value_counter.py 文件源码

def process_columns(self, df):
        """Process columns before histogram filling

        Specifically, convert timestamp columns to integers
        and numeric variables are converted to indices

        :param df: input (pandas) data frame
        :returns: output (pandas) data frame with converted timestamp columns
        :rtype: pandas DataFrame
        """

        # timestamp variables are converted to ns here
        # make temp df for value counting (used below)

        idf = df[self.str_cols].copy(deep=False)
        for col in self.dt_cols:
            self.log().debug('Converting column "%s" of type "%s" to nanosec', col, self.var_dtype[col])
            idf[col] = df[col].apply(hf.to_ns)

        # numerical variables are converted to indices here
        for col in self.num_cols + self.dt_cols:
            self.log().debug('Converting column "%s" of type "%s" to index', col, self.var_dtype[col])
            # find column specific bin_specs. if not found, use dict of default
            # values.
            dt = df[col].dtype
            is_number = isinstance(dt.type(), np.number)
            is_timestamp = isinstance(dt.type(), np.datetime64)
            sf = idf if is_timestamp else df
            bin_specs = self.bin_specs.get(col, self._unit_bin_specs if is_number else self._unit_timestamp_specs)
            idf[col] = sf[col].apply(hf.value_to_bin_index, **bin_specs)

        return idf