Eugene Yan · Tech & AI
TIER 5 2020-01-06
<!DOCTYPE html>
<html lang="en">
<head>
<!--Load inline css and scripts first-->
<style>:root{--c-light-text:#333;--c-light-background:#fff;--c-light-focus:#00ff00;--c-light-interactive:#007bff;--c-dark-text:#fff;--c-dark-subtext:#a6a6a6;--c-dark-background:#333;--c-dark-focus:#00ff00;--c-dark-interactive:#66b0ff;--c-dark-callout:#003166;--c-text:var(--c-light-text);--c-background:var(--c-light-background);--c-focus:var(--c-light-focus);--c-interactive:var(--c-light-interactive)}.dark-mode-checkbox:checked~.theme-container{--c-text:var(--c-dark-text);--c-background:var(--c-dark-background);--c-focus:var(--c-dark-focus);--c-interactive:var(--c-dark-interactive)}html.dark-mode{--c-text:var(--c-dark-text);--c-background:var(--c-dark-background);--c-focus:var(--c-dark-focus);--c-interactive:var(--c-dark-interactive)}html.dark-mode .tag{background-color:#3e3e3e;color:var(--c-dark-interactive)}html.dark-mode a.tag:hover{background-color:var(--c-dark-interactive);color:#3e3e3e}a{text-decoration:none;background-color:transparent;color:var(--c-interactive)}</style>
<!-- darkmode JS at start of the doc so to ensure consistent view mode -->
<link href="/js/darkmode.js" rel="preload" as="script">
<script src="/js/darkmode.js" type="f28497f9592da7f32b5a2b50-text/javascript"></script>
<!--Add active class to nav bar-->
<link href="/js/navbar.js" rel="preload" as="script">
<script src="/js/navbar.js" defer type="f28497f9592da7f32b5a2b50-text/javascript"></script>
<!-- Load jQuery before anchor.min.js -->
<link href="/js/jquery-3.7.1.min.js" rel="preload" as="script">
<script src="/js/jquery-3.7.1.min.js" defer type="f28497f9592da7f32b5a2b50-text/javascript"></script>
<!--Add anchors to headers-->
<link href="/js/anchor.min.js" rel="preload" as="script">
<script src="/js/anchor.min.js" defer type="f28497f9592da7f32b5a2b50-text/javascript"></script>
<!-- Algolia Insights -->
<script type="f28497f9592da7f32b5a2b50-text/javascript">
var ALGOLIA_INSIGHTS_SRC = "/js/search-insights.min.js"; // Using local version
!function(e,a,t,n,s,i,c){e.AlgoliaAnalyticsObject=s,e[s]=e[s]||function(){
(e[s].queue=e[s].queue||[]).push(arguments)},e[s].version=(n.match(/@([^\/]+)\/?.*/) || [])[1],i=a.createElement(t),c=a.getElementsByTagName(t)[0],
i.async=1,i.src=n,c.parentNode.insertBefore(i,c)
}(window,document,"script",ALGOLIA_INSIGHTS_SRC,"aa");
</script>
<script type="f28497f9592da7f32b5a2b50-text/javascript">
if (typeof aa === 'function') {
aa('init', {
appId: '2XJCLEABQD',
apiKey: 'b61ec4cb64bd32d62c053466fccbfa43',
useCookie: true
});
}
</script>
<meta charset="utf-8">
<meta name="HandheldFriendly" content="True">
<meta name="MobileOptimized" content="320">
<meta name="viewport" content="width=device-width, initial-scale=0.86, maximum-scale=3.0, minimum-scale=0.86">
<meta name="description" content="Building a baseline recsys based on data scraped off Amazon. Warning - Lots of charts! (Part 1 of 2).">
<meta name="author" content="Eugene Yan">
<meta content="eugeneyan.com" property="og:site_name">
<meta name=twitter:card content=summary_large_image>
<meta name=twitter:domain content=eugeneyan.com>
<meta content="Building a Strong Baseline Recommender in PyTorch, on a Laptop" property="og:title">
<meta name=twitter:title content="Building a Strong Baseline Recommender in PyTorch, on a Laptop">
<meta content="article" property="og:type">
<meta content="Building a baseline recsys based on data scraped off Amazon. Warning - Lots of charts! (Part 1 of 2)." property="og:description">
<meta name=twitter:description content="Building a baseline recsys based on data scraped off Amazon. Warning - Lots of charts! (Part 1 of 2).">
<meta content="https://eugeneyan.com/writing/recommender-systems-baseline-pytorch/" property="og:url">
<meta content="2020-01-06T00:00:00+00:00" property="article:published_time">
<meta content="https://eugeneyan.com/about/" property="article:author">
<meta content="https://eugeneyan.com/assets/og_image/matrix-factorization.jpg" property="og:image">
<meta name=twitter:image content="https://eugeneyan.com/assets/og_image/matrix-factorization.jpg">
<meta content="posts" property="article:section">
<meta content="recsys" property="article:tag">
<meta content="deeplearning" property="article:tag">
<meta content="python" property="article:tag">
<meta content="🛠" property="article:tag">
<title>Building a Strong Baseline Recommender in PyTorch, on a Laptop</title>
<!-- styles -->
<script src="/cdn-cgi/scripts/7d0fa10a/cloudflare-static/rocket-loader.min.js" data-cf-settings="f28497f9592da7f32b5a2b50-|49"></script><link href="/css/main.min.css" rel="preload" as="style" onload="this.rel='stylesheet'" type="text/css">
<link rel="stylesheet" href="/css/main.css" type="text/css">
<!-- Preconnect to Google Fonts domains to reduce latency -->
<link rel="preconnect" href="https://fonts.googleapis.com" crossorigin>
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
<script src="/cdn-cgi/scripts/7d0fa10a/cloudflare-static/rocket-loader.min.js" data-cf-settings="f28497f9592da7f32b5a2b50-|49"></script><link href="https://fonts.googleapis.com/css2?family=Merriweather:wght@400;700&family=Raleway&display=swap"
rel="preload" as="style" onload="this.rel='stylesheet'">
<link href="https://fonts.googleapis.com/css2?family=Merriweather:wght@400;700&family=Raleway&display=swap"
rel="stylesheet">
<script src="/cdn-cgi/scripts/7d0fa10a/cloudflare-static/rocket-loader.min.js" data-cf-settings="f28497f9592da7f32b5a2b50-|49"></script><link href="/css/monokai.css" rel="preload" as="style" onload="this.rel='stylesheet'" type="text/css">
<link href="/css/monokai.css" rel="stylesheet" type="text/css">
<link rel="shortcut icon" type="image/png" href="https://eugeneyan.com/assets/favicon/favicon.ico">
<link rel="apple-touch-icon" sizes="180x180" href="https://eugeneyan.com/assets/favicon/apple-touch-icon.webp">
<link rel="icon" type="image/png" sizes="32x32" href="https://eugeneyan.com/assets/favicon/favicon-32x32.webp">
<link rel="icon" type="image/png" sizes="16x16" href="https://eugeneyan.com/assets/favicon/favicon-16x16.webp">
<link rel="manifest" href="/assets/favicon/site.webmanifest">
<link rel="canonical" href="https://eugeneyan.com/writing/recommender-systems-baseline-pytorch/"/>
<!-- Collect tags-->
<!-- google analytics - i will not share this data with google -->
<!-- Global site tag (gtag.js) - Google Analytics -->
<script async src="https://www.googletagmanager.com/gtag/js?id=G-4CKMNLRMCV" type="f28497f9592da7f32b5a2b50-text/javascript"></script>
<script type="f28497f9592da7f32b5a2b50-text/javascript">
window.dataLayer = window.dataLayer || [];
function gtag(){dataLayer.push(arguments);}
gtag('js', new Date());
gtag('config', 'G-4CKMNLRMCV');
</script>
</head>
<input class="dark-mode-checkbox" id="dark-mode" name="dark-mode-checkbox" type="checkbox"/>
<label class="dark-mode-label" for="dark-mode"></label>
<body>
<div class="theme-container grow">
<div class="container" style="width: 95%">
<div class="header">
<div class="row">
<div class="col-sm-3">
<h1 class="text-muted nav"><a href="/">eugeneyan</a></h1>
</div>
<div class="col-sm-9">
<ul id="nav" class="nav-margin nav nav-pills float-sm-right">
<li><a href="/start-here/" title="Start Here">Start Here</a></li>
<li><a href="/writing/" title="Writing">Writing</a></li>
<li><a href="/speaking/" title="Speaking">Speaking</a></li>
<li><a href="/prototyping/" title="Prototyping">Prototyping</a></li>
<li><a href="/about/" title="About">About</a></li>
<li><a href="/search/" title="Search"><img class="icon icon-search" src="/assets/icon-search.svg" loading="lazy" alt=""/></a></li>
</ul>
</div>
</div>
</div>
<div class="notes">
<div class="note single">
<h1 class="title">Building a Strong Baseline Recommender in PyTorch, on a Laptop</h1>
<p class="date">
<info datetime="2020-01-06 00:00:00 +0000">
<span class="no-italics">[
<a class='tag' href="/tag/recsys/">recsys</a>
<a class='tag' href="/tag/deeplearning/">deeplearning</a>
<a class='tag' href="/tag/python/">python</a>
<a class='tag' href="/tag/🛠/">🛠</a>
]
</span> · 14 min read
</info>
</p>
<!-- Post content -->
<div class="notebody">
<blockquote>
<p>P.S. Looking for the code for this? Available on github: <a href="https://github.com/eugeneyan/recsys-nlp-graph" target="_blank">recsys-nlp-graph</a></p>
</blockquote>
<p>Recommender systems (“recsys”) are a fairly old topic that started back in the 1990s. The key idea—we can use opinions and behaviours of users to suggest and personalize relevant and interesting content for them.</p>
<p>Adding yet another post on the standard item-user collaborative filtering wouldn’t contribute much to the hundreds, if not thousands, of posts available.</p>
<p>Thankfully, this is not one of those.</p>
<h2 id="overview">Overview</h2>
<p>A web search on recommender systems surfaces articles on “collaborative filtering”, “content-based”, “user-item matrix”, etc.</p>
<p>Since then, there has been much progress applying newer techniques for recsys. Unfortunately, easily readable articles or blogs on them are few and far between.</p>
<p>Thus, in this pair of articles, I’ll be sharing about <em>seven</em> different implementations of recsys.</p>
<p>The articles cover the end-to-end, from data acquisition and preparation, and (classic) matrix factorization. It also includes applying techniques from graphs and natural language processing. A result comparison of the different approaches on real-world data will also be discussed (I hope you love learning curves.)</p>
<h2 id="data-acquisition">Data Acquisition</h2>
<p>We can’t build a recsys without data (well, we can’t build most machine learning systems without data).</p>
<p>Thankfully, Professor Julian McAuley, Associate Professor at UC San Diego has a great collection of data sets (e.g., product reviews, meta data, social networks). For this post, we’ll be using the Amazon dataset (May 1996 – July 2014), specifically, the electronics and books datasets.</p>
<h2 id="parsing-json">Parsing json</h2>
<p>All of the datasets are in json format and require parsing into a format that’s easier to work with (e.g., tabular). Some of these datasets can be pretty large, with the largest having 142.8 million rows and requiring 20gb on disk.</p>
<p>Here’s an example of how a json entry for a single product looks like (what we’re interested in is the related field).</p>
<div class="language-text highlighter-rouge"><div class="highlight"><pre class="highlight"><code>{
"asin": "0000031852",
"title": "Girls Ballet Tutu Zebra Hot Pink",
"price": 3.17,
"imUrl": "http://ecx.images-amazon.com/images/I/51fAmVkTbyL._SY300_.jpg",
"related”:
{ "also_bought":[
"B00JHONN1S",
"B002BZX8Z6",
"B00D2K1M3O",
...
"B007R2RM8W"
],
"also_viewed":[
"B002BZX8Z6",
"B00JHONN1S",
"B008F0SU0Y",
...
