 'empalc.csv', 'empalc.xlsx'] = 'fusion.json')

Bases: BaseModel

filetype: Literal['fusion.json', 'fusion.zip', 'fusion.csv', 'empalc.csv', 'empalc.xlsx']

parser: Literal['chromdata']

input: Input

parameters: Params

tag: str | None

externaldate: ExternalDate | None

class dgbowl_schemas.yadg.dataschema_4_2.step.MassTrace(*, parser: Literal['masstrace'], input: Input, parameters: Params = None, tag: str | None = None, externaldate: ExternalDate | None = None)

Bases: BaseModel

Parser for mass spectroscopy traces.

class Params(*, filetype: Literal['quadstar.sac'] = 'quadstar.sac')

Bases: BaseModel

filetype: Literal['quadstar.sac']

parser: Literal['masstrace']

input: Input

parameters: Params

tag: str | None

externaldate: ExternalDate | None

class dgbowl_schemas.yadg.dataschema_4_2.step.QFTrace(*, parser: Literal['qftrace'], input: Input, parameters: Params = None, tag: str | None = None, externaldate: ExternalDate | None = None)

Bases: BaseModel

Parser for network analyzer traces.

class Params(*, filetype: Literal['labview.csv'] = 'labview.csv', method: Literal['naive', 'lorentz', 'kajfez'] = 'kajfez', height: float = 1.0, distance: float = 5000.0, cutoff: float = 0.4, threshold: float = 1e-06)

Bases: BaseModel

filetype: Literal['labview.csv']

method: Literal['naive', 'lorentz', 'kajfez']

height: float

distance: float

cutoff: float

threshold: float

parser: Literal['qftrace']

input: Input

parameters: Params

tag: str | None

externaldate: ExternalDate | None

class dgbowl_schemas.yadg.dataschema_4_2.step.XPSTrace(*, parser: Literal['xpstrace'], input: Input, parameters: Params = None, tag: str | None = None, externaldate: ExternalDate | None = None)

Bases: BaseModel

Parser for XPS traces.

class Params(*, filetype: Literal['phi.spe'] = 'phi.spe')

Bases: BaseModel

filetype: Literal['phi.spe']

parser: Literal['xpstrace']

input: Input

parameters: Params

tag: str | None

externaldate: ExternalDate | None

class dgbowl_schemas.yadg.dataschema_4_2.step.XRDTrace(*, parser: Literal['xrdtrace'], input: Input, parameters: Params = None, tag: str | None = None, externaldate: ExternalDate | None = None)

Bases: BaseModel

Parser for XRD traces.

class Params(*, filetype: Literal['panalytical.xy', 'panalytical.csv', 'panalytical.xrdml'] = 'panalytical.csv')

Bases: BaseModel

filetype: Literal['panalytical.xy', 'panalytical.csv', 'panalytical.xrdml']

parser: Literal['xrdtrace']

input: Input

parameters: Params

tag: str | None

externaldate: ExternalDate | None

dgbowl_schemas.yadg.dataschema_4_2.timestamp module

class dgbowl_schemas.yadg.dataschema_4_2.timestamp.TimestampSpec(*, index: int | None = None, format: str | None = None)

Bases: BaseModel

Specification of the column index and string format of the timestamp.

index: int | None

format: str | None

class dgbowl_schemas.yadg.dataschema_4_2.timestamp.Timestamp(*, timestamp: TimestampSpec)

Bases: BaseModel

Timestamp from a column containing a single timestamp string.

timestamp: TimestampSpec

class dgbowl_schemas.yadg.dataschema_4_2.timestamp.UTS(*, uts: TimestampSpec)

Bases: BaseModel

Timestamp from a column containing a Unix timestamp.

uts: TimestampSpec

class dgbowl_schemas.yadg.dataschema_4_2.timestamp.TimeDate(*, date: TimestampSpec | None = None, time: TimestampSpec | None = None)

Bases: BaseModel

Timestamp from a separate date and/or time column.

date: TimestampSpec | None

time: TimestampSpec | None