{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.datasets import make_blobs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(10, 2)\n"
     ]
    }
   ],
   "source": [
    "###6.3.1 生成用于聚类的各向同性高斯斑点\n",
    "## sklearn.datasets.make_blobs(n_samples=100, n_features=2, *, centers=None, cluster_std=1.0, \n",
    "#  center_box=(-10.0, 10.0), shuffle=True, random_state=None, return_centers=False)\n",
    "X, y = make_blobs(n_samples=10, centers=3, n_features=2,random_state=0)\n",
    "print(X.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 0, 1, 0, 2, 2, 2, 1, 1, 0])"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## 总结\n",
    "\n",
    "#1、为了在控制数据的统计特性（通常是特征的 correlation （相关性）和 informativeness （信息性））的同时\n",
    "#   评估数据集 (n_samples 和 n_features) 的规模的影响，也可以生成综合数据。\n",
    "#2、此处只列举了make_blobs方法，更多的方法请参考 https://scikit-learn.org/stable/datasets/sample_generators.html"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}