refactor: ⚡️ Speed up function find_cycle_vertices by 324%

[misrasaurabh1]

📄 find_cycle_vertices in src/backend/base/langflow/graph/graph/utils.py

✨ Performance Summary:

• Speed Increase: 📈 324% (3.24x faster)
• Runtime Reduction: ⏱️ From 71.5 milliseconds down to 16.9 milliseconds (best of 19 runs)

---

📝 Explanation and details

Here's an optimized version of the code. It uses a more efficient way to find the vertices on a cycle.

---

✅ Correctness verification

The new optimized code was tested for correctness. The results are listed below:

Test	Status	Details
⚙️ Existing Unit Tests	✅ 56 Passed	See below
🌀 Generated Regression Tests	✅ 29 Passed	See below
⏪ Replay Tests	🔘 None Found
🔎 Concolic Coverage Tests	🔘 None Found
📊 Coverage	100.0%

⚙️ Existing Unit Tests Details

Click to view details

- graph/graph/test_cycles.py
- graph/graph/test_utils.py

🌀 Generated Regression Tests Details

Click to view details

import networkx as nx  # used for the function to test
# imports
import pytest  # used for our unit tests
from langflow.graph.graph.utils import find_cycle_vertices

# unit tests

def test_single_cycle():
    edges = [(1, 2), (2, 3), (3, 1)]
    codeflash_output = find_cycle_vertices(edges)

def test_multiple_disjoint_cycles():
    edges = [(1, 2), (2, 1), (3, 4), (4, 3)]
    codeflash_output = find_cycle_vertices(edges)

def test_cycle_with_additional_edges():
    edges = [(1, 2), (2, 3), (3, 1), (3, 4), (4, 5)]
    codeflash_output = find_cycle_vertices(edges)

def test_acyclic_graph():
    edges = [(1, 2), (2, 3), (3, 4)]
    codeflash_output = find_cycle_vertices(edges)

def test_empty_graph():
    edges = []
    codeflash_output = find_cycle_vertices(edges)

def test_multiple_interconnected_cycles():
    edges = [(1, 2), (2, 3), (3, 1), (3, 4), (4, 5), (5, 3)]
    codeflash_output = find_cycle_vertices(edges)

def test_nested_cycles():
    edges = [(1, 2), (2, 3), (3, 1), (3, 4), (4, 5), (5, 4)]
    codeflash_output = find_cycle_vertices(edges)

def test_self_loop():
    edges = [(1, 1)]
    codeflash_output = find_cycle_vertices(edges)

def test_single_node_no_edges():
    edges = [(1, 2)]
    codeflash_output = find_cycle_vertices(edges)

def test_disconnected_nodes():
    edges = [(1, 2), (3, 4)]
    codeflash_output = find_cycle_vertices(edges)

def test_large_graph_single_cycle():
    edges = [(i, i+1) for i in range(1, 1000)] + [(1000, 1)]
    codeflash_output = find_cycle_vertices(edges)

def test_large_graph_no_cycles():
    edges = [(i, i+1) for i in range(1, 1000)]
    codeflash_output = find_cycle_vertices(edges)

def test_large_graph_multiple_cycles():
    edges = [(i, i+1) for i in range(1, 500)] + [(500, 1)] + [(i, i+1) for i in range(501, 1000)] + [(1000, 501)]
    codeflash_output = find_cycle_vertices(edges)

def test_string_nodes():
    edges = [('a', 'b'), ('b', 'c'), ('c', 'a')]
    codeflash_output = find_cycle_vertices(edges)


def test_duplicate_edges_in_cycle():
    edges = [(1, 2), (2, 3), (3, 1), (1, 2), (2, 3)]
    codeflash_output = find_cycle_vertices(edges)

def test_duplicate_edges_no_cycle():
    edges = [(1, 2), (1, 2), (2, 3), (2, 3)]
    codeflash_output = find_cycle_vertices(edges)
# codeflash_output is used to check that the output of the original code is the same as that of the optimized code.
import networkx as nx
# imports
import pytest  # used for our unit tests
from langflow.graph.graph.utils import find_cycle_vertices

