{"id":3279,"date":"2022-02-27T14:23:01","date_gmt":"2022-02-27T06:23:01","guid":{"rendered":"https:\/\/egonlin.com\/?p=3279"},"modified":"2022-02-27T14:33:25","modified_gmt":"2022-02-27T06:33:25","slug":"%e7%ac%ac%e4%ba%94%e8%8a%82%ef%bc%9a%e7%bb%86%e5%88%86%e6%9e%84%e5%bb%ba%e6%9c%ba%e5%99%a8%e5%ad%a6%e4%b9%a0%e5%ba%94%e7%94%a8%e7%a8%8b%e5%ba%8f%e7%9a%84%e6%b5%81%e7%a8%8b-%e6%95%b0%e6%8d%ae%e6%94%b6","status":"publish","type":"post","link":"https:\/\/egonlin.com\/?p=3279","title":{"rendered":"\u7b2c\u4e94\u8282\uff1a\u7ec6\u5206\u6784\u5efa\u673a\u5668\u5b66\u4e60\u5e94\u7528\u7a0b\u5e8f\u7684\u6d41\u7a0b-\u6570\u636e\u6536\u96c6"},"content":{"rendered":"

\u7ec6\u5206\u6784\u5efa\u673a\u5668\u5b66\u4e60\u5e94\u7528\u7a0b\u5e8f\u7684\u6d41\u7a0b-\u6570\u636e\u6536\u96c6<\/h1>\n

sklearn\u6570\u636e\u96c6\u5b98\u65b9\u6587\u6863\u5730\u5740\uff1ahttps:\/\/scikit-learn.org\/stable\/modules\/classes.html#module-sklearn.datasets<\/a><\/p>\n

  sklearn\u6570\u636e\u96c6\u4e00\u89c8<\/p>\n\n\n\n\n\n\n\n\n\n
\u7c7b\u578b<\/th>\n\u83b7\u53d6\u65b9\u5f0f<\/th>\n<\/tr>\n<\/thead>\n
sklearn\u751f\u6210\u7684\u968f\u673a\u6570\u636e\u96c6<\/td>\nsklearn.datasets.make_\u2026<\/td>\n<\/tr>\n
sklearn\u81ea\u5e26\u6570\u636e\u96c6<\/td>\nsklearn.datasets.load_\u2026<\/td>\n<\/tr>\n
sklearn\u5728\u7ebf\u4e0b\u8f7d\u7684\u6570\u636e\u96c6<\/td>\nsklearn.datasets.fetch_\u2026<\/td>\n<\/tr>\n
sklearn\u4e2d\u52a0\u8f7d\u7684svmlight\u683c\u5f0f\u7684\u6570\u636e\u96c6<\/td>\nsklearn.datasets.load_svmlight_file(\u2026)<\/td>\n<\/tr>\n
sklearn\u5728mldata.org\u5728\u7ebf\u4e0b\u8f7d\u7684\u6570\u636e\u96c6<\/td>\nsklearn.datasets.fetch_mldata(\u2026)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

1.1 \u901a\u8fc7sklearn\u751f\u6210\u968f\u673a\u6570\u636e<\/h1>\n

  \u901a\u8fc7sklearn\u6539\u53d8\u751f\u6210\u968f\u673a\u6570\u636e\u65b9\u6cd5\u7684\u53c2\u6570\uff0c\u65e2\u53ef\u4ee5\u83b7\u5f97\u7528\u4e0d\u5c3d\u7684\u6570\u636e\uff0c\u5e76\u4e14\u6570\u636e\u7684\u6837\u672c\u6570\u3001\u7279\u5f81\u6570\u3001\u6807\u8bb0\u7c7b\u522b\u6570\u3001\u566a\u58f0\u6570\u90fd\u53ef\u4ee5\u81ea\u5b9a\u4e49\uff0c\u975e\u5e38\u7075\u6d3b\uff0c\u7b80\u5355\u4ecb\u7ecd\u51e0\u4e2asklearn\u7ecf\u5e38\u4f7f\u7528\u7684\u751f\u6210\u968f\u673a\u6570\u636e\u7684\u65b9\u6cd5\u3002<\/p>\n\n\n\n\n\n\n\n\n\n\n
\u65b9\u6cd5<\/th>\n\u7528\u9014<\/th>\n<\/tr>\n<\/thead>\n
make_classification()<\/td>\n\u7528\u4e8e\u5206\u7c7b<\/td>\n<\/tr>\n
maek_multilabel_classfication()<\/td>\n\u7528\u4e8e\u591a\u6807\u7b7e\u5206\u7c7b<\/td>\n<\/tr>\n
make_regression()<\/td>\n\u7528\u4e8e\u56de\u5f52<\/td>\n<\/tr>\n
make_blobs()<\/td>\n\u7528\u4e8e\u805a\u7c7b\u548c\u5206\u7c7b<\/td>\n<\/tr>\n
make_circles()<\/td>\n\u7528\u4e8e\u5206\u7c7b<\/td>\n<\/tr>\n
make_moons()<\/td>\n\u7528\u4e8e\u5206\u7c7b<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

