Çağatay Demiralp

Robert Redmond, Nathan W. Weckwerth, Brian S. Xia et al.

We recently proposed a new cluster operating system stack, DBOS, centered on a DBMS. DBOS enables unique support for ML applications by encapsulating ML code within stored procedures, centralizing ancillary ML data, providing security built into the underlying DBMS, co-locating ML code and data, and tracking data and workflow provenance. Here we demonstrate a subset of these benefits around two ML applications. We first show that image classification and object detection models using GPUs can be served as DBOS stored procedures with performance competitive to existing systems. We then present a 1D CNN trained to detect anomalies in HTTP requests on DBOS-backed web services, achieving SOTA results. We use this model to develop an interactive anomaly detection system and evaluate it through qualitative user feedback, demonstrating its usefulness as a proof of concept for future work to develop learned real-time security services on top of DBOS.

Peter Baile Chen, Fabian Wenz, Yi Zhang et al.

Existing text-to-SQL benchmarks have largely been constructed from web tables with human-generated question-SQL pairs. LLMs typically show strong results on these benchmarks, leading to a belief that LLMs are effective at text-to-SQL tasks. However, how these results transfer to enterprise settings is unclear because tables in enterprise databases might differ substantially from web tables in structure and content. To contend with this problem, we introduce a new dataset BEAVER, the first enterprise text-to-SQL benchmark sourced from real private enterprise data warehouses. This dataset includes natural language queries and their correct SQL statements, which we collected from actual query logs. We then benchmark off-the-shelf LLMs on this dataset. LLMs perform poorly, even when augmented with standard prompt engineering and RAG techniques. We identify three main reasons for the poor performance: (1) schemas of enterprise tables are more complex than the schemas in public data, resulting in SQL-generation tasks intrinsically harder; (2) business-oriented questions are often more complex, requiring joins over multiple tables, aggregations, and nested queries; (3) public LLMs cannot train on private enterprise data warehouses that are not publicly accessible, and therefore it is difficult for the model to learn to solve (1) and (2). We believe BEAVER will facilitate future research in building text-to-SQL systems that perform better in enterprise settings.

Madelon Hulsebos, Paul Groth, Çağatay Demiralp

Understanding the semantics of relational tables is instrumental for automation in data exploration and preparation systems. A key source for understanding a table is the semantics of its columns. With the rise of deep learning, learned table representations are now available, which can be applied for semantic type detection and achieve good performance on benchmarks. Nevertheless, we observe a gap between this performance and its applicability in practice. In this paper, we propose AdaTyper to address one of the most critical deployment challenges: adaptation. AdaTyper uses weak-supervision to adapt a hybrid type predictor towards new semantic types and shifted data distributions at inference time, using minimal human feedback. The hybrid type predictor of AdaTyper combines rule-based methods and a light machine learning model for semantic column type detection. We evaluate the adaptation performance of AdaTyper on real-world database tables hand-annotated with semantic column types through crowdsourcing and find that the f1-score improves for new and existing types. AdaTyper approaches an average precision of 0.6 after only seeing 5 examples, significantly outperforming existing adaptation methods based on human-provided regular expressions or dictionaries.

Çağatay Demiralp, Fabian Wenz, Peter Baile Chen et al.

Large language models (LLMs) know little about enterprise database tables in the private data ecosystem, which substantially differ from web text in structure and content. As LLMs' performance is tied to their training data, a crucial question is how useful they can be in improving enterprise database management and analysis tasks. To address this, we contribute experimental results on LLMs' performance for text-to-SQL and semantic column-type detection tasks on enterprise datasets. The performance of LLMs on enterprise data is significantly lower than on benchmark datasets commonly used. Informed by our findings and feedback from industry practitioners, we identify three fundamental challenges -- latency, cost, and quality -- and propose potential solutions to use LLMs in enterprise data workflows effectively.

Fabian Wenz, Omar Bouattour, Devin Yang et al.

