Data Mining Practical Machine Learning Tools and Techniques

During software maintenance, code comments help developers comprehend programs and reduce additional time spent on reading and navigating source code. Unfortunately, these comments are often mismatched, missing or outdated in the software projects. Developers have to infer the functionality from the source code. This paper proposes a new approach named DeepCom to automatically generate code comments for Java methods. The generated comments aim to help developers understand the functionality of Java methods. DeepCom applies Natural Language Processing (NLP) techniques to learn from a large code corpus and generates comments from learned features. We use a deep neural network that analyzes structural information of Java methods for better comments generation. We conduct experiments on a large-scale Java corpus built from 9,714 open source projects from GitHub. We evaluate the experimental results on a machine translation metric. Experimental results demonstrate that our method DeepCom outperforms the state-of-the-art by a substantial margin.

https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=5295&context=sis_research

Deep code comment generation

Wed, 05 Dec 2018 22:36:00 GMT forecasting methods and applications 3rd pdf PDF | On Jan 1, 1984, S ~G Makridakis and others published Forecasting: Methods and Applications Tue, 04 Dec 2018 23:06:00 GMT (PDF) Forecasting: Methods and Applications ResearchGate Forecasting: methods and applications. This book was published in 1998, and for nearly 20 years I maintained an associated website at this address. Fri, 30 Nov 2018 14:35:00 GMT Forecasting: methods and applications | Rob J Hyndman Prod 2100-2110 Forecasting Methods 2 1. Framework of planning decisions Let us first remember where the inventory control decisions may take place. Fri, 07 Dec 2018 14:13:00 GMT Forecasting Methods UCLouvain 2002 Forecasting: Methods and Applications Makridakis, ... this 3rd edition very wisely includes some more advanced forecasting methods such as dynamic regression, ... Sat, 01 Dec 2018 22:41:00 GMT 2002 Forecasting: Methods and Applications HEPHAESTUS Methods and Applications Third Edition Spyros Makridakis European Institute of Business ... major forecasting methods 516 The use of different forecasting Tue, 04 Dec 2018 22:37:00 GMT Methods and Applications Max Planck Society MATH6011: Forecasting â€œAll models are wrong, ... S.C. and Hyndman, R.J. 1998, Forecasting: Methods and Applications 3rd Ed., New York: Wiley as text book. Wed, 21 Nov 2018 17:31:00 GMT MATH6011: Forecasting University of Southampton Save As PDF Ebook forecasting methods and applications ... FOUR LAMAS OF DOLPO AUTOBIOGRAPHIES OF FOUR TIBETAN LAMAS INTRODUCTION AND TRANSLATIONS VOL I 3RD [PDF] Tue, 04 Dec 2018 19:10:00 GMT forecasting methods and applications makridakis pdf ... forecasting methods and applications 3rd ed Download forecasting methods and applications 3rd ed or read online books in PDF, EPUB, Tuebl, and Mobi Format. Thu, 06 Dec 2018 07:26:00 GMT forecasting methods and applications 3rd ed | Download ... INDUSTRIAL STATISTICS AND OPERATIONAL MANAGEMENT 6 : ... Some applications of forecasting ... Qualitative techniques in forecasting Time series methods Mon, 19 Nov 2018 11:49:00 GMT INDUSTRIAL STATISTICS AND OPERATIONAL MANAGEMENT 6 ... 3 Hierarchical forecasting 9 3 Advanced methods 9. Forecasting: principles and practice 7 Assumptions â€¢ This is not an introduction to R. I assume you are broadly ... Thu, 06 Dec 2018 22:49:00 GMT Forecasting: Principles & Practice, Rob J Hyndman, 2014 forecasting methods and applications 3rd ed Download forecasting methods and applications 3rd ed or read online here in PDF or EPUB. Please click button to get ... Mon, 03 Dec 2018 08:27:00 GMT Forecasting Methods And Applications 3rd Ed | Download ... Forecasting methods can be classified as qualitative or quantitative. ... practical applications. 15-4 Chapter 15 Time Series Analysis and Forecasting Fri, 07 Dec 2018 12:33:00 GMT PDF Time Series Analysis and Forecasting Cengage FORECASTING METHODS AND APPLICATIONS 3RD EDITION PDF READ Forecasting Methods And Applications 3rd Edition pdf. Download Forecasting Methods And Applications 3rd ... Sun, 11 Nov 2018 17:14:00 GMT Free Forecasting Methods And Applications 3rd Edition PDF Forecasting Methods and Applications. 3rd ed. New York: John Wiley & Sons, 1998. Sat, 08 Dec 2018 09:40:00 GMT Forecasting Methods and Applications Book Harvard ... Preface In preparing the manuscript for the third edition of Forecasting: methods and applications, one of our primary goals has been to make the book as complete and ... Wed, 05 Dec 2018

Forecasting methods and applications.