"B00BFXLZ8M"
],
"bought_together":[
"B002BZX8Z6"
]
},
"salesRank":
{
"Toys & Games":211836
},
"brand": "Coxlures",
"categories":[
[ "Sports & Outdoors",
"Other Sports",
"Dance"
]
]
}
</code></pre></div></div>
<p>Needless to say, we’re not going to be able to load this fully into ram on a regular laptop with 16gb ram (which I used for this exercise).</p>
<p>To parse the json to csv, I iterated through the json file row by row, converted the json into comma-delimited format, and wrote it out to CSV. (Note: This requires that we know the full keys of the json beforehand).</p>
<p>At the end, we have product metadata in nice tabular format. This includes columns for title and description, brand, categories, price, and related products.</p>
<h2 id="getting-product-relationships">Getting product relationships</h2>
<p>To get the product relationships, we need the data in the “related” field. This contains relationships on “also bought”, “also viewed”, “bought together”, etc.</p>
<p>Extracting this requires a bit of extra work as it is contained in a dictionary of lists. Did I mention that it’s also in string format?</p>
<p>To get the relationships, we take the following steps:</p>
<ul>
<li>Evaluate the string and convert to dictionary format</li>
<li>Get the associated product IDs for each relationship</li>
<li>Explode it so each product-pair is a single row with a single relationship</li>
</ul>
<p>In the end, what we have is a skinny three column table, with columns for product 1, product 2, and relationships (i.e., also bought, also viewed, bought together). At this point, each product pair can have multiple relationships between them.</p>
<p>Here’s a sample:</p>
<div class="language-text highlighter-rouge"><div class="highlight"><pre class="highlight"><code>product1 | product2 | relationship
--------------------------------------
B001T9NUFS | B003AVEU6G | also_viewed
0000031895 | B002R0FA24 | also_viewed
B007ZN5Y56 | B005C4Y4F6 | also_viewed
0000031909 | B00538F5OK | also_bought
B00CYBULSO | B00B608000 | also_bought
B004FOEEHC | B00D9C32NI | bought_together
</code></pre></div></div>
<h2 id="converting-relationships-into-a-single-score">Converting relationships into a single score</h2>
<p>Now that we have product-pairs and their relationships, we’ll need to convert them into some kind of single score/weight.</p>
<p>For this exercise, I’ll simplify and assume the relationships are bidirectional (i.e., symmetric in direction). (Note: Product-pair relationships <em>can</em> be asymmetric; people who buy phones would also buy a phone case, but not vice versa).</p>
<p>How do we convert those relationship types into numeric scores?</p>
<p>One simple way is to assign 1.0 if a product-pair have any/multiple relationships, and 0.0 otherwise.</p>
<p>However, this would ignore the various relationship types—should a product pair with an “also bought” relationship have the same score as one that has an “also viewed” relationship?</p>
<p>To address this, weights were assigned based on relationships (bought together = 1.2, also bought = 1.0, also viewed = 0.5) and summed across all unique product pairs. This results in a single numeric score for each product pair (sample below).</p>
<div class="language-text highlighter-rouge"><div class="highlight"><pre class="highlight"><code>product1 | product2 | weight
--------------------------------
B001T9NUFS | B003AVEU6G | 0.5
0000031895 | B002R0FA24 | 0.5
B007ZN5Y56 | B005C4Y4F6 | 0.5
0000031909 | B00538F5OK | 1.0
B00CYBULSO | B00B608000 | 1.0
B004FOEEHC | B00D9C32NI | 1.2
</code></pre></div></div>
<p>For the electronics dataset, there’re 418,749 unique products and 4,005,262 product-pairs (sparsity = 4 million / 420k ** 2 = 0.9999). For books, we have 1,948,370 unique products, and 26,595,848 product pairs (sparsity=0.9999).</p>
<blockquote>
<p>Yeap, recommendation data is <em>very sparse</em>.</p>
</blockquote>
<h2 id="train-validation-split">Train-validation split</h2>
<p>The data sets were randomly split into 2/3 train and 1/3 validation. This can be done with sklearn.train_val_split or random indices. Easy-peasy.</p>
<p>Done, amirite?</p>
<p>Unfortunately, not.</p>
<p>You might have noticed that our dataset of product-pairs consists only of positive cases. Thus, for our validation set (and the training set during training time), we need to create negative samples.</p>
<p>Creating negative samples in an efficient manner is not so straightforward.</p>
<p>Assuming we have 1 million positive product-pairs, to create a validation set with 50:50 positive-negative pairs would mean 1 million negative samples.</p>
<p>If we randomly (and naïvely) sample from our product pool to create these negative samples, it would mean random sampling 2 million times. Calling <code class="language-plaintext highlighter-rouge">random</code> these many times takes very long—believe me, I (naïvely) tried it.</p>
<p>To get around this, I applied this <em>hack</em>:</p>
<ul>
<li>Put the set of products in an array</li>
<li>Shuffle the array</li>
</ul>
<p>For each iteration, take a slice of the array at the iteration x 2</p>
<ul>
<li>If iteration = 0, product-pair = array[0: 0+2]</li>
<li>If iteration = 1, product-pair = array[2:, 2+2]</li>
<li>If iteration = 10, product-pair = array[20: 20+2]</li>
<li>Once the array is exhausted, (re)shuffle and repeat</li>
</ul>
<blockquote>
<p>This greatly reduced the amount of random operations required and was about 100x faster than the naïve approach.</p>
</blockquote>
<h2 id="collaborating-filtering-how-it-is-commonly-known">Collaborating filtering (how it is commonly known)</h2>
<p>Collaborative filtering uses information on user behaviours, activities, or preferences to predict what other users will like based on item or user similarity. In contrast, content filtering is based solely on item metadata (i.e., brand, price, category, etc.).</p>
<p>Most collaborative filtering articles are on user-item collaborative filtering (more specifically, matrix factorization). And there’s always an (obligatory) user-item matrix (Fig. 1).</p>
<p><img src="/assets/recsys_fig1.webp" class="center" loading="lazy" /></p>
<p class="image-caption">Figure 1. Cliché representation of collaborative filtering</p>
<p>However, if we don’t have user data (like in this case), can this still work?</p>
<p>Why not?</p>
<p>Instead of a user-item matrix, we have an item-item matrix. We then learn latent factors for each item and determine how strongly they’re related to other items.</p>
<p>One way to do this is to load the entire item-item matrix (in memory) and apply something like Python’s <a href="http://surpriselib.com" target="_blank">surprise</a> or SparkML’s <a href="https://spark.apache.org/docs/2.2.0/ml-collaborative-filtering.html" target="_blank">Alternating Least Squares</a>.</p>
<p>However, this can be very resource intensive if you have to load the entire dataset into memory or apply some distributed learning approach.</p>
<blockquote>
<p>Our datasets are very sparse (99.99% empty). Can we make use of the sparsity to make it more resource efficient? (Hint: Yes, we can.)</p>
</blockquote>
<h2 id="implementation-1-matrix-factorization-iteratively-pair-by-pair">Implementation 1: Matrix Factorization (iteratively pair by pair)</h2>
<p>One way to reduce the memory footprint is to perform matrix factorization product-pair by product-pair, without fitting it all into memory. Let’s discuss how to implement this in PyTorch.</p>
<p>First, we load the product-pairs (just the pairs, not the entire matrix) into an array. To iterate through all samples, we just need to iterate through the array.</p>
<p>Next, we need to create negative product-pair samples. Here’s the approach taken to generate negative samples:</p>
<ul>
<li>For each product pair (e.g., 001-002), we take the product on the left (i.e., 001) and pair it with n (e.g., five) negative product samples to form negative product-pairs</li>
<li>The negative samples are based on the set of products available, with the probability of each product being sampled proportional to their frequency of occurrence in the training set</li>
</ul>
<p>Thus, each (positive) product-pair (i.e., 001-002) will also have five related negative product-pairs during training.</p>
<h3 id="continous-labels">Continous labels</h3>
<p>For each product-pair, we have numeric scores based on some weightage (bought together = 1.2, also bought = 1.0, also viewed = 0.5). Let’s first train on these continuous labels. This is similar to working with explicit ratings.</p>
<h3 id="binary-labels">Binary labels</h3>
<p>To do it in the binary case (such as with implicit feedback), actual scores greater than 0 are converted to 1. Then, a final sigmoid layer is added to convert the score to between 0 – 1. Also, we use a loss function like binary cross entropy (BCE).</p>
<h3 id="regularization">Regularization</h3>
<p>Regularization—no doubt it’s key in machine learning. How can we apply it?</p>
<p>One approach is adding L2 regularization to ensure embeddings weights don’t grow too large. We do this by by adding a cost of <code class="language-plaintext highlighter-rouge">sum(embedding.weights**2) * C</code> (regularization param) to the total loss.</p>
<p>At a high level, for each pair:</p>
<ul>
<li>Get the embedding for each product</li>
<li>Multiply embeddings and sum the resulting vector (this is the prediction)</li>
<li>Reduce the difference between predicted score and actual score (via gradient descent and a loss function like mean squared error or BCE)</li>
</ul>
<p>Here’s some pseudo-code on how iterative matrix factorization would work:</p>
<figure class="highlight"><pre><code class="language-python" data-lang="python"><span class="k">for</span> <span class="n">product_pair</span><span class="p">,</span> <span class="n">label</span> <span class="ow">in</span> <span class="n">train_set</span><span class="p">:</span>
<span class="c1"># Get embedding for each product
</span> <span class="n">product1_emb</span> <span class="o">=</span> <span class="n">embedding</span><span class="p">(</span><span class="n">product1</span><span class="p">)</span>
<span class="n">product2_emb</span> <span class="o">=</span> <span class="n">embedding</span><span class="p">(</span><span class="n">product2</span><span class="p">)</span>
<span class="c1"># Predict product-pair score (interaction term and sum)
</span> <span class="n">prediction</span> <span class="o">=</span> <span class="n">sig</span><span class="p">(</span><span class="nb">sum</span><span class="p">(</span><span class="n">product1_emb</span> <span class="o">*</span> <span class="n">product2_emb</span><span class="p">,</span> <span class="n">dim</span><span class="o">=</span><span class="mi">1</span><span class="p">))</span>
<span class="n">l2_reg</span> <span class="o">=</span> <span class="k">lambda</span> <span class="o">*</span> <span class="nb">sum</span><span class="p">(</span><span class="n">embedding</span><span class="p">.</span><span class="n">weight</span> <span class="o">**</span> <span class="mi">2</span><span class="p">)</span>
<span class="c1"># Minimize loss
</span> <span class="n">loss</span> <span class="o">=</span> <span class="n">BinaryCrossEntropyLoss</span><span class="p">(</span><span class="n">prediction</span><span class="p">,</span> <span class="n">label</span><span class="p">)</span>
<span class="n">loss</span> <span class="o">+=</span> <span class="n">l2_reg</span>
<span class="n">loss</span><span class="p">.</span><span class="n">backward</span><span class="p">()</span>
<span class="n">optimizer</span><span class="p">.</span><span class="n">step</span><span class="p">()</span></code></pre></figure>
<h3 id="training-schedule">Training Schedule</h3>
<p>For the training schedule, we run it over 5 epochs with cosine annealing. For each epoch, learning rate starts high (0.01) and drops rapidly to a minimum value near zero, before being reset for to the next epoch (Fig. 2).</p>
<p><img src="/assets/recsys_fig2.webp" loading="lazy" alt="Image" /></p>
<p class="image-caption">Figure 2. Cosine Annealing learning rate schedule</p>
<h2 id="results">Results</h2>
<p>For the smaller electronics dataset (420k unique products with 4 million pairs), it took 45 minutes for 5 epochs—doesn’t seem too bad.</p>
<blockquote>
<p>Training on binary labels (1 vs. 0), we get a ROC-AUC of 0.8083. Not bad considering that random choice leads to ROC-AUC of 0.5.</p>
</blockquote>
<p>From the learning curve (Fig. 3) below, you’ll see that one epoch is sufficient to achieve close to optimal ROC-AUC. Interestingly, each time the learning rate is reset, the model seems to need to “relearn” the embeddings from scratch (AUC-ROC drops to near 0.5).</p>
<p><img src="/assets/recsys_fig3.webp" loading="lazy" alt="Image" /></p>
<p class="image-caption">Figure 3. AUC-ROC across epochs for matrix factorization; Each time learning rate is reset, the model seems to ”forget”, causing AUC-ROC to revert to ~0.5. Also, a single epoch seems sufficient.</p>
<p>However, if we look at the precision-recall curves below (Fig. 4), you see that at around 0.5 we hit the <em>“cliff of death”</em>. If we estimate the threshold slightly too low, precision drops from close to 1.0 to 0.5; slightly too high and recall is poor.</p>
<p><img src="/assets/recsys_fig4.webp" loading="lazy" alt="Image" /></p>
<p class="image-caption">Figure 4. Precision recall curves for Matrix Factorization (binary labels).</p>
<p>Using the continuous labels, performance seems significantly better (AUC-ROC = 0.9225) but we see the same cliff of death (Fig. 5). Nonetheless, this does suggest that explicit (i.e., scale) ratings can perform better than implicit ratings.</p>
<p><img src="/assets/recsys_fig5.webp" loading="lazy" alt="Image" /></p>
<p class="image-caption">Figure 5. Precision recall curves for Matrix Factorization (continuous labels).</p>
<details><summary>Why AUC-ROC for continuous labels?</summary>
<div class="detail-highlight">
<p>TL;DR: While we use continuous labels for training, the output layer is a sigmoid that return scores from 0 - 1.</p>
<hr />
<p><em>Why use continuous labels?</em> Because they’re able to better distinguish the strength of product-pair relationships. Here’s a breakdown on binary vs. continuous labels.</p>
<p><strong>Binary labels</strong>: A pair of products have a label of 1 if they have any, or multiple, relationships (e.g., <code class="language-python highlighter-rouge"><span class="n">also</span> <span class="n">viewed</span></code>, <code class="language-python highlighter-rouge"><span class="n">also</span> <span class="n">bought</span></code>, <code class="language-python highlighter-rouge"><span class="n">bought</span> <span class="n">together</span></code>); zero otherwise.</p>
<p>This means that a pair of products which only have the <code class="language-python highlighter-rouge"><span class="n">also</span> <span class="n">viewed</span></code> will have the same label as a pair of products which have all three relationships (i.e., <code class="language-python highlighter-rouge"><span class="n">also</span> <span class="n">viewed</span></code>, <code class="language-python highlighter-rouge"><span class="n">also</span> <span class="n">bought</span></code>, <code class="language-python highlighter-rouge"><span class="n">bought</span> <span class="n">together</span></code>). While this approach can tell us if a pair of products have, or do not have, a relationship, it doesn’t distinguish the strength of the relationship.</p>
<p><strong>Continuous labels</strong>: To distinguish between the strengths of relationships, we use the following labels (instead of 1 or 0) - <code class="language-python highlighter-rouge"><span class="n">bought</span> <span class="n">together</span></code> = 1.2, <code class="language-python highlighter-rouge"><span class="n">also</span> <span class="n">bought</span></code> = 1.0, <code class="language-python highlighter-rouge"><span class="n">also</span> <span class="n">viewed</span></code> = 0.5.</p>
<p>As a result, binary labels have values of 0 or 1.0 while continuous labels have values of 0, 0.5, 1.0, 1,2.</p>
<hr />
<p><em>Regardless of the type of label, we get predictions from a simple sigmoid</em>, and predictions will range from 0 - 1. (See code for matrix factorization on <a href="https://github.com/eugeneyan/recsys-nlp-graph/blob/master/src/ml/mf.py#L33" target="_blank">binary labels</a> and <a href="https://github.com/eugeneyan/recsys-nlp-graph/blob/master/src/ml/mf_continuous.py#L40" target="_blank">continuous labels</a>). Nonetheless, we use binary cross entropy loss for binary labels, and mean square error loss for continuous labels.</p>
<p>Given that the final layer for both binary and continuous labels is a sigmoid, we can use ROC AUC for both, making the results for both approaches comparable.</p>
</div>
</details>
<p>This baseline model only captures relationships between each product. But what if a product is <em>generally</em> popular or unpopular?</p>
<p>We can add biases. Implementation wise, it’s a single number for each product.</p>
<h2 id="implementation-2-matrix-factorization-with-bias">Implementation 2: Matrix Factorization with Bias</h2>
<p>If we just observe the AUC-ROC metric, adding bias doesn’t seem to help, where AUC-ROC decreases from 0.8083 to 0.7951 on binary labels, and from 0.9335 to 0.8319 on continuous labels.</p>
<p>However, if we examine the precision-recall curves, adding bias reduces the steepness of the curves where they intersect, making it more production-friendly (i.e., putting it into production). Here are the curves for both binary (Fig. 6) and continuous labels (Fig. 7).</p>
<p><img src="/assets/recsys_fig6.webp" loading="lazy" alt="Image" /></p>
<p class="image-caption">Figure 6. Precision recall curves for Matrix Factorization + bias (binary labels).</p>
<p><img src="/assets/recsys_fig7.webp" loading="lazy" alt="Image" /></p>
<p class="image-caption">Figure 7. Precision recall curves for Matrix Factorization + bias (continuous labels).</p>
<p>It may seem alarming that AUC-ROC on continuous labels drops sharply (0.9335 to 0.8319), but it shouldn’t be—it’s an artefact of how AUC-ROC is measured.</p>
<p>In the ROC curve for the continuous labels without bias (Fig. 8a), false positives only start to occur after about 0.75 of true positives are identified. Beyond the threshold of 0.5, all false positives are introduced (i.e., precision curve cliff of death in Fig. 5). The ROC curve and AUC-ROC metric doesn’t make this very observable and the AUC-ROC appears significantly better (but it really isn’t).</p>
<p><img src="/assets/recsys_fig8.webp" loading="lazy" alt="Image" /></p>
<p class="image-caption">Figure 8a (left) and 8b (right). ROC curves with and without bias.</p>
<p>On the larger books dataset, it took about 22 hours for 5 epochs—this approach seems to scale more than linearly based on the number of product-pairs (i.e., scales badly). Unfortunately, the AUC-ROC stays around 0.5 during training.</p>
<h2 id="key-takeaways">Key takeaways</h2>
<p>The (iterative) matrix factorization approach seems to do okay for a baseline, achieving decent AUC-ROC of ~0.8.</p>
<p>While the baseline approach (without bias) does well, it suffers from sharp cliffs on the precision curve. Adding bias improves on this significantly.</p>
<p>More importantly, we learnt that one shouldn’t just look at numeric metrics to understand how a machine learning model is doing. Plotting the curves can be very useful to better understand how your model performs, especially if it’s classification-based and you need to arbitrarily set some threshold.</p>
<h2 id="whats-next">What’s next?</h2>
<p>Wait, isn’t this still matrix factorization, albeit in an iterative, less memory-intensive form? Where’s the graph and NLP approaches? You tricked me!</p>
<p>Yes, the current post only covers the baseline, albeit in an updated form.</p>
<blockquote>
<p>Before trying any new-fangled techniques, we have to <em>first</em> establish a baseline, which is what this post does.</p>
</blockquote>
<p>In the next <a href="/writing/recommender-systems-graph-and-nlp-pytorch/" target="_blank">post</a>, we’ll apply graph and NLP techniques to the problem of recommender systems.</p>
<p>P.S. Looking for the code for this? Available on github: <a href="https://github.com/eugeneyan/recsys-nlp-graph" target="_blank">recsys-nlp-graph</a></p>
<h2 id="references">References</h2>
<p>McAuley, J., Targett, C., Shi, Q., & Van Den Hengel, A. (2015, August). Image-based recommendations on styles and substitutes. In Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 43-52). ACM.</p>
<br>
<p>If you found this useful, please cite this write-up as:</p>
<blockquote class="blockquote-citation">
<p>Yan, Ziyou. (Jan 2020). Building a Strong Baseline Recommender in PyTorch, on a Laptop. eugeneyan.com.
