Question

我是python的新手，这是我上网的示例代码我有两个大数据CSV文件，一个来自数据库，另一个来自公司元数据。我想比较两个表中的特定列并生成一个新的csv文件，该文件向我显示元数据中缺少记录的位置。请记住，两个csv文件的列数不同，我想分析两个csv文件中的特定列。

这是两个csv文件：

从excel表中复制的csv1

start_time  end_time    aitechid    hh_village  grpdetails1/farmername  grpdetails1/farmermobile 2016-11-26T14:01:47.329+03 2016-11-26T14:29:05.042+03  AI00001 2447    KahsuGebru  919115604 2016-11-26T19:34:42.159+03    2016-11-26T20:39:27.430+03  936891238   2473    Moto Aleka  914370833 2016-11-26T12:13:23.094+03    2016-11-26T14:25:19.178+03  914127382   2390    Hagos   914039654 2016-11-30T14:31:28.223+03    2016-11-30T14:56:33.144+03  920784222   384 Mohammed Ali    923456788 2016-11-30T14:22:38.631+03    2016-11-30T15:06:44.199+03  912320358   378 Habtamu Nuru    913856087 2016-11-29T03:41:36.532+03    2016-11-29T16:33:12.632+03  914763134   2301    Are gaining Giday   0 2016-11-29T16:21:05.012+03    2016-11-29T16:37:27.934+03  914763134   2290    G   912345678 2016-11-30T17:23:34.145+03    2016-11-30T18:00:32.142+03  914763134   2291    Haile tesfu 0 2016-11-30T20:37:54.657+03    2016-11-30T20:56:16.472+03  914763134   2300    Negative Abay   933082495 2016-11-30T21:00:22.063+03    2016-11-30T21:18:44.478+03  914763134   2291    Niguel Amare    914270455

从excel表中复制的csv2

farmermobile 941807851 946741296 9 920212218 915 939555303 961579437 919961811 100004123 972635273 918166831 961579437

我已经尝试过这段代码，但我没有得到预期的输出：

import csv


def get_key(row):
    return row["!Sample_title"], row["!Sample_geo_accession"]


def load_csv(filename):
    """Put csv data into a dict that maps title/geo to the complete row.
    """
    d = {}
    with open(filename) as f:
        for row in csv.DictReader(f, delimiter=","):
            key = get_key(row)
            assert key not in d
            d[key] = row
    return d


def diffs(old, new):
    yield from added_or_removed("ADDED", new.keys() - old.keys(), new)
    yield from added_or_removed("REMOVED", old.keys() - new.keys(), old)
    yield from changed(old, new)


def compare_row(key, old, new):
    i = -1
    for i, line in enumerate(diffs(old, new)):
        if not i:
            print("/".join(key))
        print("    " + line)
    if i >= 0:
        print()


def added_or_removed(state, keys, d):
    items = sorted((key, d[key]) for key in keys)
    for key, value in items:
        yield "{:10}: {:30} | {:30}".format(state, key, value)


def changed(old, new):
    common_columns = old.keys() & new.keys()
    for column in sorted(common_columns):
        oldvalue = old[column]
        newvalue = new[column]
        if oldvalue != newvalue:
            yield "{:10}: {:30} | {:30} | {:30}".format(
                "CHANGED",
                column,
                oldvalue.ljust(30),
                newvalue.ljust(30))


if __name__ == "__main__":
    oldcsv = load_csv("/media/dmogaka/DATA/week4/combine201709.csv")
    newcsv = load_csv("/media/dmogaka/DATA/week4/combinedmissingrecords.csv")
    # title/geo pairs that occur in both files:
    common = oldcsv.keys() & newcsv.keys()
    for key in sorted(common):
        compare_row(key, oldcsv[key], newcsv[key])

从两个具有不同列数的表中连接数据

0 个答案: