copulas 0.10.1.dev0__py3-none-any.whl

copulas/univariate/gamma.py

@@ -0,0 +1,38 @@
+"""GammaUnivariate module."""
+
+import numpy as np
+from scipy.stats import gamma
+
+from copulas.univariate.base import BoundedType, ParametricType, ScipyModel
+
+
+class GammaUnivariate(ScipyModel):
+    """Wrapper around scipy.stats.gamma.
+
+    Documentation: https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.gamma.html
+    """
+
+    PARAMETRIC = ParametricType.PARAMETRIC
+    BOUNDED = BoundedType.SEMI_BOUNDED
+    MODEL_CLASS = gamma
+
+    def _fit_constant(self, X):
+        self._params = {
+            'a': 0.0,
+            'loc': np.unique(X)[0],
+            'scale': 0.0,
+        }
+
+    def _fit(self, X):
+        a, loc, scale = gamma.fit(X)
+        self._params = {
+            'a': a,
+            'loc': loc,
+            'scale': scale,
+        }
+
+    def _is_constant(self):
+        return self._params['scale'] == 0
+
+    def _extract_constant(self):
+        return self._params['loc']

copulas/univariate/gaussian.py

@@ -0,0 +1,33 @@
+"""GaussianUnivariate module."""
+
+import numpy as np
+from scipy.stats import norm
+
+from copulas.univariate.base import BoundedType, ParametricType, ScipyModel
+
+
+class GaussianUnivariate(ScipyModel):
+    """Gaussian univariate model."""
+
+    PARAMETRIC = ParametricType.PARAMETRIC
+    BOUNDED = BoundedType.UNBOUNDED
+
+    MODEL_CLASS = norm
+
+    def _fit_constant(self, X):
+        self._params = {
+            'loc': np.unique(X)[0],
+            'scale': 0
+        }
+
+    def _fit(self, X):
+        self._params = {
+            'loc': np.mean(X),
+            'scale': np.std(X)
+        }
+
+    def _is_constant(self):
+        return self._params['scale'] == 0
+
+    def _extract_constant(self):
+        return self._params['loc']

