Find research datasets worth reusing

Exploring Design Smells for Smell-Based Defect Prediction

The archived file datasets.zip includes the datasets used for supporting the conclusions in the article Exploring Design Smells for Smell-Based Defect Prediction. In this paper, we answer two research questions: RQ1. Do Design code smells contribute to the performance of defect prediction models trained with Traditional code smells? RQ2. How do the different categories of Design smells impact the performance of the defect prediction models? Therefore, after extracting the archived file documents, you will find two sub-directories, respectively named "RQ1" and "RQ2". They include the results obtained for each one of the research questions, thus supporting our conclusions. (You will also find a README.pdf file with these same instructions regarding the datasets.) Inside "RQ1," you will find two directories, respectively named "configuration_1" and "configuration_2". They represent the different configurations for the experiments. "configuration_1" contains the datasets with results for the ten classifiers configurations with the highest scores and "configuration_2" contains the datasets with the results classifier configuration with the overall best results - Support Vector Machine with C=0.1. Furthermore, within each directory, there are three sub-directories, respectively named "designite," "designite_traditional," and "traditional." These have the datasets for each of the considered smell sets in our study. Inside "RQ2," you will find four directories. Each corresponds to a category from the design smells for the dataset "designite_traditional." These datasets were build from the same configuration as "configuration_2". Then, within every directory, there are 97 sub-directories representing the 97 projects analyzed in this study. Every project folder follows the same structure, which we define as follows. <ul> <li>The "dataset" directory contains the original training and testing dataset used.</li> <li>The "oversamples" directory contains the training dataset after oversampling for each of the feature selection approaches.</li> <li>The "score_summary" directory contains all classifier configurations considered, not only the 10 with the highest scores.</li> <li>The "scores.csv" file contains all the scores for the main classifier configurations studied in the particular experiment.</li> <li>The "selected_features" directory contains the selected features' information and the selected features dataset for each feature_selection method.</li> <li>The "selected_testing_X" directory contains the testing datasets.</li> <li>The "top_scores_summary" directory contains the classifier configurations and hyper-parameter scores for the top 10 highest scores.</li> </ul>

Data set for paper Predicting time to graduation at a large enrollmentAmerican university

A longitudinal data set of student grades, demographics, course participation, etc. for attending a large American university.

opencc-zeroOct 2020View details →

dryad40/100

Within-population sperm competition intensity does not predict asymmetry in conpopulation sperm precedence

Postcopulatory sexual selection can generate evolutionary arms races between the sexes resulting in the rapid coevolution of reproductive phenotypes. As traits affecting fertilization success diverge between populations, postmating prezygotic (PMPZ) barriers to gene flow may evolve. Conspecific sperm precedence is a form of PMPZ isolation thought to evolve early during speciation yet has mostly been studied between species. Here , we show conpopulation sperm precedence (CpSP) between Drosophila montana populations. Using Pool-seq genomic data we estimate divergence times and ask whether PMPZ isolation evolved in the face of gene flow. We find models incorporating gene flow fit the data best indicating populations experienced considerable gene flow during divergence. We find CpSP is asymmetric and mirrors asymmetry in non-competitive PMPZ isolation, suggesting these phenomena have a shared mechanism. However, we show asymmetry is unrelated to the strength of postcopulatory sexual selection acting within populations. We tested whether overlapping foreign and coevolved ejaculates within the female reproductive tract altered fertilization success but found no effect. Our results show that neither time since divergence nor sperm competitiveness predicts the strength of PMPZ isolation. We suggest that instead cryptic female choice or mutation-order divergence may drive divergence of postcopulatory phenotypes resulting in PMPZ isolation. This article is part of the theme issue 'Fifty years of sperm competition'.

Dataset of clinical biomarkers for prediction of the arboviral infection severity using SIMON analysis

The SISA dataset was used for the identification of clinical biomarkers that can predict the severity of the arboviral infection severity using SIMON analysis, as described (<a href="https://doi.org/10.1101/2020.08.16.252767">https://doi.org/10.1101/2020.08.16.252767</a>). The dataset contains clinical data from 543 individuals hospitalized due to the arboviral infection with Dengue, chikungunya, or Zika viruses from a surveillance study in Ecuador collected from 2013 to 2017 (Suppy et al., 2020, doi: 10.1371/journal.pntd.0007969). In the SISA dataset, we have excluded columns with high level of missing values (pregnancy, WomPreg and complete blood count test which was not performed for all donors and includes columns: PLT_count, Lymphocytes, CBC_N%, WBC_calc and CBC_HCT).  Additionally, 9 donors with missing values were removed and SIMON analysis was performed with this final dataset.

