{"id":146021,"date":"2025-07-21T11:31:41","date_gmt":"2025-07-21T06:01:41","guid":{"rendered":"https:\/\/data-flair.training\/blogs\/?p=146021"},"modified":"2025-07-21T11:31:41","modified_gmt":"2025-07-21T06:01:41","slug":"customer-segmentation-using-k-means-clustering","status":"publish","type":"post","link":"https:\/\/data-flair.training\/blogs\/customer-segmentation-using-k-means-clustering\/","title":{"rendered":"ML Project \u2013 Customer Segmentation Using K-Means Clustering"},"content":{"rendered":"

Program 1<\/h3>\n

Customer Segmentation Dataset<\/strong><\/a><\/p>\n

Customer Segmentation Dataset 1<\/strong><\/a><\/p>\n

# Librires\r\nimport pandas as pd\r\nimport numpy as np\r\nimport matplotlib.pyplot as plt\r\nfrom sklearn.cluster import KMeans\r\nfrom sklearn.preprocessing import StandardScaler\r\n\r\n# Step 1: Generate Synthetic Dataset\r\nnp.random.seed(42) # It ensures that every time you run the code, you get the same random numbers.\r\nn_customers = 200  # n_customers \u2192 number of values (here, 200 customers)\r\ndata = {\r\n    'CustomerID': np.arange(1, n_customers + 1),\r\n    'Annual Income (k$)': np.random.normal(60, 20, n_customers).astype(int), # 60 \u2192 mean (average annual income = $60k),20 \u2192 standard deviation (spread of incomes is +-$20k)\r\n    'Spending Score (1-100)': np.random.randint(1, 101, n_customers)\r\n}\r\ndf = pd.DataFrame(data)\r\ndf.shape\r\n\r\n# Step 2: Save Dataset (Optional)\r\ndf.to_csv(\"D:\/\/scikit_data\/KMeans\/customer_segmentation.csv\", index=False)\r\n\r\n# Step 3: Prepare Features\r\nX = df[['Annual Income (k$)', 'Spending Score (1-100)']]\r\nscaler = StandardScaler()\r\nX_scaled = scaler.fit_transform(X)\r\nX_scaled\r\n\r\n# Step 4: Apply K-Means Clustering\r\nkmeans = KMeans(n_clusters=4, random_state=42)\r\ndf['Cluster'] = kmeans.fit_predict(X_scaled)\r\ndf.to_csv(\"D:\/\/scikit_data\/KMeans\/customer_segmentation1.csv\", index=False)\r\n\r\n# Step 5: Plot Clusters with Centroids\r\nplt.figure(figsize=(8, 6))\r\nplt.scatter(df['Annual Income (k$)'], df['Spending Score (1-100)'],\r\n            c=df['Cluster'], cmap='viridis', s=50)\r\nplt.scatter(scaler.inverse_transform(kmeans.cluster_centers_)[:, 0],\r\n            scaler.inverse_transform(kmeans.cluster_centers_)[:, 1],\r\n            s=200, c='red', marker='X', label='Centroids')\r\nplt.title('Customer Segmentation Based on Spending Habits')\r\nplt.xlabel('Annual Income (k$)')\r\nplt.ylabel('Spending Score (1\u2013100)')\r\nplt.legend()\r\nplt.grid(True)\r\nplt.tight_layout()\r\nplt.show()\r\n\r\n# kmeans.cluster_centers_\r\n# These are the coordinates of the cluster centers \u2014 but in scaled form (because we normalized the data earlier).\r\n# It returns an array like:\r\n# [[ 0.56, -1.02],\r\n#  [-0.83,  0.91],\r\n#  ... ]\r\n# scaler.inverse_transform(...)\r\n# This undoes the scaling, converting the centroids back to their original values (real income and spending score).\r\n# Now you can plot them in the same scale as the original data.\r\n# [:, 0] and [:, 1]\r\n# [:, 0] \u2192 all rows, column 0 \u2192 x-values (Annual Income)\r\n# [:, 1] \u2192 all rows, column 1 \u2192 y-values (Spending Score)<\/pre>\n
Program 1 Customer Segmentation Dataset Customer Segmentation Dataset 1 # Librires import pandas as pd import numpy as np import matplotlib.pyplot as plt from sklearn.cluster import KMeans from sklearn.preprocessing import StandardScaler # Step 1:...