concrete.ml.sklearn.protocols.md

module concrete.ml.sklearn.protocols

Protocols.

Protocols are used to mix type hinting with duck-typing. Indeed we don't always want to have an abstract parent class between all objects. We are more interested in the behavior of such objects. Implementing a Protocol is a way to specify the behavior of objects.

To read more about Protocol please read: https://peps.python.org/pep-0544

class Quantizer

Quantizer Protocol.

To use to type hint a quantizer.

method dequant

dequant(X: 'ndarray') → ndarray

Dequantize some values.

Args:

• X (numpy.ndarray): Values to dequantize

.. # noqa: DAR202

Returns:

• numpy.ndarray: Dequantized values

method quant

quant(values: 'ndarray') → ndarray

Quantize some values.

Args:

• values (numpy.ndarray): Values to quantize

.. # noqa: DAR202

Returns:

• numpy.ndarray: The quantized values

class ConcreteBaseEstimatorProtocol

A Concrete Estimator Protocol.

property onnx_model

onnx_model.

.. # noqa: DAR202

Results: onnx.ModelProto

property quantize_input

Quantize input function.

method compile

compile(
    X: 'ndarray',
    configuration: 'Optional[Configuration]',
    compilation_artifacts: 'Optional[DebugArtifacts]',
    show_mlir: 'bool',
    use_virtual_lib: 'bool',
    p_error: 'float',
    global_p_error: 'float',
    verbose_compilation: 'bool'
) → Circuit

Compiles a model to a FHE Circuit.

Args:

• X (numpy.ndarray): the dequantized dataset

• configuration (Optional[Configuration]): the options for compilation

• compilation_artifacts (Optional[DebugArtifacts]): artifacts object to fill during compilation

• show_mlir (bool): whether or not to show MLIR during the compilation

• use_virtual_lib (bool): whether to compile using the virtual library that allows higher bitwidths

• p_error (float): probability of error of a single PBS

• global_p_error (float): probability of error of the full circuit. Not simulated by the VL, i.e., taken as 0

• verbose_compilation (bool): whether to show compilation information

.. # noqa: DAR202

Returns:

• Circuit: the compiled Circuit.

method fit

fit(X: 'ndarray', y: 'ndarray', **fit_params) → ConcreteBaseEstimatorProtocol

Initialize and fit the module.

Args:

• X : training data By default, you should be able to pass: * numpy arrays * torch tensors * pandas DataFrame or Series

• y (numpy.ndarray): labels associated with training data

• **fit_params: additional parameters that can be used during training

.. # noqa: DAR202

Returns:

• ConcreteBaseEstimatorProtocol: the trained estimator

method fit_benchmark

fit_benchmark(
    X: 'ndarray',
    y: 'ndarray',
    *args,
    **kwargs
) → Tuple[ConcreteBaseEstimatorProtocol, BaseEstimator]

Fit the quantized estimator and return reference estimator.

This function returns both the quantized estimator (itself), but also a wrapper around the non-quantized trained NN. This is useful in order to compare performance between the quantized and fp32 versions of the classifier

Args:

• X : training data By default, you should be able to pass: * numpy arrays * torch tensors * pandas DataFrame or Series

• y (numpy.ndarray): labels associated with training data

• *args: The arguments to pass to the underlying model.

• **kwargs: The keyword arguments to pass to the underlying model.

.. # noqa: DAR202

Returns:

• self: self fitted

• model: underlying estimator

method post_processing

post_processing(y_preds: 'ndarray') → ndarray

Post-process models predictions.

Args:

• y_preds (numpy.ndarray): predicted values by model (clear-quantized)

.. # noqa: DAR202

Returns:

• numpy.ndarray: the post-processed predictions

class ConcreteBaseClassifierProtocol

Concrete classifier protocol.

property onnx_model

onnx_model.

.. # noqa: DAR202

Results: onnx.ModelProto

property quantize_input

Quantize input function.

method compile

compile(
    X: 'ndarray',
    configuration: 'Optional[Configuration]',
    compilation_artifacts: 'Optional[DebugArtifacts]',
    show_mlir: 'bool',
    use_virtual_lib: 'bool',
    p_error: 'float',
    global_p_error: 'float',
    verbose_compilation: 'bool'
) → Circuit

Compiles a model to a FHE Circuit.

Args:

• X (numpy.ndarray): the dequantized dataset

• configuration (Optional[Configuration]): the options for compilation

• compilation_artifacts (Optional[DebugArtifacts]): artifacts object to fill during compilation

• show_mlir (bool): whether or not to show MLIR during the compilation

• use_virtual_lib (bool): whether to compile using the virtual library that allows higher bitwidths

• p_error (float): probability of error of a single PBS

• global_p_error (float): probability of error of the full circuit. Not simulated by the VL, i.e., taken as 0

• verbose_compilation (bool): whether to show compilation information

.. # noqa: DAR202

Returns:

• Circuit: the compiled Circuit.

method fit

fit(X: 'ndarray', y: 'ndarray', **fit_params) → ConcreteBaseEstimatorProtocol

Initialize and fit the module.

