tableone.py 文件源码

def _p_test(self,v,grouped_data,is_continuous,is_categorical,
            is_normal,min_observed,catlevels,
            pval=np.nan,ptest='Not tested'):
        """
        Compute p value
        """

        # do not test if any sub-group has no observations
        if min_observed == 0:
            warnings.warn('No p-value was computed for {} due to the low number of observations.'.format(v))
            return pval,ptest

        # continuous
        if is_continuous and is_normal:
            # normally distributed
            ptest = 'One-way ANOVA'
            test_stat, pval = stats.f_oneway(*grouped_data)
        elif is_continuous and not is_normal:
            # non-normally distributed
            ptest = 'Kruskal-Wallis'
            test_stat, pval = stats.kruskal(*grouped_data)
        # categorical
        elif is_categorical:
            # default to chi-squared
            ptest = 'Chi-squared'
            chi2, pval, dof, expected = stats.chi2_contingency(grouped_data)
            # if any expected cell counts are < 5, chi2 may not be valid
            # if this is a 2x2, switch to fisher exact
            if expected.min() < 5:
                if grouped_data.shape == (2,2):
                    ptest = 'Fisher''s exact'
                    oddsratio, pval = stats.fisher_exact(grouped_data)
                else:
                    ptest = 'Chi-squared (warning: expected count < 5)'
                    warnings.warn('No p-value was computed for {} due to the low number of observations.'.format(v))

        return pval,ptest