contract.base

DataStream

DataStream(
    name: str,
    *,
    description: Optional[str] = None,
    reader_params: Optional[TReaderParams] = None,
    **kwargs,
)

Bases: ABC, Generic[TData, TReaderParams]

Abstract base class for all data streams.

Provides a generic interface for data reading operations with configurable parameters and hierarchical organization.

Parameters:

Name	Type	Description	Default
name	str	Name identifier for the data stream.	required
description	Optional[str]	Optional description of the data stream.	None
reader_params	Optional[TReaderParams]	Optional parameters for the data reader.	None
**kwargs		Additional keyword arguments.	{}

Attributes:

Name	Type	Description
_is_collection	bool	Class variable indicating if this is a collection of data streams.

Raises:

Type	Description
ValueError	If name contains '::' characters which are reserved for path resolution.

Source code in src/contraqctor/contract/base.py

def __init__(
    self: Self,
    name: str,
    *,
    description: Optional[str] = None,
    reader_params: Optional[_typing.TReaderParams] = None,
    **kwargs,
) -> None:
    if "::" in name:
        raise ValueError("Name cannot contain '::' character.")
    self._name = name

    self._description = description
    self._reader_params = reader_params if reader_params is not None else _typing.UnsetParams
    self._data = _typing.UnsetData
    self._parent: Optional["DataStream"] = None

name property

name: str

Get the name of the data stream.

Returns:

Name	Type	Description
str	str	Name identifier of the data stream.

resolved_name property

resolved_name: str

Get the full hierarchical name of the data stream.

Generates a path-like name showing the stream's position in the hierarchy, using '::' as a separator between parent and child names.

Returns:

Name	Type	Description
str	str	The fully resolved name including all parent names.

description property

description: Optional[str]

Get the description of the data stream.

Returns:

Type	Description
Optional[str]	Optional[str]: Description of the data stream, or None if not provided.

parent property

parent: Optional[DataStream]

Get the parent data stream.

Returns:

Type	Description
Optional[DataStream]	Optional[DataStream]: Parent data stream, or None if this is a root stream.

is_collection property

is_collection: bool

Check if this data stream is a collection of other streams.

Returns:

Name	Type	Description
bool	bool	True if this is a collection stream, False otherwise.

reader_params property

reader_params: TReaderParams

Get the parameters for the data reader.

Returns:

Name	Type	Description
TReaderParams	TReaderParams	Parameters for the data reader.

has_data property

has_data: bool

Check if the data stream has loaded data.

Returns:

Name	Type	Description
bool	bool	True if data has been loaded, False otherwise.

data property

data: TData

Get the loaded data.

Returns:

Name	Type	Description
TData	TData	The loaded data.

Raises:

Type	Description
ValueError	If data has not been loaded yet.

read

read(
    reader_params: Optional[TReaderParams] = None,
) -> TData

Read data using the configured reader.

Parameters:

Name	Type	Description	Default
reader_params	Optional[TReaderParams]	Optional parameters to override the default reader parameters.	None

Returns:

Name	Type	Description
TData	TData	Data read from the source.

Raises:

Type	Description
ValueError	If reader parameters are not set.

Source code in src/contraqctor/contract/base.py

def read(self, reader_params: Optional[_typing.TReaderParams] = None) -> _typing.TData:
    """Read data using the configured reader.

    Args:
        reader_params: Optional parameters to override the default reader parameters.

    Returns:
        TData: Data read from the source.

    Raises:
        ValueError: If reader parameters are not set.
    """
    reader_params = reader_params if reader_params is not None else self._reader_params
    if _typing.is_unset(reader_params):
        raise ValueError("Reader parameters are not set. Cannot read data.")
    return self._reader(reader_params)

bind_reader_params

bind_reader_params(params: TReaderParams) -> Self

Bind reader parameters to the data stream.

Parameters:

Name	Type	Description	Default
params	TReaderParams	Parameters to bind to the data stream's reader.	required

Returns:

Name	Type	Description
Self	Self	The data stream instance for method chaining.

Raises:

Type	Description
ValueError	If reader parameters have already been set.

Source code in src/contraqctor/contract/base.py

def bind_reader_params(self, params: _typing.TReaderParams) -> Self:
    """Bind reader parameters to the data stream.

    Args:
        params: Parameters to bind to the data stream's reader.

    Returns:
        Self: The data stream instance for method chaining.

    Raises:
        ValueError: If reader parameters have already been set.
    """
    if not _typing.is_unset(self._reader_params):
        raise ValueError("Reader parameters are already set. Cannot bind again.")
    self._reader_params = params
    return self

at

at(name: str) -> DataStream

Get a child data stream by name.

Parameters:

Name	Type	Description	Default
name	str	Name of the child data stream to retrieve.	required

Returns:

Name	Type	Description
DataStream	DataStream	The child data stream with the given name.

Raises:

Type	Description
NotImplementedError	If the data stream does not support child access.

Examples:

# Access stream in a collection
collection = data_collection.load()
temp_stream = collection.at("temperature")

# Or using dictionary-style syntax
humidity_stream = collection["humidity"]

Source code in src/contraqctor/contract/base.py

def at(self, name: str) -> "DataStream":
    """Get a child data stream by name.

    Args:
        name: Name of the child data stream to retrieve.

    Returns:
        DataStream: The child data stream with the given name.

    Raises:
        NotImplementedError: If the data stream does not support child access.

    Examples:
        ```python
        # Access stream in a collection
        collection = data_collection.load()
        temp_stream = collection.at("temperature")

        # Or using dictionary-style syntax
        humidity_stream = collection["humidity"]
        ```
    """
    raise NotImplementedError("This method is not implemented for DataStream.")

load

load() -> Self

Load data into the data stream.

