In this project, I conducted a comprehensive analysis of customer data using Power BI. The objective was to visualize and gain insights from the data, focusing on customer demographics and product categories.

📈The analysis includes the following key visualizations:

Customer Distribution by Age: illustrates the number of customers across different age groups, providing insights into the demographic distribution.

Customer Distribution by Time: This visualization shows the count of customers segmented by year, quarter, month, and day, helping identify trends over time.

Customer Distribution by Gender: displays the distribution of customers by gender, highlighting any significant differences.

Total Amount by Product Category: depicts the total revenue generated by each product category, allowing for easy comparison.

Quantity by Product Category: shows the total quantity of products sold in each category, helping to identify popular items.

The cards display key metrics:

Average Age: 41.39 Total Customers: 1000 Total Quantity Sold: 2514 Total Amount Sold: 465 000$ Total Transactions: 1000 Additionally, I implemented filters for product category, date, gender, quantity, and age, providing users with the ability to refine their analysis.

Findings:

The analysis of customer distribution by age reveals no specific relationship between age and the quantity of products sold. This indicates that purchasing behavior may not be strongly influenced by the customer’s age. There are notable peaks in the quantity sold on May 20, 2023, and again in July, suggesting higher purchasing activity during these periods. The customer distribution by gender shows that 49% of customers are female, while 51% are male. In terms of total amount sold by product category, electronics is the top category, generating the highest revenue, followed by clothing, with beauty ranking last. Similarly, when looking at quantity sold by product category, electronics makes up 33.77%, clothing is slightly higher at 35.56%, and beauty is the smallest category at 3.67%. This project demonstrates the power of Power BI in analyzing customer data and deriving actionable insights. The visualizations created provide a clear understanding of customer behavior and preferences, which can help businesses make informed decisions.

To create the dataset, the top 10 countries leading in the incidence of COVID-19 in the world were selected as of October 22, 2020 (on the eve of the second full of pandemics), which are presented in the Global 500 ranking for 2020: USA, India, Brazil, Russia, Spain, France and Mexico. For each of these countries, no more than 10 of the largest transnational corporations included in the Global 500 rating for 2020 and 2019 were selected separately. The arithmetic averages were calculated and the change (increase) in indicators such as profitability and profitability of enterprises, their ranking position (competitiveness), asset value and number of employees. The arithmetic mean values of these indicators for all countries of the sample were found, characterizing the situation in international entrepreneurship as a whole in the context of the COVID-19 crisis in 2020 on the eve of the second wave of the pandemic. The data is collected in a general Microsoft Excel table. Dataset is a unique database that combines COVID-19 statistics and entrepreneurship statistics. The dataset is flexible data that can be supplemented with data from other countries and newer statistics on the COVID-19 pandemic. Due to the fact that the data in the dataset are not ready-made numbers, but formulas, when adding and / or changing the values in the original table at the beginning of the dataset, most of the subsequent tables will be automatically recalculated and the graphs will be updated. This allows the dataset to be used not just as an array of data, but as an analytical tool for automating scientific research on the impact of the COVID-19 pandemic and crisis on international entrepreneurship. The dataset includes not only tabular data, but also charts that provide data visualization. The dataset contains not only actual, but also forecast data on morbidity and mortality from COVID-19 for the period of the second wave of the pandemic in 2020. The forecasts are presented in the form of a normal distribution of predicted values and the probability of their occurrence in practice. This allows for a broad scenario analysis of the impact of the COVID-19 pandemic and crisis on international entrepreneurship, substituting various predicted morbidity and mortality rates in risk assessment tables and obtaining automatically calculated consequences (changes) on the characteristics of international entrepreneurship. It is also possible to substitute the actual values identified in the process and following the results of the second wave of the pandemic to check the reliability of pre-made forecasts and conduct a plan-fact analysis. The dataset contains not only the numerical values of the initial and predicted values of the set of studied indicators, but also their qualitative interpretation, reflecting the presence and level of risks of a pandemic and COVID-19 crisis for international entrepreneurship.

Traditionally, zoning plans have been represented on a 2D map. However, visualizing a zoning plan in 2D has several limitations, such as visualizing heights of buildings. Furthermore, a zoning plan is abstract, which for citizens can be hard to interpret. Therefore, the goal of this research is to explore how a zoning plan can be visualized in 3D and how it can be visualized it is understandable for the public. The 3D visualization of a zoning plan is applied in a case study, presented in Google Earth, and a survey is executed to verify how the respondents perceive the zoning plan from the case study. An important factor of zoning plans is interpretation, since it determines if the public is able to understand what is visualized by the zoning plan. This is challenging, since a zoning plan is abstract and consists of many detailed information and difficult terms. In the case study several techniques are used to visualize the zoning plan in 3D. The survey shows that visualizing heights in 3D gives a good impression of the maximum heights and is considered as an important advantage in comparison to 2D. The survey also made clear including existing buildings is useful, which can help that the public can recognize the area easier. Another important factor is interactivity. Interactivity can range from letting people navigate through a zoning plan area and in the case study users can click on a certain area or object in the plan and subsequently a menu pops up showing more detailed information of a certain object. The survey made clear that using a popup menu is useful, but this technique did not optimally work. Navigating in Google Earth was also being positively judged. Information intensity is also an important factor Information intensity concerns the level of detail of a 3D representation of an object. Zoning plans are generally not meant to be visualized in a high level of detail, but should be represented abstract. The survey could not implicitly point out that the zoning plan shows too much or too less detail, but it could point out that the majority of the respondents answered that the zoning plan does not show too much information. The interface used for the case study, Google Earth, has a substantial influence on the interpretation of the zoning plan. The legend in Google Earth is unclear and an explanation of the zoning plan is lacking, which is required to make the zoning plan more understandable. This research has shown that 3D can stimulate the interpretation of zoning plans, because users can get a better impression of the plan and is clearer than a current 2D zoning plan. However, the interpretation of a zoning plan, even in 3D, still is complex.