<\/p>\n","protected":false},"author":581,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[36],"tags":[34941,34942,21706,8431,34943,33127,33128,20697],"class_list":["post-146021","post","type-post","status-publish","format-standard","hentry","category-machine-learning","tag-customer-segmentation-using-k-means-clustering","tag-customer-segmentation-using-k-means-clustering-project","tag-customer-segmentation-using-machine-learning","tag-machine-learning","tag-machine-learning-customer-segmentation-using-k-means-clustering-project","tag-machine-learning-practical","tag-machine-learning-program","tag-machine-learning-project"],"yoast_head":"\nML Project \u2013 Customer Segmentation Using K-Means Clustering - DataFlair<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/data-flair.training\/blogs\/customer-segmentation-using-k-means-clustering\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"ML Project \u2013 Customer Segmentation Using K-Means Clustering - DataFlair\" \/>\n<meta property=\"og:description\" content=\"Program 1 Customer Segmentation Dataset Customer Segmentation Dataset 1 # Librires import pandas as pd import numpy as np import matplotlib.pyplot as plt from sklearn.cluster import KMeans from sklearn.preprocessing import StandardScaler # Step 1:...\" \/>\n<meta property=\"og:url\" content=\"https:\/\/data-flair.training\/blogs\/customer-segmentation-using-k-means-clustering\/\" \/>\n<meta property=\"og:site_name\" content=\"DataFlair\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/DataFlairWS\/\" \/>\n<meta property=\"article:published_time\" content=\"2025-07-21T06:01:41+00:00\" \/>\n<meta name=\"author\" content=\"DataFlair Team\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@DataFlairWS\" \/>\n<meta name=\"twitter:site\" content=\"@DataFlairWS\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"DataFlair Team\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"1 minute\" \/>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"ML Project \u2013 Customer Segmentation Using K-Means Clustering - DataFlair","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/data-flair.training\/blogs\/customer-segmentation-using-k-means-clustering\/","og_locale":"en_US","og_type":"article","og_title":"ML Project \u2013 Customer Segmentation Using K-Means Clustering - DataFlair","og_description":"Program 1 Customer Segmentation Dataset Customer Segmentation Dataset 1 # Librires import pandas as pd import numpy as np import matplotlib.pyplot as plt from sklearn.cluster import KMeans from sklearn.preprocessing import StandardScaler # Step 1:...","og_url":"https:\/\/data-flair.training\/blogs\/customer-segmentation-using-k-means-clustering\/","og_site_name":"DataFlair","article_publisher":"https:\/\/www.facebook.com\/DataFlairWS\/","article_published_time":"2025-07-21T06:01:41+00:00","author":"DataFlair Team","twitter_card":"summary_large_image","twitter_creator":"@DataFlairWS","twitter_site":"@DataFlairWS","twitter_misc":{"Written by":"DataFlair Team","Est. reading time":"1 minute"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/data-flair.training\/blogs\/customer-segmentation-using-k-means-clustering\/#article","isPartOf":{"@id":"https:\/\/data-flair.training\/blogs\/customer-segmentation-using-k-means-clustering\/"},"author":{"name":"DataFlair Team","@id":"https:\/\/data-flair.training\/blogs\/#\/schema\/person\/c187795dc82ab948373cca526df7c445"},"headline":"ML Project \u2013 Customer Segmentation Using K-Means Clustering","datePublished":"2025-07-21T06:01:41+00:00","mainEntityOfPage":{"@id":"https:\/\/data-flair.training\/blogs\/customer-segmentation-using-k-means-clustering\/"},"wordCount":14,"commentCount":0,"publisher":{"@id":"https:\/\/data-flair.training\/blogs\/#organization"},"keywords":["customer segmentation using k-means clustering","customer segmentation using k-means clustering project","Customer Segmentation using Machine Learning","machine learning","machine learning customer segmentation using k-means clustering project","machine learning practical","machine learning program","machine learning project"],"articleSection":["Machine Learning Tutorials"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/data-flair.training\/blogs\/customer-segmentation-using-k-means-clustering\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/data-flair.training\/blogs\/customer-segmentation-using-k-means-clustering\/","url":"https:\/\/data-flair.training\/blogs\/customer-segmentation-using-k-means-clustering\/","name":"ML