Files & data
Read and write files safely; parse JSON, CSV, and common text formats.
Detect Outliers in CSV Data Using Z-Score in Python
Read a CSV file and detect outliers in a numeric column by computing z-scores, flagging those exceeding a given threshold — no machine learning required.
import csv
import statistics
from math import sqrt
def detect_outliers(csv_path, column_name, threshold=2.0):
"""Detect outliers in a numeric column using z-score method."""
values = []
with open(csv_path, 'r', newline='') as f:
reader = csv.DictReader(f)
if column_name not in reader.field…Export SQLite Query Results to CSV in Python
Connects to a SQLite database, runs a query, and writes the result rows and column headers to a CSV file using the standard library.
import sqlite3
import csv
def export_query_to_csv(db_path, query, csv_path):
conn = sqlite3.connect(db_path)
cursor = conn.cursor()
cursor.execute(query)
rows = cursor.fetchall()
column_names = [description[0] for description in cursor.description]
with open(csv_path, 'w', newline='', encodi…How to Convert CSV Column Types While Reading in Python
Read a CSV file and automatically convert column values to int, float, str, or bool based on type suffixes in the header names.
import csv
from pathlib import Path
from typing import Any
def read_csv_with_types(filepath: str) -> list[dict[str, Any]]:
"""Read CSV and convert column types based on header suffixes."""
converters = {
"int": int,
"float": float,
"str": str,
"bool": lambda v: v.strip().lower(…How to Filter CSV Rows by Column Value in Python
Filter CSV rows based on a column value condition using the standard csv module and a lambda function.
import csv
def filter_csv(input_file, output_file, column, condition):
with open(input_file, newline='', encoding='utf-8') as infile, \
open(output_file, 'w', newline='', encoding='utf-8') as outfile:
reader = csv.DictReader(infile)
fieldnames = reader.fieldnames
writer = csv.Dict…How to Handle Missing Values in a CSV Numeric Column in Python
Clean missing entries in a CSV numeric column by filling them with the mean, median, a custom value, or dropping rows.
import csv
from pathlib import Path
import statistics
def clean_csv_numeric(input_path: str, output_path: str, column: str, strategy: str = "mean") -> None:
"""
Handles missing values in a numeric column of a CSV file.
Strategies: 'mean', 'median', 'drop', or 'fill' with a specified value.
"""
row…How to Sum a CSV Column by Group in Python
This code reads a CSV string and sums a specified column for each unique value of a group key using the csv module and defaultdict.
import csv
from collections import defaultdict
from io import StringIO
def aggregate_csv(csv_data, group_key, sum_column):
totals = defaultdict(float)
reader = csv.DictReader(StringIO(csv_data))
for row in reader:
key = row[group_key]
totals[key] += float(row[sum_column])
return dict(t…Join two CSV files on shared key column in Python
Merge rows from two CSV files by a common key column, outputting combined records to a new file.
import csv
def join_csv(file1, file2, key, output="joined.csv"):
# Read first CSV into dict keyed by the join column
with open(file1, newline="") as f1:
reader1 = csv.DictReader(f1)
data1 = {row[key]: row for row in reader1}
# Read second CSV and merge matching rows
with open(file2, n…Normalize CSV Column Names to snake_case in Python
Convert CSV header names to snake_case using a regular expression and write the updated file in place.
import csv
import re
import sys
def to_snake_case(header):
header = re.sub(r"(?<=[a-z0-9])(?=[A-Z])", "_", header)
header = re.sub(r"[^a-zA-Z0-9]+", "_", header).strip("_").lower()
return header
def normalize_csv_headers(input_path, output_path=None):
with open(input_path, newline="", encoding="utf…Parse Fixed Width Data File by Column Slices in Python
Extract fields from fixed-width text by slicing each line at defined column offsets, with a dictionary describing the boundaries.
from pathlib import Path
def parse_fixed_width(data: str, slices: dict[str, tuple[int, int]]) -> list[dict[str, str]]:
lines = data.strip().splitlines()
records = []
for line in lines:
record = {}
for name, (start, end) in slices.items():
record[name] = line[start:end].strip()…Read Parquet-Like Columnar CSV Chunks in Python
A Python generator that reads a CSV file column-by-column, yielding dictionary chunks where each key points to a list of values—mirroring how Parquet stores data columnar.
```python
import csv
from pathlib import Path
from typing import Iterator, List
def read_parquet_like_columnar(csv_path: str, column_names: List[str], chunk_size: int = 2) -> Iterator[dict]:
"""Read CSV data in columnar chunks, similar to how parquet stores columns."""
csv_file = Path(csv_path)
with csv_f…Read a CSV File with csv.DictReader in Python
Read a CSV file as a list of dictionaries, using csv.DictReader to map each row to column names.
import csv
from pathlib import Path
def read_csv_with_dictreader(file_path):
data = []
with open(file_path, mode='r', newline='', encoding='utf-8') as csvfile:
reader = csv.DictReader(csvfile)
for row in reader:
data.append(row)
return data
if __name__ == "__main__":
# Cre…Browse by section
Each section groups closely related Python snippets.
Files & data — Python code examples
What you will find here
This page collects files & data snippets — short, copy-ready Python you can paste into our free online IDE and run without installing anything. Each sample includes a plain-English explanation and the full source code.
Samples vs tutorials and challenges
Samples are quick reference — one concept per page. For step-by-step teaching, use our Python tutorials. To test yourself, try quizzes or coding challenges. Clean up style with the Python formatter.