Research at the intersection of machine learning, programming languages, and software engineering has recently taken important steps in proposing learnable probabilistic models of source code that exploit code's abundance of patterns. In this article, we survey this work. We contrast programming languages against natural languages and discuss how these similarities and differences drive the design of probabilistic models. We present a taxonomy based on the underlying design principles of each model and use it to navigate the literature. Then, we review how researchers have adapted these models to application areas and discuss cross-cutting and application-specific challenges and opportunities.

A Survey of Machine Learning for Big Code and Naturalness

Research at the intersection of machine learning, programming languages, and software engineering has recently taken important steps in proposing learnable probabilistic models of source code that exploit the abundance of patterns of code. In this article, we survey this work. We contrast programming languages against natural languages and discuss how these similarities and differences drive the design of probabilistic models. We present a taxonomy based on the underlying design principles of each model and use it to navigate the literature. Then, we review how researchers have adapted these models to application areas and discuss cross-cutting and application-specific challenges and opportunities.

https://dl.acm.org/doi/pdf/10.1145/3212695

Software defect prediction, which predicts defective code regions, can help developers find bugs and prioritize their testing efforts. To build accurate prediction models, previous studies focus on manually designing features that encode the characteristics of programs and exploring different machine learning algorithms. Existing traditional features often fail to capture the semantic differences of programs, and such a capability is needed for building accurate prediction models. To bridge the gap between programs' semantics and defect prediction features, this paper proposes to leverage a powerful representation-learning algorithm, deep learning, to learn semantic representation of programs automatically from source code. Specifically, we leverage Deep Belief Network (DBN) to automatically learn semantic features from token vectors extracted from programs' Abstract Syntax Trees (ASTs). Our evaluation on ten open source projects shows that our automatically learned semantic features significantly improve both within-project defect prediction (WPDP) and cross-project defect prediction (CPDP) compared to traditional features. Our semantic features improve WPDP on average by 14.7% in precision, 11.5% in recall, and 14.2% in F1. For CPDP, our semantic features based approach outperforms the state-of-the-art technique TCA+ with traditional features by 8.9% in F1.

Automatically learning semantic features for defect prediction

Software defect prediction, which predicts defective code regions, can assist developers in finding bugs and prioritizing their testing efforts. Traditional defect prediction features often fail to capture the semantic differences between different programs. This degrades the performance of the prediction models built on these traditional features. Thus, the capability to capture the semantics in programs is required to build accurate prediction models. To bridge the gap between semantics and defect prediction features, we propose leveraging a powerful representation-learning algorithm, deep learning, to learn the semantic representations of programs automatically from source code files and code changes. Specifically, we leverage a deep belief network (DBN) to automatically learn semantic features using token vectors extracted from the programs’ abstract syntax trees (AST) (for file-level defect prediction models) and source code changes (for change-level defect prediction models). We examine the effectiveness of our approach on two file-level defect prediction tasks (i.e., file-level within-project defect prediction and file-level cross-project defect prediction) and two change-level defect prediction tasks (i.e., change-level within-project defect prediction and change-level cross-project defect prediction). Our experimental results indicate that the DBN-based semantic features can significantly improve the examined defect prediction tasks. Specifically, the improvements of semantic features against existing traditional features (in F1) range from 2.1 to 41.9 percentage points for file-level within-project defect prediction, from 1.5 to 13.4 percentage points for file-level cross-project defect prediction, from 1.0 to 8.6 percentage points for change-level within-project defect prediction, and from 0.6 to 9.9 percentage points for change-level cross-project defect prediction.

