Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
13,064
datasets available to search
ShareScore release 0.9.0
Dataset results
13,064 results for “predictions”
All raw data for CPC18: Choice prediction competition 2018
<p>These are the complete raw data for CPC18: a choice prediction competition for decisions under risk, under ambiguity, and from experience, organized by the authors and their colleagues. The data includes 694,500 consequential choices of human decision makers choosing between two risky and/or uncertain prospects with up to 10 possible outcomes each.</p> <p>This dataset includes both the training and the testing sets of the competition. The training (calibration) set of this data is published at https://zenodo.org/record/845873#.XGqnvegzaUk.</p> <p>Part of these data (published herein at: https://zenodo.org/record/321652#.WZlniSgjE2z) were previously used in CPC15 (a previous choice prediction competition), and are described in the paper: Erev, I., Ert, E., Plonsky, O., Cohen, D., & Cohen, O. (2017). From anomalies to forecasts: Toward a descriptive model of decision under risk, under ambiguity, and from experience. <em>Psychological Review,</em> 124(4), 369-409.<em> </em>DOI: 10.1037/rev0000062 </p> <p>More details about CPC18 can be found at https://cpc-18.com/</p>
Disk replacement log file examples from a very large RAID disk system for predictive maintenance analysis
<p>README.txt</p> <p>Maintenance example belonging to: </p> <p> The MANTIS Book: Cyber Physical System Based Proactive Collaborative Maintenance<br> Chapter 9, The Future of Maintenance (2019).<br> Lambert Schomaker, Michele Albano, Erkki Jantunen, Luis Lino Ferreira<br> River Publishers (DK)<br> ISBN: 9788793609853, e-ISBN: 9788793609846, https://doi.org/10.13052/rp-9788793609846</p> <p>The figure .pdf did not make it into the book. Here are the raw data, processed <br> logs and .gnu script to produce it.</p> <p>Data: event logs on disk failure in two racks of a huge RAID disk system (2009-2016).</p> <p>disks1.raw<br> disks2.raw</p> <p>Event logs to RC-filtered time series:<br> RC-filt-disks-log.c <br> do-RC-filter-to-make-spikes-more-visible (bash script)<br> --><br> disks1.log<br> disks2.log</p> <p>Constant (horizontal line) indicating the level where users experienced system-down time<br> Disrupted-operations-threshold</p> <p>disk-replacement-log.gnu<br> disk-replacement-log.pdf<br> </p>
Predicted soil water content (volumetric %) for 33kPa and 1500kPa suctions at 6 standard depths (0, 10, 30, 60, 100 and 200 cm) at 250 m resolution
<p>Migrated to: <a href="https://doi.org/10.5281/zenodo.2629589">https://doi.org/10.5281/zenodo.2629589</a></p>
Don't count, predict! Semantic vectors
<p>Semantic vectors associated with the paper "<a href="https://www.aclweb.org/anthology/P14-1023">Don't count, predict! A systematic comparison of context-counting vs context-predicting semantics vectors</a>"</p> <p><strong>Abstract:</strong> context-predicting models (more commonly known as embeddings or neural language models) are the new kids on the distributional semantics block. Despite the buzz surrounding these models, the literature is still lacking a systematic comparison of the predictive models with classic, count-vector-based distributional semantic approaches. In this paper, we perform such an extensive evaluation, on a wide range of lexical semantics tasks and across many parameter settings. The results, to our own surprise, show that the buzz is fully justified, as the context-predicting models obtain a thorough and resounding victory against their count-based counterparts.</p>
Prince Edward Island (Canada) Predictive Soil Mapping data set (30 m)
<p>Prince Edward Island (Canada) Predictive Soil Mapping data set. Training points include:</p> <ul> <li>soil organic matter (624 points): unit: percent, g/100g ) samples from the topsoil (0-23 cm depth),</li> <li>soil types (672 points),</li> </ul> <p>Covariate layers include:</p> <ul> <li>DEM derivatives (Channel_Network_Base_Level.tif, MRRTF.tif, Relative_Slope_Position.tif, Slope.tif, TWI.tif, Valley_Depth.tif, Vertical_Distance_To_Channel_Network.tif),</li> <li>landcover_2016_reclassify.tif (categorical values),</li> <li>DSS_soil_polygons.tif (soil polygons),</li> </ul> <p>Some covariates are type numeric, some type factor. To use the pre-processed data download only the RDS file. E.g. "PEI100m.soil.rds" contains all covariates layers resampled to 100 m resolution and all training points.</p>
Data for 'Improved predictability of the Indian Ocean Dipole using seasonally modulated ENSO forcing forecasts'