Reads data from the source and stores it in the data stream.

Returns:

Name	Type	Description
Self	Self	The data stream instance for method chaining.

Examples:

from contraqctor.contract import csv

# Create and load a CSV stream
params = csv.CsvParams(path="data/measurements.csv")
csv_stream = csv.Csv("measurements", reader_params=params)
csv_stream.load()

# Access the data
df = csv_stream.data
print(f"Loaded {len(df)} rows")

Source code in src/contraqctor/contract/base.py

def load(self) -> Self:
    """Load data into the data stream.

    Reads data from the source and stores it in the data stream.

    Returns:
        Self: The data stream instance for method chaining.

    Examples:
        ```python
        from contraqctor.contract import csv

        # Create and load a CSV stream
        params = csv.CsvParams(path="data/measurements.csv")
        csv_stream = csv.Csv("measurements", reader_params=params)
        csv_stream.load()

        # Access the data
        df = csv_stream.data
        print(f"Loaded {len(df)} rows")
        ```
    """
    self._data = self.read()
    return self

load_all

load_all(
    strict: bool = False,
) -> list[tuple[DataStream, Exception], None, None]

Recursively load this data stream and all child streams.

Performs depth-first traversal to load all streams in the hierarchy.

Parameters:

Name	Type	Description	Default
strict	bool	If True, raises exceptions immediately; otherwise collects and returns them.	False

Returns:

Name	Type	Description
list	list[tuple[DataStream, Exception], None, None]	List of tuples containing streams and exceptions that occurred during loading.

Raises:

Type	Description
Exception	If strict is True and an exception occurs during loading.

Examples:

# Load all streams and handle errors
errors = collection.load_all(strict=False)

if errors:
    for stream, error in errors:
        print(f"Error loading {stream.name}: {error}")

Source code in src/contraqctor/contract/base.py

def load_all(self, strict: bool = False) -> list[tuple["DataStream", Exception], None, None]:
    """Recursively load this data stream and all child streams.

    Performs depth-first traversal to load all streams in the hierarchy.

    Args:
        strict: If True, raises exceptions immediately; otherwise collects and returns them.

    Returns:
        list: List of tuples containing streams and exceptions that occurred during loading.

    Raises:
        Exception: If strict is True and an exception occurs during loading.

    Examples:
        ```python
        # Load all streams and handle errors
        errors = collection.load_all(strict=False)

        if errors:
            for stream, error in errors:
                print(f"Error loading {stream.name}: {error}")
        ```
    """
    self.load()
    exceptions = []
    for stream in self:
        if stream is None:
            continue
        try:
            exceptions += stream.load_all(strict=strict)
        except Exception as e:
            if strict:
                raise e
            exceptions.append((stream, e))
    return exceptions

DataStreamCollectionBase

DataStreamCollectionBase(
    name: str,
    *,
    description: Optional[str] = None,
    reader_params: Optional[TReaderParams] = None,
    **kwargs,
)

Bases: DataStream[List[TDataStream], TReaderParams], Generic[TDataStream, TReaderParams]

Base class for collections of data streams.

Provides functionality for managing and accessing multiple child data streams.

Parameters:

Name	Type	Description	Default
name	str	Name identifier for the collection.	required
description	Optional[str]	Optional description of the collection.	None
reader_params	Optional[TReaderParams]	Optional parameters for the reader.	None
**kwargs		Additional keyword arguments.	{}

Source code in src/contraqctor/contract/base.py

def __init__(
    self: Self,
    name: str,
    *,
    description: Optional[str] = None,
    reader_params: Optional[_typing.TReaderParams] = None,
    **kwargs,
) -> None:
    super().__init__(name=name, description=description, reader_params=reader_params, **kwargs)
    self._hashmap: Dict[str, TDataStream] = {}
    self._update_hashmap()

name property

name: str

Get the name of the data stream.

Returns:

Name	Type	Description
str	str	Name identifier of the data stream.

resolved_name property

resolved_name: str

Get the full hierarchical name of the data stream.

Generates a path-like name showing the stream's position in the hierarchy, using '::' as a separator between parent and child names.

Returns:

Name	Type	Description
str	str	The fully resolved name including all parent names.

description property

description: Optional[str]

Get the description of the data stream.

Returns:

Type	Description
Optional[str]	Optional[str]: Description of the data stream, or None if not provided.

parent property

parent: Optional[DataStream]

Get the parent data stream.

Returns:

Type	Description
Optional[DataStream]	Optional[DataStream]: Parent data stream, or None if this is a root stream.

is_collection property

is_collection: bool

Check if this data stream is a collection of other streams.

Returns:

Name	Type	Description
bool	bool	True if this is a collection stream, False otherwise.

reader_params property

reader_params: TReaderParams

Get the parameters for the data reader.

Returns:

Name	Type	Description
TReaderParams	TReaderParams	Parameters for the data reader.

has_data property

has_data: bool

Check if the data stream has loaded data.

Returns:

Name	Type	Description
bool	bool	True if data has been loaded, False otherwise.

data property

data: TData

Get the loaded data.

Returns:

Name	Type	Description
TData	TData	The loaded data.

Raises:

Type	Description
ValueError	If data has not been loaded yet.

load

load()

Load data for this collection.

Overrides the base method to add validation that loaded data is a list of DataStreams.

Returns:

Name	Type	Description
Self		The collection instance for method chaining.

Raises:

Type	Description
ValueError	If loaded data is not a list of DataStreams.