Large language models (LLMs) have been successfully applied to many tasks, including text-to-SQL generation. However, much of this work has focused on publicly available datasets, such as Fiben, Spider, and Bird. Our earlier work showed that LLMs are much less effective in querying large private enterprise data warehouses and released Beaver, the first private enterprise text-to-SQL benchmark. To create Beaver, we leveraged SQL logs, which are often readily available. However, manually annotating these logs to identify which natural language questions they answer is a daunting task. Asking database administrators, who are highly trained experts, to take on additional work to construct and validate corresponding natural language utterances is not only challenging but also quite costly. To address this challenge, we introduce BenchPress, a human-in-the-loop system designed to accelerate the creation of domain-specific text-to-SQL benchmarks. Given a SQL query, BenchPress uses retrieval-augmented generation (RAG) and LLMs to propose multiple natural language descriptions. Human experts then select, rank, or edit these drafts to ensure accuracy and domain alignment. We evaluated BenchPress on annotated enterprise SQL logs, demonstrating that LLM-assisted annotation drastically reduces the time and effort required to create high-quality benchmarks. Our results show that combining human verification with LLM-generated suggestions enhances annotation accuracy, benchmark reliability, and model evaluation robustness. By streamlining the creation of custom benchmarks, BenchPress offers researchers and practitioners a mechanism for assessing text-to-SQL models on a given domain-specific workload. BenchPress is freely available via our public GitHub repository at https://github.com/fabian-wenz/enterprise-txt2sql and is also accessible on our website at http://dsg-mcgraw.csail.mit.edu:5000.

Madelon Hulsebos, Çağatay Demiralp, Paul Groth

The success of deep learning has sparked interest in improving relational table tasks, like data preparation and search, with table representation models trained on large table corpora. Existing table corpora primarily contain tables extracted from HTML pages, limiting the capability to represent offline database tables. To train and evaluate high-capacity models for applications beyond the Web, we need resources with tables that resemble relational database tables. Here we introduce GitTables, a corpus of 1M relational tables extracted from GitHub. Our continuing curation aims at growing the corpus to at least 10M tables. Analyses of GitTables show that its structure, content, and topical coverage differ significantly from existing table corpora. We annotate table columns in GitTables with semantic types, hierarchical relations and descriptions from Schema.org and DBpedia. The evaluation of our annotation pipeline on the T2Dv2 benchmark illustrates that our approach provides results on par with human annotations. We present three applications of GitTables, demonstrating its value for learned semantic type detection models, schema completion methods, and benchmarks for table-to-KG matching, data search, and preparation. We make the corpus and code available at https://gittables.github.io.

Yoshihiko Suhara, Jinfeng Li, Yuliang Li et al.

Inferring meta information about tables, such as column headers or relationships between columns, is an active research topic in data management as we find many tables are missing some of this information. In this paper, we study the problem of annotating table columns (i.e., predicting column types and the relationships between columns) using only information from the table itself. We develop a multi-task learning framework (called Doduo) based on pre-trained language models, which takes the entire table as input and predicts column types/relations using a single model. Experimental results show that Doduo establishes new state-of-the-art performance on two benchmarks for the column type prediction and column relation prediction tasks with up to 4.0% and 11.9% improvements, respectively. We report that Doduo can already outperform the previous state-of-the-art performance with a minimal number of tokens, only 8 tokens per column. We release a toolbox (https://github.com/megagonlabs/doduo) and confirm the effectiveness of Doduo on a real-world data science problem through a case study.

Moe Kayali, Fabian Wenz, Nesime Tatbul et al.

Leading large language models (LLMs) are trained on public data. However, most of the world's data is dark data that is not publicly accessible, mainly in the form of private organizational or enterprise data. We show that the performance of methods based on LLMs seriously degrades when tested on real-world enterprise datasets. Current benchmarks, based on public data, overestimate the performance of LLMs. We release a new benchmark dataset, the GOBY Benchmark, to advance discovery in enterprise data integration. Based on our experience with this enterprise benchmark, we propose techniques to uplift the performance of LLMs on enterprise data, including (1) hierarchical annotation, (2) runtime class-learning, and (3) ontology synthesis. We show that, once these techniques are deployed, the performance on enterprise data becomes on par with that of public data. The Goby benchmark can be obtained at https://goby-benchmark.github.io/.

Sneha Gathani, Madelon Hulsebos, James Gale et al.