<p>Abstract of the associated paper: Despite recent progress in seasonal forecast development, the predictive skill for the Indian Ocean Dipole (IOD) remains typically limited to a lead time of one season or less in both dynamical and empirical models. Here we develop a simple stochastic-dynamical model (SDM) to predict the IOD using seasonally modulated El Niño-Southern Oscillation (ENSO) forcing together with a seasonal modulation of the Indian Ocean coupled ocean-atmosphere feedback. The SDM, with either observed or forecasted ENSO forcing, exhibits generally higher skill and longer lead times for predicting IOD events than the operational Climate Forecast System Version 2 and the SINTEX system. These results affirm our hypothesis that operational IOD predictability beyond persistence is largely controlled by ENSO predictability and the signal-to-noise ratio of the system. Therefore, potential future ENSO improvements in models should also translate to more skillful IOD predictions.</p>
Freeway Inductive Loop Detector Dataset for Network-wide Traffic Speed Prediction
<p>The data is collected by the inductive loop detectors deployed on freeways in Seattle area. The freeways contain I-5, I-405, I-90, and SR-520. This data set contains spatiotemporal speed information of the freeway system. At each milepost, the speed information collected from main lane loop detectors in the same direction are averaged and integrated into 5 minutes interval speed data. The raw data is provided by Washington Start Department of Transportation (WSDOT) and processed by the <a href="http://www.uwstarlab.org/">STAR Lab</a> in the University of Washington according to data quality control and data imputation procedures [1][2]. </p> <p>The data file is a pickle file that can be easily read using the read_pickle() function in the Pandas package. The data forms as a matrix and each cell of the matrix is speed value for the specific milepost and time period. The horizontal header of the data set denotes the milepost and the vertical header indicates the timestamps. For more information on the definition of milepost, please refer to this <a href="http://data.wsdot.wa.gov/traffic/">website</a>.</p> <p>This data set been used for traffic prediction tasks in several research studies [3][4]. For more detailed information about the data set, you can also refer to this <a href="https://github.com/zhiyongc/Seattle-Loop-Data">link</a>.</p> <p><strong>References</strong>:</p> <p>[1]. Henrickson, K., Zou, Y., & Wang, Y. (2015). Flexible and robust method for missing loop detector data imputation. <em>Transportation Research Record</em>, <em>2527</em>(1), 29-36.</p> <p>[2]. Wang, Y., Zhang, W., Henrickson, K., Ke, R., & Cui, Z. (2016). <em>Digital roadway interactive visualization and evaluation network applications to WSDOT operational data usage</em> (No. WA-RD 854.1). Washington (State). Dept. of Transportation.</p> <p>[3]. Cui, Z., Ke, R., & Wang, Y. (2018). Deep bidirectional and unidirectional LSTM recurrent neural network for network-wide traffic speed prediction. <em>arXiv preprint arXiv:1801.02143</em>.</p> <p>[4]. Cui, Z., Henrickson, K., Ke, R., & Wang, Y. (2018). Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting. <em>arXiv preprint arXiv:1802.07007</em>.</p>
Hit Song Prediction (Million Song Dataset and Audio Features)
<p><strong>Hit Song Prediction Dataset</strong></p> <p>This dataset is based on the Million Song Dataset (MSD), which contains one million songs that are representative for western commercial music released between 1922 and 2011. The dataset contains release year information for 515,576 of the MSD songs. Please refer to http://millionsongdataset.com/ for further information on the million song dataset.</p> <p>For our hit song prediction experiments, we extract high- and low-level audio features using the Essentia toolkit (cf. https://essentia.upf.edu/). For the high-level features, we make use of the pre-trained classifiers as provided by Essentia. For a detailed description of the features, please visit the Essentia documentation.</p> <p><br> The dataset hence contains:</p> <ul> <li><strong>Audio features</strong>: the compressed msd_audio_features.tar.gz file contains the low- and high-level features for each track, stored as json files. Please note that we organize all MSD audio feature files based on the track's identifier with one folder holding all tracks with the same first letter of the track identifier to keep the files manageable. For each track, we provide two files: one containing the high-level and one containing the low-level features extracted by Essentia.