CSV Files Without pandas
Python's built-in csv module handles CSV files when you don't need the full power of pandas.
import csv
# Write CSV
data = [
["Name", "Age", "City"],
["Alice", 30, "New York"],
["Bob", 25, "Los Angeles"],
["Carol", 35, "Chicago"],
]
with open("people.csv", "w", newline="") as f:
writer = csv.writer(f)
writer.writerows(data)
# Read CSV as lists
with open("people.csv") as f:
reader = csv.reader(f)
header = next(reader) # Skip header row
for row in reader:
name, age, city = row
print(f"{name} lives in {city}")
# Read CSV as dicts (first row becomes keys)
with open("people.csv") as f:
reader = csv.DictReader(f)
for row in reader:
print(row["Name"], row["City"])
# Write dicts
people = [
{"Name": "Alice", "Age": 30, "City": "NYC"},
{"Name": "Bob", "Age": 25, "City": "LA"},
]
with open("output.csv", "w", newline="") as f:
writer = csv.DictWriter(f, fieldnames=["Name", "Age", "City"])
writer.writeheader()
writer.writerows(people)
JSON Data
import json
# Serialization: Python → JSON
data = {
"name": "Alice",
"age": 30,
"hobbies": ["python", "chess", "hiking"],
"address": {"city": "NYC", "zip": "10001"},
"active": True,
"score": None # Python None → JSON null
}
# Write to file
with open("data.json", "w") as f:
json.dump(data, f, indent=2) # indent for human-readable
# Write to string
json_str = json.dumps(data, indent=2)
print(json_str)
# Read from file
with open("data.json") as f:
loaded = json.load(f)
# Parse JSON string
parsed = json.loads('{"name": "Bob", "age": 25}')
print(type(parsed)) # dict
# Python → JSON type mapping
# dict → object {}
# list, tuple → array []
# str → string
# int, float → number
# True/False → true/false
# None → null
Working with Nested JSON
import json
import requests
# GitHub API response (complex nested JSON)
response = requests.get("https://api.github.com/repos/python/cpython")
repo = response.json()
print(repo["name"]) # "cpython"
print(repo["stargazers_count"])
print(repo["owner"]["login"]) # Nested object
print(repo["topics"]) # Array
# Parse array of objects
users = json.loads('[{"id": 1, "name": "Alice"}, {"id": 2, "name": "Bob"}]')
for user in users:
print(user["id"], user["name"])
# Safely access nested values
def get_nested(d, *keys, default=None):
for key in keys:
if isinstance(d, dict):
d = d.get(key, default)
else:
return default
return d
get_nested(repo, "owner", "login") # "python"
get_nested(repo, "license", "name") # "PSF-2.0" or None
Data Transformation Patterns
import json, csv
# JSON API → CSV report
response = requests.get("https://api.github.com/search/repositories?q=python&sort=stars&per_page=10")
repos = response.json()["items"]
# Extract relevant fields
records = [
{"name": r["name"], "stars": r["stargazers_count"], "url": r["html_url"]}
for r in repos
]
# Write to CSV
with open("top_repos.csv", "w", newline="") as f:
writer = csv.DictWriter(f, fieldnames=["name", "stars", "url"])
writer.writeheader()
writer.writerows(records)
# CSV → JSON transformation
with open("input.csv") as f:
reader = csv.DictReader(f)
records = list(reader) # Convert to list of dicts
with open("output.json", "w") as f:
json.dump(records, f, indent=2)
Key Takeaways
- csv.DictReader/DictWriter: work with CSV as dicts — cleaner than lists
- newline="" on Windows: prevents double newlines in CSV files
- json.dump/load for files, json.dumps/loads for strings
- indent=2 in json.dump: human-readable output for debugging
- None → null, True → true: Python/JSON type mapping to remember
Practice Exercises
- Write a script that converts a JSON file (array of objects) to CSV and vice versa.
- Read a CSV of transactions (date, amount, category), compute total by category, and write results to a new CSV.
- Fetch JSON from a public API, extract specific fields, and save as a clean CSV.