Source code in src/contraqctor/contract/base.py

@override
def load(self):
    """Load data for this collection.

    Overrides the base method to add validation that loaded data is a list of DataStreams.

    Returns:
        Self: The collection instance for method chaining.

    Raises:
        ValueError: If loaded data is not a list of DataStreams.
    """
    super().load()
    if not isinstance(self._data, list):
        self._data = _typing.UnsetData
        raise ValueError("Data must be a list of DataStreams.")
    self._update_hashmap()
    return self

at

at(name: str) -> TDataStream

Get a child data stream by name.

Parameters:

Name	Type	Description	Default
name	str	Name of the child data stream to retrieve.	required

Returns:

Name	Type	Description
TDataStream	TDataStream	The child data stream with the given name.

Raises:

Type	Description
ValueError	If data has not been loaded yet.
KeyError	If no child stream with the given name exists.

Source code in src/contraqctor/contract/base.py

@override
def at(self, name: str) -> TDataStream:
    """Get a child data stream by name.

    Args:
        name: Name of the child data stream to retrieve.

    Returns:
        TDataStream: The child data stream with the given name.

    Raises:
        ValueError: If data has not been loaded yet.
        KeyError: If no child stream with the given name exists.
    """
    if not self.has_data:
        raise ValueError("data streams have not been read yet. Cannot access data streams.")
    if name in self._hashmap:
        return self._hashmap[name]
    else:
        raise KeyError(f"Stream with name: '{name}' not found in data streams.")

iter_all

iter_all() -> Generator[DataStream, None, None]

Iterator for all child data streams, including nested collections.

Implements a depth-first traversal of the stream hierarchy.

Yields:

Name	Type	Description
DataStream	DataStream	All recursively yielded child data streams.

Source code in src/contraqctor/contract/base.py

def iter_all(self) -> Generator[DataStream, None, None]:
    """Iterator for all child data streams, including nested collections.

    Implements a depth-first traversal of the stream hierarchy.

    Yields:
        DataStream: All recursively yielded child data streams.
    """
    for value in self:
        if isinstance(value, DataStream):
            yield value
        if isinstance(value, DataStreamCollectionBase):
            yield from value.iter_all()

read

read(
    reader_params: Optional[TReaderParams] = None,
) -> TData

Read data using the configured reader.

Parameters:

Name	Type	Description	Default
reader_params	Optional[TReaderParams]	Optional parameters to override the default reader parameters.	None

Returns:

Name	Type	Description
TData	TData	Data read from the source.

Raises:

Type	Description
ValueError	If reader parameters are not set.

Source code in src/contraqctor/contract/base.py

def read(self, reader_params: Optional[_typing.TReaderParams] = None) -> _typing.TData:
    """Read data using the configured reader.

    Args:
        reader_params: Optional parameters to override the default reader parameters.

    Returns:
        TData: Data read from the source.

    Raises:
        ValueError: If reader parameters are not set.
    """
    reader_params = reader_params if reader_params is not None else self._reader_params
    if _typing.is_unset(reader_params):
        raise ValueError("Reader parameters are not set. Cannot read data.")
    return self._reader(reader_params)

bind_reader_params

bind_reader_params(params: TReaderParams) -> Self

Bind reader parameters to the data stream.

Parameters:

Name	Type	Description	Default
params	TReaderParams	Parameters to bind to the data stream's reader.	required

Returns:

Name	Type	Description
Self	Self	The data stream instance for method chaining.

Raises:

Type	Description
ValueError	If reader parameters have already been set.

Source code in src/contraqctor/contract/base.py

def bind_reader_params(self, params: _typing.TReaderParams) -> Self:
    """Bind reader parameters to the data stream.

    Args:
        params: Parameters to bind to the data stream's reader.

    Returns:
        Self: The data stream instance for method chaining.

    Raises:
        ValueError: If reader parameters have already been set.
    """
    if not _typing.is_unset(self._reader_params):
        raise ValueError("Reader parameters are already set. Cannot bind again.")
    self._reader_params = params
    return self

load_all

load_all(
    strict: bool = False,
) -> list[tuple[DataStream, Exception], None, None]

Recursively load this data stream and all child streams.

Performs depth-first traversal to load all streams in the hierarchy.

Parameters:

Name	Type	Description	Default
strict	bool	If True, raises exceptions immediately; otherwise collects and returns them.	False

Returns:

Name	Type	Description
list	list[tuple[DataStream, Exception], None, None]	List of tuples containing streams and exceptions that occurred during loading.

Raises:

Type	Description
Exception	If strict is True and an exception occurs during loading.

Examples:

# Load all streams and handle errors
errors = collection.load_all(strict=False)

if errors:
    for stream, error in errors:
        print(f"Error loading {stream.name}: {error}")

Source code in src/contraqctor/contract/base.py

def load_all(self, strict: bool = False) -> list[tuple["DataStream", Exception], None, None]:
    """Recursively load this data stream and all child streams.

    Performs depth-first traversal to load all streams in the hierarchy.

    Args:
        strict: If True, raises exceptions immediately; otherwise collects and returns them.

    Returns:
        list: List of tuples containing streams and exceptions that occurred during loading.

    Raises:
        Exception: If strict is True and an exception occurs during loading.

    Examples:
        ```python
        # Load all streams and handle errors
        errors = collection.load_all(strict=False)

        if errors:
            for stream, error in errors:
                print(f"Error loading {stream.name}: {error}")
        ```
    """
    self.load()
    exceptions = []
    for stream in self:
        if stream is None:
            continue
        try:
            exceptions += stream.load_all(strict=strict)
        except Exception as e:
            if strict:
                raise e
            exceptions.append((stream, e))
    return exceptions

DataStreamCollection

DataStreamCollection(
    name: str,
    data_streams: List[DataStream],
    *,
    description: Optional[str] = None,
)

Bases: DataStreamCollectionBase[DataStream, UnsetParamsType]

Collection of data streams with direct initialization.

