{"id":908,"date":"2025-01-12T10:08:01","date_gmt":"2025-01-12T02:08:01","guid":{"rendered":"https:\/\/www.laixuexila.com\/?p=908"},"modified":"2025-01-12T10:08:01","modified_gmt":"2025-01-12T02:08:01","slug":"python%e4%b8%ad%e7%9a%84scikit-learn%e5%ba%93%e4%bb%8b%e7%bb%8d%ef%bc%9a%e6%9c%ba%e5%99%a8%e5%ad%a6%e4%b9%a0%e5%bf%85%e5%a4%87%e5%b7%a5%e5%85%b7","status":"publish","type":"post","link":"https:\/\/www.laixuexila.com\/index.php\/2025\/01\/12\/python%e4%b8%ad%e7%9a%84scikit-learn%e5%ba%93%e4%bb%8b%e7%bb%8d%ef%bc%9a%e6%9c%ba%e5%99%a8%e5%ad%a6%e4%b9%a0%e5%bf%85%e5%a4%87%e5%b7%a5%e5%85%b7\/","title":{"rendered":"Python\u4e2d\u7684Scikit-learn\u5e93\u4ecb\u7ecd\uff1a\u673a\u5668\u5b66\u4e60\u5fc5\u5907\u5de5\u5177"},"content":{"rendered":"\n
\n

Scikit-learn<\/strong> \u662f\u4e00\u4e2a\u7528\u4e8e\u6570\u636e\u5206\u6790\u548c\u673a\u5668\u5b66\u4e60\u7684\u5f00\u6e90 Python \u5e93\uff0c\u5b83\u63d0\u4f9b\u4e86\u8bb8\u591a\u5f3a\u5927\u800c\u6613\u4e8e\u4f7f\u7528\u7684\u5de5\u5177\uff0c\u652f\u6301\u5404\u7c7b\u673a\u5668\u5b66\u4e60\u4efb\u52a1\uff0c\u5982\u5206\u7c7b\u3001\u56de\u5f52\u3001\u805a\u7c7b\u3001\u964d\u7ef4\u7b49\u3002\u5b83\u975e\u5e38\u9002\u5408\u521d\u5b66\u8005\u4ee5\u53ca\u4e13\u4e1a\u4eba\u5458\uff0c\u56e0\u5176\u7b80\u6d01\u7684API\u3001\u4e30\u5bcc\u7684\u529f\u80fd\u548c\u5e7f\u6cdb\u7684\u6587\u6863\u652f\u6301\uff0c\u4f7f\u5176\u6210\u4e3a\u673a\u5668\u5b66\u4e60\u4e2d\u7684\u5fc5\u5907\u5de5\u5177\u3002<\/p>\n<\/blockquote>\n\n\n\n

\u4e00\u3001Scikit-learn\u6982\u8ff0<\/h3>\n\n\n\n

Scikit-learn \u7684\u8bbe\u8ba1\u76ee\u6807\u662f\u4f7f\u673a\u5668\u5b66\u4e60\u7b97\u6cd5\u7684\u5b9e\u73b0\u5c3d\u53ef\u80fd\u7b80\u5355\uff0c\u56e0\u6b64\u63d0\u4f9b\u4e86\u5f88\u591a\u9ad8\u6548\u7684\u5de5\u5177\uff0c\u9002\u7528\u4e8e\u4ece\u6570\u636e\u9884\u5904\u7406\u5230\u6a21\u578b\u8bc4\u4f30\u7684\u6574\u4e2a\u673a\u5668\u5b66\u4e60\u6d41\u7a0b\u3002\u5b83\u4f9d\u8d56\u4e8e\u5176\u4ed6\u4e00\u4e9b\u91cd\u8981\u7684\u79d1\u5b66\u8ba1\u7b97\u5e93\uff0c\u5982 NumPy<\/strong>\u3001SciPy<\/strong> \u548c matplotlib<\/strong>\uff0c\u8fd9\u4e9b\u5e93\u5171\u540c\u63d0\u4f9b\u4e86\u9ad8\u6548\u7684\u6570\u636e\u5904\u7406\u548c\u5206\u6790\u80fd\u529b\u3002<\/p>\n\n\n\n

