Learn Python Programming

Python CSV Overview

CSV (Comma-Separated Values) is a simple format for storing tabular data. Python's built-in csv module makes reading and writing CSV files easy and reliable.

What Is CSV?

# CSV is plain text with values separated by commas (or other delimiters)
# Example CSV file (data.csv):
# name,age,city
# Alice,30,New York
# Bob,25,London
# Charlie,35,Tokyo

# Each line is a row, commas separate columns
# First row is usually the header

Reading CSV Files

import csv

# Basic reading with csv.reader (returns lists)
with open("data.csv", "r") as f:
    reader = csv.reader(f)
    header = next(reader)  # first row is header
    print(header)  # ["name", "age", "city"]

    for row in reader:
        name, age, city = row
        print(f"{name} is {age} years old from {city}")

# Reading as dictionaries (more readable)
with open("data.csv", "r") as f:
    reader = csv.DictReader(f)
    for row in reader:
        # Each row is an OrderedDict with header keys
        print(f"{row[\"name\"]} - {row[\"city\"]}")

# Reading with different delimiter
with open("data.tsv", "r") as f:
    reader = csv.reader(f, delimiter="\t")  # tab-separated
    for row in reader:
        print(row)

Writing CSV Files

import csv

# Writing with csv.writer (from lists)
data = [
    ["name", "age", "city"],
    ["Alice", 30, "New York"],
    ["Bob", 25, "London"],
    ["Charlie", 35, "Tokyo"],
]

with open("output.csv", "w", newline="") as f:
    writer = csv.writer(f)
    writer.writerow(data[0])   # write header
    writer.writerows(data[1:]) # write all data rows

# Writing with DictWriter (from dictionaries)
users = [
    {"name": "Alice", "age": 30, "city": "New York"},
    {"name": "Bob", "age": 25, "city": "London"},
]

with open("users.csv", "w", newline="") as f:
    fieldnames = ["name", "age", "city"]
    writer = csv.DictWriter(f, fieldnames=fieldnames)
    writer.writeheader()  # writes the header row
    writer.writerows(users)

# IMPORTANT: always use newline="" on Windows to prevent blank rows

Handling Edge Cases

import csv

# Values with commas, quotes, or newlines are auto-quoted
data = [
    ["name", "address", "note"],
    ["Alice", "123 Main St, Apt 4", "She said \"hello\""],
    ["Bob", "456 Oak Ave", "Line 1\nLine 2"],
]

with open("special.csv", "w", newline="") as f:
    writer = csv.writer(f, quoting=csv.QUOTE_MINIMAL)
    writer.writerows(data)

# Reading with different encodings
with open("data.csv", "r", encoding="utf-8-sig") as f:  # handles BOM
    reader = csv.reader(f)
    for row in reader:
        print(row)

# Skip empty rows
with open("data.csv") as f:
    reader = csv.reader(f)
    for row in reader:
        if not row or all(cell.strip() == "" for cell in row):
            continue
        print(row)

Practical Example: Data Processing

import csv

# Filter and transform CSV data
def filter_csv(input_file, output_file, min_age=25):
    """Read a CSV, filter by age, and write results."""
    with open(input_file) as fin, open(output_file, "w", newline="") as fout:
        reader = csv.DictReader(fin)
        writer = csv.DictWriter(fout, fieldnames=reader.fieldnames)
        writer.writeheader()

        count = 0
        for row in reader:
            if int(row["age"]) >= min_age:
                writer.writerow(row)
                count += 1

    print(f"Wrote {count} rows to {output_file}")

filter_csv("people.csv", "adults.csv", min_age=18)

# Convert CSV to list of dicts (load all into memory)
def load_csv(filename):
    with open(filename) as f:
        return list(csv.DictReader(f))

people = load_csv("people.csv")
print(f"Loaded {len(people)} records")
print(people[0])  # {"name": "Alice", "age": "30", "city": "New York"}

• Use csv.DictReader / csv.DictWriter for readable, header-based access.
• Always pass newline="" when opening files for writing on Windows.
• The csv module handles quoting, escaping commas, and newlines inside values automatically.
• For large CSV files, process row-by-row instead of loading everything into memory.
• For complex data analysis, consider pandas.read_csv() which is faster and more powerful.