Yellowbrick V0.6

Bengfort, Benjamin; Danielsen, Nathan; Bilbro, Rebecca; Gray, Larry; McIntyre, Kristen; Richardson, G. B.; Miller, Taylor; Mayfield, Gary; Schafer, Phillip; Keung, Jason

doi:10.5281/zenodo.1206264

Cited by 19 publications

(11 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The lower the optimal number of clusters, the more concise and specific the stream is. To find the optimal number of clusters (k), we used the elbow method Bengfort et al (2018); Susan & Malhotra (2020). Where the optimal number of clusters is represented in a graph as is an inflection point (elbow) using the average distortion score.…”

Section: Discussionmentioning

confidence: 99%

Proactive Query Expansion for Streaming Data Using External Source

Alshanik¹,

Apon²,

Du³

et al. 2022

Preprint

View full text Add to dashboard Cite

Query expansion is the process of reformulating the original query by adding relevant words. Choosing which terms to add in order to improve the performance of the query expansion methods or to enhance the quality of the retrieved results is an important aspect of any information retrieval system. Adding words that can positively impact the quality of the search query or are informative enough play an important role in returning or gathering relevant documents that cover a certain topic can result in improving the efficiency of the information retrieval system. Typically, query expansion techniques are used to add or substitute words to a given search query to collect relevant data. In this paper, we design and implement a pipeline of automated query expansion. We outline several tools using different methods to expand the query. Our methods depend on targeting emergent events in streaming data over time and finding the hidden topics from targeted documents using probabilistic topic models. We employ Dynamic Eigenvector Centrality to trigger the emergent events, and the Latent Dirichlet Allocation to discover the topics. Also, we use an external data source as a secondary stream to supplement the primary stream with relevant words and expand the query using the words from both primary and secondary streams. An experimental study is performed on Twitter data (primary stream) related to the events that happened during protests in Baltimore in 2015. The quality of the retrieved results was measured using a quality indicator of the streaming data: tweets count, hashtag count, and hashtag clustering. Results indicate that adding words from the secondary stream can significantly improve the quality of search queries and return more relevant information that covers a certain topic. Another experimental study is performed to measure the effectiveness of the proposed methods to predict future emerging events or to predict the conversations from previous time intervals using the precision of a different set of hashtags. Results show that our method increases the precision.Reproducibility: code and results are available at https://github.com/FarahAlshanik/QE

show abstract

Section: Discussionmentioning

confidence: 99%

Proactive Query Expansion for Streaming Data Using External Source

Alshanik¹,

Apon²,

Du³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Python, specifically version 3.7, was chosen as the programming language due to the availability of existing libraries and other resources for data management, machine vision, and machine learning. The Python packages used in the development of the program were as follows: Imutils [ 17 ], MatplotLib [ 18 ], NumPy [ 19 ], OpenCV [ 20 ], pandas [ 21 ], PIMS [ 22 ], scikit-learn [ 23 ], SciPy [ 24 ], and Yellowbrick [ 25 ].…”

Section: Methodsmentioning

confidence: 99%

Deterministic Lateral Displacement (DLD) Analysis Tool Utilizing Machine Learning towards High-Throughput Separation

et al. 2022

View full text Add to dashboard Cite

Deterministic lateral displacement (DLD) is a microfluidic method for the continuous separation of particles based on their size. There is growing interest in using DLD for harvesting circulating tumor cells from blood for further assays due to its low cost and robustness. While DLD is a powerful tool and development of high-throughput DLD separation devices holds great promise in cancer diagnostics and therapeutics, much of the experimental data analysis in DLD research still relies on error-prone and time-consuming manual processes. There is a strong need to automate data analysis in microfluidic devices to reduce human errors and the manual processing time. In this work, a reliable particle detection method is developed as the basis for the DLD separation analysis. Python and its available packages are used for machine vision techniques, along with existing identification methods and machine learning models. Three machine learning techniques are implemented and compared in the determination of the DLD separation mode. The program provides a significant reduction in video analysis time in DLD separation, achieving an overall particle detection accuracy of 97.86% with an average computation time of 25.274 s.

show abstract

“…The samples were grouped into classes depending on the task of the binary classification, e.g., for the model to classify CDI+ vs CDI-, the CDI- class consisted of samples from the CDI-/ABX- and the CDI-/ABX+ human subjects; for the model to classify ABX+ vs ABX-, the ABX+ class included samples from the CDI+ and the CDI-/ABX+ subjects, the ABX- class consisted of only samples from the CDI-/ABX- subjects. We used LASSO-LR using the LogisticRegressionCV module in the sk-learn and Yellowbrick 80 python packages. 43 Hyper-parameters tuning and optimization were done using gridSearchCV with a 5-CV.…”

Section: Machine Learning Analysesmentioning

confidence: 99%

Functional profile of host microbiome indicates Clostridioides difficile infection

Nzabarushimana

Tang

2022

Gut Microbes

View full text Add to dashboard Cite

Clostridioides difficile infection (CDI) is a gastro-intestinal (GI) infection that illustrates how perturbations in symbiotic host–microbiome interactions render the GI tract vulnerable to the opportunistic pathogens. CDI also serves as an example of how such perturbations could be reversed via gut microbiota modulation mechanisms, especially fecal microbiota transplantation (FMT). However, microbiome-mediated diagnosis of CDI remains understudied. Here, we evaluated the diagnostic capabilities of the fecal microbiome on the prediction of CDI. We used the metagenomic sequencing data from ten previous studies, encompassing those acquired from CDI patients treated by FMT, CDI-negative patients presenting other intestinal health conditions, and healthy volunteers taking antibiotics. We designed a hybrid species/function profiling approach that determines the abundances of microbial species in the community contributing to its functional profile. These functionally informed taxonomic profiles were then used for classification of the microbial samples. We used logistic regression (LR) models using these features, which showed high prediction accuracy (with an average ), substantiating that the species/function composition of the gut microbiome has a robust diagnostic prediction of CDI. We further assessed the confounding impact of antibiotic therapy on CDI prediction and found that it is distinguishable from the CDI impact. Finally, we devised a log-odds score computed from the output of the LR models to quantify the likelihood of CDI in a gut microbiome sample and applied it to evaluating the effectiveness of FMT based on post-FMT microbiome samples. The results showed that the gut microbiome of patients exhibited a gradual but steady improvement after receiving successful FMT, indicating the restoration of the normal microbiome functions.

show abstract

Yellowbrick V0.6

Cited by 19 publications

References 0 publications

Proactive Query Expansion for Streaming Data Using External Source

Proactive Query Expansion for Streaming Data Using External Source

Deterministic Lateral Displacement (DLD) Analysis Tool Utilizing Machine Learning towards High-Throughput Separation

Functional profile of host microbiome indicates Clostridioides difficile infection

Contact Info

Product

Resources

About