Analyzing and predicting urban land use forms in East Africa using OpenStreetMap data, satellite imagery, and Convolutional Networks

This multi-spectral satellite image data set is associated with our recent work on analyzing and predicting urban land use forms in East Africa using OpenStreetMap data, satellite imagery, and Convolutional Neural Networks. The images were extracted using an automated Python script from Google Maps Static API, based on sample locations in four East African capital cities namely Kampala, Nairobi, Dar es Salaam, and Kigali. Other data sets associated with this work, that is, ESRI shapefiles for administrative level 1 and OpenStreetMap data for the named cities may be downloaded directly from the respective URLs provided in the manuscript.

PharmaCoNER Silver Standard: Participant predictions in PharmaCoNER shared task

Introduction Predictions in the test and background set of PharmaCoNER participants.   Zip structure One directory per PharmaCoNER participant. Within each participant directory, there is one directory per run.   Corpus format description For subtask 1 annotations are distributed in Brat format. See Brat webpage for more information <a href="https://brat.nlplab.org/standoff.html">https://brat.nlplab.org/standoff.html</a> For subtask-2, codes are associated with each document are given in a TSV file with the following columns:  <pre>articleID code </pre> Resources: <ul> <li><a href="https://temu.bsc.es/pharmaconer/">Web</a></li> <li>Citation: A. G. Agirre, M. Marimon, A. Intxaurrondo, O. Rabal, M. Villegas, M. Krallinger, Pharmaconer: Pharmacological substances, compounds and proteins named entity recognition track, in: Proceedings of The 5th Workshop on BioNLP Open Shared Tasks, 2019, pp. 1–10.</li> <li><a href="https://doi.org/10.5281/zenodo.4270157">Gold Standard corpus</a></li> <li><a href="https://doi.org/10.5281/zenodo.3763276">Annotation guidelines</a></li> <li><a href="https://github.com/TeMU-BSC/PharmaCoNER-Tagger">PharmaCoNER tagger</a></li> </ul>   All credit to PharmaCoNER participants.  For further information, please visit <a href="https://temu.bsc.es/pharmaconer/">https://temu.bsc.es/pharmaconer/</a> or email us at encargo-pln-life@bsc.es Copyright (c) 2018 Secretaría de Estado para el Avance Digital (SEAD)

Enhanced Bug Prediction in JavaScript Programs with Hybrid Call-Graph Based Invocation Metrics (Training Dataset)

This dataset consists of multiple files which contain bug prediction training data. The entries in the dataset are JavaScript functions either being buggy or non-buggy. Bug related information was obtained from the project EsLint contained in BugsJS (https://github.com/BugsJS/eslint). The buggy instances were collected throughout the lifetime of the project, however we added non-buggy entries from the latest version which is tagged as fix (entries which were previously included as buggy were not included as non-buggy later on). The dataset is based on hybrid call graphs which are constructed by https://github.com/sed-szeged/hcg-js-framework. The result of this tool is a call graph where the edges are associated with a confidence level which shows how likely the given edge is a valid call edge. We used different threshold values from which we considered the edges to be valid. The following threshold values were used: <ul> <li>0.00</li> <li>0.05</li> <li>0.20</li> <li>0.30</li> </ul> The prefix in the dataset file names are coming from the used threshold. The the datasets include coupling metrics NII (Nubmer of Incoming Invocations) and NOI (Number of Outgoing Invocations) which were calculated by a static source code analyzer called SourceMeter. Hybrid counterparts of these metrics (HNII and HNOI) are based on the given threshold values. There are four variants for all of these datasets: <ul> <li>Both static (NII, NOi) and hybrid (HNII, HNOI) coupling metrics are included with additional static source code metrics and information about the entries (file without any postfix). Column contained only in this dataset are: <ul> <li>ID</li> <li>Name</li> <li>Longname</li> <li>Parent ID</li> <li>Component ID</li> <li>Path</li> <li>Line</li> <li>Column</li> <li>EndLine</li> <li>EndColumn</li> </ul> </li> <li>Both static (NII, NOi) and hybrid (HNII, HNOI) coupling metrics are included with additional static source code metrics (file with '_h+s' postfix)</li> <li>Only static (NII, NOI) coupling metrics are included with additional static source code metrics (file with '_s' postfix)</li> <li>Only hybrid (HNII, HNOI) coupling metrics are included with additional static source code metrics (file with '_h' postfix)</li> </ul> Static source code metrics which are contained in all dataset are the following: <ul> <li>McCC - McCabe Cyclomatic Complexity</li> <li>NL - Nesting Level</li> <li>NLE - Nesting Level Else If</li> <li>CD - Comment Density</li> <li>CLOC - Comment Lines of Code</li> <li>DLOC - Documentation Lines of Code</li> <li>TCD - Total Comment Density (Comment Lines in an emedded function will be also considered)</li> <li>TCLOC - Total Comment Lines of Code (Comment Lines in an emedded function will be also considered)</li> <li>LLOC - Logical Lines of Code (Comment and empty lines not counted)</li> <li>LOC - Lines of Code (Comment and empty lines are counted)</li> <li>NOS - Number of Statements</li> <li>NUMPAR - Number of Parameters</li> <li>TLLOC - Logical Lines of Code (Lines in embedded functions are also counted)</li> <li>TLOC - Lines of Code (Lines in embedded functions are also counted)</li> <li>TNOS - Total Number of Statements (Statements in embedded functions are also counted)</li> </ul>