Dataset

This dataset was created by Ighotegunor Great

Contents

Analysis of ‘Adoptable Dogs’ provided by Analyst-2 (analyst-2.ai), based on source dataset retrieved from https://www.kaggle.com/jmolitoris/adoptable-dogs on 13 February 2022.

--- Dataset description provided by original source is as follows ---

Context

This dataset was created when I practiced webscraping.

Content

The data is a compilation of information on dogs who were available for adoption on December 12, 2019 in the Hungarian Database of Homeless Pets. In total, there were 2,937 dogs in the database. It contains information on dogs' names, breed, color, age, sex, the date they were found, and some characteristics of their personalities.

Inspiration

I thought it would be interesting to have a dataset that looks at adoptable dogs' characteristics. It is not really well-suited for prediction, but could be a good practice dataset for data visualization and working with categorical data.

--- Original source retains full ownership of the source dataset ---

This dynamic World Elevation TopoBathy service combines topography (land elevation) and bathymetry (water depths) around the world. Heights are based on multiple sources and are orthometric (sea level = 0, and bathymetric values are negative downward from sea level). The source data of land elevation in this service is same as in the Terrain layer. When possible, the water areas are represented by the best available bathymetry. What can you do with this layer?Use for Visualization: This layer is generally not optimal for direct visualization. By default, 32 bit floating point values are returned, resulting in higher bandwidth requirements. Therefore, usage should be limited to applications requiring elevation data values. Alternatively, client applications can select additional functions, applied on the server, that return rendered data. For visualizations such as hillshade or elevation tinted hillshade, consider using the appropriate server-side function defined on this service. Use for Analysis: Yes. This layer provides data as floating point elevation values suitable for use in analysis. NOTE: This image services combine data from different sources and resample the data dynamically to the requested projection, extent and pixel size. For analyses using ArcGIS Desktop, you can filter a dataset, specify the projection, extent and cell size using the Make Image Server Layer geoprocessing tool. Server Functions: This layer has server functions defined for the following elevation derivatives. In ArcGIS desktop, server function can be invoked from Layer Properties - Processing Templates.

Slope Degrees Slope Percentage Hillshade Multi-Directional Hillshade Elevation Tinted HillshadeSlope MapData Sources and Coverage: This layer is compiled from a variety of best available sources from several data providers. To see the coverage and extents of various datasets comprising this service in an interactive map, see Elevation Coverage Map.Mosaic Method: This image service uses a default mosaic method of "By Attribute”, using Field 'Best' and target of 0. Each of the rasters has been attributed with ‘Best’ field value that is generally a function of the pixel size such that higher resolution datasets are displayed at higher priority. Other mosaic methods can be set, but care should be taken as the order of the rasters may change. Where required, queries can also be set to display only specific datasets such as only NED or the lock raster mosaic rule used to lock to a specific dataset.Accuracy: The accuracy of these services will vary as a function of location and data source. Please refer to the metadata available in the services, and follow the links to the original sources for further details. An estimate of CE90 and LE90 is included as attributes, where available.This layer allows query, identify, and export image requests. The layer is restricted to a 5,000 x 5,000 pixel limit in a single request. This layer is part of a larger collection of elevation layers that you can use to perform a variety of mapping analysis tasks.Disclaimer: Bathymetry data sources are not to be used for navigation/safety at sea.

Additional file 1. Example of chromoMap interactive plot constructed using various features of chromoMap including polyploidy (used as multi-track), feature-associated data visualization (scatter and bar plots), chromosome heatmaps, data filters (color-coded scatter and bars). Differential gene expression in a cohort of patients positive for COVID19 and healthy individuals (NCBI Gene Expression Omnibus id: GSE162835) [12]. Each set of five tracks labeled with the same chromosome ID (e.g. 1-22, X & Y) contains the following information: From top to bottom: (1) number of differentially expressed genes (DEGs) (FDR < 0.05) (bars over the chromosome depictions) per genomic window (green boxes within the chromosome). Windows containing ≥ 5 DEGs are shown in yellow. (2) DEGs (FDR < 0.05) between healthy individuals and patients positive for COVID19 visualized as a scatterplot above the chromosome depiction (genes with logFC ≥ 2 or logFC ≤ −2 are highlighted in orange). Dots above the grey dashed line represent upregulated genes in COVID19 positive patients. Heatmap within chromosome depictions indicates the average LogFC value per window. (3–4) Normalized expression of differentially expressed genes (scatterplot) and of each genomic window containing DEG (green scale heatmap) in (3) patients with severe/critical outcomes and (4) asymptomatic/mild outcome patients. (5) logFC of DEGs between healthy individuals and patients positive for COVID19 visualized as scatter plot color-coded based on the metabolic pathway each DEG belongs to.

