{"id":10021261,"date":"2026-02-20T14:46:03","date_gmt":"2026-02-20T06:46:03","guid":{"rendered":"https:\/\/itmax.cn\/?p=10021261"},"modified":"2026-02-20T14:46:03","modified_gmt":"2026-02-20T06:46:03","slug":"python-%e6%9c%ba%e5%99%a8%e5%ad%a6%e4%b9%a0%ef%bc%9ascikit-learn-%e6%a0%b8%e5%bf%83%e7%ae%97%e6%b3%95%e5%ae%9e%e6%88%98","status":"publish","type":"post","link":"https:\/\/itmax.cn\/?p=10021261","title":{"rendered":"Python \u673a\u5668\u5b66\u4e60\uff1aScikit-learn \u6838\u5fc3\u7b97\u6cd5\u5b9e\u6218"},"content":{"rendered":"

Python \u673a\u5668\u5b66\u4e60\uff1aScikit-learn \u6838\u5fc3\u7b97\u6cd5\u5b9e\u6218<\/h2>\n

\u673a\u5668\u5b66\u4e60\u662f\u4eba\u5de5\u667a\u80fd\u7684\u91cd\u8981\u5206\u652f\uff0cScikit-learn \u662f Python \u6700\u6d41\u884c\u7684\u673a\u5668\u5b66\u4e60\u5e93\u3002\u672c\u6587\u5c06\u6df1\u5165\u63a2\u8ba8 Scikit-learn \u7684\u6838\u5fc3\u7b97\u6cd5\u548c\u5b9e\u6218\u5e94\u7528\uff0c\u5e2e\u52a9\u8bfb\u8005\u638c\u63e1\u673a\u5668\u5b66\u4e60\u7684\u6838\u5fc3\u6280\u672f\u3002<\/p>\n

\u76d1\u7763\u5b66\u4e60<\/h3>\n

\u76d1\u7763\u5b66\u4e60\u4f7f\u7528\u6807\u8bb0\u6570\u636e\u8bad\u7ec3\u6a21\u578b\uff0c\u9884\u6d4b\u65b0\u6570\u636e\u7684\u6807\u7b7e\u3002<\/p>\n

