How to use copulas - 8 common examples

To help you get started, we’ve selected a few copulas examples, based on popular ways it is used in public projects.

Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.

github HDI-Project / SDV / sdv / tabular / copulas.py View on Github external
def _fit(self, data):
        """Fit the model to the table.

        Args:
            table_data (pandas.DataFrame):
                Data to be fitted.
        """
        self._model = copulas.multivariate.GaussianMultivariate(distribution=self._distribution)
        self._model.fit(data)
        self._update_metadata()
github HDI-Project / SDV / sdv / models / copulas.py View on Github external
def fit(self, table_data):
        """Fit the model to the table.

        Impute the table data before fit the model.

        Args:
            table_data (pandas.DataFrame):
                Data to be fitted.
        """
        table_data = impute(table_data)
        self.model = multivariate.GaussianMultivariate(distribution=self.distribution)
        self.model.fit(table_data)
github HDI-Project / SDV / sdv / models / copulas.py View on Github external
in order to set expected parameters for the copula.

        Args:
            dict:
                Copula flatten parameters.
        """
        parameters = unflatten_dict(parameters)
        parameters.setdefault('fitted', True)
        parameters.setdefault('distribution', self.distribution)

        parameters = self._unflatten_gaussian_copula(parameters)
        for param in parameters['distribs'].values():
            param.setdefault('type', self.distribution)
            param.setdefault('fitted', True)

        self.model = multivariate.GaussianMultivariate.from_dict(parameters)
github HDI-Project / SDV / sdv / tabular / copulas.py View on Github external
Add additional keys after unflatte the parameters
        in order to set expected parameters for the copula.

        Args:
            dict:
                Copula flatten parameters.
            unflatten (bool):
                Whether the parameters need to be unflattened or not.
        """
        if unflatten:
            parameters = unflatten_dict(parameters)
            parameters.setdefault('distribution', self._distribution)

            parameters = self._unflatten_gaussian_copula(parameters)

        self._model = copulas.multivariate.GaussianMultivariate.from_dict(parameters)
github HDI-Project / SDV / sdv / tabular / copulas.py View on Github external
unflatten_dict)


class GaussianCopula(BaseTabularModel):
    """Model wrapping ``copulas.multivariate.GaussianMultivariate`` copula.

    Args:
        distribution (copulas.univariate.Univariate or str):
            Copulas univariate distribution to use.
        categorical_transformer (str):
            Type of transformer to use for the categorical variables, to choose
            from ``one_hot_encoding``, ``label_encoding``, ``categorical`` and
            ``categorical_fuzzy``.
    """

    DEFAULT_DISTRIBUTION = copulas.univariate.Univariate
    _distribution = None
    _categorical_transformer = None
    _model = None

    HYPERPARAMETERS = {
        'distribution': {
            'type': 'str or copulas.univariate.Univariate',
            'default': 'copulas.univariate.Univariate',
            'description': 'Univariate distribution to use to model each column',
            'choices': [
                'copulas.univariate.Univariate',
                'copulas.univariate.GaussianUnivariate',
                'copulas.univariate.GammaUnivariate',
                'copulas.univariate.BetaUnivariate',
                'copulas.univariate.StudentTUnivariate',
                'copulas.univariate.GaussianKDE',
github HDI-Project / SDV / sdv / models / copulas.py View on Github external
Copula flatten parameters.
        """
        parameters = unflatten_dict(parameters)
        parameters.setdefault('fitted', True)
        parameters.setdefault('distribution', self.distribution)

        parameters = self._unflatten_gaussian_copula(parameters)
        for param in parameters['distribs'].values():
            param.setdefault('type', self.distribution)
            param.setdefault('fitted', True)

        self.model = multivariate.GaussianMultivariate.from_dict(parameters)


class GaussianCopulaTruncated(GaussianCopula):
    DISTRIBUTION = univariate.TruncatedGaussian
github HDI-Project / SDV / sdv / tabular / copulas.py View on Github external
values = list()
        triangle = np.tril(self._model.covariance)

        for index, row in enumerate(triangle.tolist()):
            values.append(row[:index + 1])

        self._model.covariance = np.array(values)
        params = self._model.to_dict()
        univariates = dict()
        for name, univariate in zip(params.pop('columns'), params['univariates']):
            univariates[name] = univariate
            if 'scale' in univariate:
                scale = univariate['scale']
                if scale == 0:
                    scale = copulas.EPSILON

                univariate['scale'] = np.log(scale)

        params['univariates'] = univariates

        return flatten_dict(params)
github HDI-Project / SDV / sdv / sdv.py View on Github external
# -*- coding: utf-8 -*-

"""Main module."""
import pickle

from copulas.univariate import GaussianUnivariate

from sdv.metadata import Metadata
from sdv.modeler import Modeler
from sdv.models.copulas import GaussianCopula
from sdv.sampler import Sampler

DEFAULT_MODEL = GaussianCopula
DEFAULT_MODEL_KWARGS = {
    'distribution': GaussianUnivariate
}


class NotFittedError(Exception):
    pass


class SDV:
    """Automated generative modeling and sampling tool.

    Allows the users to generate synthetic data after creating generative models for their data.

    Args:
        model (type):
            Class of the ``copula`` to use. Defaults to
            ``sdv.models.copulas.GaussianCopula``.

copulas

Create tabular synthetic data using copulas-based modeling.

BSL-1.0
Latest version published 3 months ago

Package Health Score

88 / 100
Full package analysis