selection.py 文件源码

def calc_regression(self, label):
        """
        Calculate least squares regression for *label*. If *weighted* is ``True``, calculates weighted least squares; else ordinary least squares.

        Regression results are stored in ``'/main/label/scores'``

        """
        if self.check_store("/main/{}/scores".format(label)):
            return
        elif "/main/{}/scores".format(label) in self.store.keys():
            # need to remove the current keys because we are using append
            self.store.remove("/main/{}/scores".format(label))

        logging.info("Calculating {} regression coefficients ({})".format(self.scoring_method, label), extra={'oname' : self.name})
        # append is required because it takes the "min_itemsize" argument, and put doesn't
        longest = self.store.select("/main/{}/log_ratios".format(label), "columns='index'").index.map(len).max()
        chunk = 1
        if self.scoring_method == "WLS":
            for data in self.store.select_as_multiple(["/main/{}/log_ratios".format(label), "/main/{}/weights".format(label)], chunksize=self.chunksize):
                logging.info("Calculating weighted least squares for chunk {} ({} rows)".format(chunk, len(data.index)), extra={'oname' : self.name})
                result = data.apply(regression_apply, args=[self.timepoints, True], axis="columns")
                self.store.append("/main/{}/scores".format(label), result, min_itemsize={"index" : longest})
                chunk += 1
        elif self.scoring_method == "OLS":
            for data in self.store.select("/main/{}/log_ratios".format(label), chunksize=self.chunksize):
                logging.info("Calculating ordinary least squares for chunk {} ({} rows)".format(chunk, len(data.index)), extra={'oname' : self.name})
                result = data.apply(regression_apply, args=[self.timepoints, False], axis="columns")
                self.store.append("/main/{}/scores".format(label), result, min_itemsize={"index" : longest})
                chunk += 1
        else:
            raise ValueError('Invalid regression scoring method "{}" [{}]'.format(self.scoring_method, self.name))

        # need to read from the file, calculate percentiles, and rewrite it
        logging.info("Calculating slope standard error percentiles ({})".format(label), extra={'oname' : self.name})
        data = self.store['/main/{}/scores'.format(label)]
        data['score'] = data['slope']
        data['SE'] = data['SE_slope']
        data['SE_pctile'] = [stats.percentileofscore(data['SE'], x, "weak") for x in data['SE']]
        data = data[['score', 'SE', 'SE_pctile', 'slope', 'intercept', 'SE_slope', 't', 'pvalue_raw']] # reorder columns
        self.store.put("/main/{}/scores".format(label), data, format="table", data_columns=data.columns)