\u6838\u5fc3\u529f\u80fd\uff1a<\/h4>\n\n\n\n
    \n
  • \u5206\u7c7b\uff08Classification\uff09<\/strong>\uff1a\u6839\u636e\u8f93\u5165\u6570\u636e\u9884\u6d4b\u7c7b\u522b\u6807\u7b7e\uff08\u5982\u5783\u573e\u90ae\u4ef6\u5206\u7c7b\u3001\u56fe\u7247\u8bc6\u522b\u7b49\uff09\u3002<\/li>\n\n\n\n
  • \u56de\u5f52\uff08Regression\uff09<\/strong>\uff1a\u6839\u636e\u8f93\u5165\u6570\u636e\u9884\u6d4b\u6570\u503c\u8f93\u51fa\uff08\u5982\u623f\u4ef7\u9884\u6d4b\u3001\u80a1\u7968\u4ef7\u683c\u9884\u6d4b\u7b49\uff09\u3002<\/li>\n\n\n\n
  • \u805a\u7c7b\uff08Clustering\uff09<\/strong>\uff1a\u5c06\u6570\u636e\u5206\u7ec4\uff0c\u6bcf\u4e00\u7ec4\u4e2d\u7684\u6570\u636e\u5177\u6709\u76f8\u4f3c\u6027\uff08\u5982\u5ba2\u6237\u7fa4\u4f53\u5206\u6790\uff09\u3002<\/li>\n\n\n\n
  • \u964d\u7ef4\uff08Dimensionality Reduction\uff09<\/strong>\uff1a\u51cf\u5c11\u6570\u636e\u7684\u7279\u5f81\u7ef4\u5ea6\uff0c\u4ee5\u4fbf\u66f4\u597d\u5730\u8fdb\u884c\u53ef\u89c6\u5316\u6216\u63d0\u9ad8\u8ba1\u7b97\u6548\u7387\uff08\u5982PCA\u3001t-SNE\uff09\u3002<\/li>\n\n\n\n
  • \u6a21\u578b\u9009\u62e9\uff08Model Selection\uff09<\/strong>\uff1a\u5982\u4ea4\u53c9\u9a8c\u8bc1\u3001\u7f51\u683c\u641c\u7d22\u7b49\uff0c\u7528\u4e8e\u8bc4\u4f30\u548c\u9009\u62e9\u6700\u4f73\u6a21\u578b\u3002<\/li>\n\n\n\n
  • \u6570\u636e\u9884\u5904\u7406\uff08Preprocessing\uff09<\/strong>\uff1a\u6570\u636e\u7684\u6807\u51c6\u5316\u3001\u5f52\u4e00\u5316\u3001\u7f3a\u5931\u503c\u5904\u7406\u3001\u7279\u5f81\u63d0\u53d6\u7b49\u3002<\/li>\n<\/ul>\n\n\n\n

    \u4e8c\u3001Scikit-learn\u7684\u5b89\u88c5<\/h3>\n\n\n\n

    \u8981\u4f7f\u7528 Scikit-learn\uff0c\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u547d\u4ee4\u8fdb\u884c\u5b89\u88c5\uff1a<\/p>\n\n\n\n