Context

PromptCloud and DataStock extracted this data from Booking.com to find out the rates and prices and states hotels were available for the period of 1 year from December 2018 to December 2019. This is a sample dataset of 30K records.

You can download the full dataset here

Content

This dataset was procured to give knowledge about the various hotels that are present on Booking.com. This dataset will be helpful for the researchers and students who want these type of specific datasets that can be used for various case studies and projects based on different hotels across the globe that is available on booking.com

The Data Fields That This File Contain Are: Root Folders 456 Root Folders Each Root Folder Contains - Uniq_ID - Hotel_ID - Hotel_Name - Review_Count - Default_Rank - Price_Rank - OTA

Acknowledgements

This dataset was created by PromptCloud's In-House Data Crawling Team

Inspiration

We want users to use clean and raw data which will help them gain access to knowledge about different sites and help them in their various projects or research that they might conduct. We want our customers to feel that they can depend on datasets like this from us and that is what drives us. Customer satisfaction is our main priority and we only wish the best for them and they keep us going.### Context

PromptCloud and DataStock extracted this data from Booking.com to find out the rates and prices and states hotels were available for the time period of 1 year from December 2018 to December 2019. This is a sample dataset of 30K records.

You can download the full dataset here

Content

This dataset was procured to give knowledge about the various hotels that are present on Booking.com. This dataset will be helpful for the researchers and students who want these type of specific datasets that can be used for various case studies and projects based on different hotels across the globe that is available on booking.com

The Data Fields That This File Contain Are: Root Folders 456 Root Folders Each Root Folder Contains - Uniq_ID - Hotel_ID - Hotel_Name - Review_Count - Default_Rank - Price_Rank - OTA

Acknowledgements

This dataset was created by PromptCloud's In-House Data Crawling Team

Inspiration

We want users to use clean and raw data which will help them gain access to knowledge about different sites and help them in their various projects or research that they might conduct. We want our customers to feel that they can depend on datasets like this from us and that is what drives us. Customer satisfaction is our main priority and we only wish the best for them and they keep us going.

description: Resources for Advanced Data Analysis and VisualizationResearchers who have access to the latest analysis and visualization tools are able to use large amounts of complex data to find efficiencies in projects, designs, and resources. The Data Analysis and Assessment Center (DAAC) at ERDC's Information Technology Laboratory (ITL) provides visualization and analysis tools and support services to enable the analysis of an ever-increasing volume of data.Simplify Data Analysis and Visualization ResearchThe resources provided by the DAAC enable any user to conduct important data analysis and visualization that provides valuable insight into projects and designs and helps to find ways to save resources. The DAAC provides new tools like ezVIZ, and services such as the DAAC website, a rich resource of news about the DAAC, training materials, a community forum and tutorials on how to use data analysis and other issues.The DAAC can perform collaborative work when users prefer to do the work themselves but need help in choosing which visualization program and/or technique and using the visualization tools. The DAAC also carries out custom projects to produce high-quality animations of data, such as movies, which allow researchers to communicate their results to others.Communicate Research in ContextDAAC provides leading animation and modeling software which allows scientists and researchers may communicate all aspects of their research by setting their results in context through conceptual visualization and data analysis.Success StoriesWave Breaking and Associated Droplet and Bubble FormationWave breaking and associated droplet and bubble formation are among the most challenging problems in the field of free-surface hydrodynamics. The method of computational fluid dynamics (CFD) was used to solve this problem numerically for flow about naval vessels. The researchers wanted to animate the time-varying three-dimensional data sets using isosurfaces, but transferring the data back to the local site was a problem because the data sets were large. The DAAC visualization team solved the problem by using EnSight and ezVIZ to generate the isosurfaces, and photorealistic rendering software to produce the images for the animation.Explosive Structure Interaction Effects in Urban TerrainKnown as the Breaching Project, this research studied the effects of high-explosive (HE) charges on brick or reinforced concrete walls. The results of this research will enable the war fighter to breach a wall to enter a building where enemy forces are conducting operations against U.S. interests. Images produced show computed damaged caused by an HE charge on the outer and inner sides of a reinforced concrete wall. The ability to quickly and meaningfully analyze large simulation data sets helps guide further development of new HE package designs and better ways to deploy the HE packages. A large number of designs can be simulated and analyzed to find the best at breaching the wall. The project saves money in greatly reduced field test costs by testing only the designs which were identified in analysis as the best performers.SpecificationsAmethyst, the seven-node Linux visualization cluster housed at the DAAC, is supported by ParaView, EnSight, and ezViz visualization tools and configured as follows:Six computer nodes, each with the following specifications:CPU: 8 dual-core 2.4 Ghz, 64-bit AMD Opteron Processors (16 effective cores)Memory: 128-G RAMVideo: NVidia Quadro 5500 1-GB memoryNetwork: Infiniband Interconnect between nodes, and Gigabit Ethernet to Defense Research and Engineering Network (DREN)One storage node:Disk Space: 20-TB TerraGrid file system, mounted on all nodes as /viz and /work; abstract: Resources for Advanced Data Analysis and VisualizationResearchers who have access to the latest analysis and visualization tools are able to use large amounts of complex data to find efficiencies in projects, designs, and resources. The Data Analysis and Assessment Center (DAAC) at ERDC's Information Technology Laboratory (ITL) provides visualization and analysis tools and support services to enable the analysis of an ever-increasing volume of data.Simplify Data Analysis and Visualization ResearchThe resources provided by the DAAC enable any user to conduct important data analysis and visualization that provides valuable insight into projects and designs and helps to find ways to save resources. The DAAC provides new tools like ezVIZ, and services such as the DAAC website, a rich resource of news about the DAAC, training materials, a community forum and tutorials on how to use data analysis and other issues.The DAAC can perform collaborative work when users prefer to do the work themselves but need help in choosing which visualization program and/or technique and using the visualization tools. The DAAC also carries out custom projects to produce high-quality animations of data, such as movies, which allow researchers to communicate their results to others.Communicate Research in ContextDAAC provides leading animation and modeling software which allows scientists and researchers may communicate all aspects of their research by setting their results in context through conceptual visualization and data analysis.Success StoriesWave Breaking and Associated Droplet and Bubble FormationWave breaking and associated droplet and bubble formation are among the most challenging problems in the field of free-surface hydrodynamics. The method of computational fluid dynamics (CFD) was used to solve this problem numerically for flow about naval vessels. The researchers wanted to animate the time-varying three-dimensional data sets using isosurfaces, but transferring the data back to the local site was a problem because the data sets were large. The DAAC visualization team solved the problem by using EnSight and ezVIZ to generate the isosurfaces, and photorealistic rendering software to produce the images for the animation.Explosive Structure Interaction Effects in Urban TerrainKnown as the Breaching Project, this research studied the effects of high-explosive (HE) charges on brick or reinforced concrete walls. The results of this research will enable the war fighter to breach a wall to enter a building where enemy forces are conducting operations against U.S. interests. Images produced show computed damaged caused by an HE charge on the outer and inner sides of a reinforced concrete wall. The ability to quickly and meaningfully analyze large simulation data sets helps guide further development of new HE package designs and better ways to deploy the HE packages. A large number of designs can be simulated and analyzed to find the best at breaching the wall. The project saves money in greatly reduced field test costs by testing only the designs which were identified in analysis as the best performers.SpecificationsAmethyst, the seven-node Linux visualization cluster housed at the DAAC, is supported by ParaView, EnSight, and ezViz visualization tools and configured as follows:Six computer nodes, each with the following specifications:CPU: 8 dual-core 2.4 Ghz, 64-bit AMD Opteron Processors (16 effective cores)Memory: 128-G RAMVideo: NVidia Quadro 5500 1-GB memoryNetwork: Infiniband Interconnect between nodes, and Gigabit Ethernet to Defense Research and Engineering Network (DREN)One storage node:Disk Space: 20-TB TerraGrid file system, mounted on all nodes as /viz and /work

