Spaces:
Running
Running
initial update to test
Browse files- index.html +92 -7
- style.css +14 -14
- xorbs.json +0 -0
index.html
CHANGED
|
@@ -3,17 +3,102 @@
|
|
| 3 |
<head>
|
| 4 |
<meta charset="utf-8" />
|
| 5 |
<meta name="viewport" content="width=device-width" />
|
| 6 |
-
<title>
|
| 7 |
<link rel="stylesheet" href="style.css" />
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
</head>
|
| 9 |
<body>
|
| 10 |
<div class="card">
|
| 11 |
-
<h1>
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
</div>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
</body>
|
| 19 |
</html>
|
|
|
|
| 3 |
<head>
|
| 4 |
<meta charset="utf-8" />
|
| 5 |
<meta name="viewport" content="width=device-width" />
|
| 6 |
+
<title>xet-repo-dedupe</title>
|
| 7 |
<link rel="stylesheet" href="style.css" />
|
| 8 |
+
<script src="https://cdn.jsdelivr.net/npm/vega@5"></script>
|
| 9 |
+
<script src="https://cdn.jsdelivr.net/npm/vega-lite@5"></script>
|
| 10 |
+
<script src="https://cdn.jsdelivr.net/npm/vega-embed@6"></script>
|
| 11 |
+
<style>
|
| 12 |
+
#vis {
|
| 13 |
+
width: 100%;
|
| 14 |
+
text-align: center;
|
| 15 |
+
}
|
| 16 |
+
</style>
|
| 17 |
</head>
|
| 18 |
<body>
|
| 19 |
<div class="card">
|
| 20 |
+
<h1>Visualizing Repo-level Dedupe</h1>
|
| 21 |
+
<p>This visualization demonstrates the amount of <a target="_blank" rel="noopener noreferrer" href="https://huggingface.co/blog/from-files-to-chunks">chunk-level dedupe</a> across all public repos.</p>
|
| 22 |
+
<p>"Dedupe factor" is defined as the number of re-uses of a given "xorb". A "xorb" is a collection of content-defined chunks, typically around 1,000 chunks comprising up to 64 MB of total data.</p>
|
| 23 |
+
<p>Interactions:
|
| 24 |
+
<ul>
|
| 25 |
+
<li>
|
| 26 |
+
Hover to select a xorb, and highlight the same xorb in all other repos in <strong><span style="color: red">red</span></strong>.
|
| 27 |
+
</li>
|
| 28 |
+
<li>
|
| 29 |
+
Click to select a row (repo), and fade out all repos that don't contain any overlapping data. Double-click to clear selection.
|
| 30 |
+
</li>
|
| 31 |
+
</ul>
|
| 32 |
+
</p>
|
| 33 |
</div>
|
| 34 |
+
<div id="vis"></div>
|
| 35 |
+
<script>
|
| 36 |
+
var vlSpec = {
|
| 37 |
+
"$schema": "https://vega.github.io/schema/vega-lite/v5.json",
|
| 38 |
+
"resolve": {"scale": {"x": "independent"}},
|
| 39 |
+
"width": 600,
|
| 40 |
+
"height": 12,
|
| 41 |
+
"params": [
|
| 42 |
+
{
|
| 43 |
+
"name": "highlight",
|
| 44 |
+
"select": {"type": "point", "fields": ["xorb_id"], "on": "pointerover"}
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"name": "select",
|
| 48 |
+
"select": {"type": "point", "fields": ["repo"], "toggle": "false"}
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"name": "xorbs_selected",
