python-performance-optimization — detailed patterns and worked examples

For advanced optimization techniques including NumPy vectorization, caching, memory management, parallelization, async I/O, database optimization, and benchmarking tools, see references/advanced-patterns.md. Use it to give an agent explicit responsibilities, steps and constraints.

Editorial note: curated source snapshot published by Collider.club under the MIT License. Source attribution is preserved in the front matter.

Source snapshot

python-performance-optimization — detailed patterns and worked examples

Profiling Tools

Pattern 1: cProfile - CPU Profiling

import cProfile
import pstats
from pstats import SortKey

def slow_function():
    """Function to profile."""
    total = 0
    for i in range(1000000):
        total += i
    return total

def another_function():
    """Another function."""
    return [i**2 for i in range(100000)]

def main():
    """Main function to profile."""
    result1 = slow_function()
    result2 = another_function()
    return result1, result2

# Profile the code
if __name__ == "__main__":
    profiler = cProfile.Profile()
    profiler.enable()

    main()

    profiler.disable()

    # Print stats
    stats = pstats.Stats(profiler)
    stats.sort_stats(SortKey.CUMULATIVE)
    stats.print_stats(10)  # Top 10 functions

    # Save to file for later analysis
    stats.dump_stats("profile_output.prof")

Command-line profiling:

# Profile a script
python -m cProfile -o output.prof script.py

# View results
python -m pstats output.prof
# In pstats:
# sort cumtime
# stats 10

Pattern 2: line_profiler - Line-by-Line Profiling

# Install: pip install line-profiler

# Add @profile decorator (line_profiler provides this)
@profile
def process_data(data):
    """Process data with line profiling."""
    result = []
    for item in data:
        processed = item * 2
        result.append(processed)
    return result

# Run with:
# kernprof -l -v script.py

Manual line profiling:

from line_profiler import LineProfiler

def process_data(data):
    """Function to profile."""
    result = []
    for item in data:
        processed = item * 2
        result.append(processed)
    return result

if __name__ == "__main__":
    lp = LineProfiler()
    lp.add_function(process_data)

    data = list(range(100000))

    lp_wrapper = lp(process_data)
    lp_wrapper(data)

    lp.print_stats()

Pattern 3: memory_profiler - Memory Usage

# Install: pip install memory-profiler

from memory_profiler import profile

@profile
def memory_intensive():
    """Function that uses lots of memory."""
    # Create large list
    big_list = [i for i in range(1000000)]

    # Create large dict
    big_dict = {i: i**2 for i in range(100000)}

    # Process data
    result = sum(big_list)

    return result

if __name__ == "__main__":
    memory_intensive()

# Run with:
# python -m memory_profiler script.py

Pattern 4: py-spy - Production Profiling

# Install: pip install py-spy

# Profile a running Python process
py-spy top --pid 12345

# Generate flamegraph
py-spy record -o profile.svg --pid 12345

# Profile a script
py-spy record -o profile.svg -- python script.py

# Dump current call stack
py-spy dump --pid 12345

Optimization Patterns

Pattern 5: List Comprehensions vs Loops

import timeit

# Slow: Traditional loop
def slow_squares(n):
    """Create list of squares using loop."""
    result = []
    for i in range(n):
        result.append(i**2)
    return result

# Fast: List comprehension
def fast_squares(n):
    """Create list of squares using comprehension."""
    return [i**2 for i in range(n)]

# Benchmark
n = 100000

slow_time = timeit.timeit(lambda: slow_squares(n), number=100)
fast_time = timeit.timeit(lambda: fast_squares(n), number=100)

print(f"Loop: {slow_time:.4f}s")
print(f"Comprehension: {fast_time:.4f}s")
print(f"Speedup: {slow_time/fast_time:.2f}x")

# Even faster for simple operations: map
def faster_squares(n):
    """Use map for even better performance."""
    return list(map(lambda x: x**2, range(n)))

Pattern 6: Generator Expressions for Memory

import sys

def list_approach():
    """Memory-intensive list."""
    data = [i**2 for i in range(1000000)]
    return sum(data)

def generator_approach():
    """Memory-efficient generator."""
    data = (i**2 for i in range(1000000))
    return sum(data)