Abstract

This dataset and its metadata statement were supplied to the Bioregional Assessment Programme by a third party and are presented here as originally supplied.

This three-dimensional visualisation product is intended to accompany the reports from the Great Artesian Basin Water Resource Assessment, specifically "The three-dimensional visualisation of the Great Artesian Basin" report (Nelson et al., 2012). The report describes products, outputs and outcomes of the three-dimensional (3D) visualisation component of the Great Artesian Basin Water Resource Assessment (the Assessment). This report specifically encompasses the following topics associated with the 3D visualisation component: - The requirements and potential benefits - The effective datasets - Methodology used in content creation - The output datasets - Discussions regarding outcomes, limitations and future directions The Assessment is designed to assist water managers in the Great Artesian Basin (GAB) to meet National Water Initiative commitments. The key datasets of the 3D visualisation component include contact surfaces between major aquifers and aquitards with coverage of significant portions of the GAB, well lithostratigraphic and wire-line data and hydrogeochemistry produced by State and National Agencies. These datasets are manipulated within GOCAD® to develop the 3D visualisation component and communication products for use by end users to assist visualisation and conceptualisation of the GAB. While many options have been investigated for distribution of these 3D products, 2D screen captures and content delivery via the Geoscience Australia (GA) World Wind 3D data viewer will be the most efficient and effective products. This 3D visualisation should be viewed in reference to the "Lexicon of the lithostratigraphic and hydrogeological units of the Great Artesian Basin and its Cenozoic cover" report (Radke et al., 2012) also created as part of the Assessment. LINEAGE (continued from Lineage field) REFERENCES 1. Welsh, W.D. 2000. GABFLOW: A steady state groundwater flow model of the Great Artesian Basin, Bureau Rural Sciences. Canberra. 2. Nelson GJ, Carey H, Radke BM and Ransley TR (2012) The three-dimensional visualisation of the Great Artesian Basin. A report to the Australian Government from the CSIRO Great Artesian Basin Water Resource Assessment. CSIRO Water for a Healthy Country Flagship, Australia. 3. Radke BM, Kellett JR, Ransley TR and Bell JG (2012) Lexicon of the lithostratigraphic and hydrogeological units of the Great Artesian Basin and its Cenozoic cover. A technical report to the Australian Government from the CSIRO Great Artesian Basin Water Resource Assessment. CSIRO Water for a Healthy Country Flagship, Australia. 4. Ransley TR and Smerdon BD (eds) (2012) Hydrostratigraphy, hydrogeology and system conceptualisation of the Great Artesian Basin. A technical report to the Australian Government from the CSIRO Great Artesian Basin Water Resource Assessment. CSIRO Water for a Healthy Country Flagship, Australia. 5. Senior and associates (1997). Geoscience Australia internal data set and contour interpretations by Senior B. Canberra, Groundwater Group, Environmental Geoscience Division, Geoscience Australia. 6. Van der Wielen S, Kirkby A, Britt A, Nicoll M and Skirrow R (in prep.) An integrated, multiuse 3D map for the greater Eromanga Basin, Australia. Geoscience Australia record 2011/XX, Canberra. METHOD The data are visualised in the Geoscience Australia (GA) 3D Data Viewer, a virtual globe application developed at GA using the NASA World Wind Java SDK. A public version of the Viewer is available on the GA website at http://www.ga.gov.au/apps/world-wind, and the source code for the tool is available open-source at http://github.com/ga-m3dv/ga-worldwind-suite.