Deep Semantic Feature Learning for Software Defect Prediction

To improve software reliability, many rule-based techniques have been proposed to infer programming rules and detect violations of these rules as bugs. These rule-based approaches often rely on the highly frequent appearances of certain patterns in a project to infer rules. It is known that if a pattern does not appear frequently enough, rules are not learned, thus missing many bugs. In this paper, we propose a new approach—Bugram—that leverages n-gram language models instead of rules to detect bugs. Bugram models program tokens sequentially, using the n-gram language model. Token sequences from the program are then assessed according to their probability in the learned model, and low probability sequences are marked as potential bugs. The assumption is that low probability token sequences in a program are unusual, which may indicate bugs, bad practices, or unusual/special uses of code of which developers may want to be aware. We evaluate Bugram in two ways. First, we apply Bugram on the latest versions of 16 open source Java projects. Results show that Bugram detects 59 bugs, 42 of which are manually verified as correct, 25 of which are true bugs and 17 are code snippets that should be refactored. Among the 25 true bugs, 23 cannot be detected by PR-Miner. We have reported these bugs to developers, 7 of which have already been confirmed by developers (4 of them have already been fixed), while the rest await confirmation. Second, we further compare Bugram with three additional graph- and rule-based bug detection tools, i.e., JADET, Tikanga, and GrouMiner. We apply Bugram on 14 Java projects evaluated in these three studies. Bugram detects 21 true bugs, at least 10 of which cannot be detected by these three tools. Our results suggest that Bugram is complementary to existing rule-based bug detection approaches.

Bugram: bug detection with n-gram language models

Test case prioritization (TCP) is a practical activity in software testing for exposing faults earlier. Researchers have proposed many TCP techniques to reorder test cases. Among them, coverage-based TCPs have been widely investigated. Specifically, coverage-based TCP approaches leverage coverage information between source code and test cases, i.e., static code coverage and dynamic code coverage, to schedule test cases. Existing coverage-based TCP techniques mainly focus on maximizing coverage while often do not consider the likely distribution of faults in source code. However, software faults are not often equally distributed in source code, e.g., around 80% faults are located in about 20% source code. Intuitively, test cases that cover the faulty source code should have higher priorities, since they are more likely to find faults. In this paper, we present a quality-aware test case prioritization technique, QTEP, to address the limitation of existing coverage-based TCP algorithms. In QTEP, we leverage code inspection techniques, i.e., a typical statistic defect prediction model and a typical static bug finder, to detect fault-prone source code and then adapt existing coverage-based TCP algorithms by considering the weighted source code in terms of fault-proneness. Our evaluation with 16 variant QTEP techniques on 33 different versions of 7 open source Java projects shows that QTEP could improve existing coverage-based TCP techniques for both regression and new test cases. Specifically, the improvement of the best variant of QTEP for regression test cases could be up to 15.0% and on average 7.6%, and for all test cases (both regression and new test cases), the improvement could be up to 10.0% and on average 5.0%.

QTEP: quality-aware test case prioritization

In crowdsourced testing, an important task is to identify the test reports that actually reveal fault - true fault, from the large number of test reports submitted by crowd workers. Most existing approaches towards this problem utilized supervised machine learning techniques, which often require users to manually label a large amount of training data. Such process is time-consuming and labor-intensive. Thus, reducing the onerous burden of manual labeling while still being able to achieve good performance is crucial. Active learning is one potential technique to address this challenge, which aims at training a good classifier with as few labeled data as possible. Nevertheless, our observation on real industrial data reveals that existing active learning approaches generate poor and unstable performances on crowdsourced testing data. We analyze the deep reason and find that the dataset has significant local biases. To address the above problems, we propose LOcal-based Active ClassiFication (LOAF) to classify true fault from crowdsourced test reports. LOAF recommends a small portion of instances which are most informative within local neighborhood, and asks user their labels, then learns classifiers based on local neighborhood. Our evaluation on 14,609 test reports of 34 commercial projects from one of the Chinese largest crowdsourced testing platforms shows that our proposed LOAF can generate promising results. In addition, its performance is even better than existing supervised learning approaches which built on large amounts of labelled historical data. Moreover, we also implement our approach and evaluate its usefulness using real-world case studies. The feedbacks from testers demonstrate its practical value.

Song Wang

Papers

Automatically learning semantic features for defect prediction

Deep Semantic Feature Learning for Software Defect Prediction

Bugram: bug detection with n-gram language models

QTEP: quality-aware test case prioritization

Local-based active classification of test report to assist crowdsourced testing