Big data & Spark
PySpark jobs, partitioning, batch processing, and large-dataset transform patterns.
Cache persist MEMORY_ONLY mock in Python
Mock a MEMORY_ONLY persistence cache in Python with an LRU eviction policy and optional persistence flag.
import time
class LRUCache:
def __init__(self, capacity, persistence="MEMORY_ONLY"):
self.capacity = capacity
self.persistence = persistence
self.cache = {}
self.access_order = []
self.hits = 0
self.misses = 0
def get(self, key):
if key in self.cache:
…Compaction Small Files Mock in Python
Simulates a small-files compaction job by creating small mock files and merging them into a single output file using Python's standard library.
from pathlib import Path
import tempfile
import os
def create_small_files(directory: Path, file_count: int = 5, lines_per_file: int = 3):
"""Create several small mock files with sample content."""
directory.mkdir(exist_ok=True)
for i in range(file_count):
file_path = directory / f"part-{i:04d}.tx…Delta Lake ACID Transaction Log Mock in Python
Simulates Delta Lake's transactional log with JSON files for atomic commits, versioned operations, and crash recovery
import json
import time
from pathlib import Path
class DeltaLog:
def __init__(self, path):
self.log_dir = Path(path)
self.log_dir.mkdir(parents=True, exist_ok=True)
self.version = 0
def _write_txn(self, action, payload):
txn = {
"version": self.version,
…How to Filter and Project Spark DataFrames with PySpark SQL
Simulate a SQL SELECT with WHERE using PySpark DataFrame select and filter to project columns and apply conditions.
from pyspark.sql import SparkSession
from pyspark.sql.functions import col
spark = SparkSession.builder.appName("QueryFilterMock").master("local[2]").getOrCreate()
data = [
("Alice", 28, "Engineering"),
("Bob", 35, "Sales"),
("Carol", 32, "Engineering"),
("David", 25, "Marketing"),
("Eve", 29, "E…How to Implement MapReduce Word Count in Python Using a Dict
Simulate a MapReduce word count pipeline in Python with a mock dict, splitting text into words, shuffling, and reducing to frequency counts.
def map_reduce_word_count(text: str) -> dict:
"""Simulate a MapReduce pipeline to count word frequencies."""
# MAP phase: split into words and emit (word, 1) pairs
mapped = []
for word in text.lower().split():
# Clean word of punctuation
clean_word = ''.join(char for char in word if cha…How to Implement a Mock MapReduce for Word Count in Python
Simulates a MapReduce word count pipeline with mapper, shuffle, and reducer phases using Python dicts and standard library modules.
from collections import defaultdict
import re
def mapper(text):
"""Split text into words and emit (word, 1) pairs."""
words = re.findall(r'\b\w+\b', text.lower())
return [(word, 1) for word in words]
def reducer(pairs):
"""Group word-count pairs and sum counts."""
counts = defaultdict(int)
fo…How to Mock DataFrame Schema Columns in Python
Create an empty pandas DataFrame with only the specified column names to mock a schema before any data is loaded.
import pandas as pd
def mock_schema(columns):
return pd.DataFrame(columns=columns)
if __name__ == "__main__":
cols = ["name", "age", "city"]
df = mock_schema(cols)
print(df)
print(f"Columns: {list(df.columns)}, Shape: {df.shape}")How to Mock Partition Pruning in Python
A dataclass-based mock that filters partitions by year and month to emulate Spark's partition pruning logic.
from dataclasses import dataclass
from typing import List
@dataclass(frozen=True)
class Partition:
id: int
year: int
month: int
class PartitionPruner:
"""Mock partition pruning: only keep partitions that match the filter."""
def __init__(self, partitions: List[Partition]):
self._partiti…How to Mock a Hash Join on Large and Small Tables in Python
This code efficiently joins a large dataset (1000 rows) with a small lookup table (20 rows) by building a dictionary hash lookup, mimicking a hash join strategy used in big data systems.
import random
from pprint import pprint
# Large table: 1000 rows (id, group_id, value)
large = [{"id": i, "group_id": random.randint(1, 20), "value": random.random() * 100} for i in range(1000)]
# Small table: 20 rows (group_id, label)
small = [{"group_id": g, "label": f"Group-{g}"} for g in range(1, 21)]
# Mock a …How to Mock a User-Defined Function (UDF) in Python
Wrap a real UDF implementation with call logging to simulate and track invocations in a data pipeline.
from typing import Any, Callable
# Mock a user-defined function (UDF) that was previously complex or external
def mock_udf(name: str, implementation: Callable[..., Any], *, calls: list[Any]) -> Callable[..., Any]:
"""Wrap a real implementation with call logging to simulate a UDF."""
def wrapper(*args: Any, *…How to Simulate a MapReduce Mock with Combine Phase in Python
Simulates a MapReduce pipeline with a combiner that aggregates local counts per reducer to reduce network and compute overhead.
from collections import defaultdict
def map_phase(lines):
intermediate = defaultdict(list)
for line in lines:
for word in line.strip().lower().split():
intermediate[word].append(1)
return dict(intermediate)
def combine_phase(intermediate, num_reducers=3):
combined = defaultdict(li…Mock Predicate Pushdown in Python for Big Data Queries
Simulate predicate pushdown by applying filters at the storage layer before materializing rows, showing how big data engines optimize queries.
class Query:
def __init__(self, table, rows):
self.table = table
self.rows = rows
def filter(self, predicate):
return Query(
self.table,
[row for row in self.rows if all(predicate(row) for predicate in predicate)]
)
def filter_pushdown(self, predica…Mock RDD in Python: Simulate Spark RDD Lazy Transformations
Simulate Apache Spark RDD behavior in Python with lazy maps, filters, partitions, and a collect action.
import random
def mock_rdd(data, num_slices=2):
"""
A simple simulation of Spark RDD behavior with lazy evaluation,
transformations, and an action.
"""
class SimpleRDD:
def __init__(self, data, num_slices=2):
self.data = data
self.num_slices = num_slices
…Modeling a Hive Metastore Table Schema in Python
A dataclass that mimics a Hive metastore table schema—columns, partition keys, storage format, and location—with helper methods for description and mutation.
from dataclasses import dataclass, field
from typing import Dict, List, Optional
@dataclass
class HiveTable:
"""Simple mock of a Hive metastore table schema."""
name: str
database: str = "default"
columns: List[Dict[str, str]] = field(default_factory=list)
partition_keys: List[Dict[str, str]] = f…Browse by section
Each section groups closely related Python snippets.
Big data & Spark — Python code examples
What you will find here
This page collects big data & spark 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.