Files & data

import csv
import json

def csv_to_json(csv_filepath, json_filepath):
    """Convert a CSV file to a JSON file."""
    with open(csv_filepath, mode='r', newline='') as csv_file:
        reader = csv.DictReader(csv_file)
        data = [row for row in reader]

    with open(json_filepath, mode='w') as json_file:
      …

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…

import csv

def export_to_csv(data, filename):
    """Export a list of dicts to a CSV file."""
    if not data:
        print("No data to export")
        return
    
    # Get column names from the keys of the first dict
    fieldnames = list(data[0].keys())
    
    with open(filename, 'w', newline='', encoding='utf…

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…

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(…

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…

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…

import json
from pathlib import Path

def parse_json_file(filepath):
    """Read and parse a JSON file, returning its contents."""
    path = Path(filepath)
    with path.open('r', encoding='utf-8') as f:
        return json.load(f)

def parse_txt_lines(filepath):
    """Read a text file and return non-empty stripped …

import csv
from pathlib import Path

data_file = Path("data.tsv")

# Sample TSV content (tab-separated)
sample = """name\tage\tcity
Alice\t30\tNew York
Bob\t25\tLos Angeles
Carol\t35\tChicago
"""
data_file.write_text(sample)

with data_file.open("r", newline="", encoding="utf-8") as f:
    reader = csv.DictReader(f, d…

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…

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…

import csv
from io import StringIO

def parse_csv(data, delimiter='|', quotechar='"'):
    reader = csv.reader(StringIO(data), delimiter=delimiter, quotechar=quotechar)
    rows = [row for row in reader]
    return rows

if __name__ == "__main__":
    sample = 'Alice|"Smith, Jr."|25\nBob|"Johnson, Sr."|30'
    result …

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…

import csv
import os

def split_csv(input_file, chunk_size=1000, output_prefix="chunk"):
    """Split a large CSV file into smaller chunks."""
    with open(input_file, 'r', newline='') as infile:
        reader = csv.reader(infile)
        header = next(reader)
        
        file_count = 1
        row_count = 0
  …

import csv
from pathlib import Path

fieldnames = ["name", "city", "age"]
rows = [
    {"name": "Alice", "city": "New York", "age": 30},
    {"name": "Bob", "city": "Los Angeles", "age": 25},
    {"name": "Charlie", "city": "Chicago", "age": 35},
]

path = Path("people.csv")
with path.open("w", newline="") as csvfile:…