Full Metadata available from: http://www.ga.gov.au/metadata-gateway/metadata/record/77777/

Dataset History

SOURCE DATA: **HYDROSTRATIGRAPHY Formation bases [available from http://www.ga.gov.au using catalogue numbers listed below ] 01 3-second Digital Elevation Model surface [catalogue #75990] 02 Base of Cenozoic surface [catalogue #75991] 03 Base of Mackunda Formation and equivalents surface [catalogue #76021] 04 Base of Rolling Downs Group surface [catalogue #76022] 05 Base of Hooray Sandstone and equivalents surface [catalogue #76023] 06 Base of Injune Creek Group surface [catalogue #76024] 07 Base of Hutton Sandstone surface [catalogue #76025] 05-07 Base of Algebuckina Sandstone surface [catalogue #76952] 08A Base of Evergreen and Marburg formations [catalogue #76026] 08B Base of Poolowanna Formation [catalogue #76953] 09 Base of Precipice Sandstone and equivalents surface [catalogue #76027] 10 Base of Jurassic-Cretaceous surface [catalogue #76028] Other Formation Bases 1. Beautified surfaces (with minimised crossovers) for formation bases 02 to 10 Constraints 1. Well constraints for formation bases 02 to 10. These are positions in 3D space where the surface is known to intersect. See Nelson et al (2012) for more information. **GROUNDWATER 1. Water table elevation of the Great Artesian Basin [available from http://www.ga.gov.au , catalogue #75830] 2. Modelled potentiometric surface of the Cadna-owie - Hooray aquifer (Welsh, 2000) **BOUNDARIES 1. Revised Great Artesian Basin Jurassic-Cretaceous boundary [available from http://www.ga.gov.au , catalogue # 75904] 2. GABWRA reporting region boundaries for the Carpentaria, Central Eromanga, Surat and Western Eromanga basins (Ransley TR & Smerdon BD (eds), 2012) **GEOLOGY 1. Geoscience Australia - Fault surfaces over 40km Senior and associates (1997). 2. Known structural faults in the Eromanga Basin Vertical fault traces from Van der Wielen et. al. (2011/in press) **GEOSCIENCE AUSTRALIA DATA SETS Additional objects that are optional packages to the Assessment 3D visualisation are sourced from the GA Common Earth Model datasets which include: - 1:1,000,000 scale surface geology maps of Australia - Radiometric map of Australia, 2nd Edition, 2010 - Gravity anomaly map of the Australian Region, 3rd Edition, 2008 - Magnetic anomaly map of Australia, 5th Edition, 2009 - Australia's Dynamic Land Cover Map, 1st Edition, 2010 *** References and method listed in Abstract due to space constraints in Lineage field ***

Dataset Citation

Geoscience Australia (2013) Three-dimensional visualisation of the Great Artesian Basin - GABWRA. Bioregional Assessment Source Dataset. Viewed 12 December 2018, http://data.bioregionalassessments.gov.au/dataset/98e49f7c-28a6-4ad1-83c7-fdf606954fbc.