1.1.1 make_classification()<\/h2>\n\n\n\n\n\n\n\n\n\n\n
\u53c2\u6570<\/th>\n\u89e3\u91ca<\/th>\n<\/tr>\n<\/thead>\n
n_features<\/td>\n\u7279\u5f81\u4e2a\u6570= n_informative\uff08\uff09 + n_redundant + n_repeated<\/td>\n<\/tr>\n
n_informative<\/td>\n\u591a\u4fe1\u606f\u7279\u5f81\u7684\u4e2a\u6570<\/td>\n<\/tr>\n
n_redundant<\/td>\n\u5197\u4f59\u4fe1\u606f\uff0cinformative\u7279\u5f81\u7684\u968f\u673a\u7ebf\u6027\u7ec4\u5408<\/td>\n<\/tr>\n
n_repeated<\/td>\n\u91cd\u590d\u4fe1\u606f\uff0c\u968f\u673a\u63d0\u53d6n_informative\u548cn_redundant \u7279\u5f81<\/td>\n<\/tr>\n
n_classes<\/td>\n\u5206\u7c7b\u7c7b\u522b<\/td>\n<\/tr>\n
n_clusters_per_class<\/td>\n\u67d0\u4e00\u4e2a\u7c7b\u522b\u662f\u7531\u51e0\u4e2acluster\u6784\u6210\u7684<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n
import numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nfrom matplotlib.font_manager import FontProperties\nfrom sklearn import datasets\n%matplotlib inline\nfont = FontProperties(fname='\/Library\/Fonts\/Heiti.ttc')<\/code><\/pre>\n
from sklearn import datasets\ntry:\n    X1, y1 = datasets.make_classification(\n        n_samples=50, n_classes=3, n_clusters_per_class=2, n_informative=2)\n    print(X1.shape)\nexcept Exception as e:\n    print('error:{}'.format(e))\n\n# \u4e0b\u9762\u9519\u8bef\u4fe1\u606fn_classes * n_clusters_per_class must be smaller or equal 2 ** n_informative\uff0c\n# \u5f53n_clusters_per_class=2\u65f6\uff0c\u610f\u5473\u7740\u8be5\u751f\u6210\u968f\u673a\u6570\u7684n_classes\u5e94\u8be5\u5c0f\u4e8e2\uff0c\u53ef\u4ee5\u7406\u89e3\u6210\u4e00\u5206\u7c7b\u6216\u4e8c\u5206\u7c7b<\/code><\/pre>\n
error:n_classes * n_clusters_per_class must be smaller or equal 2 ** n_informative<\/code><\/pre>\n
import matplotlib.pyplot as plt\n%matplotlib inline\n\nplt.figure(figsize=(10, 10))\n\nplt.subplot(221)\nplt.title("One informative feature, one cluster per class", fontsize=12)\nX1, y1 = datasets.make_classification(n_samples=1000, random_state=1, n_features=2, n_redundant=0, n_informative=1,\n                                      n_clusters_per_class=1)\nplt.scatter(X1[:, 0], X1[:, 1], marker='*', c=y1)\n\nplt.subplot(222)\nplt.title("Two informative features, one cluster per class", fontsize=12)\nX1, y1 = datasets.make_classification(n_samples=1000, random_state=1, n_features=2, n_redundant=0, n_informative=2,\n                                      n_clusters_per_class=1)\nplt.scatter(X1[:, 0], X1[:, 1], marker='*', c=y1)\n\nplt.subplot(223)\nplt.title("Two informative features, two clusters per class", fontsize=12)\nX1, y1 = datasets.make_classification(\n    n_samples=1000, random_state=1, n_features=2, n_redundant=0, n_informative=2)\nplt.scatter(X1[:, 0], X1[:, 1], marker='*', c=y1)\n\nplt.subplot(224)\nplt.title("Multi-class, two informative features, one cluster",\n          fontsize=12)\nX1, y1 = datasets.make_classification(n_samples=1000, random_state=1, n_features=2, n_redundant=0, n_informative=2,\n                                      n_clusters_per_class=1, n_classes=4)\nplt.scatter(X1[:, 0], X1[:, 1], marker='*', c=y1)\nplt.show()<\/code><\/pre>\n