The fundamental goal of business data analysis is to improve business decisions using data. Business users often make decisions to achieve key performance indicators (KPIs) such as increasing customer retention or sales, or decreasing costs. To discover the relationship between data attributes hypothesized to be drivers and those corresponding to KPIs of interest, business users currently need to perform lengthy exploratory analyses. This involves considering multitudes of combinations and scenarios and performing slicing, dicing, and transformations on the data accordingly, e.g., analyzing customer retention across quarters of the year or suggesting optimal media channels across strata of customers. However, the increasing complexity of datasets combined with the cognitive limitations of humans makes it challenging to carry over multiple hypotheses, even for simple datasets. Therefore mentally performing such analyses is hard. Existing commercial tools either provide partial solutions or fail to cater to business users altogether. Here we argue for four functionalities to enable business users to interactively learn and reason about the relationships between sets of data attributes thereby facilitating data-driven decision making. We implement these functionalities in SystemD, an interactive visual data analysis system enabling business users to experiment with the data by asking what-if questions. We evaluate the system through three business use cases: marketing mix modeling, customer retention analysis, and deal closing analysis, and report on feedback from multiple business users. Users find the SystemD functionalities highly useful for quick testing and validation of their hypotheses around their KPIs of interest, addressing their unmet analysis needs. The feedback also suggests that the UX design can be enhanced to further improve the understandability of these functionalities.

Madelon Hulsebos, Sneha Gathani, James Gale et al.

Understanding the semantics of tables at scale is crucial for tasks like data integration, preparation, and search. Table understanding methods aim at detecting a table's topic, semantic column types, column relations, or entities. With the rise of deep learning, powerful models have been developed for these tasks with excellent accuracy on benchmarks. However, we observe that there exists a gap between the performance of these models on these benchmarks and their applicability in practice. In this paper, we address the question: what do we need for these models to work in practice? We discuss three challenges of deploying table understanding models and propose a framework to address them. These challenges include 1) difficulty in customizing models to specific domains, 2) lack of training data for typical database tables often found in enterprises, and 3) lack of confidence in the inferences made by models. We present SigmaTyper which implements this framework for the semantic column type detection task. SigmaTyper encapsulates a hybrid model trained on GitTables and integrates a lightweight human-in-the-loop approach to customize the model. Lastly, we highlight avenues for future research that further close the gap towards making table understanding effective in practice.

Dongjin Choi, Sara Evensen, Çağatay Demiralp et al.

Despite rapid developments in the field of machine learning research, collecting high-quality labels for supervised learning remains a bottleneck for many applications. This difficulty is exacerbated by the fact that state-of-the-art models for NLP tasks are becoming deeper and more complex, often increasing the amount of training data required even for fine-tuning. Weak supervision methods, including data programming, address this problem and reduce the cost of label collection by using noisy label sources for supervision. However, until recently, data programming was only accessible to users who knew how to program. To bridge this gap, the Data Programming by Demonstration framework was proposed to facilitate the automatic creation of labeling functions based on a few examples labeled by a domain expert. This framework has proven successful for generating high-accuracy labeling models for document classification. In this work, we extend the DPBD framework to span-level annotation tasks, arguably one of the most time-consuming NLP labeling tasks. We built a novel tool, TagRuler, that makes it easy for annotators to build span-level labeling functions without programming and encourages them to explore trade-offs between different labeling models and active learning strategies. We empirically demonstrated that an annotator could achieve a higher F1 score using the proposed tool compared to manual labeling for different span-level annotation tasks.

James Gale, Max Seiden, Gretchen Atwood et al.

The new generation of cloud data warehouses (CDWs) brings large amounts of data and compute power closer to users in enterprises. The ability to directly access the warehouse data, interactively analyze and explore it at scale can empower users to improve their decision making cycles. However, existing tools for analyzing data in CDWs are either limited in ad-hoc transformations or difficult to use for business users, the largest user segment in enterprises. Here we introduce Sigma Worksheet, a new interactive system that enables users to easily perform ad-hoc visual analysis of data in CDWs at scale. For this, Sigma Worksheet provides an accessible spreadsheet-like interface for data analysis through direct manipulation. Sigma Worksheet dynamically constructs matching SQL queries from user interactions on this familiar interface, building on the versatility and expressivity of SQL. Sigma Worksheet executes constructed queries directly on CDWs, leveraging the superior characteristics of the new generation CDWs, including scalability. To evaluate Sigma Worksheet, we first demonstrate its expressivity through two real life use cases, cohort analysis and sessionization. We then measure the performance of the Worksheet generated queries with a set of experiments using the TPC-H benchmark. Results show the performance of our compiled SQL queries is comparable to that of the reference queries of the benchmark. Finally, to assess the usefulness of Sigma Worksheet in deployment, we elicit feedback through a 100-person survey followed by a semi-structured interview study with 70 participants. We find that Sigma Worksheet is easier to use and learn, improving the productivity of users. Our findings also suggest Sigma Worksheet can further improve user experience by providing guidance to users at various steps of data analysis.