# Memory comparison
list_data = [i for i in range(1000000)]
gen_data = (i for i in range(1000000))

print(f"List size: {sys.getsizeof(list_data)} bytes")
print(f"Generator size: {sys.getsizeof(gen_data)} bytes")

# Generators use constant memory regardless of size

Pattern 7: String Concatenation

import timeit

def slow_concat(items):
    """Slow string concatenation."""
    result = ""
    for item in items:
        result += str(item)
    return result

def fast_concat(items):
    """Fast string concatenation with join."""
    return "".join(str(item) for item in items)

def faster_concat(items):
    """Even faster with list."""
    parts = [str(item) for item in items]
    return "".join(parts)

items = list(range(10000))

# Benchmark
slow = timeit.timeit(lambda: slow_concat(items), number=100)
fast = timeit.timeit(lambda: fast_concat(items), number=100)
faster = timeit.timeit(lambda: faster_concat(items), number=100)

print(f"Concatenation (+): {slow:.4f}s")
print(f"Join (generator): {fast:.4f}s")
print(f"Join (list): {faster:.4f}s")

Pattern 8: Dictionary Lookups vs List Searches

import timeit

# Create test data
size = 10000
items = list(range(size))
lookup_dict = {i: i for i in range(size)}

def list_search(items, target):
    """O(n) search in list."""
    return target in items

def dict_search(lookup_dict, target):
    """O(1) search in dict."""
    return target in lookup_dict

target = size - 1  # Worst case for list

# Benchmark
list_time = timeit.timeit(
    lambda: list_search(items, target),
    number=1000
)
dict_time = timeit.timeit(
    lambda: dict_search(lookup_dict, target),
    number=1000
)

print(f"List search: {list_time:.6f}s")
print(f"Dict search: {dict_time:.6f}s")
print(f"Speedup: {list_time/dict_time:.0f}x")

Pattern 9: Local Variable Access

import timeit

# Global variable (slow)
GLOBAL_VALUE = 100

def use_global():
    """Access global variable."""
    total = 0
    for i in range(10000):
        total += GLOBAL_VALUE
    return total

def use_local():
    """Use local variable."""
    local_value = 100
    total = 0
    for i in range(10000):
        total += local_value
    return total

# Local is faster
global_time = timeit.timeit(use_global, number=1000)
local_time = timeit.timeit(use_local, number=1000)

print(f"Global access: {global_time:.4f}s")
print(f"Local access: {local_time:.4f}s")
print(f"Speedup: {global_time/local_time:.2f}x")

Pattern 10: Function Call Overhead

import timeit

def calculate_inline():
    """Inline calculation."""
    total = 0
    for i in range(10000):
        total += i * 2 + 1
    return total

def helper_function(x):
    """Helper function."""
    return x * 2 + 1

def calculate_with_function():
    """Calculation with function calls."""
    total = 0
    for i in range(10000):
        total += helper_function(i)
    return total

# Inline is faster due to no call overhead
inline_time = timeit.timeit(calculate_inline, number=1000)
function_time = timeit.timeit(calculate_with_function, number=1000)

print(f"Inline: {inline_time:.4f}s")
print(f"Function calls: {function_time:.4f}s")

For advanced optimization techniques including NumPy vectorization, caching, memory management, parallelization, async I/O, database optimization, and benchmarking tools, see references/advanced-patterns.md

About Collider.club

This card belongs to the curated knowledge base of Collider.club — a closed business club for entrepreneurs, engineers, investors and domain experts building projects for international markets. Members work across DeFi, AI/ML, FinTech, Web3, banking, hardware and venture capital, and the club runs closed sessions on high-margin niches with anonymous speakers.

• Club: https://collider.club
• Collection: Collider.club curated card library (mdrss-card/v2)
• Maintainer: Collider.club editorial team

License

MIT License — Copyright (c) 2026 Collider.club. Full text: LICENSE · https://opensource.org/licenses/MIT