Reading and Writing CSV and JSON in Python

import pandas as pd # Wrong encoding: common error for European or Latin American data try: df = pd.read_csv('data.csv') except UnicodeDecodeError: df = pd.read_csv('data.csv', encoding='latin-1') # Custom delimiter (common: semicolon in German/French Excel) df = pd.read_csv('data.csv', sep=';') # Keep leading zeros on ID-like columns df = pd.read_csv('data.csv', dtype={'zip_code': str, 'phone': str}) # Parse dates at load time df = pd.read_csv('data.csv', parse_dates=['signup_date']) # Treat sentinel values as NaN df = pd.read_csv('data.csv', na_values=['', 'N/A', '-999', 'unknown']) # Large files: stream in chunks for chunk in pd.read_csv('huge.csv', chunksize=10_000): process(chunk)

# index=False is almost always what you want df.to_csv('output.csv', index=False) # Use UTF-8 (default but be explicit) df.to_csv('output.csv', encoding='utf-8', index=False) # Keep floats readable df.to_csv('output.csv', float_format='%.3f', index=False) # Compress for big files df.to_csv('output.csv.gz', compression='gzip', index=False)

import json import pandas as pd # Simple read with open('data.json') as f: data = json.load(f) # Line-delimited JSON (common for big data) df = pd.read_json('data.jsonl', lines=True) # Deeply nested JSON into a flat table records = [ {'user': {'id': 1, 'name': 'Alice'}, 'events': [{'type': 'click'}]} ] flat = pd.json_normalize( records, record_path='events', meta=[['user', 'id'], ['user', 'name']] ) print(flat)

import json import numpy as np data = {'scores': [0.1, 0.2, 0.3], 'name': 'test'} # Pretty-printed, human-readable with open('out.json', 'w') as f: json.dump(data, f, indent=2, ensure_ascii=False) # numpy types crash default json; convert them class NPEncoder(json.JSONEncoder): def default(self, o): if isinstance(o, np.integer): return int(o) if isinstance(o, np.floating): return float(o) if isinstance(o, np.ndarray): return o.tolist() return super().default(o) with open('out.json', 'w') as f: json.dump(data, f, cls=NPEncoder, indent=2)