Args:

• X : training data By default, you should be able to pass: * numpy arrays * torch tensors * pandas DataFrame or Series

• y (numpy.ndarray): labels associated with training data

• **fit_params: additional parameters that can be used during training

.. # noqa: DAR202

Returns:

• ConcreteBaseEstimatorProtocol: the trained estimator

method fit_benchmark

fit_benchmark(
    X: 'ndarray',
    y: 'ndarray',
    *args,
    **kwargs
) → Tuple[ConcreteBaseEstimatorProtocol, BaseEstimator]

Fit the quantized estimator and return reference estimator.

This function returns both the quantized estimator (itself), but also a wrapper around the non-quantized trained NN. This is useful in order to compare performance between the quantized and fp32 versions of the classifier

Args:

• X : training data By default, you should be able to pass: * numpy arrays * torch tensors * pandas DataFrame or Series

• y (numpy.ndarray): labels associated with training data

• *args: The arguments to pass to the underlying model.

• **kwargs: The keyword arguments to pass to the underlying model.

.. # noqa: DAR202

Returns:

• self: self fitted

• model: underlying estimator

method post_processing

post_processing(y_preds: 'ndarray') → ndarray

Post-process models predictions.

Args:

• y_preds (numpy.ndarray): predicted values by model (clear-quantized)

.. # noqa: DAR202

Returns:

• numpy.ndarray: the post-processed predictions

method predict

predict(X: 'ndarray', execute_in_fhe: 'bool') → ndarray

Predicts for each sample the class with highest probability.

Args:

• X (numpy.ndarray): Features

• execute_in_fhe (bool): Whether the inference should be done in fhe or not.

.. # noqa: DAR202

Returns: numpy.ndarray

method predict_proba

predict_proba(X: 'ndarray', execute_in_fhe: 'bool') → ndarray

Predicts for each sample the probability of each class.

Args:

• X (numpy.ndarray): Features

• execute_in_fhe (bool): Whether the inference should be done in fhe or not.

.. # noqa: DAR202

Returns: numpy.ndarray

class ConcreteBaseRegressorProtocol

Concrete regressor protocol.

property onnx_model

onnx_model.

.. # noqa: DAR202

Results: onnx.ModelProto

property quantize_input

Quantize input function.

method compile

compile(
    X: 'ndarray',
    configuration: 'Optional[Configuration]',
    compilation_artifacts: 'Optional[DebugArtifacts]',
    show_mlir: 'bool',
    use_virtual_lib: 'bool',
    p_error: 'float',
    global_p_error: 'float',
    verbose_compilation: 'bool'
) → Circuit

Compiles a model to a FHE Circuit.

Args:

• X (numpy.ndarray): the dequantized dataset

• configuration (Optional[Configuration]): the options for compilation

• compilation_artifacts (Optional[DebugArtifacts]): artifacts object to fill during compilation

• show_mlir (bool): whether or not to show MLIR during the compilation

• use_virtual_lib (bool): whether to compile using the virtual library that allows higher bitwidths

• p_error (float): probability of error of a single PBS

• global_p_error (float): probability of error of the full circuit. Not simulated by the VL, i.e., taken as 0

• verbose_compilation (bool): whether to show compilation information

.. # noqa: DAR202

Returns:

• Circuit: the compiled Circuit.

method fit

fit(X: 'ndarray', y: 'ndarray', **fit_params) → ConcreteBaseEstimatorProtocol

Initialize and fit the module.

Args:

• X : training data By default, you should be able to pass: * numpy arrays * torch tensors * pandas DataFrame or Series

• y (numpy.ndarray): labels associated with training data

• **fit_params: additional parameters that can be used during training

.. # noqa: DAR202

Returns:

• ConcreteBaseEstimatorProtocol: the trained estimator

method fit_benchmark

fit_benchmark(
    X: 'ndarray',
    y: 'ndarray',
    *args,
    **kwargs
) → Tuple[ConcreteBaseEstimatorProtocol, BaseEstimator]

Fit the quantized estimator and return reference estimator.

This function returns both the quantized estimator (itself), but also a wrapper around the non-quantized trained NN. This is useful in order to compare performance between the quantized and fp32 versions of the classifier

Args:

• X : training data By default, you should be able to pass: * numpy arrays * torch tensors * pandas DataFrame or Series

• y (numpy.ndarray): labels associated with training data

• *args: The arguments to pass to the underlying model.

• **kwargs: The keyword arguments to pass to the underlying model.

.. # noqa: DAR202

Returns:

• self: self fitted

• model: underlying estimator

method post_processing

post_processing(y_preds: 'ndarray') → ndarray

Post-process models predictions.

Args:

• y_preds (numpy.ndarray): predicted values by model (clear-quantized)

.. # noqa: DAR202

Returns:

• numpy.ndarray: the post-processed predictions

method predict

predict(X: 'ndarray', execute_in_fhe: 'bool') → ndarray

Predicts for each sample the expected value.

Args:

• X (numpy.ndarray): Features

• execute_in_fhe (bool): Whether the inference should be done in fhe or not.

.. # noqa: DAR202

Returns: numpy.ndarray