liquidcarbon

from functools import reduce
import numpy as np
import pandas as pd

class Counts:
    """COUNT ... GROUP BY on every column of a large dataset"""

    def __init__(self, file, ddl_file, n_cols=None, n_top=10):
        self.file = file
        self.columns = get_columns_from_ddl(ddl_file)

liquidcarbon

import sys

def fix(file, sep, nf, output):
    """Checks and fixes prematurely terminated lines in a tabular file.

        :param file: input file
        :param sep: delimiter or its ASCII **octal** code
        :param nf: expected number of fields
        :param output: output file
        :return: None