Passive Acoustic Monitoring (PAM) is emerging as a solution for monitoring species and environmental change over large spatial and temporal scales. However, drawing rigorous conclusions based on acoustic recordings is challenging, as there is no consensus over which approaches, and indices are best suited for characterizing marine and terrestrial acoustic environments. Here, we describe the application of multiple machine-learning techniques to the analysis of a large PAM dataset. We combine pre-trained acoustic classification models (VGGish, NOAA & Google Humpback Whale Detector), dimensionality reduction (UMAP), and balanced random forest algorithms to demonstrate how machine-learned acoustic features capture different aspects of the marine environment. The UMAP dimensions derived from VGGish acoustic features exhibited good performance in separating marine mammal vocalizations according to species and locations. RF models trained on the acoustic features performed well for labelled sounds in the 8 kHz range, however, low and high-frequency sounds could not be classified using this approach. The workflow presented here shows how acoustic feature extraction, visualization, and analysis allow for establishing a link between ecologically relevant information and PAM recordings at multiple scales. The datasets and scripts provided in this repository allow replicating the results presented in the publication. Methods Data acquisition and preparation We collected all records available in the Watkins Marine Mammal Database website listed under the “all cuts'' page. For each audio file in the WMD the associated metadata included a label for the sound sources present in the recording (biological, anthropogenic, and environmental), as well as information related to the location and date of recording. To minimize the presence of unwanted sounds in the samples, we only retained audio files with a single source listed in the metadata. We then labelled the selected audio clips according to taxonomic group (Odontocetae, Mysticetae), and species. We limited the analysis to 12 marine mammal species by discarding data when a species: had less than 60 s of audio available, had a vocal repertoire extending beyond the resolution of the acoustic classification model (VGGish), or was recorded in a single country. To determine if a species was suited for analysis using VGGish, we inspected the Mel-spectrograms of 3-s audio samples and only retained species with vocalizations that could be captured in the Mel-spectrogram (Appendix S1). The vocalizations of species that produce very low frequency, or very high frequency were not captured by the Mel-spectrogram, thus we removed them from the analysis. To ensure that records included the vocalizations of multiple individuals for each species, we only considered species with records from two or more different countries. Lastly, to avoid overrepresentation of sperm whale vocalizations, we excluded 30,000 sperm whale recordings collected in the Dominican Republic. The resulting dataset consisted in 19,682 audio clips with a duration of 960 milliseconds each (0.96 s) (Table 1). The Placentia Bay Database (PBD) includes recordings collected by Fisheries and Oceans Canada in Placentia Bay (Newfoundland, Canada), in 2019. The dataset consisted of two months of continuous recordings (1230 hours), starting on July 1st, 2019, and ending on August 31st 2029. The data was collected using an AMAR G4 hydrophone (sensitivity: -165.02 dB re 1V/µPa at 250 Hz) deployed at 64 m of depth. The hydrophone was set to operate following 15 min cycles, with the first 60 s sampled at 512 kHz, and the remaining 14 min sampled at 64 kHz. For the purpose of this study, we limited the analysis to the 64 kHz recordings. Acoustic feature extraction The audio files from the WMD and PBD databases were used as input for VGGish (Abu-El-Haija et al., 2016; Chung et al., 2018), a CNN developed and trained to perform general acoustic classification. VGGish was trained on the Youtube8M dataset, containing more than two million user-labelled audio-video files. Rather than focusing on the final output of the model (i.e., the assigned labels), here the model was used as a feature extractor (Sethi et al., 2020). VGGish converts audio input into a semantically meaningful vector consisting of 128 features. The model returns features at multiple resolution: ~1 s (960 ms); ~5 s (4800 ms); ~1 min (59’520 ms); ~5 min (299’520 ms). All of the visualizations and results pertaining to the WMD were prepared using the finest feature resolution of ~1 s. The visualizations and results pertaining to the PBD were prepared using the ~5 s features for the humpback whale detection example, and were then averaged to an interval of 30 min in order to match the temporal resolution of the environmental measures available for the area. UMAP ordination and visualization UMAP is a non-linear dimensionality reduction algorithm based on the concept of topological data analysis which, unlike other dimensionality reduction techniques (e.g., tSNE), preserves both the local and global structure of multivariate datasets (McInnes et al., 2018). To allow for data visualization and to reduce the 128 features to two dimensions for further analysis, we applied Uniform Manifold Approximation and Projection (UMAP) to both datasets and inspected the resulting plots. The UMAP algorithm generates a low-dimensional representation of a multivariate dataset while maintaining the relationships between points in the global dataset structure (i.e., the 128 features extracted from VGGish). Each point in a UMAP plot in this paper represents an audio sample with duration of ~ 1 second (WMD dataset), ~ 5 seconds (PBD dataset, humpback whale detections), or 30 minutes (PBD dataset, environmental variables). Each point in the two-dimensional UMAP space also represents a vector of 128 VGGish features. The nearer two points are in the plot space, the nearer the two points are in the 128-dimensional space, and thus the distance between two points in UMAP reflects the degree of similarity between two audio samples in our datasets. Areas with a high density of samples in UMAP space should, therefore, contain sounds with similar characteristics, and such similarity should decrease with increasing point distance. Previous studies illustrated how VGGish and UMAP can be applied to the analysis of terrestrial acoustic datasets (Heath et al., 2021; Sethi et al., 2020). The visualizations and classification trials presented here illustrate how the two techniques (VGGish and UMAP) can be used together for marine ecoacoustics analysis. UMAP visualizations were prepared the umap-learn package for Python programming language (version 3.10). All UMAP visualizations presented in this study were generated using the algorithm’s default parameters.
Labelling sound sources The labels for the WMD records (i.e., taxonomic group, species, location) were obtained from the database metadata. For the PBD recordings, we obtained measures of wind speed, surface temperature, and current speed from (Fig 1) an oceanographic buy located in proximity of the recorder. We choose these three variables for their different contributions to background noise in marine environments. Wind speed contributes to underwater background noise at multiple frequencies, ranging 500 Hz to 20 kHz (Hildebrand et al., 2021). Sea surface temperature contributes to background noise at frequencies between 63 Hz and 125 Hz (Ainslie et al., 2021), while ocean currents contribute to ambient noise at frequencies below 50 Hz (Han et al., 2021) Prior to analysis, we categorized the environmental variables and assigned the categories as labels to the acoustic features (Table 2). Humpback whale vocalizations in the PBD recordings were processed using the humpback whale acoustic detector created by NOAA and Google (Allen et al., 2021), providing a model score for every ~5 s sample. This model was trained on a large dataset (14 years and 13 locations) using humpback whale recordings annotated by experts (Allen et al., 2021). The model returns scores ranging from 0 to 1 indicating the confidence in the predicted humpback whale presence. We used the results of this detection model to label the PBD samples according to presence of humpback whale vocalizations. To verify the model results, we inspected all audio files that contained a 5 s sample with a model score higher than 0.9 for the month of July. If the presence of a humpback whale was confirmed, we labelled the segment as a model detection. We labelled any additional humpback whale vocalization present in the inspected audio files as a visual detection, while we labelled other sources and background noise samples as absences. In total, we labelled 4.6 hours of recordings. We reserved the recordings collected in August to test the precision of the final predictive model. Label prediction performance We used Balanced Random Forest models (BRF) provided in the imbalanced-learn python package (Lemaître et al., 2017) to predict humpback whale presence and environmental conditions from the acoustic features generated by VGGish. We choose BRF as the algorithm as it is suited for datasets characterized by class imbalance. The BRF algorithm performs under sampling of the majority class prior to prediction, allowing to overcome class imbalance (Lemaître et al., 2017). For each model run, the PBD dataset was split into training (80%) and testing (20%) sets. The training datasets were used to fine-tune the models though a nested k-fold cross validation approach with ten-folds in the outer loop, and five-folds in the inner loop. We selected nested cross validation as it allows optimizing model hyperparameters and performing model evaluation in a single step. We used the default parameters of the BRF algorithm, except for the ‘n_estimators’ hyperparameter, for which we tested