https://eugeneyan.com/writing/recommender-systems-baseline-pytorch/.</p>
</blockquote>
<p>or</p>
<div class="citation"><pre><code>@article{yan2020matrix,
title = {Building a Strong Baseline Recommender in PyTorch, on a Laptop},
author = {Yan, Ziyou},
journal = {eugeneyan.com},
year = {2020},
month = {Jan},
url = {https://eugeneyan.com/writing/recommender-systems-baseline-pytorch/}
}</code></pre>
</div>
<br>
<style>
#share-buttons {
display: inline-block;
vertical-align: middle;
}
#share-buttons:after {
content: "";
display: block;
clear: both;
}
#share-buttons > div {
position: relative;
text-align: left;
height: 36px;
width: 32px;
float: left;
text-align: center;
}
#share-buttons > div > svg {
height: 16px;
fill: #808080;
margin-top: 10px;
}
#share-buttons > div:hover {
cursor: pointer;
}
</style>
<span style="font-size: 18px">Share on: </span>
<div id="share-buttons">
<div class="twitter" title="Share this on Twitter" onclick="if (!window.__cfRLUnblockHandlers) return false; window.open('https://twitter.com/intent/tweet?text=Great read! Building a Strong Baseline Recommender in PyTorch, on a Laptop&url=https://eugeneyan.com/writing/recommender-systems-baseline-pytorch/&via=eugeneyan', 'pop-up', 'left=20,top=20,width=500,height=500,toolbar=1,resizable=0');" data-cf-modified-f28497f9592da7f32b5a2b50-="">
<img class="icon about-icon-large" src="/assets/icon-twitter.svg" loading="lazy" alt=""/>
</div>
<div class="linkedin" title="Share this on Linkedin" onclick="if (!window.__cfRLUnblockHandlers) return false; window.open('https://www.linkedin.com/shareArticle?mini=true&url=https://eugeneyan.com/writing/recommender-systems-baseline-pytorch/&source=eugeneyan.com', 'pop-up', 'left=20,top=20,width=500,height=500,toolbar=1,resizable=0');" data-cf-modified-f28497f9592da7f32b5a2b50-="">
<img class="icon about-icon-large" src="/assets/icon-linkedin.svg" loading="lazy" alt=""/>
</div>
<div class="bluesky" title="Share this on Bluesky" onclick="if (!window.__cfRLUnblockHandlers) return false; window.open('https://bsky.app/intent/compose?text=Great read! Building a Strong Baseline Recommender in PyTorch, on a Laptop https://eugeneyan.com/writing/recommender-systems-baseline-pytorch/', 'pop-up', 'left=20,top=20,width=500,height=500,toolbar=1,resizable=0');" data-cf-modified-f28497f9592da7f32b5a2b50-="">
<img class="icon about-icon-large" src="/assets/bluesky.svg" loading="lazy" alt=""/>
</div>
<div class="facebook fb-share-button" title="Share this on Facebook" onclick="if (!window.__cfRLUnblockHandlers) return false; window.open('https://www.facebook.com/dialog/share?app_id=249237293114028&display=popup&href=https://eugeneyan.com/writing/recommender-systems-baseline-pytorch/&&redirect_uri=https://eugeneyan.com/writing/recommender-systems-baseline-pytorch/', 'pop-up', 'left=20,top=20,width=500,height=500,toolbar=1,resizable=0');" data-cf-modified-f28497f9592da7f32b5a2b50-="">
<img class="icon about-icon-large" src="/assets/icon-facebook.svg" loading="lazy" alt=""/>
</div>
<div class="mail" title="Share this through Email" onclick="if (!window.__cfRLUnblockHandlers) return false; window.open('mailto:?subject=Great read! Building a Strong Baseline Recommender in PyTorch, on a Laptop&body=https://eugeneyan.com/writing/recommender-systems-baseline-pytorch/');" data-cf-modified-f28497f9592da7f32b5a2b50-="">
<img class="icon about-icon-large" src="/assets/icon-mail.svg" loading="lazy" alt=""/>
</div>
</div>
</div>
<!-- Page navigation -->
<hr>
<div id="algolia-recs-container" style="display: none;">
<div id="algolia-related-products" style="margin-bottom: 2em;"></div>
<div id="algolia-fbt"></div>
<style>
/* Common styles for both recommendation widgets */
.algolia-recs-section-header {
font-family: 'Raleway', Helvetica, sans-serif;
font-size: 1em; /* Adjust as needed, smaller than default h3 */
font-weight: bold;
margin-top: 0; /* Remove or reduce top margin */
margin-bottom: 15px; /* Space between header and recommendation cards */
color: var(--c-text); /* Use theme's text color */
font-style: italic;
}
/* Related Products Widget Styles */
#algolia-related-products .ais-RelatedProducts-list {
display: flex;
flex-direction: row; /* Arrange items horizontally */
flex-wrap: nowrap; /* Prevent wrapping to new lines, if possible */
justify-content: flex-start; /* Align items to the start of the container */
padding-left: 0; /* Remove default list padding */
list-style-type: none; /* Remove list bullets */
margin: 0;
}
#algolia-related-products .ais-RelatedProducts-item {
width: 32%; /* Adjust for 3 items: 32% * 3 items + 2% * 2 margins = 100% */
margin-right: 2%;
box-sizing: border-box; /* Include padding and border in the element's total width */
/* Optional: Basic card styling (uncomment to use) */
border: 1px solid color-mix(in srgb, var(--c-background) 85%, var(--c-text) 15%); /* Theme-aware light grey border */
padding: 0; /* Remove overall card padding, will be handled by elements */
text-align: left; /* Or 'center' if you prefer */
background-color: var(--c-background);
border-radius: 4px;
box-shadow: 0 2px 4px rgba(0,0,0,0.1);
}
#algolia-related-products .ais-RelatedProducts-item:last-child {
margin-right: 0; /* No margin for the last item in the row */
}
/* Styling for images within recommendation items */
#algolia-related-products .ais-RelatedProducts-item img {
display: block; /* Can help remove extra space below image */
width: calc(100% - 4px); /* Full width minus 2px L/R margins */
max-width: 100%; /* Ensures image does not exceed container if intrinsically smaller */
/* height: auto; -- Controlled by inline style's max-height and object-fit */
object-fit: cover; /* Ensure image covers the area, also in inline style */
margin: 2px; /* 2px margin on top, left, right. Bottom is overridden by inline style. */
/* margin-bottom: 8px; -- This is set by inline style in JS template */
}
/* Styling for the wrapper link to make the whole card clickable */
#algolia-related-products .ais-RelatedProducts-item a.ais-RelatedProducts-item-link-wrapper {
display: block; /* Make the link fill the list item */
text-decoration: none; /* Remove underline */
color: inherit; /* Use parent's text color */
}
#algolia-related-products .related-product-title {
font-family: 'Raleway', Helvetica, sans-serif;
font-size: 0.75em;
display: -webkit-box;
-webkit-line-clamp: 2; /* Limit to 2 lines for WebKit browsers */
line-clamp: 2; /* Standard property */
-webkit-box-orient: vertical;
overflow: hidden;
text-overflow: ellipsis;
padding: 0 7px 7px 7px; /* 0 top, 7px L/R/B for text area */
line-height: 1.5; /* Adjust for better readability */
height: 3.3em; /* Current height: 3.3em. For 2 lines with 0.75em font & 1.5 line-height, calculated height would be 2.25em. */
color: var(--c-interactive); /* Use theme's interactive color */
}
/* This container will wrap the image and score, taking the original image's layout space. */
#algolia-related-products .ais-RelatedProducts-item .recommendation-image-container {
position: relative; /* For positioning the score absolutely within */
display: block; /* Matches original image display and ensures proper block layout */
width: calc(100% - 4px); /* Adopts width from original image styling */
margin: 2px; /* Adopts margin from original image styling */
margin-bottom: 8px; /* Adopts specific bottom margin from original image's inline style */
line-height: 0; /* Prevents unexpected space if child elements are treated as inline */
}
/* The image itself, now filling the container */
#algolia-related-products .ais-RelatedProducts-item .recommendation-image-container img {
display: block;
width: 100%; /* Fill the container's width */
max-width: 20em; /* Optional: retain original max-width constraint for the image content */
height: auto; /* Maintain aspect ratio by default */
max-height: 12em; /* Constrain image height (adjust as needed) */
object-fit: cover; /* Ensures image covers the allocated space, cropping if necessary */
margin: 0 auto; /* Center image if max-width kicks in and it's narrower than container */
}
/* The score overlay box */
#algolia-related-products .ais-RelatedProducts-item .recommendation-score {
position: absolute;
bottom: 3px; /* Padding from the bottom edge of the container */
right: 3px; /* Padding from the right edge of the container */
background-color: color-mix(in srgb, var(--c-background) 85%, var(--green) 15%); /* Theme-aware light green */
color: var(--green); /* Theme's green color for text */
padding: 3px 6px; /* Slightly adjusted padding */
font-family: 'Raleway', Helvetica, sans-serif;
font-size: 0.75em;
font-weight: bold;
border-radius: 10px; /* More rounded corners like the example */
border: 1px solid var(--green); /* Theme's green color for border */
line-height: 1; /* Critical for small text in a small box */
z-index: 10; /* Ensure it's above the image */
box-shadow: 0 1px 2px rgba(0,0,0,0.15); /* Softer shadow */
display: flex; /* To align icon and text nicely */
align-items: center; /* Vertically center icon and text */
}
/* Styling for the SVG icon within the score box */
#algolia-related-products .ais-RelatedProducts-item .recommendation-score-icon {
width: 0.9em; /* Scale with score's font size */
height: 0.9em;
vertical-align: -0.1em; /* Fine-tune vertical alignment */
margin-right: 4px; /* Space between icon and score number */
fill: var(--green); /* Theme's green color for icon */
}
/* Frequently Bought Together Widget Styles */
#algolia-fbt .ais-FrequentlyBoughtTogether-list {
display: flex;
flex-direction: row; /* Arrange items horizontally */
flex-wrap: nowrap; /* Prevent wrapping to new lines, if possible */
justify-content: flex-start; /* Align items to the start of the container */
padding-left: 0; /* Remove default list padding */
list-style-type: none; /* Remove list bullets */
margin: 0;
}
#algolia-fbt .ais-FrequentlyBoughtTogether-item {
width: 32%; /* Adjust for 3 items: 32% * 3 items + 2% * 2 margins = 100% */
margin-right: 2%;
box-sizing: border-box; /* Include padding and border in the element's total width */
/* Optional: Basic card styling (uncomment to use) */
border: 1px solid color-mix(in srgb, var(--c-background) 85%, var(--c-text) 15%); /* Theme-aware light grey border */
padding: 0; /* Remove overall card padding, will be handled by elements */
text-align: left; /* Or 'center' if you prefer */
background-color: var(--c-background);
border-radius: 4px;
box-shadow: 0 2px 4px rgba(0,0,0,0.1);
}
#algolia-fbt .ais-FrequentlyBoughtTogether-item:last-child {
margin-right: 0; /* No margin for the last item in the row */
}
/* Styling for images within recommendation items */
#algolia-fbt .ais-FrequentlyBoughtTogether-item img {
display: block; /* Can help remove extra space below image */
width: calc(100% - 4px); /* Full width minus 2px L/R margins */
max-width: 100%; /* Ensures image does not exceed container if intrinsically smaller */
/* height: auto; -- Controlled by inline style's max-height and object-fit */
object-fit: cover; /* Ensure image covers the area, also in inline style */
margin: 2px; /* 2px margin on top, left, right. Bottom is overridden by inline style. */
/* margin-bottom: 8px; -- This is set by inline style in JS template */
}
/* Styling for the wrapper link to make the whole card clickable */
#algolia-fbt .ais-FrequentlyBoughtTogether-item a.ais-FrequentlyBoughtTogether-item-link-wrapper {
display: block; /* Make the link fill the list item */
text-decoration: none; /* Remove underline */
color: inherit; /* Use parent's text color */
}
#algolia-fbt .fbt-product-title {
font-family: 'Raleway', Helvetica, sans-serif;
font-size: 0.75em;
display: -webkit-box;
-webkit-line-clamp: 2; /* Limit to 2 lines for WebKit browsers */
line-clamp: 2; /* Standard property */
-webkit-box-orient: vertical;
overflow: hidden;
text-overflow: ellipsis;
padding: 0 7px 7px 7px; /* 0 top, 7px L/R/B for text area */
line-height: 1.5; /* Adjust for better readability */
height: 3.3em; /* Current height: 3.3em. For 2 lines with 0.75em font & 1.5 line-height, calculated height would be 2.25em. */
color: var(--c-interactive); /* Use theme's interactive color */
}
