10 Python CSV Processing Scripts for System Administration Tasks | https://linuxtech.in/10-python-csv-processing-scripts-for-system-administration-tasks

01-read-csv-file-and-print-each-row.py

import csv

with open('file.csv', 'r') as csvfile:
    csvreader = csv.reader(csvfile)
    for row in csvreader:
        print(row)

02-write-data-to-a-csv-file.py

import csv

data = [['Name', 'Age', 'City'], ['John', '25', 'New York'], ['Jane', '30', 'Los Angeles']]

with open('file.csv', 'w', newline='') as csvfile:
    csvwriter = csv.writer(csvfile)
    csvwriter.writerows(data)

03-count-number-of-rows-in-a-csv-file.py

import csv

with open('file.csv', 'r') as csvfile:
    csvreader = csv.reader(csvfile)
    row_count = sum(1 for row in csvreader)
    print(row_count)

04-filter-data-in-a-csv-file.py

import csv

with open('file.csv', 'r') as csvfile:
    csvreader = csv.reader(csvfile)
    for row in csvreader:
        if row[2].strip() == 'New York':
            print(row)

05-sort-data-in-a-csv-file.py

import csv

with open('sort.csv', 'r') as csvfile:
    csvreader = csv.reader(csvfile)
    next(csvreader)
    sorted_csv = sorted(csvreader, key=lambda row: row[1])
    for row in sorted_csv:
        print(row)

06-extract-specific-columns-from-a-csv-file.py

import csv

input_file = 'file.csv'

columns_to_extract = ['Age', 'Name'] # Replace with the header names of the columns you want to extract

with open(input_file, 'r') as csv_file:
    reader = csv.DictReader(csv_file)

    headers = reader.fieldnames
    headers_to_print = [header for header in headers if header in columns_to_extract]
    print(','.join(headers_to_print))

    for row in reader:
        row_to_print = [row[column] for column in columns_to_extract]
        print(','.join(row_to_print))

07-replace-values-in-a-csv-file.py

import csv

with open('file.csv', 'r') as csvfile:
    csvreader = csv.reader(csvfile)
    data = []
    for row in csvreader:
        if row[2] == 'New York':
            row[2] = 'NY'
        data.append(row)
    with open('updated_file.csv', 'w', newline='') as outfile:
        csvwriter = csv.writer(outfile)
        csvwriter.writerows(data)

08-calculate-average-of-a-column-in-a-csv-file.py

import csv

with open('file.csv', 'r') as csvfile:
    csvreader = csv.reader(csvfile)
    next(csvreader)
    total = 0
    count = 0
    for row in csvreader:
        total += int(row[1])
        count += 1
    average = total / count
    print(average)

09-remove-duplicates-from-a-csv-file.py

import csv

with open('file.csv', 'r') as csvfile:
    csvreader = csv.reader(csvfile)
    data = []
    seen = set()
    for row in csvreader:
        if row[2] not in seen:
            data.append(row)
            seen.add(row[2])

with open('unique_file.csv', 'w', newline='') as outfile:
    csvwriter = csv.writer(outfile)
    csvwriter.writerows(data)

10-sort-a-csv-file-based-on-a-column.py

import csv

with open('sortcl.csv', 'r') as csvfile:
    csvreader = csv.reader(csvfile)
    header = next(csvreader)
    index = header.index('Age')
    sorted_data = sorted(csvreader, key=lambda row: row[index])
    print(header)
    for row in sorted_data:
        print(row)

file.csv

sort.csv

sortcl.csv

uniq.csv