from sklearn.model_selection import train_test_split\nfrom sklearn.linear_model import LinearRegression\nfrom sklearn.metrics import mean_squared_error, r2_score\nimport numpy as np\n\ndef supervised_learning_demo():\n    print("\u76d1\u7763\u5b66\u4e60\u6f14\u793a:")\n    \n    X = np.random.rand(100, 1) * 10\n    y = 2 * X.ravel() + 1 + np.random.randn(100) * 0.5\n    \n    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)\n    \n    model = LinearRegression()\n    model.fit(X_train, y_train)\n    \n    y_pred = model.predict(X_test)\n    \n    print(f"\u5747\u65b9\u8bef\u5dee: {mean_squared_error(y_test, y_pred):.4f}")\n    print(f"R2 \u5206\u6570: {r2_score(y_test, y_pred):.4f}")\n\nsupervised_learning_demo()<\/code><\/pre>\n
\u65e0\u76d1\u7763\u5b66\u4e60<\/h3>\n
\u65e0\u76d1\u7763\u5b66\u4e60\u53d1\u73b0\u6570\u636e\u4e2d\u7684\u9690\u85cf\u6a21\u5f0f\u3002<\/p>\n
from sklearn.cluster import KMeans\nfrom sklearn.datasets import make_blobs\n\ndef unsupervised_learning_demo():\n    print("\u65e0\u76d1\u7763\u5b66\u4e60\u6f14\u793a:")\n    \n    X, _ = make_blobs(n_samples=300, centers=4, cluster_std=0.60, random_state=0)\n    \n    kmeans = KMeans(n_clusters=4)\n    kmeans.fit(X)\n    \n    labels = kmeans.labels_\n    centers = kmeans.cluster_centers_\n    \n    print(f"\u805a\u7c7b\u6807\u7b7e: {np.unique(labels)}")\n    print(f"\u805a\u7c7b\u4e2d\u5fc3\u5f62\u72b6: {centers.shape}")\n\nunsupervised_learning_demo()<\/code><\/pre>\n
\u5206\u7c7b\u7b97\u6cd5<\/h3>\n
\u5206\u7c7b\u7b97\u6cd5\u5c06\u6570\u636e\u5206\u914d\u5230\u9884\u5b9a\u4e49\u7684\u7c7b\u522b\u4e2d\u3002<\/p>\n
from sklearn.datasets import load_iris\nfrom sklearn.ensemble import RandomForestClassifier\nfrom sklearn.metrics import accuracy_score, classification_report\n\ndef classification_demo():\n    print("\u5206\u7c7b\u7b97\u6cd5\u6f14\u793a:")\n    \n    iris = load_iris()\n    X, y = iris.data, iris.target\n    \n    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)\n    \n    model = RandomForestClassifier(n_estimators=100)\n    model.fit(X_train, y_train)\n    \n    y_pred = model.predict(X_test)\n    \n    print(f"\u51c6\u786e\u7387: {accuracy_score(y_test, y_pred):.4f}")\n    print("\u5206\u7c7b\u62a5\u544a:")\n    print(classification_report(y_test, y_pred, target_names=iris.target_names))\n\nclassification_demo()<\/code><\/pre>\n
\u56de\u5f52\u7b97\u6cd5<\/h3>\n
\u56de\u5f52\u7b97\u6cd5\u9884\u6d4b\u8fde\u7eed\u503c\u3002<\/p>\n
from sklearn.datasets import load_boston\nfrom sklearn.ensemble import GradientBoostingRegressor\n\ndef regression_demo():\n    print("\u56de\u5f52\u7b97\u6cd5\u6f14\u793a:")\n    \n    boston = load_boston()\n    X, y = boston.data, boston.target\n    \n    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)\n    \n    model = GradientBoostingRegressor(n_estimators=100)\n    model.fit(X_train, y_train)\n    \n    y_pred = model.predict(X_test)\n    \n    print(f"\u5747\u65b9\u8bef\u5dee: {mean_squared_error(y_test, y_pred):.4f}")\n    print(f"R2 \u5206\u6570: {r2_score(y_test, y_pred):.4f}")\n\nregression_demo()<\/code><\/pre>\n
\u673a\u5668\u5b66\u4e60\u6d41\u7a0b<\/h3>\n
graph TD\n    A[\u6570\u636e\u6536\u96c6] --> B[\u6570\u636e\u9884\u5904\u7406]\n    B --> C[\u7279\u5f81\u5de5\u7a0b]\n    C --> D[\u6a21\u578b\u8bad\u7ec3]\n    D --> E[\u6a21\u578b\u8bc4\u4f30]\n    E --> F[\u6a21\u578b\u4f18\u5316]\n    F --> G[\u6a21\u578b\u90e8\u7f72]<\/code><\/pre>\n
\u7279\u5f81\u5de5\u7a0b<\/h3>\n
\u7279\u5f81\u5de5\u7a0b\u63d0\u53d6\u548c\u8f6c\u6362\u6570\u636e\u7279\u5f81\u3002<\/p>\n
from sklearn.preprocessing import StandardScaler, LabelEncoder\nfrom sklearn.feature_selection import SelectKBest, f_classif\n\ndef feature_engineering_demo():\n    print("\u7279\u5f81\u5de5\u7a0b\u6f14\u793a:")\n    \n    print("1. \u7279\u5f81\u7f29\u653e")\n    scaler = StandardScaler()\n    X_scaled = scaler.fit_transform(X)\n    \n    print("2. \u6807\u7b7e\u7f16\u7801")\n    encoder = LabelEncoder()\n    y_encoded = encoder.fit_transform(y)\n    \n    print("3. \u7279\u5f81\u9009\u62e9")\n    selector = SelectKBest(f_classif, k=10)\n    X_selected = selector.fit_transform(X, y_encoded)\n\nfeature_engineering_demo()<\/code><\/pre>\n
\u6a21\u578b\u8bc4\u4f30<\/h3>\n
\u6a21\u578b\u8bc4\u4f30\u4f7f\u7528\u5404\u79cd\u6307\u6807\u8861\u91cf\u6a21\u578b\u6027\u80fd\u3002<\/p>\n