Sajjadur Rahman, Peter Griggs, Çağatay Demiralp

With the increase in scale and availability of digital text generated on the web, enterprises such as online retailers and aggregators often use text analytics to mine and analyze the data to improve their services and products alike. Text data analysis is an iterative, non-linear process with diverse workflows spanning multiple stages, from data cleaning to visualization. Existing text analytics systems usually accommodate a subset of these stages and often fail to address challenges related to data heterogeneity, provenance, workflow reusability and reproducibility, and compatibility with established practices. Based on a set of design considerations we derive from these challenges, we propose Leam, a system that treats the text analysis process as a single continuum by combining advantages of computational notebooks, spreadsheets, and visualization tools. Leam features an interactive user interface for running text analysis workflows, a new data model for managing multiple atomic and composite data types, and an expressive algebra that captures diverse sets of operations representing various stages of text analysis and enables coordination among different components of the system, including data, code, and visualizations. We report our current progress in Leam development while demonstrating its usefulness with usage examples. Finally, we outline a number of enhancements to Leam and identify several research directions for developing an interactive visual text analysis system.

Sara Evensen, Chang Ge, Dongjin Choi et al.

Data programming is a programmatic weak supervision approach to efficiently curate large-scale labeled training data. Writing data programs (labeling functions) requires, however, both programming literacy and domain expertise. Many subject matter experts have neither programming proficiency nor time to effectively write data programs. Furthermore, regardless of one's expertise in coding or machine learning, transferring domain expertise into labeling functions by enumerating rules and thresholds is not only time consuming but also inherently difficult. Here we propose a new framework, data programming by demonstration (DPBD), to generate labeling rules using interactive demonstrations of users. DPBD aims to relieve the burden of writing labeling functions from users, enabling them to focus on higher-level semantics such as identifying relevant signals for labeling tasks. We operationalize our framework with Ruler, an interactive system that synthesizes labeling rules for document classification by using span-level annotations of users on document examples. We compare Ruler with conventional data programming through a user study conducted with 10 data scientists creating labeling functions for sentiment and spam classification tasks. We find that Ruler is easier to use and learn and offers higher overall satisfaction, while providing discriminative model performances comparable to ones achieved by conventional data programming.

Xiong Zhang, Jonathan Engel, Sara Evensen et al.

Reviews are integral to e-commerce services and products. They contain a wealth of information about the opinions and experiences of users, which can help better understand consumer decisions and improve user experience with products and services. Today, data scientists analyze reviews by developing rules and models to extract, aggregate, and understand information embedded in the review text. However, working with thousands of reviews, which are typically noisy incomplete text, can be daunting without proper tools. Here we first contribute results from an interview study that we conducted with fifteen data scientists who work with review text, providing insights into their practices and challenges. Results suggest data scientists need interactive systems for many review analysis tasks. In response we introduce Teddy, an interactive system that enables data scientists to quickly obtain insights from reviews and improve their extraction and modeling pipelines.

Dan Zhang, Yoshihiko Suhara, Jinfeng Li et al.

Detecting the semantic types of data columns in relational tables is important for various data preparation and information retrieval tasks such as data cleaning, schema matching, data discovery, and semantic search. However, existing detection approaches either perform poorly with dirty data, support only a limited number of semantic types, fail to incorporate the table context of columns or rely on large sample sizes for training data. We introduce Sato, a hybrid machine learning model to automatically detect the semantic types of columns in tables, exploiting the signals from the context as well as the column values. Sato combines a deep learning model trained on a large-scale table corpus with topic modeling and structured prediction to achieve support-weighted and macro average F1 scores of 0.925 and 0.735, respectively, exceeding the state-of-the-art performance by a significant margin. We extensively analyze the overall and per-type performance of Sato, discussing how individual modeling components, as well as feature categories, contribute to its performance.