A specialized collection where child streams are passed directly instead of being created by a reader function.

Parameters:

Name	Type	Description	Default
name	str	Name identifier for the collection.	required
data_streams	List[DataStream]	List of child data streams to include.	required
description	Optional[str]	Optional description of the collection.	None

Examples:

from contraqctor.contract import csv, text, DataStreamCollection

# Create streams
text_stream = text.Text("readme", reader_params=text.TextParams(path="README.md"))
csv_stream = csv.Csv("data", reader_params=csv.CsvParams(path="data.csv"))

# Create the collection
collection = DataStreamCollection("project_files", [text_stream, csv_stream])

# Load and use
collection.load_all()
readme_content = collection["readme"].data

Initializes a special DataStreamGroup where the data streams are passed directly, without a reader.

Source code in src/contraqctor/contract/base.py

@override
def __init__(
    self,
    name: str,
    data_streams: List[DataStream],
    *,
    description: Optional[str] = None,
) -> None:
    """Initializes a special DataStreamGroup where the data streams are passed directly, without a reader."""
    super().__init__(
        name=name,
        description=description,
        reader_params=_typing.UnsetParams,
    )
    self.bind_data_streams(data_streams)

name property

name: str

Get the name of the data stream.

Returns:

Name	Type	Description
str	str	Name identifier of the data stream.

resolved_name property

resolved_name: str

Get the full hierarchical name of the data stream.

Generates a path-like name showing the stream's position in the hierarchy, using '::' as a separator between parent and child names.

Returns:

Name	Type	Description
str	str	The fully resolved name including all parent names.

description property

description: Optional[str]

Get the description of the data stream.

Returns:

Type	Description
Optional[str]	Optional[str]: Description of the data stream, or None if not provided.

parent property

parent: Optional[DataStream]

Get the parent data stream.

Returns:

Type	Description
Optional[DataStream]	Optional[DataStream]: Parent data stream, or None if this is a root stream.

is_collection property

is_collection: bool

Check if this data stream is a collection of other streams.

Returns:

Name	Type	Description
bool	bool	True if this is a collection stream, False otherwise.

reader_params property

reader_params: TReaderParams

Get the parameters for the data reader.

Returns:

Name	Type	Description
TReaderParams	TReaderParams	Parameters for the data reader.

has_data property

has_data: bool

Check if the data stream has loaded data.

Returns:

Name	Type	Description
bool	bool	True if data has been loaded, False otherwise.

data property

data: TData

Get the loaded data.

Returns:

Name	Type	Description
TData	TData	The loaded data.

Raises:

Type	Description
ValueError	If data has not been loaded yet.

parameters staticmethod

parameters(*args, **kwargs) -> UnsetParamsType

Parameters function to return UnsetParams.

Returns:

Name	Type	Description
UnsetParamsType	UnsetParamsType	Special unset parameters value.

Source code in src/contraqctor/contract/base.py

@staticmethod
def parameters(*args, **kwargs) -> _typing.UnsetParamsType:
    """Parameters function to return UnsetParams.

    Returns:
        UnsetParamsType: Special unset parameters value.
    """
    return _typing.UnsetParams

read

read(*args, **kwargs) -> List[DataStream]

Read data from the collection.

Returns:

Type	Description
List[DataStream]	List[DataStream]: The pre-set data streams.

Raises:

Type	Description
ValueError	If data streams have not been set yet.

Source code in src/contraqctor/contract/base.py

@override
def read(self, *args, **kwargs) -> List[DataStream]:
    """Read data from the collection.

    Returns:
        List[DataStream]: The pre-set data streams.

    Raises:
        ValueError: If data streams have not been set yet.
    """
    if not self.has_data:
        raise ValueError("Data streams have not been read yet.")
    return self._data

bind_data_streams

bind_data_streams(data_streams: List[DataStream]) -> Self

Bind a list of data streams to the collection.

Parameters:

Name	Type	Description	Default
data_streams	List[DataStream]	List of data streams to include in the collection.	required

Returns:

Name	Type	Description
Self	Self	The collection instance for method chaining.

Raises:

Type	Description
ValueError	If data streams have already been set.

Source code in src/contraqctor/contract/base.py

def bind_data_streams(self, data_streams: List[DataStream]) -> Self:
    """Bind a list of data streams to the collection.

    Args:
        data_streams: List of data streams to include in the collection.

    Returns:
        Self: The collection instance for method chaining.

    Raises:
        ValueError: If data streams have already been set.
    """
    if self.has_data:
        raise ValueError("Data streams are already set. Cannot bind again.")
    self._data = data_streams
    self._update_hashmap()
    return self

add_stream

add_stream(stream: DataStream) -> Self

Add a new data stream to the collection.

Parameters:

Name	Type	Description	Default
stream	DataStream	Data stream to add to the collection.	required

Returns:

Name	Type	Description
Self	Self	The collection instance for method chaining.

Raises:

Type	Description
KeyError	If a stream with the same name already exists.

Examples:

from contraqctor.contract import json, DataStreamCollection

# Create an empty collection
collection = DataStreamCollection("api_data", [])

# Add streams
collection.add_stream(
    json.Json("config", reader_params=json.JsonParams(path="config.json"))
)

# Load the data
collection.load_all()

Source code in src/contraqctor/contract/base.py

def add_stream(self, stream: DataStream) -> Self:
    """Add a new data stream to the collection.

