tableone.py 文件源码

def _create_significance_table(self,data):
        """
        Create a table containing p values for significance tests. Add features of
        the distributions and the p values to the dataframe.
        """

        # list features of the variable e.g. matched, paired, n_expected
        df=pd.DataFrame(index=self.continuous+self.categorical,
            columns=['continuous','nonnormal','min_observed','pval','ptest'])

        df.index.rename('variable', inplace=True)
        df['continuous'] = np.where(df.index.isin(self.continuous),True,False)
        df['nonnormal'] = np.where(df.index.isin(self.nonnormal),True,False)

        # list values for each variable, grouped by groupby levels
        for v in df.index:

            # compute p value
            is_continuous = df.loc[v]['continuous']
            is_categorical = ~df.loc[v]['continuous']
            is_normal = ~df.loc[v]['nonnormal']

            # if continuous, group data into list of lists
            if is_continuous:
                catlevels = None
                grouped_data = []
                for s in self.groupbylvls:
                    lvl_data = data[data[self.groupby]==s].dropna(subset=[v])[v]
                    grouped_data.append(lvl_data.values)
                min_observed = len(min(grouped_data,key=len))
            # if categorical, create contingency table
            elif is_categorical:
                catlevels = sorted(data[v].astype('category').cat.categories)
                grouped_data = pd.crosstab(data[self.groupby],data[v])
                min_observed = grouped_data.sum(axis=1).min()

            # minimum number of observations across all levels
            df.loc[v,'min_observed'] = min_observed

            # compute pvalues
            df.loc[v,'pval'],df.loc[v,'ptest'] = self._p_test(v, 
                grouped_data,is_continuous,is_categorical,
                is_normal,min_observed,catlevels)

        return df