/* This container will wrap the image and score, taking the original image's layout space. */
#algolia-fbt .ais-FrequentlyBoughtTogether-item .recommendation-image-container {
position: relative; /* For positioning the score absolutely within */
display: block; /* Matches original image display and ensures proper block layout */
width: calc(100% - 4px); /* Adopts width from original image styling */
margin: 2px; /* Adopts margin from original image styling */
margin-bottom: 8px; /* Adopts specific bottom margin from original image's inline style */
line-height: 0; /* Prevents unexpected space if child elements are treated as inline */
}
/* The image itself, now filling the container */
#algolia-fbt .ais-FrequentlyBoughtTogether-item .recommendation-image-container img {
display: block;
width: 100%; /* Fill the container's width */
max-width: 20em; /* Optional: retain original max-width constraint for the image content */
height: auto; /* Maintain aspect ratio by default */
max-height: 12em; /* Constrain image height (adjust as needed) */
object-fit: cover; /* Ensures image covers the allocated space, cropping if necessary */
margin: 0 auto; /* Center image if max-width kicks in and it's narrower than container */
}
/* The score overlay box */
#algolia-fbt .ais-FrequentlyBoughtTogether-item .recommendation-score {
position: absolute;
bottom: 3px; /* Padding from the bottom edge of the container */
right: 3px; /* Padding from the right edge of the container */
background-color: color-mix(in srgb, var(--c-background) 85%, var(--green) 15%); /* Theme-aware light green */
color: var(--green); /* Theme's green color for text */
padding: 3px 6px; /* Slightly adjusted padding */
font-family: 'Raleway', Helvetica, sans-serif;
font-size: 0.75em;
font-weight: bold;
border-radius: 10px; /* More rounded corners like the example */
border: 1px solid var(--green); /* Theme's green color for border */
line-height: 1; /* Critical for small text in a small box */
z-index: 10; /* Ensure it's above the image */
box-shadow: 0 1px 2px rgba(0,0,0,0.15); /* Softer shadow */
display: flex; /* To align icon and text nicely */
align-items: center; /* Vertically center icon and text */
}
/* Styling for the SVG icon within the score box */
#algolia-fbt .ais-FrequentlyBoughtTogether-item .recommendation-score-icon {
width: 0.9em; /* Scale with score's font size */
height: 0.9em;
vertical-align: -0.1em; /* Fine-tune vertical alignment */
margin-right: 4px; /* Space between icon and score number */
fill: var(--green); /* Theme's green color for icon */
}
</style>
<script type="f28497f9592da7f32b5a2b50-text/javascript">
// Function to load a script and return a promise
function loadScript(src) {
return new Promise((resolve, reject) => {
if (document.querySelector(`script[src="${src}"]`)) {
resolve(); // Already loaded
return;
}
const script = document.createElement('script');
script.src = src;
script.onload = () => resolve();
script.onerror = () => reject(new Error(`Script load error for ${src}`));
document.head.appendChild(script);
});
}
function initAlgoliaRecommendations() {
Promise.all([
loadScript('https://cdn.jsdelivr.net/npm/algoliasearch@4/dist/algoliasearch-lite.umd.js'),
loadScript('https://cdn.jsdelivr.net/npm/instantsearch.js@4')
])
.then(() => {
// Initialize the Related Products widget
initRelatedProducts();
// Initialize the Frequently Bought Together widget
initFrequentlyBoughtTogether();
})
.catch(error => {
// Handle error silently
});
}
function initRelatedProducts() {
// Ensure container exists
if (!document.getElementById('algolia-related-products')) {
// Container not found, stopping initialization
return;
}
const recSearchClient = algoliasearch(
'2XJCLEABQD',
'b61ec4cb64bd32d62c053466fccbfa43'
);
const relatedSearch = instantsearch({
indexName: 'eugeneyan.com',
searchClient: recSearchClient,
clickAnalytics: true,
insights: true, // Enable insights for click tracking on recommendations
});
relatedSearch.addWidgets([
instantsearch.widgets.relatedProducts({
container: '#algolia-related-products',
objectIDs: ['/writing/recommender-systems-baseline-pytorch/'],
limit: 3,
queryParameters: {
attributesToRetrieve: ['title', 'url', 'image', 'score', '_score'], // Specify only needed attributes
attributesToHighlight: [], // Disable highlighting
attributesToSnippet: [] // Disable snippeting
},
translations: {
title: '', // Custom title is in _layouts/post.html
},
transformItems: function(items) {
const containerElement = document.getElementById('algolia-recs-container');
const relatedElement = document.getElementById('algolia-related-products');
// Hide the Related Products container element first if there are no items
if (items.length === 0 && relatedElement) {
relatedElement.style.display = 'none';
} else if (relatedElement) {
relatedElement.style.display = 'block';
}
// Then handle the main recommendations container visibility
if (items.length > 0 && containerElement) {
containerElement.style.display = 'block';
} else if (containerElement && !document.getElementById('algolia-fbt').hasChildNodes()) {
containerElement.style.display = 'none';
} else {
}
return items;
},
templates: {
header() { // Removed unused results, html parameters
// Return a PLAIN string for the header
return '<h4 class="algolia-recs-section-header">You Might Also Like (content-based)</h4>';
},
item: function(hit, { html, sendEvent }) { // Added sendEvent to params
const itemUrl = `${hit.url || '#'}`;
const indexName = 'eugeneyan.com'; // Get index name for insights
let imageUrl;
// Ensure hit.image is not null, undefined, or an empty/whitespace string before using it.
if (hit.image && typeof hit.image === 'string' && hit.image.trim() !== '') {
imageUrl = `/assets/og_image/${hit.image}`;
} else {
imageUrl = `/assets/og_image/default-v4.jpg`; // Default image
}
let scoreValue = null;
if (typeof hit.score === 'number') scoreValue = hit.score.toFixed(2);
else if (typeof hit._score === 'number') scoreValue = hit._score.toFixed(2);
// else if (typeof hit.your_custom_score_field === 'number') scoreValue = hit.your_custom_score_field.toFixed(2);
const scoreElement = scoreValue ? `<div class="recommendation-score"><svg viewbox="0 0 24 24" class="recommendation-score-icon" xmlns="http://www.w3.org/2000/svg"><path d="M16 6l2.29 2.29-4.88 4.88-4-4L2 16.59 3.41 18l6-6 4 4 6.3-6.29L22 12V6h-6z"></path></svg>${scoreValue}</div>` : '';
const imageAndScoreTag = `
<div class="recommendation-image-container">
<img src="${imageUrl}" alt="${hit.title || 'Recommendation cover image'}">
${scoreElement}
</div>`;
const title = hit.title || 'Untitled Post';
return `
<a href="${itemUrl}"
class="ais-RelatedProducts-item-link-wrapper"
onClick="${() => {
sendEvent('click', hit, 'Related Item Clicked');
}}"
>
${imageAndScoreTag}
<div class="related-product-title">${title}</div>
</a>
`;
},
empty(results, { html }) {
const containerElement = document.getElementById('algolia-recs-container');
const relatedElement = document.getElementById('algolia-related-products');
// Hide Related Products container since there are no results
if (relatedElement) {
relatedElement.style.display = 'none';
}
// Check if the FBT widget also has no items before hiding the main container
const fbtWidgetContainer = document.getElementById('algolia-fbt');
if (containerElement && (!fbtWidgetContainer || !fbtWidgetContainer.hasChildNodes())) {
containerElement.style.display = 'none';
}
// Return an empty string to prevent rendering 'undefined'
return '';
}
}
})
]);
relatedSearch.start();
}
function initFrequentlyBoughtTogether() {
// Ensure container exists
if (!document.getElementById('algolia-fbt')) {
// Container not found, stopping initialization
return;
}
const recSearchClient = algoliasearch(
'2XJCLEABQD',
'b61ec4cb64bd32d62c053466fccbfa43'
);
const fbtSearch = instantsearch({
indexName: 'eugeneyan.com',
searchClient: recSearchClient,
clickAnalytics: true,
insights: true, // Enable insights for click tracking on recommendations
});
fbtSearch.addWidgets([
instantsearch.widgets.frequentlyBoughtTogether({
container: '#algolia-fbt',
objectIDs: ['/writing/recommender-systems-baseline-pytorch/'],
limit: 3,
queryParameters: {
attributesToRetrieve: ['title', 'url', 'image', 'score', '_score'], // Specify only needed attributes
attributesToHighlight: [], // Disable highlighting
attributesToSnippet: [] // Disable snippeting
},
translations: {
title: '', // Custom title is in _layouts/post.html
},
transformItems: function(items) {
const containerElement = document.getElementById('algolia-recs-container');
if (items.length > 0 && containerElement) {
containerElement.style.display = 'block';
} else if (containerElement && !document.getElementById('algolia-related-products').hasChildNodes()) {
containerElement.style.display = 'none';
} else {
}
return items;
},
templates: {
header() {
// Return a PLAIN string for the header - only if we have items to display
// The header should not render if there's no content
return '<h4 class="algolia-recs-section-header">Frequently Read Together (behavioral-based)</h4>';
},
item: function(hit, { html, sendEvent }) {
const itemUrl = `${hit.url || '#'}`;
const indexName = 'eugeneyan.com'; // Get index name for insights
let imageUrl;
// Ensure hit.image is not null, undefined, or an empty/whitespace string before using it.
if (hit.image && typeof hit.image === 'string' && hit.image.trim() !== '') {
imageUrl = `/assets/og_image/${hit.image}`;
} else {
imageUrl = `/assets/og_image/default-v4.jpg`; // Default image
}
let scoreValue = null;
if (typeof hit.score === 'number') scoreValue = hit.score.toFixed(2);
else if (typeof hit._score === 'number') scoreValue = hit._score.toFixed(2);
// else if (typeof hit.your_custom_score_field === 'number') scoreValue = hit.your_custom_score_field.toFixed(2);
const scoreElement = scoreValue ? `<div class="recommendation-score"><svg viewbox="0 0 24 24" class="recommendation-score-icon" xmlns="http://www.w3.org/2000/svg"><path d="M16 6l2.29 2.29-4.88 4.88-4-4L2 16.59 3.41 18l6-6 4 4 6.3-6.29L22 12V6h-6z"></path></svg>${scoreValue}</div>` : '';
const imageAndScoreTag = `
<div class="recommendation-image-container">
<img src="${imageUrl}" alt="${hit.title || 'Recommendation cover image'}">
${scoreElement}
</div>`;
const title = hit.title || 'Untitled Post';
return `
<a href="${itemUrl}"
class="ais-FrequentlyBoughtTogether-item-link-wrapper"
onClick="${() => {
sendEvent('click', hit, 'FBT Item Clicked');
}}"
>
${imageAndScoreTag}
<div class="fbt-product-title">${title}</div>
</a>
`;
},
empty(results, { html }) {
const containerElement = document.getElementById('algolia-recs-container');
const fbtElement = document.getElementById('algolia-fbt');
// Hide FBT container since there are no results
if (fbtElement) {
fbtElement.style.display = 'none';
}
// Check if the Related Products widget also has no items before hiding the main container
const relatedWidgetContainer = document.getElementById('algolia-related-products');
if (containerElement && (!relatedWidgetContainer || !relatedWidgetContainer.hasChildNodes())) {
containerElement.style.display = 'none';
}
// Return an empty string to prevent rendering 'undefined'
return '';
}
}
})
]);
fbtSearch.start();
}
document.addEventListener('DOMContentLoaded', function() {
let recsLoaded = false;
function checkLoad() {
if (recsLoaded) return;
if ((window.scrollY + window.innerHeight) >= document.body.scrollHeight - 500) {
recsLoaded = true;
window.removeEventListener('scroll', checkLoad);
initAlgoliaRecommendations();
}
}
window.addEventListener('scroll', checkLoad, { passive: true });
checkLoad();
});
</script>
</div>
<br>
<!-- <div id="algolia-recs-container" style="display: none;">
<div id="algolia-related-products" style="margin-bottom: 2em;"></div>
<style>
/* Common styles for both recommendation widgets */
.algolia-recs-section-header {
font-family: 'Raleway', Helvetica, sans-serif;
font-size: 1em; /* Adjust as needed, smaller than default h3 */
font-weight: bold;
margin-top: 0; /* Remove or reduce top margin */
margin-bottom: 15px; /* Space between header and recommendation cards */
color: var(--c-text); /* Use theme's text color */
font-style: italic;
}
/* Related Products Widget Styles */