Madelon Hulsebos, Kevin Hu, Michiel Bakker et al.

Correctly detecting the semantic type of data columns is crucial for data science tasks such as automated data cleaning, schema matching, and data discovery. Existing data preparation and analysis systems rely on dictionary lookups and regular expression matching to detect semantic types. However, these matching-based approaches often are not robust to dirty data and only detect a limited number of types. We introduce Sherlock, a multi-input deep neural network for detecting semantic types. We train Sherlock on $686,765$ data columns retrieved from the VizNet corpus by matching $78$ semantic types from DBpedia to column headers. We characterize each matched column with $1,588$ features describing the statistical properties, character distributions, word embeddings, and paragraph vectors of column values. Sherlock achieves a support-weighted F$_1$ score of $0.89$, exceeding that of machine learning baselines, dictionary and regular expression benchmarks, and the consensus of crowdsourced annotations.

Wenbo Tao, Xiaoyu Liu, Çağatay Demiralp et al.

Scalable interactive visual data exploration is crucial in many domains due to increasingly large datasets generated at rapid rates. Details-on-demand provides a useful interaction paradigm for exploring large datasets, where users start at an overview, find regions of interest, zoom in to see detailed views, zoom out and then repeat. This paradigm is the primary user interaction mode of widely-used systems such as Google Maps, Aperture Tiles and ForeCache. These earlier systems, however, are highly customized with hardcoded visual representations and optimizations. A more general framework is needed to facilitate the development of visual data exploration systems at scale. In this paper, we present Kyrix, an end-to-end system for developing scalable details-on-demand data exploration applications. Kyrix provides developers with a declarative model for easy specification of general visualizations. Behind the scenes, Kyrix utilizes a suite of performance optimization techniques to achieve a response time within 500ms for various user interactions. We also report results from a performance study which shows that a novel dynamic fetching scheme adopted by Kyrix outperforms tile-based fetching used in earlier systems.

Kevin Hu, Neil Gaikwad, Michiel Bakker et al.

Researchers currently rely on ad hoc datasets to train automated visualization tools and evaluate the effectiveness of visualization designs. These exemplars often lack the characteristics of real-world datasets, and their one-off nature makes it difficult to compare different techniques. In this paper, we present VizNet: a large-scale corpus of over 31 million datasets compiled from open data repositories and online visualization galleries. On average, these datasets comprise 17 records over 3 dimensions and across the corpus, we find 51% of the dimensions record categorical data, 44% quantitative, and only 5% temporal. VizNet provides the necessary common baseline for comparing visualization design techniques, and developing benchmark models and algorithms for automating visual analysis. To demonstrate VizNet's utility as a platform for conducting online crowdsourced experiments at scale, we replicate a prior study assessing the influence of user task and data distribution on visual encoding effectiveness, and extend it by considering an additional task: outlier detection. To contend with running such studies at scale, we demonstrate how a metric of perceptual effectiveness can be learned from experimental results, and show its predictive power across test datasets.

Marco Cavallo, Çağatay Demiralp

Dimensionality reduction is a common method for analyzing and visualizing high-dimensional data. However, reasoning dynamically about the results of a dimensionality reduction is difficult. Dimensionality-reduction algorithms use complex optimizations to reduce the number of dimensions of a dataset, but these new dimensions often lack a clear relation to the initial data dimensions, thus making them difficult to interpret. Here we propose a visual interaction framework to improve dimensionality-reduction based exploratory data analysis. We introduce two interaction techniques, forward projection and backward projection, for dynamically reasoning about dimensionally reduced data. We also contribute two visualization techniques, prolines and feasibility maps, to facilitate the effective use of the proposed interactions. We apply our framework to PCA and autoencoder-based dimensionality reductions. Through data-exploration examples, we demonstrate how our visual interactions can improve the use of dimensionality reduction in exploratory data analysis.

Selim Kalaycı, Çağatay Demiralp, Zeynep H. Gümüş

Precision oncology tests that profile tumors to identify clinically actionable targets have rapidly entered clinical practice. Effective visual presentation of the results of these tests is crucial in accurate clinical decision-making. In current practice, these results are typically delivered to oncologists as static prints, who then incorporate them into their clinical decision-making process. However, due to a lack of guidelines for standardization, different vendors use different report formats. There is very little known on the effectiveness of these report formats or the criteria necessary to improve them. In this study, we have aimed to identify both the tasks and the needs of oncologists from precision oncology report design and then to improve the designs based on these findings. To this end, we report results from multiple interviews and a survey study (n=32) conducted with practicing oncologists. Based on these results, we compiled a set of design criteria for precision oncology reports and developed a prototype report design using these criteria, along with feedback from oncologists.