Context

While studying neural networks in machine learning, I found an ingenious 2-D scatter pattern at the cn231 course by Andrej Karpathy. Decision boundaries for the three classes of points cannot be straight lines. He uses it to compare the behavior of a linear classifier and a neural network classifier. Often, we are content with the percentage of accuracy of our prediction or classification algorithm but a visualization tool helps our intuition about the trends and behavior of the classifier. It was definitely useful to catch something strange in the last example of this description. How does your preferred method or algorithm do with this input?

https://github.com/pliptor/PicoNN/raw/master/extras/input.png" alt="spiral">

Content

• The 2D scatter train pattern is a collection of 300 points with (X,Y) coordinates where `-1

A visualization plot of a data set of molecular data is a useful tool for gaining insight into a set of molecules. In chemoinformatics, most visualization plots are of molecular descriptors, and the statistical model most often used to produce a visualization is principal component analysis (PCA). This paper takes PCA, together with four other statistical models (NeuroScale, GTM, LTM, and LTM-LIN), and evaluates their ability to produce clustering in visualizations not of molecular descriptors but of molecular fingerprints. Two different tasks are addressed: understanding structural information (particularly combinatorial libraries) and relating structure to activity. The quality of the visualizations is compared both subjectively (by visual inspection) and objectively (with global distance comparisons and local k-nearest-neighbor predictors). On the data sets used to evaluate clustering by structure, LTM is found to perform significantly better than the other models. In particular, the clusters in LTM visualization space are consistent with the relationships between the core scaffolds that define the combinatorial sublibraries. On the data sets used to evaluate clustering by activity, LTM again gives the best performance but by a smaller margin. The results of this paper demonstrate the value of using both a nonlinear projection map and a Bernoulli noise model for modeling binary data.

Context

Analysis and Visualization of spread of coronavirus in India.

Content

The dataset raw_data.csv file, contains information about the coronavirus infected patients from time period 2-Feb-2020 to 14-April-2020 in India. It has information of all the states, their districts and cities. The data is very much useful in realising the threats that are being caused by the virus and also the source from where it is being spread in India. Also the travel history of patients and their Current health Status makes it easier to develop a model and predict the covid19 hotspots in the nation.

Acknowledgements

We wouldn't be here without the help of covid19india website. The dataset was obtained from website mentioned.

Inspiration

The cases of coronavirus infected people are increasing, this has caused to serious health calamities across the country. This has led to huge crisis on healthcare and Medicine and also the organisations that work to face and tackle coronavirus. Therefore it is of great importance that the data needs to be analysed and solutions need to be found out by looking for parameters that will help take down the virus.

The reserve system has identified a need to increase its collective capacity to process and synthesize Surface Elevation Table data and to create visualizations and educational tools for scientists, managers, and the public. This project addresses these needs by developing standardized tools to quality-check Surface Elevation Table data, perform trend analyses, and generate informative visualizations for a variety of technical and non-technical audiences. The team’s collaborative approach to developing statistical methods and outreach products will build both technical expertise and broader understanding of how the data can be used to better understand how sea level rise is impacting marshes.