Project \u2013 Customer Segmentation Using K-Means Clustering - DataFlair","isPartOf":{"@id":"https:\/\/data-flair.training\/blogs\/#website"},"datePublished":"2025-07-21T06:01:41+00:00","breadcrumb":{"@id":"https:\/\/data-flair.training\/blogs\/customer-segmentation-using-k-means-clustering\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/data-flair.training\/blogs\/customer-segmentation-using-k-means-clustering\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/data-flair.training\/blogs\/customer-segmentation-using-k-means-clustering\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Blog Home","item":"https:\/\/data-flair.training\/blogs\/"},{"@type":"ListItem","position":2,"name":"Machine Learning Tutorials","item":"https:\/\/data-flair.training\/blogs\/category\/machine-learning\/"},{"@type":"ListItem","position":3,"name":"ML Project \u2013 Customer Segmentation Using K-Means Clustering"}]},{"@type":"WebSite","@id":"https:\/\/data-flair.training\/blogs\/#website","url":"https:\/\/data-flair.training\/blogs\/","name":"DataFlair","description":"Learn Today. Lead Tomorrow.","publisher":{"@id":"https:\/\/data-flair.training\/blogs\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/data-flair.training\/blogs\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/data-flair.training\/blogs\/#organization","name":"DataFlair","url":"https:\/\/data-flair.training\/blogs\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/data-flair.training\/blogs\/#\/schema\/logo\/image\/","url":"https:\/\/data-flair.training\/blogs\/wp-content\/uploads\/sites\/2\/2016\/07\/Data-Flair.png","contentUrl":"https:\/\/data-flair.training\/blogs\/wp-content\/uploads\/sites\/2\/2016\/07\/Data-Flair.png","width":106,"height":48,"caption":"DataFlair"},"image":{"@id":"https:\/\/data-flair.training\/blogs\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/DataFlairWS\/","https:\/\/x.com\/DataFlairWS","https:\/\/www.linkedin.com\/company\/dataflair-web-services-pvt-ltd\/","https:\/\/www.youtube.com\/user\/DataFlairWS"]},{"@type":"Person","@id":"https:\/\/data-flair.training\/blogs\/#\/schema\/person\/c187795dc82ab948373cca526df7c445","name":"DataFlair Team","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/2302ebc438084d2f1f993edc1996a0aae01332e81f3227cba8df0c48ec010ca4?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/2302ebc438084d2f1f993edc1996a0aae01332e81f3227cba8df0c48ec010ca4?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/2302ebc438084d2f1f993edc1996a0aae01332e81f3227cba8df0c48ec010ca4?s=96&d=mm&r=g","caption":"DataFlair Team"},"description":"DataFlair Team provides high-impact content on programming, Java, Python, C++, DSA, AI, ML, data Science, Android, Flutter, MERN, Web Development, and technology. We make complex concepts easy to grasp, helping learners of all levels succeed in their tech careers.","url":"https:\/\/data-flair.training\/blogs\/author\/dfteam6\/"}]}},"amp_enabled":true,"_links":{"self":[{"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/posts\/146021","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/users\/581"}],"replies":[{"embeddable":true,"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/comments?post=146021"}],"version-history":[{"count":4,"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/posts\/146021\/revisions"}],"predecessor-version":[{"id":146039,"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/posts\/146021\/revisions\/146039"}],"wp:attachment":[{"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/media?parent=146021"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/categories?post=146021"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/tags?post=146021"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}