</li> <li><strong>Billboard data:</strong> the folder billboard_data contains two files: msd_bb_matches.csv contains information about the MSD tracks that were also featured in the Billboard Hot 100 charts. Here, we provide the MSD id, Echo Nest id, artist name, track title, release year, peak position in Billboard charts and the number of weeks in the charts. The second file, msd_bb_non_matches.csv contains meta-information about the tracks of the MSD that were not featured in the Billboard Hot 100 and hence were used as negative samples. Here, we provide the MSD id, Echo Nest id, artist name, track title and the release year.</li> </ul> <p><br> If you make use of the dataset, please kindly cite the following paper:</p> <p>Eva Zangerle, Michael Vötter, Ramona Huber, and Yi-Hsuan Yang. Hit Song Prediction: Leveraging Low- and High-Level Audio Features. In Proceedings of the 20th International Society for Music Information Retrieval Conference 2019 (ISMIR 2019), 2019.</p> <p><br> @inproceedings{zangerle_ismir19,<br> title = {{Hit Song Prediction: Leveraging Low- and High-Level Audio Features}},<br> author = {Eva Zangerle and Ramona Huber and Michael V\"{o}tter and Yi-Hsuan Yang},<br> year = {2019},<br> booktitle = {{Proceedings of the 20th International Society for Music Information Retrieval Conference 2019 (ISMIR 2019)}},<br> }</p>
SLDeep: Statement-Level Software Defect Prediction Using Deep-Learning Models on Static Code Features
<p>Software defect prediction (SDP) seeks to estimate fault-prone areas of the code to focus testing activities on more suspicious portions. Consequently, high-quality software is released with less time and effort. The current SDP techniques however work at coarse-grained units, such as a module or a class, putting some burden on the developers to locate the fault. To address this issue, we propose Statement-Level software defect prediction using Deep-learning model (SLDeep). To reify our proposal, we defined a suite of 32 statement-level metrics, such as the number of binary and unary operators used in a statement. Then, we applied as learning model, long short-term memory (LSTM). The significance of SLDeep for intelligent and expert systems is that it demonstrates a novel use of deep-learning models to the solution of a practical problem faced by software developers. We conducted experiments using more than 100,000 C/C++ programs within the Code4Bench. The programs total 2,356,458 lines of code with 292,064 faulty lines. The benchmark comprises diverse set of programs and versions, written by thousands of developers. Therefore, it tends to give a model that can be used for cross-project SDP. In the experiments, our trained model could successfully classify the unseen data with average performance measures 0.945, 0.971, and 0.976 in terms of recall, precision, and accuracy, respectively. These experimental results suggest that SLDeep is effective for statement-level SDP. The impact of this work is twofold. Working at statement-level further alleviates developer’s burden in pinpointing the fault locations. Second, cross-project feature of SLDeep helps defect prediction research become more industrially-viable</p> <p>for more information visit <a href="https://github.com/sldeep/SLDeep">https://github.com/sldeep/SLDeep</a></p>
Integrated knowledge graphs and embeddings vectors for drug-drug interaction prediction
<p>The associated Knowledge Graphs for predicting potential drug-drug interaction, which is used in our paper titled "Drug-Drug Interaction Prediction Based on Knowledge Graph Embeddings and Convolutional-LSTM Network". Please consider citing the following paper if you plan or used our datasets.</p> <p>Md. Rezaul Karim, Michael Cochez, Joao Bosco Jares, Mamtaz Uddin, Oya Beyan, and Stefan Decker, "Drug-Drug Interaction Prediction Based on Knowledge Graph Embeddings and Convolutional-LSTM Network", In 10th ACM Int’l Conference on Bioinformatics, Computational Biology and Health Informatics (ACM-BCB ’19), September 7–10, 2019, Niagara Falls, NY, USA.</p>
Extended data for the paper "Reliable generation of native-like decoys limits predictive ability in fragment-based protein structure prediction"
<p>Extended data for the paper:<br> Reliable generation of native-like decoys limits predictive ability in fragment-based protein structure prediction</p> <p>Authors:<br> Shaun M Kandathil, Mario Garza-Fabre, Simon C Lovell and Julia Handl</p> <p>--------------------------------</p> <p>Contents of the zip file:</p> <p> </p> <p>Directory 'ECDFplots':<br> ----------------------<br> Data corresponding to Figure 3 for all targets, for the bilevel and ILS protocols. Data are available following stages 3 and 4 of the low-resolution protocol.</p> <p>Directory 'ScoreRMSDplots_3archivers':<br> --------------------------------------<br> Data corresponding to Figures 6 and 9 for all targets. Data corresponding to decoys obtained after low-resolution stages 3 and 4 can be found in subdirectories 'Stage3' and 'Stage4', respectively.<br> </p>