#algolia-related-products .ais-RelatedProducts-list {
display: flex;
flex-direction: row; /* Arrange items horizontally */
flex-wrap: nowrap; /* Prevent wrapping to new lines, if possible */
justify-content: flex-start; /* Align items to the start of the container */
padding-left: 0; /* Remove default list padding */
list-style-type: none; /* Remove list bullets */
margin: 0;
}
#algolia-related-products .ais-RelatedProducts-item {
width: 32%; /* Adjust for 3 items: 32% * 3 items + 2% * 2 margins = 100% */
margin-right: 2%;
box-sizing: border-box; /* Include padding and border in the element's total width */
/* Optional: Basic card styling (uncomment to use) */
border: 1px solid color-mix(in srgb, var(--c-background) 85%, var(--c-text) 15%); /* Theme-aware light grey border */
padding: 0; /* Remove overall card padding, will be handled by elements */
text-align: left; /* Or 'center' if you prefer */
background-color: var(--c-background);
border-radius: 4px;
box-shadow: 0 2px 4px rgba(0,0,0,0.1);
}
#algolia-related-products .ais-RelatedProducts-item:last-child {
margin-right: 0; /* No margin for the last item in the row */
}
/* Styling for images within recommendation items */
#algolia-related-products .ais-RelatedProducts-item img {
display: block; /* Can help remove extra space below image */
width: calc(100% - 4px); /* Full width minus 2px L/R margins */
max-width: 100%; /* Ensures image does not exceed container if intrinsically smaller */
/* height: auto; -- Controlled by inline style's max-height and object-fit */
object-fit: cover; /* Ensure image covers the area, also in inline style */
margin: 2px; /* 2px margin on top, left, right. Bottom is overridden by inline style. */
/* margin-bottom: 8px; -- This is set by inline style in JS template */
}
/* Styling for the wrapper link to make the whole card clickable */
#algolia-related-products .ais-RelatedProducts-item a.ais-RelatedProducts-item-link-wrapper {
display: block; /* Make the link fill the list item */
text-decoration: none; /* Remove underline */
color: inherit; /* Use parent's text color */
}
#algolia-related-products .related-product-title {
font-family: 'Raleway', Helvetica, sans-serif;
font-size: 0.75em;
display: -webkit-box;
-webkit-line-clamp: 2; /* Limit to 2 lines for WebKit browsers */
line-clamp: 2; /* Standard property */
-webkit-box-orient: vertical;
overflow: hidden;
text-overflow: ellipsis;
padding: 0 7px 7px 7px; /* 0 top, 7px L/R/B for text area */
line-height: 1.5; /* Adjust for better readability */
height: 3.3em; /* Current height: 3.3em. For 2 lines with 0.75em font & 1.5 line-height, calculated height would be 2.25em. */
color: var(--c-interactive); /* Use theme's interactive color */
}
/* This container will wrap the image and score, taking the original image's layout space. */
#algolia-related-products .ais-RelatedProducts-item .recommendation-image-container {
position: relative; /* For positioning the score absolutely within */
display: block; /* Matches original image display and ensures proper block layout */
width: calc(100% - 4px); /* Adopts width from original image styling */
margin: 2px; /* Adopts margin from original image styling */
margin-bottom: 8px; /* Adopts specific bottom margin from original image's inline style */
line-height: 0; /* Prevents unexpected space if child elements are treated as inline */
}
/* The image itself, now filling the container */
#algolia-related-products .ais-RelatedProducts-item .recommendation-image-container img {
display: block;
width: 100%; /* Fill the container's width */
max-width: 20em; /* Optional: retain original max-width constraint for the image content */
height: auto; /* Maintain aspect ratio by default */
max-height: 12em; /* Constrain image height (adjust as needed) */
object-fit: cover; /* Ensures image covers the allocated space, cropping if necessary */
margin: 0 auto; /* Center image if max-width kicks in and it's narrower than container */
}
/* The score overlay box */
#algolia-related-products .ais-RelatedProducts-item .recommendation-score {
position: absolute;
bottom: 3px; /* Padding from the bottom edge of the container */
right: 3px; /* Padding from the right edge of the container */
background-color: color-mix(in srgb, var(--c-background) 85%, var(--green) 15%); /* Theme-aware light green */
color: var(--green); /* Theme's green color for text */
padding: 3px 6px; /* Slightly adjusted padding */
font-family: 'Raleway', Helvetica, sans-serif;
font-size: 0.75em;
font-weight: bold;
border-radius: 10px; /* More rounded corners like the example */
border: 1px solid var(--green); /* Theme's green color for border */
line-height: 1; /* Critical for small text in a small box */
z-index: 10; /* Ensure it's above the image */
box-shadow: 0 1px 2px rgba(0,0,0,0.15); /* Softer shadow */
display: flex; /* To align icon and text nicely */
align-items: center; /* Vertically center icon and text */
}
/* Styling for the SVG icon within the score box */
#algolia-related-products .ais-RelatedProducts-item .recommendation-score-icon {
width: 0.9em; /* Scale with score's font size */
height: 0.9em;
vertical-align: -0.1em; /* Fine-tune vertical alignment */
margin-right: 4px; /* Space between icon and score number */
fill: var(--green); /* Theme's green color for icon */
}
</style>
<script>
// Function to load a script and return a promise
function loadScript(src) {
return new Promise((resolve, reject) => {
if (document.querySelector(`script[src="${src}"]`)) {
resolve(); // Already loaded
return;
}
const script = document.createElement('script');
script.src = src;
script.onload = () => resolve();
script.onerror = () => reject(new Error(`Script load error for ${src}`));
document.head.appendChild(script);
});
}
function initAlgoliaRecommendations() {
Promise.all([
loadScript('https://cdn.jsdelivr.net/npm/algoliasearch@4/dist/algoliasearch-lite.umd.js'),
loadScript('https://cdn.jsdelivr.net/npm/instantsearch.js@4')
])
.then(() => {
// Initialize the Related Products widget
initRelatedProducts();
})
.catch(error => {
// Handle error silently
});
}
function initRelatedProducts() {
// Ensure container exists
if (!document.getElementById('algolia-related-products')) {
// Container not found, stopping initialization
return;
}
const recSearchClient = algoliasearch(
'2XJCLEABQD',
'b61ec4cb64bd32d62c053466fccbfa43'
);
const relatedSearch = instantsearch({
indexName: 'eugeneyan.com',
searchClient: recSearchClient,
clickAnalytics: true,
insights: true, // Enable insights for click tracking on recommendations
});
relatedSearch.addWidgets([
instantsearch.widgets.relatedProducts({
container: '#algolia-related-products',
objectIDs: ['/writing/recommender-systems-baseline-pytorch/'],
limit: 3,
queryParameters: {
attributesToRetrieve: ['title', 'url', 'image', 'score', '_score'], // Specify only needed attributes
attributesToHighlight: [], // Disable highlighting
attributesToSnippet: [] // Disable snippeting
},
translations: {
title: '', // Custom title is in _layouts/post.html
},
transformItems: function(items) {
const containerElement = document.getElementById('algolia-recs-container');
const relatedElement = document.getElementById('algolia-related-products');
if (items.length === 0) {
if (relatedElement) relatedElement.style.display = 'none';
if (containerElement) containerElement.style.display = 'none';
} else {
if (relatedElement) relatedElement.style.display = 'block';
if (containerElement) containerElement.style.display = 'block';
}
return items;
},
templates: {
header() { // Removed unused results, html parameters
// Return a PLAIN string for the header
return '<h4 class="algolia-recs-section-header">You Might Also Like</h4>';
},
item: function(hit, { html, sendEvent }) { // Added sendEvent to params
const itemUrl = `${hit.url || '#'}`;
const indexName = 'eugeneyan.com'; // Get index name for insights
let imageUrl;
// Ensure hit.image is not null, undefined, or an empty/whitespace string before using it.
if (hit.image && typeof hit.image === 'string' && hit.image.trim() !== '') {
imageUrl = `/assets/og_image/${hit.image}`;
} else {
imageUrl = `/assets/og_image/default-v4.jpg`; // Default image
}
let scoreValue = null;
if (typeof hit.score === 'number') scoreValue = hit.score.toFixed(2);
else if (typeof hit._score === 'number') scoreValue = hit._score.toFixed(2);
// else if (typeof hit.your_custom_score_field === 'number') scoreValue = hit.your_custom_score_field.toFixed(2);
const scoreElement = scoreValue ? `<div class="recommendation-score"><svg viewbox="0 0 24 24" class="recommendation-score-icon" xmlns="http://www.w3.org/2000/svg"><path d="M16 6l2.29 2.29-4.88 4.88-4-4L2 16.59 3.41 18l6-6 4 4 6.3-6.29L22 12V6h-6z"></path></svg>${scoreValue}</div>` : '';
const imageAndScoreTag = `
<div class="recommendation-image-container">
<img src="${imageUrl}" alt="${hit.title || 'Recommendation cover image'}">
${scoreElement}
</div>`;
const title = hit.title || 'Untitled Post';
return `
<a href="${itemUrl}"
class="ais-RelatedProducts-item-link-wrapper"
onClick="${() => {
sendEvent('click', hit, 'Related Item Clicked');
}}"
>
${imageAndScoreTag}
<div class="related-product-title">${title}</div>
</a>
`;
},
empty(results, { html }) {
const containerElement = document.getElementById('algolia-recs-container');
const relatedElement = document.getElementById('algolia-related-products');
if (relatedElement) {
relatedElement.style.display = 'none';
}
// If this 'empty' template is called, it means related products are empty.
// So, the main container should also be hidden.
if (containerElement) {
containerElement.style.display = 'none';
}
// Return an empty string to prevent rendering 'undefined'
return '';
}
}
})
]);
relatedSearch.start();
}
document.addEventListener('DOMContentLoaded', function() {
let recsLoaded = false;
function checkLoad() {
if (recsLoaded) return;
if ((window.scrollY + window.innerHeight) >= document.body.scrollHeight - 500) {
recsLoaded = true;
window.removeEventListener('scroll', checkLoad);
initAlgoliaRecommendations();
}
}
window.addEventListener('scroll', checkLoad, { passive: true });
checkLoad();
});
</script>
</div> -->
<span style="font-family: 'Raleway', Helvetica, sans-serif;">Browse related tags:</span> <span class="no-italics">[
<a class='tag' href="/tag/recsys/">recsys</a>
<a class='tag' href="/tag/deeplearning/">deeplearning</a>
<a class='tag' href="/tag/python/">python</a>
<a class='tag' href="/tag/🛠/">🛠</a>
]
</span> <span style="font-family: 'Raleway', Helvetica, sans-serif;"> or </span><a href="/search/" title="Search" style="text-decoration: none; font-family: 'Raleway', Helvetica, sans-serif;"><img class="icon icon-search" src="/assets/icon-search.svg" loading="lazy" alt="" style="vertical-align: middle; margin-right: 0.25em;"/>Search</a>
<div class="PageNavigation">
<a class="prev sans-serif" href="/writing/omscs-cs6200-introduction-to-operating-systems/">« OMSCS CS6200 (Introduction to OS) Review and Tips</a>
<a class="next sans-serif" href="/writing/recommender-systems-graph-and-nlp-pytorch/">Beating the Baseline Recommender with Graph & NLP in Pytorch »</a>
</div>
<hr>
<p style="font-size: 15px; text-align: center; margin: 2em 0 0.5em">Join <b>11,800+</b> readers getting updates on machine learning, RecSys, LLMs, and engineering.</p>
<script src="https://f.convertkit.com/ckjs/ck.6.js" type="f28497f9592da7f32b5a2b50-text/javascript"></script>