Dataset for "Toward closure between predicted and observed particle viscosity over a wide range temperature and relative humidity"

Raw data and processing scripts associated with the paper "Toward closure between predicted and observed particle viscosity over a wide range temperature and relative humidity". Please see README.md for details.

Vortex input files -- Ashe et al., "Minding the data-gap trap: predicting the dynamics of abundant dolphin species under uncertainty"

Vortex input file used for analyses presented in: "Minding the data-gap trap: predicting the dynamics of abundant dolphin species under uncertainty",  by Erin Ashe, Rob Williams, Christopher Clark, Christine Erbe, Leah Gerber, Ailsa Hall, Philip Hammond, Robert C. Lacy, Randall Reeves, & Nicole Vollmer

Dataset for: African manatee (Trichechus senegalensis) habitat suitability at Lake Ossa, Cameroon using trophic state models and predictions of submerged aquatic vegetation

See research article here: https://onlinelibrary.wiley.com/doi/epdf/10.1002/ece3.8202 Aim: The present study aims at investigating the past and current trophic status of Lake Ossa and evaluating its potential impact on African manatee health. Location: Lake Ossa is known as a refuge for the threatened African manatees in Cameroon. Little information exists on the water quality and health of the ecosystem as reflected by its chemical and biological characteristics. Methods: Aquatic biotic and abiotic parameters including water clarity, nitrogen, phosphorous and chlorophyll concentrations were measured monthly during four months at each of 18 water sampling stations evenly distributed across the lake. These parameters were then compared with historical values obtained from the literature to examine the dynamic trophic state of Lake Ossa. Results: Results indicate that Lake Ossa’s trophic state parameters doubled in only three decades (from 1985 to 2016), moving from a mesotrophic to a eutrophic state. The decreasing nutrient gradient moving from the mouth of the lake (in the south) to the north indicates that the flow of the adjacent Sanaga River is the primary source of nutrient input. Further analysis suggests that the poor transparency of the lake is not associated with chlorophyll concentrations but rather with the suspended sediments brought-in by the Sanaga River. Consequently, our model demonstrated that despite nutrient enrichment, less than 5% of the lake bottom surface sustained submerged aquatic vegetation. Thus, shoreline emergent vegetation is the primary food available for the local manatee population. During the dry season, water recedes drastically and disconnects from the dominant shoreline emergent vegetation, decreasing accessibility for manatees. Main conclusions: The current study revealed major environmental concerns (eutrophication and sedimentation) that may negatively impact habitat quality for manatees. Efficient land use and water management across the entire watershed may be necessary to mitigate such issues.

dataset for paper Vanhaebost J, Faouzi M, Mangin P, Michaud K: New reference tables and user-friendly Internet application for predicted heart weights. Int J Legal Med 2014, 128(4):615-620.

The heart weight is the most important parameter in the determination of cardiac hypertrophy. The obtained heart weight value should be compared against tables of normal weights by age, gender and body weight and height In the study by Vanhaebost et al.  has been shown in the Swiss population that the heart weight increases along with the increase of the body weight, body height, BMI and body surface area (BSA). The mean heart weight is greater in men than in women at a similar body weight. The reference tables for predicted heart weights obtained from this study are presented as an user-friendly internet application (<a href="http://calc.chuv.ch/Heartweight">http://calc.chuv.ch/Heartweight</a>)  enabling the comparison of heart weights observed at autopsy with the reference values.

