summaryselections.py 文件源码

def __init__(self, model, statistics_calc, backend, n_samples = 1000, seed = None):
        self.model = model
        self.statistics_calc = statistics_calc
        self.backend = backend
        self.rng = np.random.RandomState(seed)
        self.model.prior.reseed(self.rng.randint(np.iinfo(np.uint32).max, dtype=np.uint32)) 

        # main algorithm                 
        seed_arr = self.rng.randint(1, n_samples*n_samples, size=n_samples, dtype=np.int32)
        seed_pds = self.backend.parallelize(seed_arr)     

        sample_parameters_statistics_pds = self.backend.map(self._sample_parameter_statistics, seed_pds)
        sample_parameters_and_statistics = self.backend.collect(sample_parameters_statistics_pds)
        sample_parameters, sample_statistics = [list(t) for t in zip(*sample_parameters_and_statistics)]
        sample_parameters = np.array(sample_parameters)
        sample_statistics = np.concatenate(sample_statistics)

        self.coefficients_learnt = np.zeros(shape=(sample_parameters.shape[1],sample_statistics.shape[1]))
        regr = linear_model.LinearRegression(fit_intercept=True)
        for ind in range(sample_parameters.shape[1]):
            regr.fit(sample_statistics, sample_parameters[:,ind]) 
            self.coefficients_learnt[ind,:] = regr.coef_