Sentinel-2, 10, 20, and 60m Multispectral, Multitemporal, 13-band imagery is rendered on-the-fly and available for visualization. This imagery layer pulls directly from the Sentinel-2 on AWS collection and is updated daily with new imagery.This imagery layer can be applied across a number of industries, scientific disciplines, and management practices. Some applications include, but are not limited to, land cover and environmental monitoring, climate change, deforestation, disaster and emergency management, national security, plant health and precision agriculture, forest monitoring, watershed analysis and runoff predictions, land-use planning, tracking urban expansion, highlighting burned areas and estimating fire severity.Geographic CoverageGlobalContinental land masses from 65.4° South to 72.1° North, with these special guidelines:All coastal waters up to 20 km from the shoreAll islands greater than 100 km2All EU islandsAll closed seas (e.g. Caspian Sea)The Mediterranean SeaTemporal CoverageThe revisit time for each point on Earth is every 5 days.This layer is updated daily with new imagery.This imagery layer includes a rolling collection of imagery acquired within the past 14 months.The number of images available will vary depending on location.Product LevelThis service provides Level-1C Top of Atmosphere imagery.Alternatively, Sentinel-2 Level-2A is also available.Image Selection/FilteringThe most recent and cloud free images are displayed by default.Any image available within the past 14 months can be displayed via custom filtering.Filtering can be done based on attributes such as Acquisition Date, Estimated Cloud Cover, and Tile ID.Tile_ID is computed as [year][month][day]T[hours][minutes][seconds]_[UTMcode][latitudeband][square]_[sequence]. More…Visual RenderingDefault rendering is Natural Color (bands 4,3,2) with Dynamic Range Adjustment (DRA).The DRA version of each layer enables visualization of the full dynamic range of the images.Rendering (or display) of band combinations and calculated indices is done on-the-fly from the source images via Raster Functions.Various pre-defined Raster Functions can be selected or custom functions created.Available renderings include: Agriculture with DRA, Bathymetric with DRA, Color-Infrared with DRA, Natural Color with DRA, Short-wave Infrared with DRA, Geology with DRA, NDMI Colorized, Normalized Difference Built-Up Index (NDBI), NDWI Raw, NDWI - with VRE Raw, NDVI – with VRE Raw (NDRE), NDVI - VRE only Raw, NDVI Raw, Normalized Burn Ratio, NDVI Colormap.Multispectral BandsBandDescriptionWavelength (µm)Resolution (m)1Coastal aerosol0.433 - 0.453602Blue0.458 - 0.523103Green0.543 - 0.578104Red0.650 - 0.680105Vegetation Red Edge0.698 - 0.713206Vegetation Red Edge0.733 - 0.748207Vegetation Red Edge0.773 - 0.793208NIR0.785 - 0.900108ANarrow NIR0.855 - 0.875209Water vapour0.935 - 0.9556010SWIR – Cirrus1.365 - 1.3856011SWIR-11.565 - 1.6552012SWIR-22.100 - 2.28020Additional NotesOverviews exist with a spatial resolution of 150m and are updated every quarter based on the best and latest imagery available at that time.To work with source images at all scales, the ‘Lock Raster’ functionality is available.NOTE: ‘Lock Raster’ should only be used on the layer for short periods of time, as the imagery and associated record Object IDs may change daily.This ArcGIS Server dynamic imagery layer can be used in Web Maps and ArcGIS Desktop as well as Web and Mobile applications using the REST based Image services API.Images can be exported up to a maximum of 4,000 columns x 4,000 rows per request.Data SourceSentinel-2 imagery is the result of close collaboration between the (European Space Agency) ESA, the European Commission and USGS. Data is hosted by the Amazon Web Services as part of their Registry of Open Data. Users can access the imagery from Sentinel-2 on AWS , or alternatively access EarthExplorer or the Copernicus Data Space Ecosystem to download the scenes.For information on Sentinel-2 imagery, see Sentinel-2.

The cartographic level represents the chemical status of the surface water bodies of the Liguria Region) referred to in the Resolution of the Regional Council n. 1161/2021. The map shows the results of the chemical classification of surface water bodies (sea, transitional waters, rivers and lakes) based on monitoring data for the period 2014-2019 according to the provisions of Annex I to part III of Legislative Decree 152/2006; the quality classes are as follows: good, not good. - Year: 2022 - Coverage: Entire regional territory

InfographicVQA is a dataset that comprises a diverse collection of infographics along with natural language questions and answers annotations. The collected questions require methods to jointly reason over the document layout, textual content, graphical elements, and data visualizations. We curate the dataset with emphasis on questions that require elementary reasoning and basic arithmetic skills.

Boletes are favored by consumers because of their unique flavor, rich nutrition and delicious taste. However, the different nutritional values of each species lead to obvious price differences, so shoddy products appear on the market, which affects food safety. The aim of this study was to find a rapid and effective method for boletes species identification. In this paper, 1,707 samples of eight boletes species were selected as the research objects. The original Mid-Infrared (MIR) spectroscopy data were adopted for support vector machine (SVM) modeling. The 11,949 spectral images belong to seven data sets such as two-dimensional correlation spectroscopy (2DCOS) and three-dimensional correlation spectroscopy (3DCOS) were used to carry out Alexnet and Residual network (Resnet) modeling, thus we established 15 models for the identification of boletes species. The results show that the SVM method needs to process complex feature data, the time cost is more than 11 times of other models, and the accuracy is not high enough, so it is not recommended to be used in data processing with large sample size. From the perspective of datasets, synchronous 2DCOS and synchronous 3DCOS have the best modeling results, while one-dimensional (1D) MIR Spectrum dataset has the worst modeling results. After comprehensive analysis, the modeling effect of Resnet on the synchronous 2DCOS dataset is the best. Moreover, we use large-screen visualization technology to visually display the sample information of this research and obtain their distribution rules in terms of species and geographical location. This research shows that deep learning combined with 2DCOS and 3DCOS spectral images can effectively and accurately identify boletes species, which provides a reference for the identification of other fields, such as food and Chinese herbal medicine.

Technical comparison between data visualization technologies.