|
| 52 |
+
"expr": "pluck(data('source_0'), 'repo_xorb_selected')"
|
| 53 |
+
},
|
| 54 |
+
{"name": "any_xorbs_selected", "expr": "extent(xorbs_selected)[0] != null"}
|
| 55 |
+
],
|
| 56 |
+
"transform": [
|
| 57 |
+
{
|
| 58 |
+
"calculate": "(select.repo != null ? indexof(select.repo, datum.repo) : -1) + 1",
|
| 59 |
+
"as": "repo_selected"
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"calculate": "if(datum.repo_selected > 0, datum.xorb_id, null)",
|
| 63 |
+
"as": "repo_xorb_selected"
|
| 64 |
+
}
|
| 65 |
+
],
|
| 66 |
+
"data": {
|
| 67 |
+
"url": "xorbs.json"
|
| 68 |
+
},
|
| 69 |
+
"mark": "rect",
|
| 70 |
+
"encoding": {
|
| 71 |
+
"x": {
|
| 72 |
+
"field": "xorb_id",
|
| 73 |
+
"axis": null,
|
| 74 |
+
"stack": "normalize"
|
| 75 |
+
},
|
| 76 |
+
"color": {
|
| 77 |
+
"condition": [
|
| 78 |
+
{"test": "datum.xorb_id == highlight.xorb_id", "value": "orange"}
|
| 79 |
+
],
|
| 80 |
+
"field": "dedupe_factor",
|
| 81 |
+
"type": "quantitative",
|
| 82 |
+
"scale": {"domain": [0, 10]}
|
| 83 |
+
},
|
| 84 |
+
"opacity": {
|
| 85 |
+
"condition": [
|
| 86 |
+
{
|
| 87 |
+
"test": "any_xorbs_selected && indexof(xorbs_selected, datum.xorb_id) == -1",
|
| 88 |
+
"value": 0.2
|
| 89 |
+
}
|
| 90 |
+
]
|
| 91 |
+
},
|
| 92 |
+
"tooltip": {"field": "dedupe_factor"},
|
| 93 |
+
"row": {
|
| 94 |
+
"field": "repo",
|
| 95 |
+
"spacing": 1,
|
| 96 |
+
"header": {"labelAngle": 0, "labelAlign": "left"},
|
| 97 |
+
"sort": {"field": "dedupe_factor", "order": "descending"}
|
| 98 |
+
}
|
| 99 |
+
}
|
| 100 |
+
};
|
| 101 |
+
vegaEmbed('#vis', vlSpec);
|
| 102 |
+
</script>
|
| 103 |
</body>
|
| 104 |
</html>
|
style.css
CHANGED
|
@@ -1,28 +1,28 @@
|
|
| 1 |
body {
|
| 2 |
-
|
| 3 |
-
|
| 4 |
}
|
| 5 |
|
| 6 |
h1 {
|
| 7 |
-
|
| 8 |
-
|
| 9 |
}
|
| 10 |
|
| 11 |
p {
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
|
| 16 |
}
|
| 17 |
|
| 18 |
.card {
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
|
| 24 |
}
|
| 25 |
|
| 26 |
.card p:last-child {
|
| 27 |
-
|
| 28 |
}
|
|
|
|
| 1 |
body {
|
| 2 |
+
padding: 2rem;
|
| 3 |
+
font-family: -apple-system, BlinkMacSystemFont, "Arial", sans-serif;
|
| 4 |
}
|
| 5 |
|
| 6 |
h1 {
|
| 7 |
+
font-size: 16px;
|
| 8 |
+
margin-top: 0;
|
| 9 |
}
|
| 10 |
|
| 11 |
p {
|
| 12 |
+
color: rgb(107, 114, 128);
|
| 13 |
+
font-size: 15px;
|
| 14 |
+
margin-bottom: 10px;
|
| 15 |
+
margin-top: 5px;
|
| 16 |
}
|
| 17 |
|
| 18 |
.card {
|
| 19 |
+
max-width: 620px;
|
| 20 |
+
margin: 0 auto;
|
| 21 |
+
padding: 16px;
|
| 22 |
+
border: 1px solid lightgray;
|
| 23 |
+
border-radius: 16px;
|
| 24 |
}
|
| 25 |
|
| 26 |
.card p:last-child {
|
| 27 |
+
margin-bottom: 0;
|
| 28 |
}
|
xorbs.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|