The features of the selected papers in the field of air quality prediction

The table is a part of a submitted manuscript (Iskandaryan, D., Ramos, F., & Trilles, S. The Role of Datasets in Air Quality Prediction.  Submitted to Atmosphere.) and includes the following features extracted from the selected papers: Year, Case Study, Prediction Target, Dataset Type, Data Rate, Period (Days), Open Data, Algorithm, Time Granularity and Evaluation Metric. The relevant papers were selected from a systematic review in Air Quality Prediction Using Machine Learning Technologies. The works were queried in Association for Computing Machinery, IEEE Xplore, Scopus and Web of Science databases using the following query: ("machine learning") AND ("prediction"OR "forecast") AND ("air quality" OR "air pollution"), which was being applied to title, abstract and keywords. After filtering the results guided by the Preferred Reporting Items for Systematic Reviews and Meta-Analyses,  ninety-three papers were selected. The goal of this review is to understand which features are used in the field, in particular to answer the following questions:  1) What types of datasets are used to improve air quality predictions?; and 2) What characteristics of the dataset are important for efficient and effective air quality forecasting?  Twenty-six datasets were used by the authors as supplemental air quality data in order to predict air quality more accurately. Those datasets are: "MET"- meteorological data; "Spatial"- topographical characteristics, the locations of the stations; "Temporal"-includes the day of the month, day of the week, the hour of the day; "AOD"- aerosol optical depth; "Social Media"- microblog data; "Traffic"; "PBL Height"- planetary boundary layer height;  "Land Use"; "BEV"- Built Environment Variables; "UV Index"; "SP"- Sound Pressure; "PD"-Population Density; "Human Movements"- floating population and estimated traffic volume;  "Altitude";  "OMI-SO2"-Satellite-retrieved SO2 from Ozone Monitoring Instrument-SO2; "PPS"- Pollution Point Source; "TS"-Transportation Source; "WFD’"- weather forecast data; "POI Distribution"; "FAPE"- factory air pollution emission; "RND"- Road Network Distribution; "Elevation"; "AEI"- Anthropogenic Emission Inventory; "NDVI"; "Chemical"- chemical component forecast data (organic carbon, black carbon, sea salt, etc.); "Emission".

Simulated NGS read datasets for novel human virus prediction

This repository contains simulated Illumina read datasets for novel human virus prediction and associated metadata extracted from the Virus Host Database (<a href="https://www.genome.jp/virushostdb/">https://www.genome.jp/virushostdb/</a>). The reads are 250bp long and were simulated with Mason (<a href="https://www.seqan.de/apps/mason/">https://www.seqan.de/apps/mason/</a>) from genomes downloaded from NCBI. The training-validation-test split was done on whole viral sequences to ensure "novelty" of validation and test viruses. The training sets contain 10 million reads per class, validation sets - 1.25 million reads per class, and test sets - 1.25 million paired reads per class. The negative class sets contain reads simulated from chordate-infecting ("cho"), metazoan-infecting ("met"), eukariote-infecting ("euk") and all-nonhuman viruses. The positive class contains human-infecting viruses. The stratified dataset ("strat") contains an equal number of reads from "cho", "met but not cho", "euk but not met" and "all but not euk".  Species-level datasets ("humspec", "allspec" and "chospec", with the corresponding fasta and *_species.rds files) are constructed analogously, but ensuring that all viruses of a given species were assigned to either training, val or test set. This is a stricter setting modelling a "novel viral species" scenario while reflecting within-species phenotype diversity. blast_hits.gz contains blast hits of human virome reads form Moustafa et al., 2017 (https://doi.org/10.1371/journal.ppat.1006292) blasted against our training database (see paper for details). In the second column you can find the matched label and the accession number of the matched reference. blast_labels_complete.gz contains extracted labels for all virome reads, including those without any matches. Note: one of the read headers (>3c8ac47039d32b11c8fe23f588e444e9) from Moustafa et al. is slightly corrupted with null characters. You can remove them with sed 's/\x0//g' or equivalent.

Latitudinal core habitat prediction data for the manuscript: "Seascape topography slows predicted range shifts in fish under climate change"

Latitudinal locations of core environmental habitat for yellowtail kingfish (Seriola lalandi), Australian bonito (Sarda australis), Australian spotted mackerel (Scomberomorus munroi), narrow-barred Spanish mackerel (Scomberomorus commerson) and common dolphinfish (Coryphaena hippurus) nearshore of the continental shelf break (i.e. 200-m isobath) within 145 – 160°E, 15 – 45°S and between years 1998 – 2018.