from sklearn.metrics import confusion_matrix, roc_auc_score, roc_curve\n\ndef model_evaluation_demo():\n    print("\u6a21\u578b\u8bc4\u4f30\u6f14\u793a:")\n    \n    print("1. \u6df7\u6dc6\u77e9\u9635")\n    cm = confusion_matrix(y_test, y_pred)\n    print(f"\u6df7\u6dc6\u77e9\u9635:\/n{cm}")\n    \n    print("2. ROC AUC")\n    y_prob = model.predict_proba(X_test)[:, 1]\n    auc = roc_auc_score(y_test, y_prob)\n    print(f"ROC AUC: {auc:.4f}")\n\nmodel_evaluation_demo()<\/code><\/pre>\n
\u8d85\u53c2\u6570\u8c03\u4f18<\/h3>\n
\u8d85\u53c2\u6570\u8c03\u4f18\u4f18\u5316\u6a21\u578b\u6027\u80fd\u3002<\/p>\n
from sklearn.model_selection import GridSearchCV\n\ndef hyperparameter_tuning_demo():\n    print("\u8d85\u53c2\u6570\u8c03\u4f18\u6f14\u793a:")\n    \n    param_grid = {\n        'n_estimators': [50, 100, 200],\n        'max_depth': [None, 10, 20],\n        'min_samples_split': [2, 5, 10]\n    }\n    \n    grid_search = GridSearchCV(\n        RandomForestClassifier(),\n        param_grid,\n        cv=5,\n        scoring='accuracy'\n    )\n    \n    grid_search.fit(X_train, y_train)\n    \n    print(f"\u6700\u4f73\u53c2\u6570: {grid_search.best_params_}")\n    print(f"\u6700\u4f73\u5206\u6570: {grid_search.best_score_:.4f}")\n\nhyperparameter_tuning_demo()<\/code><\/pre>\n
\u4ea4\u53c9\u9a8c\u8bc1<\/h3>\n
\u4ea4\u53c9\u9a8c\u8bc1\u8bc4\u4f30\u6a21\u578b\u7684\u6cdb\u5316\u80fd\u529b\u3002<\/p>\n
from sklearn.model_selection import cross_val_score\n\ndef cross_validation_demo():\n    print("\u4ea4\u53c9\u9a8c\u8bc1\u6f14\u793a:")\n    \n    model = RandomForestClassifier(n_estimators=100)\n    \n    scores = cross_val_score(model, X, y, cv=5, scoring='accuracy')\n    \n    print(f"\u4ea4\u53c9\u9a8c\u8bc1\u5206\u6570: {scores}")\n    print(f"\u5e73\u5747\u5206\u6570: {scores.mean():.4f}")\n    print(f"\u6807\u51c6\u5dee: {scores.std():.4f}")\n\ncross_validation_demo()<\/code><\/pre>\n
\u6a21\u578b\u6301\u4e45\u5316<\/h3>\n
\u6a21\u578b\u6301\u4e45\u5316\u4fdd\u5b58\u8bad\u7ec3\u597d\u7684\u6a21\u578b\u3002<\/p>\n
import joblib\n\ndef model_persistence_demo():\n    print("\u6a21\u578b\u6301\u4e45\u5316\u6f14\u793a:")\n    \n    model = RandomForestClassifier(n_estimators=100)\n    model.fit(X_train, y_train)\n    \n    joblib.dump(model, 'model.joblib')\n    \n    loaded_model = joblib.load('model.joblib')\n    \n    y_pred = loaded_model.predict(X_test)\n    print(f"\u52a0\u8f7d\u6a21\u578b\u9884\u6d4b: {y_pred[:5]}")\n\nmodel_persistence_demo()<\/code><\/pre>\n
\u603b\u7ed3<\/h3>\n
Scikit-learn \u63d0\u4f9b\u4e86\u4e30\u5bcc\u7684\u673a\u5668\u5b66\u4e60\u7b97\u6cd5\u548c\u5de5\u5177\uff0c\u652f\u6301\u4ece\u6570\u636e\u9884\u5904\u7406\u5230\u6a21\u578b\u90e8\u7f72\u7684\u5b8c\u6574\u6d41\u7a0b\u3002\u638c\u63e1\u8fd9\u4e9b\u6838\u5fc3\u6280\u672f\uff0c\u5bf9\u4e8e\u6784\u5efa\u673a\u5668\u5b66\u4e60\u5e94\u7528\u81f3\u5173\u91cd\u8981\u3002<\/p>\n
\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0c\u9700\u8981\u6839\u636e\u6570\u636e\u7279\u70b9\u9009\u62e9\u5408\u9002\u7684\u7b97\u6cd5\uff0c\u5e73\u8861\u6a21\u578b\u590d\u6742\u5ea6\u548c\u6027\u80fd\u3002\u826f\u597d\u7684\u673a\u5668\u5b66\u4e60\u5b9e\u8df5\u80fd\u591f\u663e\u8457\u63d0\u9ad8\u6a21\u578b\u7684\u51c6\u786e\u6027\u548c\u53ef\u9760\u6027\u3002<\/p>\n
https:\/\/segmentfault.com\/a\/1190000047614884<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"
Python \u673a\u5668\u5b66\u4e60\uff1aScikit-learn \u6838\u5fc3\u7b97\u6cd5\u5b9e\u6218 \u673a\u5668\u5b66\u4e60\u662f\u4eba\u5de5\u667a\u80fd\u7684\u91cd\u8981\u5206\u652f\uff0cScikit-l […]<\/p>\n","protected":false},"author":4,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[4],"tags":[],"class_list":["post-10021261","post","type-post","status-publish","format-standard","hentry","category-share"],"jetpack_sharing_enabled":true,"jetpack_featured_media_url":"","_links":{"self":[{"href":"https:\/\/itmax.cn\/index.php?rest_route=\/wp\/v2\/posts\/10021261","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/itmax.cn\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/itmax.cn\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/itmax.cn\/index.php?rest_route=\/wp\/v2\/users\/4"}],"replies":[{"embeddable":true,"href":"https:\/\/itmax.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=10021261"}],"version-history":[{"count":0,"href":"https:\/\/itmax.cn\/index.php?rest_route=\/wp\/v2\/posts\/10021261\/revisions"}],"wp:attachment":[{"href":"https:\/\/itmax.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=10021261"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/itmax.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=10021261"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/itmax.cn\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=10021261"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}