<form action="https://app.convertkit.com/forms/4004980/subscriptions" class="seva-form formkit-form" method="post" data-sv-form="4004980" data-uid="96a310b6ce" data-format="inline" data-version="6" data-options="{"settings":{"after_subscribe":{"action":"message","success_message":"Just sent a confirmation! Check your inbox.","redirect_url":""},"analytics":{"google":null,"fathom":null,"facebook":null,"segment":null,"pinterest":null,"sparkloop":null,"googletagmanager":null},"modal":{"trigger":"timer","scroll_percentage":null,"timer":5,"devices":"all","show_once_every":15},"powered_by":{"show":false,"url":"https://convertkit.com/features/forms?utm_campaign=poweredby&utm_content=form&utm_medium=referral&utm_source=dynamic"},"recaptcha":{"enabled":false},"return_visitor":{"action":"show","custom_content":""},"slide_in":{"display_in":"bottom_right","trigger":"timer","scroll_percentage":null,"timer":5,"devices":"all","show_once_every":15},"sticky_bar":{"display_in":"top","trigger":"timer","scroll_percentage":null,"timer":5,"devices":"all","show_once_every":15}},"version":"6"}" min-width="400 500 600 700 800"><div data-style="clean"><ul class="formkit-alert formkit-alert-error" data-element="errors" data-group="alert"></ul><div data-element="fields" data-stacked="false" class="seva-fields formkit-fields"><div class="formkit-field"><input class="formkit-input" name="email_address" style="color: rgb(0, 0, 0); border-color: rgb(227, 227, 227); border-radius: 4px; font-weight: 400;" aria-label="Your email address..." placeholder="Your email address..." required="" type="email"></div><button data-element="submit" class="formkit-submit formkit-submit" style="color: rgb(255, 255, 255); background-color: rgb(0, 123, 255); border-radius: 5px; font-weight: 400;"><div class="formkit-spinner"><div></div><div></div><div></div></div><span class="">Get email updates</span></button></div></div><style>.formkit-form[data-uid="96a310b6ce"] *{box-sizing:border-box;}.formkit-form[data-uid="96a310b6ce"]{-webkit-font-smoothing:antialiased;-moz-osx-font-smoothing:grayscale;}.formkit-form[data-uid="96a310b6ce"] legend{border:none;font-size:inherit;margin-bottom:10px;padding:0;position:relative;display:table;}.formkit-form[data-uid="96a310b6ce"] fieldset{border:0;padding:0.01em 0 0 0;margin:0;min-width:0;}.formkit-form[data-uid="96a310b6ce"] body:not(:-moz-handler-blocked) fieldset{display:table-cell;}.formkit-form[data-uid="96a310b6ce"] h1,.formkit-form[data-uid="96a310b6ce"] h2,.formkit-form[data-uid="96a310b6ce"] h3,.formkit-form[data-uid="96a310b6ce"] h4,.formkit-form[data-uid="96a310b6ce"] h5,.formkit-form[data-uid="96a310b6ce"] h6{color:inherit;font-size:inherit;font-weight:inherit;}.formkit-form[data-uid="96a310b6ce"] h2{font-size:1.5em;margin:1em 0;}.formkit-form[data-uid="96a310b6ce"] h3{font-size:1.17em;margin:1em 0;}.formkit-form[data-uid="96a310b6ce"] p{color:inherit;font-size:inherit;font-weight:inherit;}.formkit-form[data-uid="96a310b6ce"] ol:not([template-default]),.formkit-form[data-uid="96a310b6ce"] ul:not([template-default]),.formkit-form[data-uid="96a310b6ce"] blockquote:not([template-default]){text-align:left;}.formkit-form[data-uid="96a310b6ce"] p:not([template-default]),.formkit-form[data-uid="96a310b6ce"] hr:not([template-default]),.formkit-form[data-uid="96a310b6ce"] blockquote:not([template-default]),.formkit-form[data-uid="96a310b6ce"] ol:not([template-default]),.formkit-form[data-uid="96a310b6ce"] ul:not([template-default]){color:inherit;font-style:initial;}.formkit-form[data-uid="96a310b6ce"] .ordered-list,.formkit-form[data-uid="96a310b6ce"] .unordered-list{list-style-position:outside !important;padding-left:1em;}.formkit-form[data-uid="96a310b6ce"] .list-item{padding-left:0;}.formkit-form[data-uid="96a310b6ce"][data-format="modal"]{display:none;}.formkit-form[data-uid="96a310b6ce"][data-format="slide in"]{display:none;}.formkit-form[data-uid="96a310b6ce"][data-format="sticky bar"]{display:none;}.formkit-sticky-bar .formkit-form[data-uid="96a310b6ce"][data-format="sticky bar"]{display:block;}.formkit-form[data-uid="96a310b6ce"] .formkit-input,.formkit-form[data-uid="96a310b6ce"] .formkit-select,.formkit-form[data-uid="96a310b6ce"] .formkit-checkboxes{width:100%;}.formkit-form[data-uid="96a310b6ce"] .formkit-button,.formkit-form[data-uid="96a310b6ce"] .formkit-submit{border:0;border-radius:5px;color:#ffffff;cursor:pointer;display:inline-block;text-align:center;font-size:15px;font-weight:500;cursor:pointer;margin-bottom:15px;overflow:hidden;padding:0;position:relative;vertical-align:middle;}.formkit-form[data-uid="96a310b6ce"] .formkit-button:hover,.formkit-form[data-uid="96a310b6ce"] .formkit-submit:hover,.formkit-form[data-uid="96a310b6ce"] .formkit-button:focus,.formkit-form[data-uid="96a310b6ce"] .formkit-submit:focus{outline:none;}.formkit-form[data-uid="96a310b6ce"] .formkit-button:hover > span,.formkit-form[data-uid="96a310b6ce"] .formkit-submit:hover > span,.formkit-form[data-uid="96a310b6ce"] .formkit-button:focus > span,.formkit-form[data-uid="96a310b6ce"] .formkit-submit:focus > span{background-color:rgba(0,0,0,0.1);}.formkit-form[data-uid="96a310b6ce"] .formkit-button > span,.formkit-form[data-uid="96a310b6ce"] .formkit-submit > span{display:block;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;padding:12px 24px;}.formkit-form[data-uid="96a310b6ce"] .formkit-input{background:#ffffff;font-size:15px;padding:12px;border:1px solid #e3e3e3;-webkit-flex:1 0 auto;-ms-flex:1 0 auto;flex:1 0 auto;line-height:1.4;margin:0;-webkit-transition:border-color ease-out 300ms;transition:border-color ease-out 300ms;}.formkit-form[data-uid="96a310b6ce"] .formkit-input:focus{outline:none;border-color:#1677be;-webkit-transition:border-color ease 300ms;transition:border-color ease 300ms;}.formkit-form[data-uid="96a310b6ce"] .formkit-input::-webkit-input-placeholder{color:inherit;opacity:0.8;}.formkit-form[data-uid="96a310b6ce"] .formkit-input::-moz-placeholder{color:inherit;opacity:0.8;}.formkit-form[data-uid="96a310b6ce"] .formkit-input:-ms-input-placeholder{color:inherit;opacity:0.8;}.formkit-form[data-uid="96a310b6ce"] .formkit-input::placeholder{color:inherit;opacity:0.8;}.formkit-form[data-uid="96a310b6ce"] [data-group="dropdown"]{position:relative;display:inline-block;width:100%;}.formkit-form[data-uid="96a310b6ce"] [data-group="dropdown"]::before{content:"";top:calc(50% - 2.5px);right:10px;position:absolute;pointer-events:none;border-color:#4f4f4f transparent transparent transparent;border-style:solid;border-width:6px 6px 0 6px;height:0;width:0;z-index:999;}.formkit-form[data-uid="96a310b6ce"] [data-group="dropdown"] select{height:auto;width:100%;cursor:pointer;color:#333333;line-height:1.4;margin-bottom:0;padding:0 6px;-webkit-appearance:none;-moz-appearance:none;appearance:none;font-size:15px;padding:12px;padding-right:25px;border:1px solid #e3e3e3;background:#ffffff;}.formkit-form[data-uid="96a310b6ce"] [data-group="dropdown"] select:focus{outline:none;}.formkit-form[data-uid="96a310b6ce"] [data-group="checkboxes"]{text-align:left;margin:0;}.formkit-form[data-uid="96a310b6ce"] [data-group="checkboxes"] [data-group="checkbox"]{margin-bottom:10px;}.formkit-form[data-uid="96a310b6ce"] [data-group="checkboxes"] [data-group="checkbox"] *{cursor:pointer;}.formkit-form[data-uid="96a310b6ce"] [data-group="checkboxes"] [data-group="checkbox"]:last-of-type{margin-bottom:0;}.formkit-form[data-uid="96a310b6ce"] [data-group="checkboxes"] [data-group="checkbox"] input[type="checkbox"]{display:none;}.formkit-form[data-uid="96a310b6ce"] [data-group="checkboxes"] [data-group="checkbox"] input[type="checkbox"] + label::after{content:none;}.formkit-form[data-uid="96a310b6ce"] [data-group="checkboxes"] [data-group="checkbox"] input[type="checkbox"]:checked + label::after{border-color:#ffffff;content:"";}.formkit-form[data-uid="96a310b6ce"] [data-group="checkboxes"] [data-group="checkbox"] input[type="checkbox"]:checked + label::before{background:#10bf7a;border-color:#10bf7a;}.formkit-form[data-uid="96a310b6ce"] [data-group="checkboxes"] [data-group="checkbox"] label{position:relative;display:inline-block;padding-left:28px;}.formkit-form[data-uid="96a310b6ce"] [data-group="checkboxes"] [data-group="checkbox"] label::before,.formkit-form[data-uid="96a310b6ce"] [data-group="checkboxes"] [data-group="checkbox"] label::after{position:absolute;content:"";display:inline-block;}.formkit-form[data-uid="96a310b6ce"] [data-group="checkboxes"] [data-group="checkbox"] label::before{height:16px;width:16px;border:1px solid #e3e3e3;background:#ffffff;left:0px;top:3px;}.formkit-form[data-uid="96a310b6ce"] [data-group="checkboxes"] [data-group="checkbox"] label::after{height:4px;width:8px;border-left:2px solid #4d4d4d;border-bottom:2px solid #4d4d4d;-webkit-transform:rotate(-45deg);-ms-transform:rotate(-45deg);transform:rotate(-45deg);left:4px;top:8px;}.formkit-form[data-uid="96a310b6ce"] .formkit-alert{background:#f9fafb;border:1px solid #e3e3e3;border-radius:5px;-webkit-flex:1 0 auto;-ms-flex:1 0 auto;flex:1 0 auto;list-style:none;margin:25px auto;padding:12px;text-align:center;width:100%;}.formkit-form[data-uid="96a310b6ce"] .formkit-alert:empty{display:none;}.formkit-form[data-uid="96a310b6ce"] .formkit-alert-success{background:#d3fbeb;border-color:#10bf7a;color:#0c905c;}.formkit-form[data-uid="96a310b6ce"] .formkit-alert-error{background:#fde8e2;border-color:#f2643b;color:#ea4110;}.formkit-form[data-uid="96a310b6ce"] .formkit-spinner{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;height:0px;width:0px;margin:0 auto;position:absolute;top:0;left:0;right:0;width:0px;overflow:hidden;text-align:center;-webkit-transition:all 300ms ease-in-out;transition:all 300ms ease-in-out;}.formkit-form[data-uid="96a310b6ce"] .formkit-spinner > div{margin:auto;width:12px;height:12px;background-color:#fff;opacity:0.3;border-radius:100%;display:inline-block;-webkit-animation:formkit-bouncedelay-formkit-form-data-uid-96a310b6ce- 1.4s infinite ease-in-out both;animation:formkit-bouncedelay-formkit-form-data-uid-96a310b6ce- 1.4s infinite ease-in-out both;}.formkit-form[data-uid="96a310b6ce"] .formkit-spinner > div:nth-child(1){-webkit-animation-delay:-0.32s;animation-delay:-0.32s;}.formkit-form[data-uid="96a310b6ce"] .formkit-spinner > div:nth-child(2){-webkit-animation-delay:-0.16s;animation-delay:-0.16s;}.formkit-form[data-uid="96a310b6ce"] .formkit-submit[data-active] .formkit-spinner{opacity:1;height:100%;width:50px;}.formkit-form[data-uid="96a310b6ce"] .formkit-submit[data-active] .formkit-spinner ~ span{opacity:0;}.formkit-form[data-uid="96a310b6ce"] .formkit-powered-by[data-active="false"]{opacity:0.35;}.formkit-form[data-uid="96a310b6ce"] .formkit-powered-by-convertkit-container{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;width:100%;z-index:5;margin:10px 0;position:relative;}.formkit-form[data-uid="96a310b6ce"] .formkit-powered-by-convertkit-container[data-active="false"]{opacity:0.35;}.formkit-form[data-uid="96a310b6ce"] .formkit-powered-by-convertkit{-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;background-color:#ffffff;border:1px solid #dde2e7;border-radius:4px;color:#373f45;cursor:pointer;display:block;height:36px;margin:0 auto;opacity:0.95;padding:0;-webkit-text-decoration:none;text-decoration:none;text-indent:100%;-webkit-transition:ease-in-out all 200ms;transition:ease-in-out all 200ms;white-space:nowrap;overflow:hidden;-webkit-user-select:none;-moz-user-select:none;-ms-user-select:none;user-select:none;width:190px;background-repeat:no-repeat;background-position:center;background-image:url("data:image/svg+xml;charset=utf8,%3Csvg width='162' height='20' viewBox='0 0 162 20' fill='none' xmlns='http://www.w3.org/2000/svg'%3E%3Cpath d='M83.0561 15.2457C86.675 15.2457 89.4722 12.5154 89.4722 9.14749C89.4722 5.99211 86.8443 4.06563 85.1038 4.06563C82.6801 4.06563 80.7373 5.76407 80.4605 8.28551C80.4092 8.75244 80.0387 9.14403 79.5686 9.14069C78.7871 9.13509 77.6507 9.12841 76.9314 9.13092C76.6217 9.13199 76.3658 8.88106 76.381 8.57196C76.4895 6.38513 77.2218 4.3404 78.618 2.76974C80.1695 1.02445 82.4289 0 85.1038 0C89.5979 0 93.8406 4.07791 93.8406 9.14749C93.8406 14.7608 89.1832 19.3113 83.1517 19.3113C78.8502 19.3113 74.5179 16.5041 73.0053 12.5795C72.9999 12.565 72.9986 12.5492 73.0015 12.534C73.0218 12.4179 73.0617 12.3118 73.1011 12.2074C73.1583 12.0555 73.2143 11.907 73.2062 11.7359L73.18 11.1892C73.174 11.0569 73.2075 10.9258 73.2764 10.8127C73.3452 10.6995 73.4463 10.6094 73.5666 10.554L73.7852 10.4523C73.9077 10.3957 74.0148 10.3105 74.0976 10.204C74.1803 10.0974 74.2363 9.97252 74.2608 9.83983C74.3341 9.43894 74.6865 9.14749 75.0979 9.14749C75.7404 9.14749 76.299 9.57412 76.5088 10.1806C77.5188 13.1 79.1245 15.2457 83.0561 15.2457Z' fill='%23373F45'/%3E%3Cpath d='M155.758 6.91365C155.028 6.91365 154.804 6.47916 154.804 5.98857C154.804 5.46997 154.986 5.06348 155.758 5.06348C156.53 5.06348 