Prediction of Churning Credit Card Customers

A business manager of a consumer credit card portfolio is facing the problem of customer attrition. They want to analyze the data to find out the reason behind this and leverage the same to predict customers who are likely to drop off. We could construct a model to predict which customer might be churned and the manager could proactively provide them better services and turn customers' decisions in the opposite direction.

Predicting placenta transcriptional regulatory interactions based on spatial gene expression data and convolutional neural network

Aims: The dysfunction of placenta development is correlated to the defects of pregnancy and fetal growth. The detailed molecular mechanism of placenta development is not identified in human due to the lack of material in vivo. Image-based reconstructions of GRN are still very underdeveloped. Methods and Results: In this study, first-trimester chorionic villus and decidua tissues were collected. Next, we present a machine-learning system to infer gene interaction networks of the human placenta from immunofluorescence images of trophoblast specific transcription factors obtained by a high-resolution scanner. Conclusions: The experimental results show that deep learning models reveal regulatory roles that have not yet been fully recognized. The spatial expression data reveal new regulatory relationships that traditional experiments have failed to recognize, and has allowed the development of gene regulation networks based on the spatial distribution of gene expression. We demonstrate the effectiveness of this approach in building networks using high-resolution images of the human placenta. Our analysis is of certain significance for further exploration of the development of the placenta and the occurrence of pregnancy-related diseases in the future. The datasets and analysis provide a useful source for the researchers in the field of the maternal-fetal interface and the establishment of pregnancy.

opencc-by-4.0Sep 2020View details →

Predictive Control of Aerial Swarms in Cluttered Environments

This repository contains all data that has been used to produce the results contained in the submission to Nature Machine Intelligence titled  "Predictive Control of Aerial Swarms in Cluttered Environments". It also contains the code necessary for plotting simulation and hardware experimental data. For the code used to run simulation and hardware experiments, please visit <a href="http://doi.org/10.5281/zenodo.4379503">doi.org/10.5281/zenodo.4379503</a>.

Industrial Benchmark Dataset for Customer Escalation Prediction

This is a real-world industrial benchmark dataset from a major medical device manufacturer for the prediction of customer escalations. The dataset contains features derived from IoT (machine log) and enterprise data including labels for escalation from a fleet of thousands of customers of high-end medical devices.  The dataset accompanies the publication "System Design for a Data-driven and Explainable Customer Sentiment Monitor" (submitted). We provide an anonymized version of data collected over a period of two years. The dataset should fuel the research and development of new machine learning algorithms to better cope with real-world data challenges including sparse and noisy labels, and concept drifts. Additional challenges is the optimal fusion of enterprise and log based features for the prediction task. Thereby, interpretability of designed prediction models should be ensured  in order to have practical relevancy.  Supporting software Kindly use the corresponding <a href="https://github.com/annguy/customer-sentiment-monitor">GitHub repository</a> (https://github.com/annguy/customer-sentiment-monitor) to design and benchmark your algorithms.    Citation and Contact   If you use this dataset please cite the following publication:   <pre><code>@ARTICLE{9520354, author={Nguyen, An and Foerstel, Stefan and Kittler, Thomas and Kurzyukov, Andrey and Schwinn, Leo and Zanca, Dario and Hipp, Tobias and Jun, Sun Da and Schrapp, Michael and Rothgang, Eva and Eskofier, Bjoern}, journal={IEEE Access}, title={System Design for a Data-Driven and Explainable Customer Sentiment Monitor Using IoT and Enterprise Data}, year={2021}, volume={9}, number={}, pages={117140-117152}, doi={10.1109/ACCESS.2021.3106791}}</code></pre>   If you would like to get in touch, please contact an.nguyen@fau.de.

opencc-by-4.0Jan 2021View details →

Automated prediction of visual complexity of web pages: Tools and evaluations

This dataset includes the screenshots of the web pages used for the evaluation of ViCRAM which is described in the following paper: Eleni Michailidou, Sukru Eraslan, Yeliz Yesilada, and Simon Harper. 2020. Automated Prediction of Visual Complexity of Web Pages: Tools and Evaluations. International Journal of Human-Computer Studies (SCI-E, SSCI), 145, 102523.