    Args:
        stream: Data stream to add to the collection.

    Returns:
        Self: The collection instance for method chaining.

    Raises:
        KeyError: If a stream with the same name already exists.

    Examples:
        ```python
        from contraqctor.contract import json, DataStreamCollection

        # Create an empty collection
        collection = DataStreamCollection("api_data", [])

        # Add streams
        collection.add_stream(
            json.Json("config", reader_params=json.JsonParams(path="config.json"))
        )

        # Load the data
        collection.load_all()
        ```
    """
    if not self.has_data:
        self._data = [stream]
        self._update_hashmap()
        return self

    if stream.name in self._hashmap:
        raise KeyError(f"Stream with name: '{stream.name}' already exists in data streams.")

    self._data.append(stream)
    self._update_hashmap()
    return self

remove_stream

remove_stream(name: str) -> None

Remove a data stream from the collection.

Parameters:

Name	Type	Description	Default
name	str	Name of the data stream to remove.	required

Raises:

Type	Description
ValueError	If data streams have not been set yet.
KeyError	If no stream with the given name exists.

Source code in src/contraqctor/contract/base.py

def remove_stream(self, name: str) -> None:
    """Remove a data stream from the collection.

    Args:
        name: Name of the data stream to remove.

    Raises:
        ValueError: If data streams have not been set yet.
        KeyError: If no stream with the given name exists.
    """
    if not self.has_data:
        raise ValueError("Data streams have not been read yet. Cannot access data streams.")

    if name not in self._hashmap:
        raise KeyError(f"Data stream with name '{name}' not found in data streams.")
    self._data.remove(self._hashmap[name])
    self._update_hashmap()
    return

from_data_stream classmethod

from_data_stream(data_stream: DataStream) -> Self

Create a DataStreamCollection from a DataStream object.

Factory method to convert a single data stream or collection into a DataStreamCollection.

Parameters:

Name	Type	Description	Default
data_stream	DataStream	Source data stream to convert.	required

Returns:

Name	Type	Description
DataStreamCollection	Self	New collection containing the source stream's data.

Raises:

Type	Description
TypeError	If the source is not a DataStream.
ValueError	If the source has not been loaded yet.

Source code in src/contraqctor/contract/base.py

@classmethod
def from_data_stream(cls, data_stream: DataStream) -> Self:
    """Create a DataStreamCollection from a DataStream object.

    Factory method to convert a single data stream or collection into a DataStreamCollection.

    Args:
        data_stream: Source data stream to convert.

    Returns:
        DataStreamCollection: New collection containing the source stream's data.

    Raises:
        TypeError: If the source is not a DataStream.
        ValueError: If the source has not been loaded yet.
    """
    if not isinstance(data_stream, DataStream):
        raise TypeError("data_stream must be an instance of DataStream.")
    if not data_stream.has_data:
        raise ValueError("DataStream has not been loaded yet. Cannot create DataStreamCollection.")
    data = data_stream.data if data_stream.is_collection else [data_stream.data]
    return cls(name=data_stream.name, data_streams=data, description=data_stream.description)

bind_reader_params

bind_reader_params(params: TReaderParams) -> Self

Bind reader parameters to the data stream.

Parameters:

Name	Type	Description	Default
params	TReaderParams	Parameters to bind to the data stream's reader.	required

Returns:

Name	Type	Description
Self	Self	The data stream instance for method chaining.

Raises:

Type	Description
ValueError	If reader parameters have already been set.

Source code in src/contraqctor/contract/base.py

def bind_reader_params(self, params: _typing.TReaderParams) -> Self:
    """Bind reader parameters to the data stream.

    Args:
        params: Parameters to bind to the data stream's reader.

    Returns:
        Self: The data stream instance for method chaining.

    Raises:
        ValueError: If reader parameters have already been set.
    """
    if not _typing.is_unset(self._reader_params):
        raise ValueError("Reader parameters are already set. Cannot bind again.")
    self._reader_params = params
    return self

at

at(name: str) -> TDataStream

Get a child data stream by name.

Parameters:

Name	Type	Description	Default
name	str	Name of the child data stream to retrieve.	required

Returns:

Name	Type	Description
TDataStream	TDataStream	The child data stream with the given name.

Raises:

Type	Description
ValueError	If data has not been loaded yet.
KeyError	If no child stream with the given name exists.

Source code in src/contraqctor/contract/base.py

@override
def at(self, name: str) -> TDataStream:
    """Get a child data stream by name.

    Args:
        name: Name of the child data stream to retrieve.

    Returns:
        TDataStream: The child data stream with the given name.

    Raises:
        ValueError: If data has not been loaded yet.
        KeyError: If no child stream with the given name exists.
    """
    if not self.has_data:
        raise ValueError("data streams have not been read yet. Cannot access data streams.")
    if name in self._hashmap:
        return self._hashmap[name]
    else:
        raise KeyError(f"Stream with name: '{name}' not found in data streams.")

load

load()

Load data for this collection.

Overrides the base method to add validation that loaded data is a list of DataStreams.

Returns:

Name	Type	Description
Self		The collection instance for method chaining.

Raises:

Type	Description
ValueError	If loaded data is not a list of DataStreams.

Source code in src/contraqctor/contract/base.py

@override
def load(self):
    """Load data for this collection.

    Overrides the base method to add validation that loaded data is a list of DataStreams.

    Returns:
        Self: The collection instance for method chaining.

