将一个csv拆分为python中的多个文件

Question

我在python中有一个大约5000行的csv文件我想将它分成五个文件.

我为它写了一个代码,但它没有用

import codecs
import csv
NO_OF_LINES_PER_FILE = 1000
def again(count_file_header,count):
    f3 = open('write_'+count_file_header+'.csv', 'at')
    with open('import_1458922827.csv', 'rb') as csvfile:
        candidate_info_reader = csv.reader(csvfile, delimiter=',', quoting=csv.QUOTE_ALL)
        co = 0      
        for row in candidate_info_reader:
            co = co + 1
            count  = count + 1
            if count <= count:
                pass
            elif count >= NO_OF_LINES_PER_FILE:
                count_file_header = count + NO_OF_LINES_PER_FILE
                again(count_file_header,count)
            else:
                writer = csv.writer(f3,delimiter = ',', lineterminator='\n',quoting=csv.QUOTE_ALL)
                writer.writerow(row)

def read_write():
    f3 = open('write_'+NO_OF_LINES_PER_FILE+'.csv', 'at')
    with open('import_1458922827.csv', 'rb') as csvfile:


        candidate_info_reader = csv.reader(csvfile, delimiter=',', quoting=csv.QUOTE_ALL)

        count = 0       
        for row in candidate_info_reader:
            count  = count + 1
            if count >= NO_OF_LINES_PER_FILE:
                count_file_header = count + NO_OF_LINES_PER_FILE
                again(count_file_header,count)
            else:
                writer = csv.writer(f3,delimiter = ',', lineterminator='\n',quoting=csv.QUOTE_ALL)
                writer.writerow(row)

read_write()

上面的代码创建了许多空内容的文件.

如何将一个文件拆分为五个csv文件？

Answer 1

在Python中

使用readlines()和writelines()执行此操作,这是一个示例:

>>> csvfile = open('import_1458922827.csv', 'r').readlines()
>>> filename = 1
>>> for i in range(len(csvfile)):
...     if i % 1000 == 0:
...         open(str(filename) + '.csv', 'w+').writelines(csvfile[i:i+1000])
...         filename += 1

输出文件名称将被编号1.csv,2.csv,...等等.

从终端

仅供参考,您可以使用split以下命令从命令行执行此操作:

$ split -l 1000 import_1458922827.csv

Answer 2

我建议你不要发明一个轮子.有现成的解决方案.来源于此

import os


def split(filehandler, delimiter=',', row_limit=1000,
          output_name_template='output_%s.csv', output_path='.', keep_headers=True):
    import csv
    reader = csv.reader(filehandler, delimiter=delimiter)
    current_piece = 1
    current_out_path = os.path.join(
        output_path,
        output_name_template % current_piece
    )
    current_out_writer = csv.writer(open(current_out_path, 'w'), delimiter=delimiter)
    current_limit = row_limit
    if keep_headers:
        headers = reader.next()
        current_out_writer.writerow(headers)
    for i, row in enumerate(reader):
        if i + 1 > current_limit:
            current_piece += 1
            current_limit = row_limit * current_piece
            current_out_path = os.path.join(
                output_path,
                output_name_template % current_piece
            )
            current_out_writer = csv.writer(open(current_out_path, 'w'), delimiter=delimiter)
            if keep_headers:
                current_out_writer.writerow(headers)
        current_out_writer.writerow(row)

使用它像:

split(open('/your/pat/input.csv', 'r'));

Answer 3

一个带有 Pandas 的简单 Python 3 解决方案，不会切断最后一批

def to_csv_batch(src_csv, dst_dir, size=30000, index=False):

    import pandas as pd
    import math
    
    # Read source csv
    df = pd.read_csv(src_csv)
    
    # Initial values
    low = 0
    high = size

    # Loop through batches
    for i in range(math.ceil(len(df) / size)):

        fname = dst_dir+'/Batch_' + str(i+1) + '.csv'
        df[low:high].to_csv(fname, index=index)
        
        # Update selection
        low = high
        if (high + size < len(df)):
            high = high + size
        else:
            high = len(df)

使用示例

to_csv_batch('Batch_All.csv', 'Batches')

Answer 4

一个python3友好的解决方案：

def split_csv(source_filepath, dest_folder, split_file_prefix,
                records_per_file):
    """
    Split a source csv into multiple csvs of equal numbers of records,
    except the last file.

    Includes the initial header row in each split file.

    Split files follow a zero-index sequential naming convention like so:

        `{split_file_prefix}_0.csv`
    """
    if records_per_file <= 0:
        raise Exception('records_per_file must be > 0')

    with open(source_filepath, 'r') as source:
        reader = csv.reader(source)
        headers = next(reader)

        file_idx = 0
        records_exist = True

        while records_exist:

            i = 0
            target_filename = f'{split_file_prefix}_{file_idx}.csv'
            target_filepath = os.path.join(dest_folder, target_filename)

            with open(target_filepath, 'w') as target:
                writer = csv.writer(target)

                while i < records_per_file:
                    if i == 0:
                        writer.writerow(headers)

                    try:
                        writer.writerow(next(reader))
                        i += 1
                    except StopIteration:
                        records_exist = False
                        break

            if i == 0:
                # we only wrote the header, so delete that file
                os.remove(target_filepath)

            file_idx += 1

Answer 5

我稍微修改了接受的答案以使其更简单

编辑：添加了导入语句，修改了打印异常的打印语句。header_row = rows.__next__()@Alex F 代码片段是为 python2 编写的，对于 python3，您还需要使用header_row = rows.next(). 谢谢你指出。

import os
import csv
def split_csv_into_chunks(file_location, out_dir, file_size=2):
    count = 0
    current_piece = 1

    # file_to_split_name.csv
    file_name = file_location.split("/")[-1].split(".")[0]
    split_file_name_template = file_name + "__%s.csv"
    splited_files_path = []

    if not os.path.exists(out_dir):
        os.makedirs(out_dir)
    try:
        with open(file_location, "rb") as csv_file:
            rows = csv.reader(csv_file, delimiter=",")
            headers_row = rows.next()
            for row in rows:
                if count % file_size == 0:
                    current_out_path = os.path.join(out_dir,
                                                    split_file_name_template%str(current_piece))
                    current_out_writer = None

                    current_out_writer = csv.writer(open(current_out_path, 'w'), delimiter=",")
                    current_out_writer.writerow(headers_row)
                    splited_files_path.append(current_out_path)
                    current_piece += 1

                current_out_writer.writerow(row)
                count += 1
        return True, splited_files_path
    except Exception as e:
        print("Exception occurred as {}".format(e))
        return False, splited_files_path