156.712 5.46997 156.712 5.98857C156.712 6.47905 156.516 6.91365 155.758 6.91365ZM142.441 12.9304V9.32833L141.415 9.32323V8.90392C141.415 8.44719 141.786 8.07758 142.244 8.07986L142.441 8.08095V6.55306L144.082 6.09057V8.08073H145.569V8.50416C145.569 8.61242 145.548 8.71961 145.506 8.81961C145.465 8.91961 145.404 9.01047 145.328 9.08699C145.251 9.16351 145.16 9.2242 145.06 9.26559C144.96 9.30698 144.853 9.32826 144.745 9.32822H144.082V12.7201C144.082 13.2423 144.378 13.4256 144.76 13.4887C145.209 13.5629 145.583 13.888 145.583 14.343V14.9626C144.029 14.9626 142.441 14.8942 142.441 12.9304Z' fill='%23373F45'/%3E%3Cpath d='M110.058 7.92554C108.417 7.88344 106.396 8.92062 106.396 11.5137C106.396 14.0646 108.417 15.0738 110.058 15.0318C111.742 15.0738 113.748 14.0646 113.748 11.5137C113.748 8.92062 111.742 7.88344 110.058 7.92554ZM110.07 13.7586C108.878 13.7586 108.032 12.8905 108.032 11.461C108.032 10.1013 108.878 9.20569 110.071 9.20569C111.263 9.20569 112.101 10.0995 112.101 11.459C112.101 12.8887 111.263 13.7586 110.07 13.7586Z' fill='%23373F45'/%3E%3Cpath d='M118.06 7.94098C119.491 7.94098 120.978 8.33337 120.978 11.1366V14.893H120.063C119.608 14.893 119.238 14.524 119.238 14.0689V10.9965C119.238 9.66506 118.747 9.16047 117.891 9.16047C117.414 9.16047 116.797 9.52486 116.502 9.81915V14.069C116.502 14.1773 116.481 14.2845 116.44 14.3845C116.398 14.4845 116.337 14.5753 116.261 14.6519C116.184 14.7284 116.093 14.7891 115.993 14.8305C115.893 14.8719 115.786 14.8931 115.678 14.8931H114.847V8.10918H115.773C115.932 8.10914 116.087 8.16315 116.212 8.26242C116.337 8.36168 116.424 8.50033 116.46 8.65577C116.881 8.19328 117.428 7.94098 118.06 7.94098ZM122.854 8.09713C123.024 8.09708 123.19 8.1496 123.329 8.2475C123.468 8.34541 123.574 8.48391 123.631 8.64405L125.133 12.8486L126.635 8.64415C126.692 8.48402 126.798 8.34551 126.937 8.2476C127.076 8.1497 127.242 8.09718 127.412 8.09724H128.598L126.152 14.3567C126.091 14.5112 125.986 14.6439 125.849 14.7374C125.711 14.831 125.549 14.881 125.383 14.8809H124.333L121.668 8.09713H122.854Z' fill='%23373F45'/%3E%3Cpath d='M135.085 14.5514C134.566 14.7616 133.513 15.0416 132.418 15.0416C130.496 15.0416 129.024 13.9345 129.024 11.4396C129.024 9.19701 130.451 7.99792 132.191 7.99792C134.338 7.99792 135.254 9.4378 135.158 11.3979C135.139 11.8029 134.786 12.0983 134.38 12.0983H130.679C130.763 13.1916 131.562 13.7662 132.615 13.7662C133.028 13.7662 133.462 13.7452 133.983 13.6481C134.535 13.545 135.085 13.9375 135.085 14.4985V14.5514ZM133.673 10.949C133.785 9.87621 133.061 9.28752 132.191 9.28752C131.321 9.28752 130.734 9.93979 130.679 10.9489L133.673 10.949Z' fill='%23373F45'/%3E%3Cpath d='M137.345 8.11122C137.497 8.11118 137.645 8.16229 137.765 8.25635C137.884 8.35041 137.969 8.48197 138.005 8.62993C138.566 8.20932 139.268 7.94303 139.759 7.94303C139.801 7.94303 140.068 7.94303 140.489 7.99913V8.7265C140.489 9.11748 140.15 9.4147 139.759 9.4147C139.31 9.4147 138.651 9.5829 138.131 9.8773V14.8951H136.462V8.11112L137.345 8.11122ZM156.6 14.0508V8.09104H155.769C155.314 8.09104 154.944 8.45999 154.944 8.9151V14.8748H155.775C156.23 14.8748 156.6 14.5058 156.6 14.0508ZM158.857 12.9447V9.34254H157.749V8.91912C157.749 8.46401 158.118 8.09506 158.574 8.09506H158.857V6.56739L160.499 6.10479V8.09506H161.986V8.51848C161.986 8.97359 161.617 9.34254 161.161 9.34254H160.499V12.7345C160.499 13.2566 160.795 13.44 161.177 13.503C161.626 13.5774 162 13.9024 162 14.3574V14.977C160.446 14.977 158.857 14.9086 158.857 12.9447ZM98.1929 10.1124C98.2033 6.94046 100.598 5.16809 102.895 5.16809C104.171 5.16809 105.342 5.44285 106.304 6.12953L105.914 6.6631C105.654 7.02011 105.16 7.16194 104.749 6.99949C104.169 6.7702 103.622 6.7218 103.215 6.7218C101.335 6.7218 99.9169 7.92849 99.9068 10.1123C99.9169 12.2959 101.335 13.5201 103.215 13.5201C103.622 13.5201 104.169 13.4717 104.749 13.2424C105.16 13.0799 105.654 13.2046 105.914 13.5615L106.304 14.0952C105.342 14.7819 104.171 15.0566 102.895 15.0566C100.598 15.0566 98.2033 13.2842 98.1929 10.1124ZM147.619 5.21768C148.074 5.21768 148.444 5.58663 148.444 6.04174V9.81968L151.82 5.58131C151.897 5.47733 151.997 5.39282 152.112 5.3346C152.227 5.27638 152.355 5.24607 152.484 5.24611H153.984L150.166 10.0615L153.984 14.8749H152.484C152.355 14.8749 152.227 14.8446 152.112 14.7864C151.997 14.7281 151.897 14.6436 151.82 14.5397L148.444 10.3025V14.0508C148.444 14.5059 148.074 14.8749 147.619 14.8749H146.746V5.21768H147.619Z' fill='%23373F45'/%3E%3Cpath d='M0.773438 6.5752H2.68066C3.56543 6.5752 4.2041 6.7041 4.59668 6.96191C4.99219 7.21973 5.18994 7.62695 5.18994 8.18359C5.18994 8.55859 5.09326 8.87061 4.8999 9.11963C4.70654 9.36865 4.42822 9.52539 4.06494 9.58984V9.63379C4.51611 9.71875 4.84717 9.88721 5.05811 10.1392C5.27197 10.3882 5.37891 10.7266 5.37891 11.1543C5.37891 11.7314 5.17676 12.1841 4.77246 12.5122C4.37109 12.8374 3.81152 13 3.09375 13H0.773438V6.5752ZM1.82373 9.22949H2.83447C3.27393 9.22949 3.59473 9.16064 3.79688 9.02295C3.99902 8.88232 4.1001 8.64502 4.1001 8.31104C4.1001 8.00928 3.99023 7.79102 3.77051 7.65625C3.55371 7.52148 3.20801 7.4541 2.7334 7.4541H1.82373V9.22949ZM1.82373 10.082V12.1167H2.93994C3.37939 12.1167 3.71045 12.0332 3.93311 11.8662C4.15869 11.6963 4.27148 11.4297 4.27148 11.0664C4.27148 10.7324 4.15723 10.4849 3.92871 10.3237C3.7002 10.1626 3.35303 10.082 2.88721 10.082H1.82373Z' fill='%23373F45'/%3E%3Cpath d='M13.011 6.5752V10.7324C13.011 11.207 12.9084 11.623 12.7034 11.9805C12.5012 12.335 12.2068 12.6089 11.8201 12.8022C11.4363 12.9927 10.9763 13.0879 10.4402 13.0879C9.6433 13.0879 9.02368 12.877 8.5813 12.4551C8.13892 12.0332 7.91772 11.4531 7.91772 10.7148V6.5752H8.9724V10.6401C8.9724 11.1704 9.09546 11.5615 9.34155 11.8135C9.58765 12.0654 9.96557 12.1914 10.4753 12.1914C11.4656 12.1914 11.9607 11.6714 11.9607 10.6313V6.5752H13.011Z' fill='%23373F45'/%3E%3Cpath d='M15.9146 13V6.5752H16.9649V13H15.9146Z' fill='%23373F45'/%3E%3Cpath d='M19.9255 13V6.5752H20.9758V12.0991H23.696V13H19.9255Z' fill='%23373F45'/%3E%3Cpath d='M28.2828 13H27.2325V7.47607H25.3428V6.5752H30.1724V7.47607H28.2828V13Z' fill='%23373F45'/%3E%3Cpath d='M41.9472 13H40.8046L39.7148 9.16796C39.6679 9.00097 39.6093 8.76074 39.539 8.44727C39.4687 8.13086 39.4262 7.91113 39.4116 7.78809C39.3823 7.97559 39.3339 8.21875 39.2665 8.51758C39.2021 8.81641 39.1479 9.03905 39.1039 9.18554L38.0405 13H36.8979L36.0673 9.7832L35.2236 6.5752H36.2958L37.2143 10.3193C37.3578 10.9199 37.4604 11.4502 37.5219 11.9102C37.5541 11.6611 37.6025 11.3828 37.6669 11.0752C37.7314 10.7676 37.79 10.5186 37.8427 10.3281L38.8886 6.5752H39.9301L41.0024 10.3457C41.1049 10.6943 41.2133 11.2158 41.3276 11.9102C41.3715 11.4912 41.477 10.958 41.644 10.3105L42.558 6.5752H43.6215L41.9472 13Z' fill='%23373F45'/%3E%3Cpath d='M45.7957 13V6.5752H46.846V13H45.7957Z' fill='%23373F45'/%3E%3Cpath d='M52.0258 13H50.9755V7.47607H49.0859V6.5752H53.9155V7.47607H52.0258V13Z' fill='%23373F45'/%3E%3Cpath d='M61.2312 13H60.1765V10.104H57.2146V13H56.1643V6.5752H57.2146V9.20312H60.1765V6.5752H61.2312V13Z' fill='%23373F45'/%3E%3C/svg%3E");}.formkit-form[data-uid="96a310b6ce"] .formkit-powered-by-convertkit:hover,.formkit-form[data-uid="96a310b6ce"] .formkit-powered-by-convertkit:focus{background-color:#ffffff;-webkit-transform:scale(1.025) perspective(1px);-ms-transform:scale(1.025) perspective(1px);transform:scale(1.025) perspective(1px);opacity:1;}.formkit-form[data-uid="96a310b6ce"] .formkit-powered-by-convertkit[data-variant="dark"],.formkit-form[data-uid="96a310b6ce"] .formkit-powered-by-convertkit[data-variant="light"]{background-color:transparent;border-color:transparent;width:166px;}.formkit-form[data-uid="96a310b6ce"] .formkit-powered-by-convertkit[data-variant="light"]{color:#ffffff;background-image:url("data:image/svg+xml;charset=utf8,%3Csvg width='162' height='20' viewBox='0 0 162 20' fill='none' xmlns='http://www.w3.org/2000/svg'%3E%3Cpath d='M83.0561 15.2457C86.675 15.2457 89.4722 12.5154 89.4722 9.14749C89.4722 5.99211 86.8443 4.06563 85.1038 4.06563C82.6801 4.06563 80.7373 5.76407 80.4605 8.28551C80.4092 8.75244 80.0387 9.14403 79.5686 9.14069C78.7871 9.13509 77.6507 9.12841 76.9314 9.13092C76.6217 9.13199 76.3658 8.88106 76.381 8.57196C76.4895 6.38513 77.2218 4.3404 78.618 2.76974C80.1695 1.02445 82.4289 0 85.1038 0C89.5979 0 93.8406 4.07791 93.8406 9.14749C93.8406 14.7608 89.1832 19.3113 83.1517 19.3113C78.8502 19.3113 74.5179 16.5041 73.0053 12.5795C72.9999 12.565 72.9986 12.5492 73.0015 12.534C73.0218 12.4179 73.0617 12.3118 73.1011 12.2074C73.1583 12.0555 73.2143 11.907 73.2062 11.7359L73.18 11.1892C73.174 11.0569 73.2075 10.9258 73.2764 10.8127C73.3452 10.6995 73.4463 10.6094 73.5666 10.554L73.7852 10.4523C73.9077 10.3957 74.0148 10.3105 74.0976 10.204C74.1803 10.0974 74.2363 9.97252 74.2608 9.83983C74.3341 9.43894 74.6865 9.14749 75.0979 9.14749C75.7404 9.14749 76.299 9.57412 76.5088 10.1806C77.5188 13.1 79.1245 15.2457 83.0561 15.2457Z' fill='white'/%3E%3Cpath d='M155.758 6.91365C155.028 6.91365 154.804 6.47916 154.804 5.98857C154.804 5.46997 154.986 5.06348 155.758 5.06348C156.53 5.06348 156.712 5.46997 156.712 5.98857C156.712 6.47905 156.516 6.91365 155.758 6.91365ZM142.441 12.9304V9.32833L141.415 9.32323V8.90392C141.415 8.44719 141.786 8.07758 142.244 8.07986L142.441 8.08095V6.55306L144.082 6.09057V8.08073H145.569V8.50416C145.569 8.61242 145.548 8.71961 145.506 8.81961C145.465 8.91961 145.404 9.01047 145.328 9.08699C145.251 9.16351 145.16 9.2242 145.06 9.26559C144.96 9.30698 144.853 9.32826 144.745 9.32822H144.082V12.7201C144.082 13.2423 144.378 13.4256 144.76 13.4887C145.209 13.5629 145.583 13.888 145.583 14.343V14.9626C144.029 14.9626 142.441 14.8942 142.441 12.9304Z' fill='white'/%3E%3Cpath d='M110.058 7.92554C108.417 7.88344 106.396 8.92062 106.396 11.5137C106.396 14.0646 108.417 15.0738 110.058 15.0318C111.742 15.0738 113.748 14.0646 113.748 11.5137C113.748 8.92062 111.742 7.88344 110.058 7.92554ZM110.07 13.7586C108.878 13.7586 108.032 12.8905 108.032 11.461C108.032 10.1013 108.878 9.20569 110.071 9.20569C111.263 9.20569 112.101 10.0995 112.101 11.459C112.101 12.8887 111.263 13.7586 110.07 13.7586Z' fill='white'/%3E%3Cpath d='M118.06 7.94098C119.491 7.94098 120.978 8.33337 120.978 11.1366V14.893H120.063C119.608 14.893 119.238 14.524 119.238 14.0689V10.9965C119.238 9.66506 118.747 9.16047 117.891 9.16047C117.414 9.16047 116.797 9.52486 116.502 9.81915V14.069C116.502 14.1773 116.481 14.2845 116.44 14.3845C116.398 14.4845 116.337 14.5753 116.261 14.6519C116.184 14.7284 116.093 14.7891 115.993 14.8305C115.893 14.8719 115.786 14.8931 115.678 14.8931H114.847V8.10918H115.773C115.932 8.10914 116.087 8.16315 116.212 8.26242C116.337 8.36168 116.424 8.50033 116.46 8.65577C116.881 8.19328 117.428 7.94098 118.06 7.94098ZM122.854 8.09713C123.024 8.09708 123.19 8.1496 123.329 8.2475C123.468 8.34541 123.574 8.48391 123.631 8.64405L125.133 12.8486L126.635 8.64415C126.692 8.48402 126.798 8.34551 126.937 8.2476C127.076 8.1497 127.242 8.09718 127.412 8.09724H128.598L126.152 14.3567C126.091 14.5112 125.986 14.6439 125.849 14.7374C125.711 14.831 125.549 14.881 125.383 14.8809H124.333L121.668 8.09713H122.854Z' fill='white'/%3E%3Cpath d='M135.085 14.5514C134.566 14.7616 133.513 15.0416 132.418 15.0416C130.496 15.0416 129.024 13.9345 129.024 11.4396C129.024 9.19701 130.451 7.99792 132.191 7.99792C134.338 7.99792 135.254 9.4378 135.158 11.3979C135.139 11.8029 134.786 12.0983 134.38 12.0983H130.679C130.763 13.1916 131.562 13.7662 132.615 13.7662C133.028 13.7662 133.462 13.7452 133.983 13.6481C134.535 13.545 135.085 13.9375 135.085 14.4985V14.5514ZM133.673 10.949C133.785 9.87621 133.061 9.28752 132.191 9.28752C131.321 9.28752 130.734 9.93979 130.679 10.9489L133.673 10.949Z' fill='white'/%3E%3Cpath d='M137.345 8.11122C137.497 8.11118 137.645 8.16229 137.765 8.25635C137.884 8.35041 137.969 8.48197 138.005 8.62993C138.566 8.20932 139.268 7.94303 139.759 7.94303C139.801 7.94303 140.068 7.94303 140.489 7.99913V8.7265C140.489 9.11748 140.15 9.4147 139.759 9.4147C139.31 9.4147 138.651 9.5829 138.131 9.8773V14.8951H136.462V8.11112L137.345 8.11122ZM156.6 14.0508V8.09104H155.769C155.314 8.09104 154.944 8.45999 154.944 8.9151V14.8748H155.775C156.23 14.8748 156.6 14.5058 156.6 