Automatic and feature-specific prediction related neural activity in the human auditory system
<p>Downsampled (to 100Hz) data of the paper "Automatic and feature specific prediction related neural activity in the human auditory system"</p>
Dataset of Paper "Material selection and prediction of solar irradiance in plastic devices for application of solar water disinfection (SODIS) to inactivate viruses, bacteria and protozoa"
<p>Datasets of Paper “Predictive evaluation of solar irradiance in solar disinfection water plastic containers”.</p> <p>Data of the transmission spectra of the polymers: PMMA, PET, PC and PP.</p> <p>Data of the extinction coefficient spectra of the polymers: PMMA, PP, PC and PET.</p> <p>Data of the spectral incident radiation as a function of the thickness for PMMA, PET, PC and PP containers.</p> <p>Data of the spectral incident radiation required for inactivation of <em>MS2</em> virus, <em>E. coli</em> bacteria and <em>C. parvum</em> protozoa in a PMMA, PET, PC and PP containers.</p>
Consumer 'Smart Home' Technology Predictions For 2019
<p>Source: <a href="https://www.forbes.com/sites/moorinsights/2019/01/09/consumer-smart-home-technology-predictions-for-2019/#">https://www.forbes.com/sites/moorinsights/2019/01/09/consumer-smart-home-technology-predictions-for-2019</a></p>
Crop & Progenitor Results Predicted Distributions
<p>Results obtained from using the sdmdl package on the dataset obtained for the 'Crop & Progenitor' case study.</p> <p>For all 52 species in the case study it contains:</p> <p>1) Fully trained model. Serialized to a .h5 file.</p> <p>2) Feature impact graph, showing the 20 most important variables sorted by their impact on the model output (in descending order).</p> <p>3) Raster file, containing the final predicticted distribution. Values are on a scale from 0 to 1, representing the probability of a species presence.</p> <p>4) Illustration map, showing the global predicted distribution of a species.</p>
Virtual tide gauges for predicting relative sea level rise supporting data
<p>Data and results from the publication</p> <p> Hawkins R., Husson L., Choblet G., Bodin T. and Pfeffer J.,<br> "Virtual tide gauges for predicting relative sea level rise",<br> JGR: Solid Earth,<br> 2019 (submitted)<br> </p> <p>Software available from </p> <p>https://github.com/rhyshawkins/TransTessellate2D/</p> <p> </p>
GTEx v8 Elastic Net prediction models
<p>Elastic Net prediction models and LD reference (PrediXcan/MultiXcan support, individual-level or summary-level versions)</p> <p># Data usage policy</p> <p>When using this data, you must acknowledge the source by citing the publication "Widespread dose-dependent effects of RNA expression and splicing on complex diseases and traits" (https://doi.org/10.1101/814350).</p> <p> </p> <p># Disclaimer</p> <p>The data is provided "as is", and the authors assume no responsibility for errors or omissions. <br> The User assumes the entire risk associated with its use of these data. <br> The authors shall not be held liable for any use or misuse of the data described and/or contained herein. <br> The User bears all responsibility in determining whether these data are fit for the User's intended use. </p> <p>The information contained in these data is not better than the original sources from which they were derived,<br> and both scale and accuracy may vary across the data set. <br> These data may not have the accuracy, resolution, completeness, timeliness, or other characteristics<br> appropriate for applications that potential users of the data may contemplate. <br> <br> The user is responsible to comply with any data usage policy from the original GWAS studies;<br> refer to the list of traits described [here](https://www.biorxiv.org/content/10.1101/814350v1)<br> to identify their respective Consortia's requirements.</p> <p><br> THE DATA IS PROVIDED WITHOUT WARRANTY OF ANY KIND,<br> EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,<br> FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.<br> IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,<br> WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,<br> OUT OF OR IN CONNECTION WITH THE DATA OR THE USE OR OTHER DEALINGS IN THE DATA.</p>
