Visualization

100%

✓ Published0🌍 Public

Last edited Dec 31, 2017

Created on Dec 31, 2017

This interactive scatterplot visualizes a principal component analysis of citation data from 2,000 philosophy articles, with k-means clustering applied to reveal groupings. The D3.js (v3) visualization uses SVG circles positioned via a zoomable, panning coordinate system, with color encoding cluster membership and tooltips showing exact coordinates. Users can click a button to switch the x-axis variable, triggering animated transitions of the data points. The code leverages `d3.scale.linear`, `d3.svg.axis`, `d3.behavior.zoom`, and the `d3.tip` library for interactivity, with data loaded from a CSV file.

AI-generated description

A Principle Component Analysis of the Citation-Data of 2000 Philosophy-Articles from the 90s. Clusters are generated with K-Means.

The Scatterplot is forked from <a href='http://bl.ocks.org/peterssonjonas/'>peterssonjonas</a>'s block: <a href='http://bl.ocks.org/peterssonjonas/4a0e7cb8d23231243e0e'>D3 Zoomable Scatterplot</a>

forked from <a href='http://bl.ocks.org/MNoichl/'>MNoichl</a>'s block: <a href='http://bl.ocks.org/MNoichl/ab5a637122ee56e422168fd6c8db0cbf'>PCA 2000 Philososophy-Articles</a>

forked from <a href='http://bl.ocks.org/MNoichl/'>MNoichl</a>'s block: <a href='http://bl.ocks.org/MNoichl/2c30fbf420756562e926f27f25773066'>DB-Index for Phi-Sample</a>

mit Licensed

Similar vizzes

Loading thumbnail…

Visualization

A zoomable scatterplot displays a Principal Component Analysis of citation data from 2,000 philosophy articles, with points colored by K-Means clusters. The visualization uses D3 v3’s linear scales, axes, and zoom behavior to explore the bidimensional projection. Points are rendered as SVG circles with tooltips via d3-tip, and a button switches the x-axis variable, triggering a transition on the dot transforms. Data is loaded from a CSV file, and the plot includes a categorical color legend.

MMNoichl

96% match

Loading thumbnail…

Visualization

This interactive scatterplot visualizes a Principal Component Analysis of citation data from 2,000 philosophy articles from the 1990s, with points colored by K-Means clusters. Users can zoom and pan the plot using d3.behavior.zoom and hover over points to see tooltips generated by d3.tip. The visualization is built with D3 v3, rendering SVG circles, and includes a button that switches the x-axis to display carbohydrate values, triggering a transition that updates the axis and dot positions.

MMNoichl

95% match

Loading thumbnail…

Visualization

This visualization displays a principal component analysis of citation data from 2,000 philosophy articles, projecting each article into a 2D scatterplot where points are colored by K-Means cluster assignment. The chart, built with D3 v3 and rendered as SVG, supports zooming and panning through the d3.behavior.zoom API. Each dot represents an article, with mouseover tooltips provided by the d3-tip library. The visualization includes an interactive button that switches the x-axis to display carbohydrate values, demonstrating a data-viewing alternative, though the primary dataset remains the citation components.

MMNoichl

94% match

Loading thumbnail…

Visualization

This visualization plots the Davies-Bouldin index against the number of clusters for a k-means analysis of philosophy papers, revealing how clustering quality varies with cluster count. The code uses d3.v3 with SVG circles positioned via linear scales, reading data from a CSV file that tracks citation patterns across analytical and continental philosophy journals. A d3.tip tooltip displays exact values on hover, while d3.behavior.zoom enables interactive panning and zooming of the scatterplot. The animation and transitions are handled through d3's built-in transition methods.

MMNoichl

86% match

Loading thumbnail…

Visualization

This interactive scatter plot displays the Davies-Bouldin index (y-axis) against the number of clusters k (x-axis) for K-means clustering results on citation data from philosophy journals. It visualizes how clustering quality changes from 2 to 10 clusters, showing a minimum at k=7. The visualization uses D3 v3 with `d3.scale.linear`, `d3.svg.axis`, and `d3.scale.category20`, rendering circles in SVG. A button switches the x-axis to a different (unused) data column, while the underlying data comes from a CSV file loaded via `d3.csv`, with tooltips via the d3-tip library and zoom/pan through `d3.behavior.zoom`.

MMNoichl

84% match

Loading thumbnail…

Visualization

This visualization plots the Davies-Bouldin Index against the number of clusters (k) for clustered citation data from philosophy journals, showing that 7 clusters yield the lowest index and thus the best clustering. The scatterplot uses d3.svg.axis, d3.scale.linear, and d3.behavior.zoom for panning and zooming, with circles colored by cluster and tooltips via d3.tip. Data comes from a CSV file containing clustering results from the author's analysis.

MMNoichl

79% match

Loading thumbnail…

Visualization

This visualization shows the Davies-Bouldin Index values for K-Means clustering of citation data from the top 2000 papers of the 1990s, with each point representing a different cluster count. A lower DB index indicates better clustering, revealing that 15 clusters achieve a notably better score (5.9) than 2 clusters (9.2). The scatter plot uses d3.svg.axis for axes, d3.scale.linear for positioning, and d3.tip for tooltips, with d3.behavior.zoom enabling interactive panning and zooming. Data comes from a CSV file containing K values and their corresponding DB and W metrics.

MMNoichl

72% match

Loading thumbnail…

Gist 2f2eacadf93dfd159da1

This visualization shows journal impact data from the 2012 Journal Citation Reports, rendered as an interactive scatter plot. Each point represents a journal, with position encoding impact factor versus total citations and point size mapping the Article Influence Score. The view is implemented with React managing the component state and D3.js handling the layout and scales. Points are drawn using WebGL for efficient rendering of hundreds of journals, and the animation smoothly transitions points when the underlying data or filters change. SVG is used for axes, labels, and interactive hover effects, while the WebGL layer renders the data points themselves. The visualization enables exploration of relationships between citation metrics across physics, chemistry, and biology journals.

BBenHeubl

72% match