    Raises:
        ValueError: If loaded data is not a list of DataStreams.
    """
    super().load()
    if not isinstance(self._data, list):
        self._data = _typing.UnsetData
        raise ValueError("Data must be a list of DataStreams.")
    self._update_hashmap()
    return self

load_all

load_all(
    strict: bool = False,
) -> list[tuple[DataStream, Exception], None, None]

Recursively load this data stream and all child streams.

Performs depth-first traversal to load all streams in the hierarchy.

Parameters:

Name	Type	Description	Default
strict	bool	If True, raises exceptions immediately; otherwise collects and returns them.	False

Returns:

Name	Type	Description
list	list[tuple[DataStream, Exception], None, None]	List of tuples containing streams and exceptions that occurred during loading.

Raises:

Type	Description
Exception	If strict is True and an exception occurs during loading.

Examples:

# Load all streams and handle errors
errors = collection.load_all(strict=False)

if errors:
    for stream, error in errors:
        print(f"Error loading {stream.name}: {error}")

Source code in src/contraqctor/contract/base.py

def load_all(self, strict: bool = False) -> list[tuple["DataStream", Exception], None, None]:
    """Recursively load this data stream and all child streams.

    Performs depth-first traversal to load all streams in the hierarchy.

    Args:
        strict: If True, raises exceptions immediately; otherwise collects and returns them.

    Returns:
        list: List of tuples containing streams and exceptions that occurred during loading.

    Raises:
        Exception: If strict is True and an exception occurs during loading.

    Examples:
        ```python
        # Load all streams and handle errors
        errors = collection.load_all(strict=False)

        if errors:
            for stream, error in errors:
                print(f"Error loading {stream.name}: {error}")
        ```
    """
    self.load()
    exceptions = []
    for stream in self:
        if stream is None:
            continue
        try:
            exceptions += stream.load_all(strict=strict)
        except Exception as e:
            if strict:
                raise e
            exceptions.append((stream, e))
    return exceptions

iter_all

iter_all() -> Generator[DataStream, None, None]

Iterator for all child data streams, including nested collections.

Implements a depth-first traversal of the stream hierarchy.

Yields:

Name	Type	Description
DataStream	DataStream	All recursively yielded child data streams.

Source code in src/contraqctor/contract/base.py

def iter_all(self) -> Generator[DataStream, None, None]:
    """Iterator for all child data streams, including nested collections.

    Implements a depth-first traversal of the stream hierarchy.

    Yields:
        DataStream: All recursively yielded child data streams.
    """
    for value in self:
        if isinstance(value, DataStream):
            yield value
        if isinstance(value, DataStreamCollectionBase):
            yield from value.iter_all()

Dataset

Dataset(
    name: str,
    data_streams: List[DataStream],
    *,
    version: str | Version = "0.0.0",
    description: Optional[str] = None,
)

Bases: DataStreamCollection

A version-tracked collection of data streams.

Extends DataStreamCollection by adding semantic versioning support.

Parameters:

Name	Type	Description	Default
name	str	Name identifier for the dataset.	required
data_streams	List[DataStream]	List of data streams to include in the dataset.	required
version	str | Version	Semantic version string or Version object. Defaults to "0.0.0".	'0.0.0'
description	Optional[str]	Optional description of the dataset.	None

Examples:

from contraqctor.contract import text, csv, Dataset

# Create streams
text_stream = text.Text("notes", reader_params=text.TextParams(path="notes.txt"))
csv_stream = csv.Csv("data", reader_params=csv.CsvParams(path="data.csv"))

# Create a versioned dataset
dataset = Dataset(
    "experiment_results",
    [text_stream, csv_stream],
    version="1.2.3"
)

# Load the dataset
dataset.load_all(strict=True)

# Access streams
txt = dataset["notes"].data
csv_data = dataset["data"].data

print(f"Dataset version: {dataset.version}")

Initializes a Dataset with a version and a list of data streams.

Source code in src/contraqctor/contract/base.py

@override
def __init__(
    self,
    name: str,
    data_streams: List[DataStream],
    *,
    version: str | Version = "0.0.0",
    description: Optional[str] = None,
) -> None:
    """Initializes a Dataset with a version and a list of data streams."""
    super().__init__(
        name=name,
        data_streams=data_streams,
        description=description,
    )
    self._version = self._parse_semver(version)

version property

version: Version

Get the semantic version of the dataset.

Returns:

Name	Type	Description
Version	Version	Semantic version object.

name property

name: str

Get the name of the data stream.

Returns:

Name	Type	Description
str	str	Name identifier of the data stream.

resolved_name property

resolved_name: str

Get the full hierarchical name of the data stream.

Generates a path-like name showing the stream's position in the hierarchy, using '::' as a separator between parent and child names.

Returns:

Name	Type	Description
str	str	The fully resolved name including all parent names.

description property

description: Optional[str]

Get the description of the data stream.

Returns:

Type	Description
Optional[str]	Optional[str]: Description of the data stream, or None if not provided.

parent property

parent: Optional[DataStream]

Get the parent data stream.

Returns:

Type	Description
Optional[DataStream]	Optional[DataStream]: Parent data stream, or None if this is a root stream.

is_collection property

is_collection: bool

Check if this data stream is a collection of other streams.

Returns:

Name	Type	Description
bool	bool	True if this is a collection stream, False otherwise.

reader_params property

reader_params: TReaderParams

Get the parameters for the data reader.

Returns:

Name	Type	Description
TReaderParams	TReaderParams	Parameters for the data reader.

has_data property

has_data: bool

Check if the data stream has loaded data.

Returns:

Name	Type	Description
bool	bool	True if data has been loaded, False otherwise.

data property

data: TData

Get the loaded data.

