cenreg.distribution package

Submodules

cenreg.distribution.cdf module

class cenreg.distribution.cdf.CumulativeDist(b: ndarray, p: ndarray | None = None, cum_p: ndarray | None = None, interpolate: Literal['linear', 'left', 'right'] = 'linear', confidence_interval: ndarray | None = None)

Bases: object

Cumulative distribution function.

cdf(y: float | ndarray) → ndarray

Cumulative distribution function (i.e., inverse of quantile function).

Parameters:: y (np.ndarray | float) – Values for which the CDF is computed. y can be a scalar or a one-dimensional array or a two-dimensional array.
Returns:: cum_p – CDF values for each value in y.
Return type:: np.ndarray

icdf(quantiles: float | ndarray) → ndarray

Inverse cumulative distribution function (i.e., quantile function).

If the input is 0.0, return self.b[0]. If the input is 1.0, return self.b[-1]. If the input is between 0.0 and 1.0, return the corresponding bin value.

Note: For any alpha in [0.0, 1.0], we usually assume that self.cdf(self.icdf(alpha)) == alpha holds. However, the inverse CDF of empirical distribution defined here does not always satisfy this property.

Parameters:: quantiles (float | np.ndarray) – Quantiles for which the inverse CDF is computed.
Returns:: icdf_values – Compute inverse CDF values for each value in quantiles.
Return type:: np.ndarray

survival_function(y: float | ndarray) → ndarray

Survival function (i.e., 1 - CDF).

Parameters:: y (np.ndarray | float) – Values for which the survival function is computed.
Returns:: survival_values – Survival function values for each value in y. Array shape is equal to the shape of y.
Return type:: np.ndarray

cenreg.distribution.interpolate module

cenreg.distribution.interpolate.linear_interpolation(kx: ndarray, ky: ndarray, x: ndarray) → ndarray

Linear interpolation.

Parameters:

kx (np.ndarray) – One-dimensional or two-dimensional array containing the x-coordinates of the data points.
ky (np.ndarray) – One-dimensional or two-dimensional array containing the y-coordinates of the data points.
x (np.ndarray) – One-dimensional or two-dimensional array containing the x-coordinates where to evaluate the interpolated values.

Returns:

ret – One-dimensional or two-dimensional array containing the interpolated values.

Return type:

np.ndarray

cenreg.distribution.quantile module

class cenreg.distribution.quantile.QuantileDist(q: ndarray, v: ndarray, interpolate: str = 'linear')

Bases: object

Quantile function.

cdf(y: float | int | ndarray)