\"\"<\/div><\/p>\n
1.1.2 make_multilabel_classification()<\/h2>\n
X1, y1 = datasets.make_multilabel_classification(\n    n_samples=1000, n_classes=4, n_features=2, random_state=1)\ndatasets.make_multilabel_classification()\n\nprint('\u6837\u672c\u7ef4\u5ea6:{}'.format(X1.shape))\n\n# \u4e00\u4e2a\u6837\u672c\u53ef\u80fd\u6709\u591a\u4e2a\u6807\u8bb0\nprint(y1[0:5, :])<\/code><\/pre>\n
\u6837\u672c\u7ef4\u5ea6:(1000, 2)\n[[1 1 0 0]\n [0 0 0 0]\n [1 1 0 0]\n [0 0 0 1]\n [0 0 0 0]]<\/code><\/pre>\n
plt.scatter(X1[:, 0], X1[:, 1], marker='*', c=y1)\nplt.show()<\/code><\/pre>\n
\"\"<\/div><\/p>\n
1.1.3 make_regression()<\/h2>\n
import matplotlib.pyplot as plt\n%matplotlib inline\nfrom sklearn import datasets\nX1, y1 = datasets.make_regression(n_samples=500, n_features=1, noise=20)\nplt.scatter(X1, y1, color='r', s=10, marker='*')\nplt.show()<\/code><\/pre>\n
\"\"<\/div><\/p>\n
1.1.4 make_blobs<\/h2>\n
<\/p>
<\/div>
\u67e5\u770b\u66f4\u591a<\/h2>
\u8054\u7cfb\u7ba1\u7406\u5458\u5fae\u4fe1tutu19192010\uff0c\u6ce8\u518c\u8d26\u53f7<\/p>\n<\/div>
<\/div>
<\/td><\/tr>
<\/td><\/tr><\/tbody><\/table>
<\/td><\/tr><\/tbody><\/table><\/form>
Register<\/a><\/div>
Forgotten username or password?<\/a><\/div>
<\/div><\/div><\/div>
<\/div>","protected":false},"excerpt":{"rendered":"
\u7ec6\u5206\u6784\u5efa\u673a\u5668\u5b66\u4e60\u5e94\u7528\u7a0b\u5e8f\u7684\u6d41\u7a0b-\u6570\u636e\u6536\u96c6 sklearn\u6570\u636e\u96c6\u5b98\u65b9\u6587\u6863\u5730\u5740\uff1ahttps:\/\/scikit-le […]<\/p>\n","protected":false},"author":3,"featured_media":3275,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[276,301],"tags":[],"_links":{"self":[{"href":"https:\/\/egonlin.com\/index.php?rest_route=\/wp\/v2\/posts\/3279"}],"collection":[{"href":"https:\/\/egonlin.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/egonlin.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/egonlin.com\/index.php?rest_route=\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/egonlin.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=3279"}],"version-history":[{"count":0,"href":"https:\/\/egonlin.com\/index.php?rest_route=\/wp\/v2\/posts\/3279\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/egonlin.com\/index.php?rest_route=\/wp\/v2\/media\/3275"}],"wp:attachment":[{"href":"https:\/\/egonlin.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3279"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/egonlin.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=3279"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/egonlin.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=3279"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}