data_utils

Functions for heliping to build the datasets

QQuantLib.qml4var.data_utils.bs_cdf(s_t: float, s_0: float = 1.0, risk_free_rate: float = 0.0, volatility: float = 0.5, maturity: float = 0.5, **kwargs)

Black Scholes PDF

QQuantLib.qml4var.data_utils.bs_pdf(s_t: float, s_0: float = 1.0, risk_free_rate: float = 0.0, volatility: float = 0.5, maturity: float = 0.5, **kwargs)

Black Scholes PDF

QQuantLib.qml4var.data_utils.bs_samples(number_samples: int, s_0: float = 1.0, risk_free_rate: float = 0.0, volatility: float = 0.5, maturity: float = 0.5, **kwargs)

Black Scholes Samples

QQuantLib.qml4var.data_utils.empirical_cdf(data_points)

Given an array of data points create the corresponding empirical distribution function :param data_points: numpy array with data sampled :type data_points: numpy array

Returns:

emp_cdf – numpy array with the empirical cdf of the input data

Return type:

numpy array

QQuantLib.qml4var.data_utils.empirical_distribution_function_old(data_points: numpy.array)

Given an array of data points create the corresponding empirical distribution dunction :param data_points: numpy array with data sampled :type data_points: numpy array

Returns:

batch_ – QLM Batch with the jobs for computing graidents

Return type:

QLM Batch

QQuantLib.qml4var.data_utils.saving_datasets(x_train, y_train, x_test, y_test, **kwargs)

Saving Data sets