copulas/univariate/gaussian_kde.py

@@ -0,0 +1,193 @@
+"""GaussianKDE module."""
+
+import numpy as np
+from scipy.special import ndtr
+from scipy.stats import gaussian_kde
+
+from copulas import EPSILON, random_state, store_args, validate_random_state
+from copulas.optimize import bisect, chandrupatla
+from copulas.univariate.base import BoundedType, ParametricType, ScipyModel
+
+
+class GaussianKDE(ScipyModel):
+    """A wrapper for gaussian Kernel density estimation.
+
+    It was implemented in scipy.stats toolbox. gaussian_kde is slower than statsmodels
+    but allows more flexibility.
+
+    When a sample_size is provided the fit method will sample the
+    data, and mask the real information. Also, ensure the number of
+    entries will be always the value of sample_size.
+
+    Args:
+        sample_size(int): amount of parameters to sample
+    """
+
+    PARAMETRIC = ParametricType.NON_PARAMETRIC
+    BOUNDED = BoundedType.UNBOUNDED
+    MODEL_CLASS = gaussian_kde
+
+    @store_args
+    def __init__(self, sample_size=None, random_state=None, bw_method=None, weights=None):
+        self.random_state = validate_random_state(random_state)
+        self._sample_size = sample_size
+        self.bw_method = bw_method
+        self.weights = weights
+
+    def _get_model(self):
+        dataset = self._params['dataset']
+        self._sample_size = self._sample_size or len(dataset)
+        return gaussian_kde(dataset, bw_method=self.bw_method, weights=self.weights)
+
+    def _get_bounds(self):
+        X = self._params['dataset']
+        lower = np.min(X) - (5 * np.std(X))
+        upper = np.max(X) + (5 * np.std(X))
+
+        return lower, upper
+
+    def probability_density(self, X):
+        """Compute the probability density for each point in X.
+
+        Arguments:
+            X (numpy.ndarray):
+                Values for which the probability density will be computed.
+                It must have shape (n, 1).
+
+        Returns:
+            numpy.ndarray:
+                Probability density values for points in X.
+
+        Raises:
+            NotFittedError:
+                if the model is not fitted.
+        """
+        self.check_fit()
+        return self._model.evaluate(X)
+
+    @random_state
+    def sample(self, n_samples=1):
+        """Sample values from this model.
+
+        Argument:
+            n_samples (int):
+                Number of values to sample
+
+        Returns:
+            numpy.ndarray:
+                Array of shape (n_samples, 1) with values randomly
+                sampled from this model distribution.
+
+        Raises:
+            NotFittedError:
+                if the model is not fitted.
+        """
+        self.check_fit()
+        return self._model.resample(size=n_samples)[0]
+
+    def cumulative_distribution(self, X):
+        """Compute the cumulative distribution value for each point in X.
+
+        Arguments:
+            X (numpy.ndarray):
+                Values for which the cumulative distribution will be computed.
+                It must have shape (n, 1).
+
+        Returns:
+            numpy.ndarray:
+                Cumulative distribution values for points in X.
+
+        Raises:
+            NotFittedError:
+                if the model is not fitted.
+        """
+        self.check_fit()
+        X = np.array(X)
+        stdev = np.sqrt(self._model.covariance[0, 0])
+        lower = ndtr((self._get_bounds()[0] - self._model.dataset) / stdev)[0]
+        uppers = ndtr((X[:, None] - self._model.dataset) / stdev)
+        return (uppers - lower).dot(self._model.weights)
+
+    def percent_point(self, U, method='chandrupatla'):
+        """Compute the inverse cumulative distribution value for each point in U.
+
+        Arguments:
+            U (numpy.ndarray):
+                Values for which the cumulative distribution will be computed.
+                It must have shape (n, 1) and values must be in [0,1].
+            method (str):
+                Whether to use the `chandrupatla` or `bisect` solver.
+
+        Returns:
+            numpy.ndarray:
+                Inverse cumulative distribution values for points in U.
+
+        Raises:
+            NotFittedError:
+                if the model is not fitted.
+        """
+        self.check_fit()
+
+        if len(U.shape) > 1:
+            raise ValueError(f'Expected 1d array, got {(U, )}.')
+
+        if np.any(U > 1.0) or np.any(U < 0.0):
+            raise ValueError('Expected values in range [0.0, 1.0].')
+
+        is_one = U >= 1.0 - EPSILON
+        is_zero = U <= EPSILON
+        is_valid = ~(is_zero | is_one)
+
+        lower, upper = self._get_bounds()
+
+        def _f(X):
+            return self.cumulative_distribution(X) - U[is_valid]
+
+        X = np.zeros(U.shape)
+        X[is_one] = float('inf')
+        X[is_zero] = float('-inf')
+        if is_valid.any():
+            lower = np.full(U[is_valid].shape, lower)
+            upper = np.full(U[is_valid].shape, upper)
+            if method == 'bisect':
+                X[is_valid] = bisect(_f, lower, upper)
+            else:
+                X[is_valid] = chandrupatla(_f, lower, upper)
+
+        return X
+
+    def _fit_constant(self, X):
+        sample_size = self._sample_size or len(X)
+        constant = np.unique(X)[0]
+        self._params = {
+            'dataset': [constant] * sample_size,
+        }
+
+    def _fit(self, X):
+        if self._sample_size:
+            X = gaussian_kde(X, bw_method=self.bw_method,
+                             weights=self.weights).resample(self._sample_size)
+        self._params = {
+            'dataset': X.tolist()
+        }
+        self._model = self._get_model()
+
+    def _is_constant(self):
+        return len(np.unique(self._params['dataset'])) == 1
+
+    def _extract_constant(self):
+        return self._params['dataset'][0]
+
+    def _set_params(self, params):
+        """Set the parameters of this univariate.
+
+        Args:
+            params (dict):
+                Parameters to recreate this instance.
+        """
+        self._params = params.copy()
+        if self._is_constant():
+            constant = self._extract_constant()
+            self._set_constant_value(constant)
+        else:
+            self._model = self._get_model()

copulas/univariate/log_laplace.py

@@ -0,0 +1,38 @@
+"""LogLaplace module."""
+
+import numpy as np
+from scipy.stats import loglaplace
+
+from copulas.univariate.base import BoundedType, ParametricType, ScipyModel
+
+
+class LogLaplace(ScipyModel):
+    """Wrapper around scipy.stats.loglaplace.
+
+    Documentation: https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.loglaplace.html
+    """
+
+    PARAMETRIC = ParametricType.PARAMETRIC
+    BOUNDED = BoundedType.SEMI_BOUNDED
+    MODEL_CLASS = loglaplace
+
+    def _fit_constant(self, X):
+        self._params = {
+            'c': 2.0,
+            'loc': np.unique(X)[0],
+            'scale': 0.0,
+        }
+
+    def _fit(self, X):
+        c, loc, scale = loglaplace.fit(X)
+        self._params = {
+            'c': c,
+            'loc': loc,
+            'scale': scale,
+        }
+
+    def _is_constant(self):
+        return self._params['scale'] == 0
+
+    def _extract_constant(self):
+        return self._params['loc']