14.0508ZM158.857 12.9447V9.34254H157.749V8.91912C157.749 8.46401 158.118 8.09506 158.574 8.09506H158.857V6.56739L160.499 6.10479V8.09506H161.986V8.51848C161.986 8.97359 161.617 9.34254 161.161 9.34254H160.499V12.7345C160.499 13.2566 160.795 13.44 161.177 13.503C161.626 13.5774 162 13.9024 162 14.3574V14.977C160.446 14.977 158.857 14.9086 158.857 12.9447ZM98.1929 10.1124C98.2033 6.94046 100.598 5.16809 102.895 5.16809C104.171 5.16809 105.342 5.44285 106.304 6.12953L105.914 6.6631C105.654 7.02011 105.16 7.16194 104.749 6.99949C104.169 6.7702 103.622 6.7218 103.215 6.7218C101.335 6.7218 99.9169 7.92849 99.9068 10.1123C99.9169 12.2959 101.335 13.5201 103.215 13.5201C103.622 13.5201 104.169 13.4717 104.749 13.2424C105.16 13.0799 105.654 13.2046 105.914 13.5615L106.304 14.0952C105.342 14.7819 104.171 15.0566 102.895 15.0566C100.598 15.0566 98.2033 13.2842 98.1929 10.1124ZM147.619 5.21768C148.074 5.21768 148.444 5.58663 148.444 6.04174V9.81968L151.82 5.58131C151.897 5.47733 151.997 5.39282 152.112 5.3346C152.227 5.27638 152.355 5.24607 152.484 5.24611H153.984L150.166 10.0615L153.984 14.8749H152.484C152.355 14.8749 152.227 14.8446 152.112 14.7864C151.997 14.7281 151.897 14.6436 151.82 14.5397L148.444 10.3025V14.0508C148.444 14.5059 148.074 14.8749 147.619 14.8749H146.746V5.21768H147.619Z' fill='white'/%3E%3Cpath d='M0.773438 6.5752H2.68066C3.56543 6.5752 4.2041 6.7041 4.59668 6.96191C4.99219 7.21973 5.18994 7.62695 5.18994 8.18359C5.18994 8.55859 5.09326 8.87061 4.8999 9.11963C4.70654 9.36865 4.42822 9.52539 4.06494 9.58984V9.63379C4.51611 9.71875 4.84717 9.88721 5.05811 10.1392C5.27197 10.3882 5.37891 10.7266 5.37891 11.1543C5.37891 11.7314 5.17676 12.1841 4.77246 12.5122C4.37109 12.8374 3.81152 13 3.09375 13H0.773438V6.5752ZM1.82373 9.22949H2.83447C3.27393 9.22949 3.59473 9.16064 3.79688 9.02295C3.99902 8.88232 4.1001 8.64502 4.1001 8.31104C4.1001 8.00928 3.99023 7.79102 3.77051 7.65625C3.55371 7.52148 3.20801 7.4541 2.7334 7.4541H1.82373V9.22949ZM1.82373 10.082V12.1167H2.93994C3.37939 12.1167 3.71045 12.0332 3.93311 11.8662C4.15869 11.6963 4.27148 11.4297 4.27148 11.0664C4.27148 10.7324 4.15723 10.4849 3.92871 10.3237C3.7002 10.1626 3.35303 10.082 2.88721 10.082H1.82373Z' fill='white'/%3E%3Cpath d='M13.011 6.5752V10.7324C13.011 11.207 12.9084 11.623 12.7034 11.9805C12.5012 12.335 12.2068 12.6089 11.8201 12.8022C11.4363 12.9927 10.9763 13.0879 10.4402 13.0879C9.6433 13.0879 9.02368 12.877 8.5813 12.4551C8.13892 12.0332 7.91772 11.4531 7.91772 10.7148V6.5752H8.9724V10.6401C8.9724 11.1704 9.09546 11.5615 9.34155 11.8135C9.58765 12.0654 9.96557 12.1914 10.4753 12.1914C11.4656 12.1914 11.9607 11.6714 11.9607 10.6313V6.5752H13.011Z' fill='white'/%3E%3Cpath d='M15.9146 13V6.5752H16.9649V13H15.9146Z' fill='white'/%3E%3Cpath d='M19.9255 13V6.5752H20.9758V12.0991H23.696V13H19.9255Z' fill='white'/%3E%3Cpath d='M28.2828 13H27.2325V7.47607H25.3428V6.5752H30.1724V7.47607H28.2828V13Z' fill='white'/%3E%3Cpath d='M41.9472 13H40.8046L39.7148 9.16796C39.6679 9.00097 39.6093 8.76074 39.539 8.44727C39.4687 8.13086 39.4262 7.91113 39.4116 7.78809C39.3823 7.97559 39.3339 8.21875 39.2665 8.51758C39.2021 8.81641 39.1479 9.03905 39.1039 9.18554L38.0405 13H36.8979L36.0673 9.7832L35.2236 6.5752H36.2958L37.2143 10.3193C37.3578 10.9199 37.4604 11.4502 37.5219 11.9102C37.5541 11.6611 37.6025 11.3828 37.6669 11.0752C37.7314 10.7676 37.79 10.5186 37.8427 10.3281L38.8886 6.5752H39.9301L41.0024 10.3457C41.1049 10.6943 41.2133 11.2158 41.3276 11.9102C41.3715 11.4912 41.477 10.958 41.644 10.3105L42.558 6.5752H43.6215L41.9472 13Z' fill='white'/%3E%3Cpath d='M45.7957 13V6.5752H46.846V13H45.7957Z' fill='white'/%3E%3Cpath d='M52.0258 13H50.9755V7.47607H49.0859V6.5752H53.9155V7.47607H52.0258V13Z' fill='white'/%3E%3Cpath d='M61.2312 13H60.1765V10.104H57.2146V13H56.1643V6.5752H57.2146V9.20312H60.1765V6.5752H61.2312V13Z' fill='white'/%3E%3C/svg%3E");}@-webkit-keyframes formkit-bouncedelay-formkit-form-data-uid-96a310b6ce-{0%,80%,100%{-webkit-transform:scale(0);-ms-transform:scale(0);transform:scale(0);}40%{-webkit-transform:scale(1);-ms-transform:scale(1);transform:scale(1);}}@keyframes formkit-bouncedelay-formkit-form-data-uid-96a310b6ce-{0%,80%,100%{-webkit-transform:scale(0);-ms-transform:scale(0);transform:scale(0);}40%{-webkit-transform:scale(1);-ms-transform:scale(1);transform:scale(1);}}.formkit-form[data-uid="96a310b6ce"] blockquote{padding:10px 20px;margin:0 0 20px;border-left:5px solid #e1e1e1;}.formkit-form[data-uid="96a310b6ce"] .seva-custom-content{padding:15px;font-size:16px;color:#fff;mix-blend-mode:difference;}.formkit-form[data-uid="96a310b6ce"] .formkit-modal.guard{max-width:420px;width:100%;} .formkit-form[data-uid="96a310b6ce"]{max-width:700px;}.formkit-form[data-uid="96a310b6ce"] [data-style="clean"]{width:100%;}.formkit-form[data-uid="96a310b6ce"] .formkit-fields{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-flex-wrap:wrap;-ms-flex-wrap:wrap;flex-wrap:wrap;margin:0 auto;}.formkit-form[data-uid="96a310b6ce"] .formkit-field,.formkit-form[data-uid="96a310b6ce"] .formkit-submit{margin:0 0 15px 0;-webkit-flex:1 0 100%;-ms-flex:1 0 100%;flex:1 0 100%;}.formkit-form[data-uid="96a310b6ce"] .formkit-powered-by-convertkit-container{margin:0;}.formkit-form[data-uid="96a310b6ce"] .formkit-submit{position:static;}.formkit-form[data-uid="96a310b6ce"][min-width~="700"] [data-style="clean"],.formkit-form[data-uid="96a310b6ce"][min-width~="800"] [data-style="clean"]{padding:10px;}.formkit-form[data-uid="96a310b6ce"][min-width~="700"] .formkit-fields[data-stacked="false"],.formkit-form[data-uid="96a310b6ce"][min-width~="800"] .formkit-fields[data-stacked="false"]{margin-left:-5px;margin-right:-5px;}.formkit-form[data-uid="96a310b6ce"][min-width~="700"] .formkit-fields[data-stacked="false"] .formkit-field,.formkit-form[data-uid="96a310b6ce"][min-width~="800"] .formkit-fields[data-stacked="false"] .formkit-field,.formkit-form[data-uid="96a310b6ce"][min-width~="700"] .formkit-fields[data-stacked="false"] .formkit-submit,.formkit-form[data-uid="96a310b6ce"][min-width~="800"] .formkit-fields[data-stacked="false"] .formkit-submit{margin:0 5px 15px 5px;}.formkit-form[data-uid="96a310b6ce"][min-width~="700"] .formkit-fields[data-stacked="false"] .formkit-field,.formkit-form[data-uid="96a310b6ce"][min-width~="800"] .formkit-fields[data-stacked="false"] .formkit-field{-webkit-flex:100 1 auto;-ms-flex:100 1 auto;flex:100 1 auto;}.formkit-form[data-uid="96a310b6ce"][min-width~="700"] .formkit-fields[data-stacked="false"] .formkit-submit,.formkit-form[data-uid="96a310b6ce"][min-width~="800"] .formkit-fields[data-stacked="false"] .formkit-submit{-webkit-flex:1 1 auto;-ms-flex:1 1 auto;flex:1 1 auto;} </style></form>
<hr>
<!-- Post comments -->
<script src="https://utteranc.es/client.js" repo="eugeneyan/eugeneyan-comments" issue-term="url" theme="github-light" crossorigin="anonymous" type="f28497f9592da7f32b5a2b50-text/javascript">
</script>
</div>
</div>
<footer class="footer">
<div class="footer-col-wrapper">
<div class="col-sm-3 footer-col">
<ul class="contact-list">
<!-- <li>
<img class="icon" src="/assets/bluesky.svg" loading="lazy" alt=""/>
<a rel="me" href="https://bsky.app/profile/eugeneyan.com" target="_blank" title="Bluesky">Bluesky</a>
</li> -->
<li>
<img class="icon" src="/assets/icon-twitter.svg" loading="lazy" alt=""/>
<a href="https://twitter.com/eugeneyan" target="_blank" title="Twitter">Twitter</a>
</li>
<li>
<img class="icon" src="/assets/icon-linkedin.svg" loading="lazy" alt=""/>
<a href="https://www.linkedin.com/in/eugeneyan/" target="_blank" title="Linkedin">LinkedIn</a>
</li>
<!-- <li>
<img class="icon" src="/assets/icon-threads.svg" loading="lazy" alt=""/>
<a href="https://www.threads.net/@eugeneyan" target="_blank" title="Threads">Threads</a>
</li> -->
<li>
<img class="icon" src="/assets/icon-github.svg" loading="lazy" alt=""/>
<a href="https://github.com/eugeneyan/" target="_blank" title="GitHub">GitHub</a>
</li>
</ul>
</div>
<div class="col-sm-9 footer-col">
<p>I'm a Member of Technical Staff at Anthropic. I work to bridge the field and the frontier, and help build safe, reliable AI systems that scale. I've led ML/AI teams at Amazon, Alibaba, Lazada, and a Healthtech Series A, and write about LLMs, RecSys, and engineering at <a href="https://eugeneyan.com/" target="_blank">eugeneyan.com</a>.</p>
</div>
</div>
<p class="copyright">© Eugene Yan 2015 - 2026
• <a href="/site-feedback/">Feedback</a>
• <a href="/rss/">RSS</a>
</p>
</footer>
</div> <!-- /container -->
</div>
<script src="/cdn-cgi/scripts/7d0fa10a/cloudflare-static/rocket-loader.min.js" data-cf-settings="f28497f9592da7f32b5a2b50-|49" defer></script><script defer src="https://static.cloudflareinsights.com/beacon.min.js/v833ccba57c9e4d2798f2e76cebdd09a11778172276447" integrity="sha512-57MDmcccJXYtNnH+ZiBwzC4jb2rvgVCEokYN+L/nLlmO8rfYT/gIpW2A569iJ/3b+0UEasghjuZH/ma3wIs/EQ==" data-cf-beacon='{"version":"2024.11.0","token":"4ba4ab6acad14218941be7fa4aaad127","r":1,"server_timing":{"name":{"cfCacheStatus":true,"cfEdge":true,"cfExtPri":true,"cfL4":true,"cfOrigin":true,"cfSpeedBrain":true},"location_startswith":null}}' crossorigin="anonymous"></script>
</body>
<script type="f28497f9592da7f32b5a2b50-text/javascript">
// Assemble mailto: from split data attributes on click (keeps full address out of source)
document.addEventListener('click', function(e) {
var a = e.target.closest('a.js-email');
if (!a) return;
e.preventDefault();
var d = a.dataset;
window.location.href = 'mailto:' + d.u + '@' + d.d + '.' + d.t;
});
// Ensure aa is loaded
document.addEventListener('DOMContentLoaded', function() {
if (typeof aa === 'function') {
// Get the current page path for more specific tracking
const pagePath = '/writing/recommender-systems-baseline-pytorch/';
// Determine a specific event name based on the current page
let eventName;
if (pagePath.startsWith('/tag/')) {
eventName = 'Tag Page Link Clicked';
} else {
// Count the number of segments to determine if it's a site page or post page
const pathSegments = pagePath.split('/').filter(Boolean);
if (pathSegments.length <= 1) {
// Zero or one level deep (e.g., '/', '/writing/', '/speaking/')
eventName = 'Site Page Link Clicked';
} else {
// Two or more levels deep - considered a post
eventName = 'Post Link Clicked';
}
}
// Track clicks on internal links in the main container
const container = document.querySelector('div.container');
if (container) {
container.addEventListener('click', function(e) {
const link = e.target.closest('a');
if (link && !link.classList.contains('js-email') && link.href && link.origin === window.location.origin) {
const objectID = link.pathname;
aa('clickedObjectIDs', {
index: 'eugeneyan.com',
eventName: eventName,
objectIDs: [objectID]
});
}
});
}
}
});
// Track page read depth for conversion tracking
let hasTrackedPageRead = false;
window.addEventListener('scroll', function() {
if (hasTrackedPageRead) return; // Only track once per page view
// Calculate read depth as percentage
const scrollTop = window.pageYOffset || document.documentElement.scrollTop;
const scrollHeight = document.documentElement.scrollHeight;
const clientHeight = document.documentElement.clientHeight;
const readPercentage = (scrollTop + clientHeight) / scrollHeight * 100;
// If user has read at least 50% of the page
if (readPercentage >= 50 && typeof aa === 'function') {
hasTrackedPageRead = true;
const objectID = window.location.pathname; // Use current page path as objectID
const pagePath = '/writing/recommender-systems-baseline-pytorch/';
// Create a meaningful event name
let eventName;
if (pagePath.startsWith('/tag/')) {
eventName = 'Tag Page Read 50%';
} else {
// Count the number of segments to determine if it's a site page or post page
const pathSegments = pagePath.split('/').filter(Boolean);
if (pathSegments.length <= 1) {
// Zero or one level deep (e.g., '/', '/writing/', '/speaking/')
eventName = 'Site Page Read 50%';
} else {
// Two or more levels deep - considered a post
eventName = 'Post Read 50%';
}
}
// Send the convertedObjectIDs event to Algolia
aa('convertedObjectIDs', {
index: 'eugeneyan.com',
eventName: eventName,
objectIDs: [objectID]
});
}
});
</script>
</html>