Python CSV Processing Examples

import csv
from pathlib import Path
import pandas as pd

# Read CSV with the csv module
with open("input.csv", newline="", encoding="utf-8") as f:
    reader = csv.DictReader(f)
    rows = [row for row in reader]

print(f"Read {len(rows)} rows, columns: {rows[0].keys() if rows else 'none'}")

# Write CSV with headers
output_rows = [
    {"id": 1, "name": "Alice", "amount": 100.50},
    {"id": 2, "name": "Bob", "amount": 200.75},
]

with open("output.csv", "w", newline="", encoding="utf-8") as f:
    writer = csv.DictWriter(f, fieldnames=["id", "name", "amount"])
    writer.writeheader()
    writer.writerows(output_rows)

# Pandas: read with options
df = pd.read_csv(
    "input.csv",
    encoding="utf-8",
    dtype={"id": str, "amount": float},
    parse_dates=["date"],
    na_values=["", "N/A", "null"],
    usecols=["id", "name", "amount", "date"],
)

# Pandas: write with options
df.to_csv("clean_output.csv", index=False, encoding="utf-8", float_format="%.2f")

# Process large CSV in chunks
for chunk in pd.read_csv("large_file.csv", chunksize=10_000):
    processed = chunk[chunk["status"] == "active"]
    processed.to_csv(
        "filtered.csv", mode="a", header=not Path("filtered.csv").exists(), index=False
    )