Returns:

Name	Type	Description
TData	TData	The loaded data.

Raises:

Type	Description
ValueError	If data has not been loaded yet.

read

read(*args, **kwargs) -> List[DataStream]

Read data from the collection.

Returns:

Type	Description
List[DataStream]	List[DataStream]: The pre-set data streams.

Raises:

Type	Description
ValueError	If data streams have not been set yet.

Source code in src/contraqctor/contract/base.py

@override
def read(self, *args, **kwargs) -> List[DataStream]:
    """Read data from the collection.

    Returns:
        List[DataStream]: The pre-set data streams.

    Raises:
        ValueError: If data streams have not been set yet.
    """
    if not self.has_data:
        raise ValueError("Data streams have not been read yet.")
    return self._data

bind_reader_params

bind_reader_params(params: TReaderParams) -> Self

Bind reader parameters to the data stream.

Parameters:

Name	Type	Description	Default
params	TReaderParams	Parameters to bind to the data stream's reader.	required

Returns:

Name	Type	Description
Self	Self	The data stream instance for method chaining.

Raises:

Type	Description
ValueError	If reader parameters have already been set.

Source code in src/contraqctor/contract/base.py

def bind_reader_params(self, params: _typing.TReaderParams) -> Self:
    """Bind reader parameters to the data stream.

    Args:
        params: Parameters to bind to the data stream's reader.

    Returns:
        Self: The data stream instance for method chaining.

    Raises:
        ValueError: If reader parameters have already been set.
    """
    if not _typing.is_unset(self._reader_params):
        raise ValueError("Reader parameters are already set. Cannot bind again.")
    self._reader_params = params
    return self

at

at(name: str) -> TDataStream

Get a child data stream by name.

Parameters:

Name	Type	Description	Default
name	str	Name of the child data stream to retrieve.	required

Returns:

Name	Type	Description
TDataStream	TDataStream	The child data stream with the given name.

Raises:

Type	Description
ValueError	If data has not been loaded yet.
KeyError	If no child stream with the given name exists.

Source code in src/contraqctor/contract/base.py

@override
def at(self, name: str) -> TDataStream:
    """Get a child data stream by name.

    Args:
        name: Name of the child data stream to retrieve.

    Returns:
        TDataStream: The child data stream with the given name.

    Raises:
        ValueError: If data has not been loaded yet.
        KeyError: If no child stream with the given name exists.
    """
    if not self.has_data:
        raise ValueError("data streams have not been read yet. Cannot access data streams.")
    if name in self._hashmap:
        return self._hashmap[name]
    else:
        raise KeyError(f"Stream with name: '{name}' not found in data streams.")

load

load()

Load data for this collection.

Overrides the base method to add validation that loaded data is a list of DataStreams.

Returns:

Name	Type	Description
Self		The collection instance for method chaining.

Raises:

Type	Description
ValueError	If loaded data is not a list of DataStreams.

Source code in src/contraqctor/contract/base.py

@override
def load(self):
    """Load data for this collection.

    Overrides the base method to add validation that loaded data is a list of DataStreams.

    Returns:
        Self: The collection instance for method chaining.

    Raises:
        ValueError: If loaded data is not a list of DataStreams.
    """
    super().load()
    if not isinstance(self._data, list):
        self._data = _typing.UnsetData
        raise ValueError("Data must be a list of DataStreams.")
    self._update_hashmap()
    return self

load_all

load_all(
    strict: bool = False,
) -> list[tuple[DataStream, Exception], None, None]

Recursively load this data stream and all child streams.

Performs depth-first traversal to load all streams in the hierarchy.

Parameters:

Name	Type	Description	Default
strict	bool	If True, raises exceptions immediately; otherwise collects and returns them.	False

Returns:

Name	Type	Description
list	list[tuple[DataStream, Exception], None, None]	List of tuples containing streams and exceptions that occurred during loading.

Raises:

Type	Description
Exception	If strict is True and an exception occurs during loading.

Examples:

# Load all streams and handle errors
errors = collection.load_all(strict=False)

if errors:
    for stream, error in errors:
        print(f"Error loading {stream.name}: {error}")

Source code in src/contraqctor/contract/base.py

def load_all(self, strict: bool = False) -> list[tuple["DataStream", Exception], None, None]:
    """Recursively load this data stream and all child streams.

    Performs depth-first traversal to load all streams in the hierarchy.

    Args:
        strict: If True, raises exceptions immediately; otherwise collects and returns them.

    Returns:
        list: List of tuples containing streams and exceptions that occurred during loading.

    Raises:
        Exception: If strict is True and an exception occurs during loading.

    Examples:
        ```python
        # Load all streams and handle errors
        errors = collection.load_all(strict=False)

        if errors:
            for stream, error in errors:
                print(f"Error loading {stream.name}: {error}")
        ```
    """
    self.load()
    exceptions = []
    for stream in self:
        if stream is None:
            continue
        try:
            exceptions += stream.load_all(strict=strict)
        except Exception as e:
            if strict:
                raise e
            exceptions.append((stream, e))
    return exceptions

iter_all

iter_all() -> Generator[DataStream, None, None]

Iterator for all child data streams, including nested collections.

Implements a depth-first traversal of the stream hierarchy.

Yields:

Name	Type	Description
DataStream	DataStream	All recursively yielded child data streams.

Source code in src/contraqctor/contract/base.py

def iter_all(self) -> Generator[DataStream, None, None]:
    """Iterator for all child data streams, including nested collections.

    Implements a depth-first traversal of the stream hierarchy.