Marco Cavallo, Çağatay Demiralp

With the rapid commoditization of wearable sensors, detecting human movements from sensor datasets has become increasingly common over a wide range of applications. To detect activities, data scientists iteratively experiment with different classifiers before deciding which model to deploy. Effective reasoning about and comparison of alternative classifiers are crucial in successful model development. This is, however, inherently difficult in developing classifiers for sensor data, where the intricacy of long temporal sequences, high prediction frequency, and imprecise labeling make standard evaluation methods relatively ineffective and even misleading. We introduce Track Xplorer, an interactive visualization system to query, analyze, and compare the predictions of sensor-data classifiers. Track Xplorer enables users to interactively explore and compare the results of different classifiers, and assess their accuracy with respect to the ground-truth labels and video. Through integration with a version control system, Track Xplorer supports tracking of models and their parameters without additional workload on model developers. Track Xplorer also contributes an extensible algebra over track representations to filter, compose, and compare classification outputs, enabling users to reason effectively about classifier performance. We apply Track Xplorer in a collaborative project to develop classifiers to detect movements from multisensor data gathered from Parkinson's disease patients. We demonstrate how Track Xplorer helps identify early on possible systemic data errors, effectively track and compare the results of different classifiers, and reason about and pinpoint the causes of misclassifications.

Victor Dibia, Çağatay Demiralp

Rapidly creating effective visualizations using expressive grammars is challenging for users who have limited time and limited skills in statistics and data visualization. Even high-level, dedicated visualization tools often require users to manually select among data attributes, decide which transformations to apply, and specify mappings between visual encoding variables and raw or transformed attributes. In this paper we introduce Data2Vis, a neural translation model for automatically generating visualizations from given datasets. We formulate visualization generation as a sequence to sequence translation problem where data specifications are mapped to visualization specifications in a declarative language (Vega-Lite). To this end, we train a multilayered attention-based recurrent neural network (RNN) with long short-term memory (LSTM) units on a corpus of visualization specifications. Qualitative results show that our model learns the vocabulary and syntax for a valid visualization specification, appropriate transformations (count, bins, mean) and how to use common data selection patterns that occur within data visualizations. Data2Vis generates visualizations that are comparable to manually-created visualizations in a fraction of the time, with potential to learn more complex visualization strategies at scale.

Marco Cavallo, Çağatay Demiralp

Data clustering is a common unsupervised learning method frequently used in exploratory data analysis. However, identifying relevant structures in unlabeled, high-dimensional data is nontrivial, requiring iterative experimentation with clustering parameters as well as data features and instances. The number of possible clusterings for a typical dataset is vast, and navigating in this vast space is also challenging. The absence of ground-truth labels makes it impossible to define an optimal solution, thus requiring user judgment to establish what can be considered a satisfiable clustering result. Data scientists need adequate interactive tools to effectively explore and navigate the large clustering space so as to improve the effectiveness of exploratory clustering analysis. We introduce \textit{Clustrophile~2}, a new interactive tool for guided clustering analysis. \textit{Clustrophile~2} guides users in clustering-based exploratory analysis, adapts user feedback to improve user guidance, facilitates the interpretation of clusters, and helps quickly reason about differences between clusterings. To this end, \textit{Clustrophile~2} contributes a novel feature, the Clustering Tour, to help users choose clustering parameters and assess the quality of different clustering results in relation to current analysis goals and user expectations. We evaluate \textit{Clustrophile~2} through a user study with 12 data scientists, who used our tool to explore and interpret sub-cohorts in a dataset of Parkinson's disease patients. Results suggest that \textit{Clustrophile~2} improves the speed and effectiveness of exploratory clustering analysis for both experts and non-experts.