# unit tests

def test_single_cycle():
    # Basic test with a single cycle
    edges = [(1, 2), (2, 3), (3, 1)]
    codeflash_output = find_cycle_vertices(edges)

def test_multiple_disjoint_cycles():
    # Test with multiple disjoint cycles
    edges = [(1, 2), (2, 1), (3, 4), (4, 3)]
    codeflash_output = find_cycle_vertices(edges)

def test_single_node_cycle():
    # Test with a single node cycle
    edges = [(1, 1)]
    codeflash_output = find_cycle_vertices(edges)

def test_acyclic_graph():
    # Test with an acyclic graph
    edges = [(1, 2), (2, 3), (3, 4)]
    codeflash_output = find_cycle_vertices(edges)

def test_empty_graph():
    # Test with an empty graph
    edges = []
    codeflash_output = find_cycle_vertices(edges)

def test_multiple_interconnected_cycles():
    # Test with multiple interconnected cycles
    edges = [(1, 2), (2, 3), (3, 1), (3, 4), (4, 2)]
    codeflash_output = find_cycle_vertices(edges)

def test_nested_cycles():
    # Test with nested cycles
    edges = [(1, 2), (2, 3), (3, 4), (4, 2), (3, 1)]
    codeflash_output = find_cycle_vertices(edges)

def test_self_loop_and_disjoint_cycle():
    # Test with a self-loop and a disjoint cycle
    edges = [(1, 1), (2, 3), (3, 2)]
    codeflash_output = find_cycle_vertices(edges)

def test_graph_with_isolated_nodes():
    # Test with isolated nodes
    edges = [(1, 2), (2, 1), (3, 4)]
    codeflash_output = find_cycle_vertices(edges)

def test_large_graph_one_large_cycle():
    # Test with a large graph with one large cycle
    edges = [(i, i+1) for i in range(1, 1000)] + [(1000, 1)]
    codeflash_output = find_cycle_vertices(edges)

def test_large_graph_multiple_small_cycles():
    # Test with a large graph with multiple small cycles
    edges = [(i, i+1) for i in range(1, 100)] + [(i+1, i) for i in range(1, 100, 2)]
    codeflash_output = find_cycle_vertices(edges)

def test_graph_with_parallel_edges():
    # Test with a graph with parallel edges (multigraph)
    edges = [(1, 2), (1, 2), (2, 1)]
    codeflash_output = find_cycle_vertices(edges)

def test_graph_with_no_edges_but_multiple_nodes():
    # Test with a graph with no edges but multiple nodes
    edges = [(1, 2), (3, 4)]
    codeflash_output = find_cycle_vertices(edges)

# Run the tests
if __name__ == "__main__":
    pytest.main()
# codeflash_output is used to check that the output of the original code is the same as that of the optimized code.

---

📣 **Feedback**

If you have any feedback or need assistance, feel free to join our Discord community:

[codspeed-hq]

CodSpeed Performance Report

Merging #5262 will improve performances by ×2.1

_{Comparing codeflash-ai:codeflash/optimize-find_cycle_vertices-2024-12-11T14.43.05 (6e6c072) with main (4736aae)}

Summary

⚡ 2 improvements
✅ 13 untouched benchmarks

Benchmarks breakdown

	Benchmark	main	codeflash-ai:codeflash/optimize-find_cycle_vertices-2024-12-11T14.43.05	Change
⚡	test_get_and_cache_all_types_dict	2.4 ms	1.1 ms	×2.1
⚡	test_successful_run_with_input_type_any	331.1 ms	272.8 ms	+21.4%

[ogabrielluiz]

Hey @misrasaurabh1

We need to fix these before we can merge.