On the Performance of Method-Level Bug Prediction: A Negative Result
<p>Bug prediction is aimed at identifying software artifacts that are more likely to be defective in the future. Most approaches defined so far target the prediction of bugs at class/file level. Nevertheless, past research has provided evidence that this granularity is too coarse-grained for its use in practice. As a consequence, researchers have started proposing defect prediction models targeting a finer granularity (particularly method-level granularity), providing promising evidence that it is possible to operate at this level. Particularly, models mixing product and process metrics provided the best results.</p> <p>We present a study in which we first replicate previous research on method-level bug-prediction, by using different systems and timespans. Afterward, based on the limitations of existing research, we (1) re-evaluate method-level bug prediction models more realistically and (2) analyze whether alternative features based on textual aspects, code smells, and developer-related factors can be exploited to improve method-level bug prediction abilities. Key results of our study include that (1) the performance of the previously proposed models, tested using the same strategy but on different systems/timespans, is confirmed; but, (2) when evaluated with a more practical strategy, all the models show a dramatic drop in performance, with results close to that of a random classifier. Finally, we find that (3) the contribution of alternative features within such models is limited and unable to improve the prediction capabilities significantly. As a consequence, our replication and negative results indicate that method-level bug prediction is still an open challenge.</p>
Industry-scale Application and Evaluation of Deep Learning for Drug Target Prediction
<p>Artificial intelligence (AI) is undergoing a revolution thanks to the breakthroughs of machine learning algorithms in computer vision, speech recognition, natural language processing and generative modelling. Recent works on publicly available pharmaceutical data showed that AI methods are highly promising for Drug Target prediction. However, the quality of public data might be different than that of industry data due to different labs reporting measurements, different measurement techniques, fewer samples and less diverse and specialized assays. As part of a European funded project (ExCAPE), that brought together expertise from pharmaceutical industry, machine learning, and high-performance computing, we investigated how well machine learning models obtained from public data can be transferred to internal pharmaceutical industry data. Our results show that machine learning models trained on public data can indeed maintain their predictive power to a large degree when applied to industry data. Moreover, we observed that deep learning derived machine learning models outperformed comparable models, which were trained by other machine learning algorithms, when applied to internal pharmaceutical company datasets. To our knowledge, this is the first large-scale study evaluating the potential of machine learning and especially deep learning directly at the level of industry-scale settings and moreover investigating the transferability of publicly learned target prediction models towards industrial bioactivity prediction pipelines.</p>
Descriptor dataset for predicting interfacial thermal resistance
<p>We present details of the two datasets for the ITR model training and prediction, one is the "ITR dataset" and the other one is the "descriptor dataset" of various materials. The former dataset shows the ITR values of various interfaces with the measuring temperature, synthesized method, thermal measurement method, sample pre-treatment and its original references. The latter dataset shows the physical, chemical and process descriptors of 298 different materials, which are single element or binary compounds. These materials can construct over 80,000 pair-material systems (e.g. Bi/Si) for ITR prediction. Additionally, the total energy for the binding energy can also be found in the "atom_energy_vasp" file. Further, the training data for the ITR machine-learning model are furnished under the file name“training dataset for ITR prediction” and can be directly used as training data for ITR predictions.</p> <p> </p> <p>Descriptor dataset for predicting interfacial thermal resistance is licensed under a <a href="http://creativecommons.org/licenses/by/4.0/">Creative Commons Attribution 4.0 International License</a>.</p>
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.