copulas/univariate/selection.py

@@ -0,0 +1,36 @@
+"""Univariate selection function."""
+
+import numpy as np
+from scipy.stats import kstest
+
+from copulas import get_instance
+
+
+def select_univariate(X, candidates):
+    """Select the best univariate class for this data.
+
+    Args:
+        X (pandas.DataFrame):
+            Data for which be best univariate must be found.
+        candidates (list[Univariate]):
+            List of Univariate subclasses (or instances of those) to choose from.
+
+    Returns:
+        Univariate:
+            Instance of the selected candidate.
+    """
+    best_ks = np.inf
+    best_model = None
+    for model in candidates:
+        try:
+            instance = get_instance(model)
+            instance.fit(X)
+            ks, _ = kstest(X, instance.cdf)
+            if ks < best_ks:
+                best_ks = ks
+                best_model = model
+        except Exception:
+            # Distribution not supported
+            pass
+
+    return get_instance(best_model)

copulas/univariate/student_t.py

@@ -0,0 +1,35 @@
+"""StudentTUnivariate module."""
+
+from scipy.stats import t
+
+from copulas.univariate.base import BoundedType, ParametricType, ScipyModel
+
+
+class StudentTUnivariate(ScipyModel):
+    """Wrapper around scipy.stats.t.
+
+    Documentation: https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.t.html
+    """
+
+    PARAMETRIC = ParametricType.PARAMETRIC
+    BOUNDED = BoundedType.UNBOUNDED
+
+    MODEL_CLASS = t
+
+    def _fit_constant(self, X):
+        self._fit(X)
+        self._params['scale'] = 0
+
+    def _fit(self, X):
+        dataframe, loc, scale = t.fit(X)
+        self._params = {
+            'df': dataframe,
+            'loc': loc,
+            'scale': scale
+        }
+
+    def _is_constant(self):
+        return self._params['scale'] == 0
+
+    def _extract_constant(self):
+        return self._params['loc']

copulas/univariate/truncated_gaussian.py

@@ -0,0 +1,74 @@
+"""TruncatedGaussian module."""
+
+import warnings
+
+import numpy as np
+from scipy.optimize import fmin_slsqp
+from scipy.stats import truncnorm
+
+from copulas import EPSILON, store_args, validate_random_state
+from copulas.univariate.base import BoundedType, ParametricType, ScipyModel
+
+
+class TruncatedGaussian(ScipyModel):
+    """Wrapper around scipy.stats.truncnorm.
+
+    Documentation: https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.truncnorm.html
+    """
+
+    PARAMETRIC = ParametricType.PARAMETRIC
+    BOUNDED = BoundedType.BOUNDED
+    MODEL_CLASS = truncnorm
+
+    @store_args
+    def __init__(self, minimum=None, maximum=None, random_state=None):
+        self.random_state = validate_random_state(random_state)
+        self.min = minimum
+        self.max = maximum
+
+    def _fit_constant(self, X):
+        constant = np.unique(X)[0]
+        self._params = {
+            'a': constant,
+            'b': constant,
+            'loc': constant,
+            'scale': 0.0
+        }
+
+    def _fit(self, X):
+        if self.min is None:
+            self.min = X.min() - EPSILON
+
+        if self.max is None:
+            self.max = X.max() + EPSILON
+
+        def nnlf(params):
+            loc, scale = params
+            a = (self.min - loc) / scale
+            b = (self.max - loc) / scale
+            return truncnorm.nnlf((a, b, loc, scale), X)
+
+        initial_params = X.mean(), X.std()
+        with warnings.catch_warnings():
+            warnings.simplefilter('ignore', category=RuntimeWarning)
+            optimal = fmin_slsqp(nnlf, initial_params, iprint=False, bounds=[
+                (self.min, self.max),
+                (0.0, (self.max - self.min)**2)
+            ])
+
+        loc, scale = optimal
+        a = (self.min - loc) / scale
+        b = (self.max - loc) / scale
+
+        self._params = {
+            'a': a,
+            'b': b,
+            'loc': loc,
+            'scale': scale
+        }
+
+    def _is_constant(self):
+        return self._params['a'] == self._params['b']
+
+    def _extract_constant(self):
+        return self._params['loc']

copulas/univariate/uniform.py

@@ -0,0 +1,33 @@
+"""UniformUnivariate module."""
+
+import numpy as np
+from scipy.stats import uniform
+
+from copulas.univariate.base import BoundedType, ParametricType, ScipyModel
+
+
+class UniformUnivariate(ScipyModel):
+    """Uniform univariate model."""
+
+    PARAMETRIC = ParametricType.PARAMETRIC
+    BOUNDED = BoundedType.BOUNDED
+
+    MODEL_CLASS = uniform
+
+    def _fit_constant(self, X):
+        self._params = {
+            'loc': np.min(X),
+            'scale': np.max(X) - np.min(X)
+        }
+
+    def _fit(self, X):
+        self._params = {
+            'loc': np.min(X),
+            'scale': np.max(X) - np.min(X)
+        }
+
+    def _is_constant(self):
+        return self._params['scale'] == 0
+
+    def _extract_constant(self):
+        return self._params['loc']