Measuring Cyclomatic Complexity of Source Code Using Machine Learning
Bibliographic record
Abstract
High-performance, high-quality software is a fundamental goal for all developers.To achieve this, software needs to be built with exceptional quality, featuring a simplified structure, strong coherence, and minimized complexity.Cyclomatic Complexity (CC), critical software metric, quantifies the intricacy of a program's structure and control flow.Traditionally, CC measurement has relied on laborious manual techniques or conventional programming methods, both prone to errors and inefficiency.To overcome these limitations, we present a revolutionary approach that leverages a Multinomial Naive Bayes (MNB) machine learning (ML) algorithm for automated CC measurement.This innovative method offers a more accurate, efficient, and reliable means of software complexity evaluation.Our study utilizes a vast dataset of 3,598 carefully curated programming samples from diverse programming projects across three popular languages: Java, Python, and C++.Training our MNB model on this comprehensive and diverse dataset yielded an outstanding overall accuracy of 97.3%, demonstrating the efficacy and reliability of our approach for CC measurement across different programming languages (PLs).This success can be attributed to the utilization of the NBM learning algorithm, known for its proficiency in classification tasks.Additionally, our study benefits from a larger and more diverse dataset compared to prior research, potentially contributing to the superior results.Our novel approach to CC measurement using machine learning holds significant promise for the development of more accurate and reliable code complexity assessment tools.These encouraging findings suggest that this approach has the potential to shape more effective software development practices in the future.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".