    Yields:
        DataStream: All recursively yielded child data streams.
    """
    for value in self:
        if isinstance(value, DataStream):
            yield value
        if isinstance(value, DataStreamCollectionBase):
            yield from value.iter_all()

parameters staticmethod

parameters(*args, **kwargs) -> UnsetParamsType

Parameters function to return UnsetParams.

Returns:

Name	Type	Description
UnsetParamsType	UnsetParamsType	Special unset parameters value.

Source code in src/contraqctor/contract/base.py

@staticmethod
def parameters(*args, **kwargs) -> _typing.UnsetParamsType:
    """Parameters function to return UnsetParams.

    Returns:
        UnsetParamsType: Special unset parameters value.
    """
    return _typing.UnsetParams

bind_data_streams

bind_data_streams(data_streams: List[DataStream]) -> Self

Bind a list of data streams to the collection.

Parameters:

Name	Type	Description	Default
data_streams	List[DataStream]	List of data streams to include in the collection.	required

Returns:

Name	Type	Description
Self	Self	The collection instance for method chaining.

Raises:

Type	Description
ValueError	If data streams have already been set.

Source code in src/contraqctor/contract/base.py

def bind_data_streams(self, data_streams: List[DataStream]) -> Self:
    """Bind a list of data streams to the collection.

    Args:
        data_streams: List of data streams to include in the collection.

    Returns:
        Self: The collection instance for method chaining.

    Raises:
        ValueError: If data streams have already been set.
    """
    if self.has_data:
        raise ValueError("Data streams are already set. Cannot bind again.")
    self._data = data_streams
    self._update_hashmap()
    return self

add_stream

add_stream(stream: DataStream) -> Self

Add a new data stream to the collection.

Parameters:

Name	Type	Description	Default
stream	DataStream	Data stream to add to the collection.	required

Returns:

Name	Type	Description
Self	Self	The collection instance for method chaining.

Raises:

Type	Description
KeyError	If a stream with the same name already exists.

Examples:

from contraqctor.contract import json, DataStreamCollection

# Create an empty collection
collection = DataStreamCollection("api_data", [])

# Add streams
collection.add_stream(
    json.Json("config", reader_params=json.JsonParams(path="config.json"))
)

# Load the data
collection.load_all()

Source code in src/contraqctor/contract/base.py

def add_stream(self, stream: DataStream) -> Self:
    """Add a new data stream to the collection.

    Args:
        stream: Data stream to add to the collection.

    Returns:
        Self: The collection instance for method chaining.

    Raises:
        KeyError: If a stream with the same name already exists.

    Examples:
        ```python
        from contraqctor.contract import json, DataStreamCollection

        # Create an empty collection
        collection = DataStreamCollection("api_data", [])

        # Add streams
        collection.add_stream(
            json.Json("config", reader_params=json.JsonParams(path="config.json"))
        )

        # Load the data
        collection.load_all()
        ```
    """
    if not self.has_data:
        self._data = [stream]
        self._update_hashmap()
        return self

    if stream.name in self._hashmap:
        raise KeyError(f"Stream with name: '{stream.name}' already exists in data streams.")

    self._data.append(stream)
    self._update_hashmap()
    return self

remove_stream

remove_stream(name: str) -> None

Remove a data stream from the collection.

Parameters:

Name	Type	Description	Default
name	str	Name of the data stream to remove.	required

Raises:

Type	Description
ValueError	If data streams have not been set yet.
KeyError	If no stream with the given name exists.

Source code in src/contraqctor/contract/base.py

def remove_stream(self, name: str) -> None:
    """Remove a data stream from the collection.

    Args:
        name: Name of the data stream to remove.

    Raises:
        ValueError: If data streams have not been set yet.
        KeyError: If no stream with the given name exists.
    """
    if not self.has_data:
        raise ValueError("Data streams have not been read yet. Cannot access data streams.")

    if name not in self._hashmap:
        raise KeyError(f"Data stream with name '{name}' not found in data streams.")
    self._data.remove(self._hashmap[name])
    self._update_hashmap()
    return

from_data_stream classmethod

from_data_stream(data_stream: DataStream) -> Self

Create a DataStreamCollection from a DataStream object.

Factory method to convert a single data stream or collection into a DataStreamCollection.

Parameters:

Name	Type	Description	Default
data_stream	DataStream	Source data stream to convert.	required

Returns:

Name	Type	Description
DataStreamCollection	Self	New collection containing the source stream's data.

Raises:

Type	Description
TypeError	If the source is not a DataStream.
ValueError	If the source has not been loaded yet.

Source code in src/contraqctor/contract/base.py

@classmethod
def from_data_stream(cls, data_stream: DataStream) -> Self:
    """Create a DataStreamCollection from a DataStream object.

    Factory method to convert a single data stream or collection into a DataStreamCollection.

    Args:
        data_stream: Source data stream to convert.

    Returns:
        DataStreamCollection: New collection containing the source stream's data.

    Raises:
        TypeError: If the source is not a DataStream.
        ValueError: If the source has not been loaded yet.
    """
    if not isinstance(data_stream, DataStream):
        raise TypeError("data_stream must be an instance of DataStream.")
    if not data_stream.has_data:
        raise ValueError("DataStream has not been loaded yet. Cannot create DataStreamCollection.")
    data = data_stream.data if data_stream.is_collection else [data_stream.data]
    return cls(name=data_stream.name, data_streams=data, description=data_stream.description)

FilePathBaseParam dataclass

FilePathBaseParam(path: PathLike)

Bases: ABC

Abstract base class for file-based reader parameters.

Base parameter class for readers that access files by path.

Attributes:

Name	Type	Description
path	PathLike	Path to the file or directory to read from.