如何在没有 Pandas 的情况下读取、格式化、排序和保存 csv 文件

Question

• 给定文件中的以下示例数据 test.csv

27-Mar-12,8.25,8.35,8.17,8.19,9801989
26-Mar-12,8.16,8.25,8.12,8.24,8694416
23-Mar-12,8.05,8.12,7.95,8.09,8149170

• 如何在不使用的情况下解析此文件pandas？
  1. 打开文件
  2. 将日期列datetime格式化为日期格式的字符串
  3. 按第 0 列（日期列）对所有行进行排序
  4. 保存回同一个文件，带有日期列的标题
• 与pandas这可以用一个单一的代码（长）线，不包括进口来完成。
  • 需要注意的parse_date是，如果date_parser不使用，使用会很慢。

import pandas as pd

(pd.read_csv('test.csv', header=None, parse_dates=[0], date_parser=lambda t: pd.to_datetime(t, format='%d-%b-%y'))
 .rename(columns={0: 'date'})
 .sort_values('date')
 .to_csv('test.csv', index=False))

预期形式

date,1,2,3,4,5
2012-03-23,8.05,8.12,7.95,8.09,8149170
2012-03-26,8.16,8.25,8.12,8.24,8694416
2012-03-27,8.25,8.35,8.17,8.19,9801989

• 编写此问题和答案是为了填补 Stack Overflow 上的知识内容空白。
• pandas用于此任务非常容易。
• 如果没有pandas.
• 这对于任何对此任务感到好奇的人以及禁止使用pandas.
• 我不介意看到一个带有 的解决方案numpy，但问题的主要观点是仅使用标准库中的包来完成此任务。

这三个答案都是可以接受的问题解决方案。

Answer 1

• pandas更容易解析和清理文件。
  • 需要 1 行pandas，需要 11 行代码，并且需要一个for-loop.
• 这需要以下包和函数
  • csv&datetime
  • 文件对象的方法：.seek&.truncate
  • 排序：如何
• 最初，list()用于解压csv.reader对象，但已被删除，以更新日期值，同时迭代reader.
• 可以提供自定义键函数来自sorted定义排序顺序，但我没有看到从表达式返回值的方法lambda。
  • 最初key=lambda row: datetime.strptime(row[0], '%Y-%m-%d')使用过，但已被删除，因为更新的日期列不包含月份名称。
  • 如果日期列包含月份名称，如果没有自定义排序键，则无法正确排序。

import csv
from datetime import datetime

# open the file for reading and writing
with open('test1.csv', mode='r+', newline='') as f:

   # create a reader and writer opbject
    reader, writer = csv.reader(f), csv.writer(f)
    
    data = list()
    # iterate through the reader and update column 0 to a datetime date string
    for row in reader:

        # update column 0 to a datetime date string
        row[0] = datetime.strptime(row[0], "%d-%b-%y").date().isoformat()
        
        # append the row to data
        data.append(row)

    # sort all of the rows, based on date, with a lambda expression
    data = sorted(data, key=lambda row: row[0])

    # change the stream position to the given byte offset
    f.seek(0)

    # truncate the file size
    f.truncate()

    # add a header to data
    data.insert(0, ['date', 1, 2, 3, 4, 5])

    # write data to the file
    writer.writerows(data)

更新test.csv

date,1,2,3,4,5
2012-03-23,8.05,8.12,7.95,8.09,8149170
2012-03-26,8.16,8.25,8.12,8.24,8694416
2012-03-27,8.25,8.35,8.17,8.19,9801989

%time测试

import pandas
import pandas_datareader as web

# test data with 1M rows
df = web.DataReader(ticker, data_source='yahoo', start='1980-01-01', end='2020-09-27').drop(columns=['Adj Close']).reset_index().sort_values('High', ascending=False)
df.Date = df.Date.dt.strftime('%d-%b-%y')
df = pd.concat([df]*100)
df.to_csv('test.csv', index=False, header=False)

测试

# pandas test with date_parser
%time pandas_test('test.csv')
[out]:
Wall time: 17.9 s

# pandas test without the date_parser parameter
%time pandas_test('test.csv')
[out]:
Wall time: 1min 17s

# from Paddy Alton
%time paddy('test.csv')
[out]:
Wall time: 15.9 s

# from Trenton
%time trenton('test.csv')
[out]:
Wall time: 17.7 s

# from sammywemmy with functions updated to return the correct date format
%time sammy('test.csv')
[out]:
Wall time: 22.2 s
%time sammy2('test.csv')
[out]:
Wall time: 22.2 s

测试功能

from operator import itemgetter
import csv
import pandas as pd
from datetime import datetime

def pandas_test(file):
    (pd.read_csv(file, header=None, parse_dates=[0], date_parser=lambda t: pd.to_datetime(t, format='%d-%b-%y'))
     .rename(columns={0: 'date'})
     .sort_values('date')
     .to_csv(file, index=False))


def trenton(file):
    with open(file, mode='r+', newline='') as f:
        reader, writer = csv.reader(f), csv.writer(f)
        data = list()
        for row in reader:
            row[0] = datetime.strptime(row[0], "%d-%b-%y").date().isoformat()
            data.append(row)
        data = sorted(data, key=lambda row: row[0])
        f.seek(0)
        f.truncate()
        data.insert(0, ['date', 1, 2, 3, 4, 5])
        writer.writerows(data)


def paddy(file):
    def format_date(date: str) -> str:
        formatted_date = datetime.strptime(date, "%d-%b-%y").date().isoformat()
        return formatted_date


    with open(file, "r") as f:
        lines = f.readlines()
        records = [[value for value in line.split(",")] for line in lines]
    for record in records:
        record[0] = format_date(record[0])
    sorted_records = sorted(records, key = lambda r: r[0])
    prepared_lines = [",".join(record).strip("\n") for record in sorted_records]
    field_names = "date,1,2,3,4,5"
    prepared_lines.insert(0, field_names)
    prepared_data = "\n".join(prepared_lines)
    with open(file, "w") as f:
        f.write(prepared_data)


def sammy(file):
    # updated with .date().isoformat() to return the correct format
    with open(file) as csvfile:
        fieldnames = ["date", 1, 2, 3, 4, 5]
        reader = csv.DictReader(csvfile, fieldnames=fieldnames)
        mapping = list(reader)
        mapping = [
            {
                key: datetime.strptime(value, ("%d-%b-%y")).date().isoformat()
                     if key == "date" else value
                for key, value in entry.items()
            }
            for entry in mapping
        ]

        mapping = sorted(mapping, key=itemgetter("date"))

    with open(file, mode="w", newline="") as csvfile:
        fieldnames = mapping[0].keys()
        writer = csv.DictWriter(csvfile, fieldnames=fieldnames)

        writer.writeheader()
        for row in mapping:
            writer.writerow(row)


def sammy2(file):
    # updated with .date().isoformat() to return the correct format
    with open(file) as csvfile:
        reader = csv.reader(csvfile, delimiter=",")
        mapping = dict(enumerate(reader))
        num_of_cols = len(mapping[0])
        fieldnames = ["date" if n == 0 else n
                      for n in range(num_of_cols)]
        mapping = [
                   [ datetime.strptime(val, "%d-%b-%y").date().isoformat()
                     if ind == 0 else val
                     for ind, val in enumerate(value)
                   ]
                 for key, value in mapping.items()
                  ]

        mapping = sorted(mapping, key=itemgetter(0))

    with open(file, mode="w", newline="") as csvfile:
        csvwriter = csv.writer(csvfile, delimiter=",")
        csvwriter.writerow(fieldnames)
        for row in mapping:
            csvwriter.writerow(row)