algorithm_optimisation.py

import timeit
import cProfile
import random
from io import StringIO
from typing import Callable, Dict

#importing optimised function from reverse_complement_generation.py
from reverse_complement_generation import complement_map, generate_reverse_complement

#set up and the helpers
nucleotides= ["A", "T", "G", "C"]
complement_map_upper= {k.upper():v.upper() for k, v in complement_map.items()}
translation_table= str.maketrans(complement_map_upper)

def generate_random_dna_sequence(length: int) -> str:
    """"
    Generates a random DNA sequence.
    """
    return "".join(random.choices(nucleotides, k=length))

#comparison approaches
def RC_version1_suboptimal(sequence: str) -> str:
    """"
    Method 1 - uses loop for complement generation and reversal.
    suboptimal method as it causes high python overhead
    """
    sequence = sequence.upper()
    complement_list=[]
    for base in sequence:
        complement_list.append(complement_map_upper.get(base,"N"))
    return "".join(complement_list)[::-1]


def RC_version2_list_join(sequence: str) -> str:
    """
    Method 2- Efficient O(N) using list comprehension and join
    """
    sequence = sequence.upper()
    complement_list=[complement_map_upper.get(base, "N") for base in sequence]
    return "".join(complement_list)[::-1]


#Benchmarking functions
def benchmark_functions(func:Callable, sequence_length:int, num_runs:int= 100):
    """
    Benchmarks a function using timeit
    """
    dna_sequence = generate_random_dna_sequence(sequence_length)
    execution_time= timeit.timeit(
        lambda: func(dna_sequence),
        number=num_runs
    )
    return {
        "function_name": func.__name__,
        "total_time": execution_time,
        "average_time": execution_time/num_runs * 1e6
    }

#Profiling function
def profile_functions(func:Callable, sequence_length:int):
    """"
    Profile a function using cProfile and prints the report
    """
    dna_sequence = generate_random_dna_sequence(sequence_length)
    print(f"\n\ncProfile Report for {func.__name__} Length: {sequence_length}")
    pr=cProfile.Profile()
    pr.enable()
    func(dna_sequence)
    pr.disable()

    s=StringIO()
    pr.print_stats(sort="tottime")
    print(s.getvalue())