[{"data":1,"prerenderedAt":113},["ShallowReactive",2],{"term-c\u002Fclustering":3,"related-c\u002Fclustering":102},{"id":4,"title":5,"acronym":6,"body":7,"category":83,"description":84,"difficulty":85,"extension":86,"letter":87,"meta":88,"navigation":89,"path":90,"related":91,"seo":96,"sitemap":97,"stem":100,"subcategory":6,"__hash__":101},"terms\u002Fterms\u002Fc\u002Fclustering.md","Clustering",null,{"type":8,"value":9,"toc":77},"minimark",[10,15,19,23,26,30,66,70,73],[11,12,14],"h2",{"id":13},"eli5-the-vibe-check","ELI5 — The Vibe Check",[16,17,18],"p",{},"Clustering is teaching an AI to find groups in data WITHOUT being told what the groups are. You dump in a million customer records and say 'find the natural groups.' The algorithm discovers that there are 5 types of customers you never knew about. It's unsupervised — nobody tells it what to look for.",[11,20,22],{"id":21},"real-talk","Real Talk",[16,24,25],{},"Clustering is an unsupervised learning task that groups data points by similarity without predefined labels. Common algorithms include K-means, DBSCAN, hierarchical clustering, and Gaussian Mixture Models. It is used for customer segmentation, anomaly detection, and data exploration. Evaluation is less straightforward than supervised tasks.",[11,27,29],{"id":28},"show-me-the-code","Show Me The Code",[31,32,37],"pre",{"className":33,"code":34,"language":35,"meta":36,"style":36},"language-python shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","from sklearn.cluster import KMeans\nkmeans = KMeans(n_clusters=5, random_state=42)\nkmeans.fit(X)\nlabels = kmeans.labels_  # which cluster each point belongs to\n","python","",[38,39,40,48,54,60],"code",{"__ignoreMap":36},[41,42,45],"span",{"class":43,"line":44},"line",1,[41,46,47],{},"from sklearn.cluster import KMeans\n",[41,49,51],{"class":43,"line":50},2,[41,52,53],{},"kmeans = KMeans(n_clusters=5, random_state=42)\n",[41,55,57],{"class":43,"line":56},3,[41,58,59],{},"kmeans.fit(X)\n",[41,61,63],{"class":43,"line":62},4,[41,64,65],{},"labels = kmeans.labels_  # which cluster each point belongs to\n",[11,67,69],{"id":68},"when-youll-hear-this","When You'll Hear This",[16,71,72],{},"\"We used clustering to discover customer segments.\" \u002F \"Clustering found 3 natural groups in the user behavior data.\"",[74,75,76],"style",{},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"title":36,"searchDepth":50,"depth":50,"links":78},[79,80,81,82],{"id":13,"depth":50,"text":14},{"id":21,"depth":50,"text":22},{"id":28,"depth":50,"text":29},{"id":68,"depth":50,"text":69},"ai","Clustering is teaching an AI to find groups in data WITHOUT being told what the groups are.","intermediate","md","c",{},true,"\u002Fterms\u002Fc\u002Fclustering",[92,93,94,95],"Classification","Regression","Embedding","Unsupervised Learning",{"title":5,"description":84},{"changefreq":98,"priority":99},"weekly",0.7,"terms\u002Fc\u002Fclustering","Tt05aR2dbrf4ncfK8qZxWeyTN9gIKl3ZSdPjh6DWQX8",[103,107,110],{"title":92,"path":104,"acronym":6,"category":83,"difficulty":105,"description":106},"\u002Fterms\u002Fc\u002Fclassification","beginner","Classification is teaching an AI to sort things into categories. Is this email spam or not? Is this image a cat, dog, or bird?",{"title":94,"path":108,"acronym":6,"category":83,"difficulty":85,"description":109},"\u002Fterms\u002Fe\u002Fembedding","An embedding is turning words, sentences, or entire documents into lists of numbers (vectors) that capture their meaning.",{"title":93,"path":111,"acronym":6,"category":83,"difficulty":105,"description":112},"\u002Fterms\u002Fr\u002Fregression","Regression is like classification but instead of sorting things into categories, you're predicting a number. What will this house sell for?",1776518266651]