Çağatay Demiralp

While clustering is one of the most popular methods for data mining, analysts lack adequate tools for quick, iterative clustering analysis, which is essential for hypothesis generation and data reasoning. We introduce Clustrophile, an interactive tool for iteratively computing discrete and continuous data clusters, rapidly exploring different choices of clustering parameters, and reasoning about clustering instances in relation to data dimensions. Clustrophile combines three basic visualizations -- a table of raw datasets, a scatter plot of planar projections, and a matrix diagram (heatmap) of discrete clusterings -- through interaction and intermediate visual encoding. Clustrophile also contributes two spatial interaction techniques, $\textit{forward projection}$ and $\textit{backward projection}$, and a visualization method, $\textit{prolines}$, for reasoning about two-dimensional projections obtained through dimensionality reductions.

Marco Cavallo, Çağatay Demiralp

Detecting motor activities from sensor datasets is becoming increasingly common in a wide range of applications with the rapid commoditization of wearable sensors. To detect activities, data scientists iteratively experiment with different classifiers before deciding on a single model. Evaluating, comparing, and reasoning about prediction results of alternative classifiers is a crucial step in the process of iterative model development. However, standard aggregate performance metrics (such as accuracy score) and textual display of individual event sequences have limited granularity and scalability to effectively perform this critical step. To ameliorate these limitations, we introduce Track Xplorer, an interactive visualization system to query, analyze and compare the classification output of activity detection in multi-sensor data. Track Xplorer visualizes the results of different classifiers as well as the ground truth labels and the video of activities as temporally-aligned linear tracks. Through coordinated track visualizations, Track Xplorer enables users to interactively explore and compare the results of different classifiers, assess their accuracy with respect to the ground truth labels and video. Users can brush arbitrary regions of any classifier track, zoom in and out with ease, and playback the corresponding video segment to contextualize the performance of the classifier within the selected region. Track Xplorer also contributes an algebra over track representations to filter, compose, and compare classification outputs, enabling users to effectively reason about the performance of classifiers. We demonstrate how our tool helps data scientists debug misclassifications and improve the prediction performance in developing activity classifiers for real-world, multi-sensor data gathered from Parkinson's patients.

Çağatay Demiralp, Peter J. Haas, Srinivasan Parthasarathy et al.

Current tools for exploratory data analysis (EDA) require users to manually select data attributes, statistical computations and visual encodings. This can be daunting for large-scale, complex data. We introduce Foresight, a visualization recommender system that helps the user rapidly explore large high-dimensional datasets through "guideposts." A guidepost is a visualization corresponding to a pronounced instance of a statistical descriptor of the underlying data, such as a strong linear correlation between two attributes, high skewness or concentration about the mean of a single attribute, or a strong clustering of values. For each descriptor, Foresight initially presents visualizations of the "strongest" instances, based on an appropriate ranking metric. Given these initial guideposts, the user can then look at "nearby" guideposts by issuing "guidepost queries" containing constraints on metric type, metric strength, data attributes, and data values. Thus, the user can directly explore the network of guideposts, rather than the overwhelming space of data attributes and visual encodings. Foresight also provides for each descriptor a global visualization of ranking-metric values to both help orient the user and ensure a thorough exploration process. Foresight facilitates interactive exploration of large datasets using fast, approximate sketching to compute ranking metrics. We also contribute insights on EDA practices of data scientists, summarizing results from an interview study we conducted to inform the design of Foresight.

Marco Cavallo, Çağatay Demiralp

Dimensionality reduction is a common method for analyzing and visualizing high-dimensional data across domains. Dimensionality-reduction algorithms involve complex optimizations and the reduced dimensions computed by these algorithms generally lack clear relation to the initial data dimensions. Therefore, interpreting and reasoning about dimensionality reductions can be difficult. In this work, we introduce two interaction techniques, \textit{forward projection} and \textit{backward projection}, for reasoning dynamically about scatter plots of dimensionally reduced data. We also contribute two related visualization techniques, \textit{prolines} and \textit{feasibility map} to facilitate and enrich the effective use of the proposed interactions, which we integrate in a new tool called \textit{Praxis}. To evaluate our techniques, we first analyze their time and accuracy performance across varying sample and dimension sizes. We then conduct a user study in which twelve data scientists use \textit{Praxis} so as to assess the usefulness of the techniques in performing exploratory data analysis tasks. Results suggest that our visual interactions are intuitive and effective for exploring dimensionality reductions and generating hypotheses about the underlying data.