    pip install scikit-learn<\/code><\/pre>\n\n\n\n
    \u4e09\u3001Scikit-learn\u7684\u4e3b\u8981\u6a21\u5757<\/h3>\n\n\n\n
    Scikit-learn \u4e2d\u7684\u6838\u5fc3\u6a21\u5757\u4e3b\u8981\u5305\u542b\u4ee5\u4e0b\u51e0\u4e2a\u90e8\u5206\uff1a<\/p>\n\n\n\n
    1. \u6570\u636e\u9884\u5904\u7406\uff08Preprocessing\uff09<\/strong><\/h4>\n\n\n\n
    Scikit-learn \u63d0\u4f9b\u4e86\u5f88\u591a\u5e38\u7528\u7684\u6570\u636e\u9884\u5904\u7406\u5de5\u5177\uff0c\u5982\u6807\u51c6\u5316\u3001\u5f52\u4e00\u5316\u3001\u7f3a\u5931\u503c\u586b\u5145\u7b49\u3002<\/p>\n\n\n\n
      \n
    • \u6807\u51c6\u5316<\/strong>\uff1a\u5c06\u6570\u636e\u8f6c\u6362\u4e3a\u5747\u503c\u4e3a0\uff0c\u65b9\u5dee\u4e3a1\u7684\u5206\u5e03\u3002<\/li>\n<\/ul>\n\n\n\n
        from sklearn.preprocessing import StandardScaler\n  scaler = StandardScaler()\n  X_scaled = scaler.fit_transform(X)  # X\u4e3a\u6570\u636e\u96c6<\/code><\/pre>\n\n\n\n
        \n
      • \u5f52\u4e00\u5316<\/strong>\uff1a\u5c06\u6570\u636e\u6309\u6bd4\u4f8b\u7f29\u653e\u5230\u6307\u5b9a\u8303\u56f4\uff08\u901a\u5e38\u662f [0, 1]\uff09\u3002<\/li>\n<\/ul>\n\n\n\n
          from sklearn.preprocessing import MinMaxScaler\n  scaler = MinMaxScaler()\n  X_scaled = scaler.fit_transform(X)<\/code><\/pre>\n\n\n\n
          \n
        • \u7f3a\u5931\u503c\u586b\u5145<\/strong>\uff1a\u4f7f\u7528\u5747\u503c\u3001\u4e2d\u4f4d\u6570\u6216\u6700\u5e38\u89c1\u7684\u503c\u586b\u5145\u7f3a\u5931\u7684\u6570\u636e\u3002<\/li>\n<\/ul>\n\n\n\n
            from sklearn.impute import SimpleImputer\n  imputer = SimpleImputer(strategy='mean')\n  X_imputed = imputer.fit_transform(X)<\/code><\/pre>\n\n\n\n
          2. \u76d1\u7763\u5b66\u4e60\uff08Supervised Learning\uff09<\/strong><\/h4>\n\n\n\n
          Scikit-learn \u63d0\u4f9b\u4e86\u591a\u79cd\u76d1\u7763\u5b66\u4e60\u6a21\u578b\uff0c\u5305\u62ec\u56de\u5f52\u548c\u5206\u7c7b\u4efb\u52a1\u7684\u7b97\u6cd5\u3002<\/p>\n\n\n\n
            \n
          • \u5206\u7c7b\u7b97\u6cd5<\/strong>\uff1a\u5982\u51b3\u7b56\u6811\u3001\u652f\u6301\u5411\u91cf\u673a\uff08SVM\uff09\u3001k-\u8fd1\u90bb\uff08KNN\uff09\u3001\u968f\u673a\u68ee\u6797\u3001\u903b\u8f91\u56de\u5f52\u7b49\u3002<\/li>\n\n\n\n
          • \u903b\u8f91\u56de\u5f52<\/strong>\uff08Logistic Regression\uff09\uff1a from sklearn.linear_model import LogisticRegression model = LogisticRegression() model.fit(X_train, y_train)<\/code><\/li>\n\n\n\n
          • \u652f\u6301\u5411\u91cf\u673a<\/strong>\uff08SVM\uff09\uff1a from sklearn.svm import SVC model = SVC(kernel='linear') # \u4f7f\u7528\u7ebf\u6027\u6838 model.fit(X_train, y_train)<\/code><\/li>\n\n\n\n
          • \u51b3\u7b56\u6811<\/strong>\uff08Decision Tree\uff09\uff1a from sklearn.tree import DecisionTreeClassifier model = DecisionTreeClassifier() model.fit(X_train, y_train)<\/code><\/li>\n\n\n\n
          • \u56de\u5f52\u7b97\u6cd5<\/strong>\uff1a\u5982\u7ebf\u6027\u56de\u5f52\u3001\u5cad\u56de\u5f52\u3001\u652f\u6301\u5411\u91cf\u56de\u5f52\u7b49\u3002<\/li>\n\n\n\n
          • \u7ebf\u6027\u56de\u5f52<\/strong>\uff08Linear Regression\uff09\uff1a from sklearn.linear_model import LinearRegression model = LinearRegression() model.fit(X_train, y_train)<\/code><\/li>\n\n\n\n
          • \u652f\u6301\u5411\u91cf\u56de\u5f52<\/strong>\uff08SVR\uff09\uff1a from sklearn.svm import SVR model = SVR(kernel='linear') model.fit(X_train, y_train)<\/code><\/li>\n<\/ul>\n\n\n\n
            3. \u65e0\u76d1\u7763\u5b66\u4e60\uff08Unsupervised Learning\uff09<\/strong><\/h4>\n\n\n\n
            Scikit-learn \u4e5f\u652f\u6301\u65e0\u76d1\u7763\u5b66\u4e60\u4efb\u52a1\uff0c\u5982\u805a\u7c7b\u3001\u964d\u7ef4\u7b49\u3002<\/p>\n\n\n\n
              \n
            • K-\u5747\u503c\u805a\u7c7b<\/strong>\uff08K-means Clustering\uff09\uff1a<\/li>\n<\/ul>\n\n\n\n
                from sklearn.cluster import KMeans\n  model = KMeans(n_clusters=3)  # \u805a\u7c7b\u6570\u4e3a3\n  model.fit(X)<\/code><\/pre>\n\n\n\n
                \n
              • \u4e3b\u6210\u5206\u5206\u6790<\/strong>\uff08PCA\uff0cPrincipal Component Analysis\uff09\u7528\u4e8e\u964d\u7ef4\uff1a<\/li>\n<\/ul>\n\n\n\n
                  from sklearn.decomposition import PCA\n  pca = PCA(n_components=2)  # \u5c06\u6570\u636e\u964d\u52302\u7ef4\n  X_pca = pca.fit_transform(X)<\/code><\/pre>\n\n\n\n
                4. \u6a21\u578b\u9009\u62e9\u4e0e\u8bc4\u4f30\uff08Model Selection and Evaluation\uff09<\/strong><\/h4>\n\n\n\n
                Scikit-learn \u63d0\u4f9b\u4e86\u591a\u79cd\u6a21\u578b\u8bc4\u4f30\u65b9\u6cd5\uff0c\u5982\u4ea4\u53c9\u9a8c\u8bc1\u3001\u51c6\u786e\u7387\u3001\u6df7\u6dc6\u77e9\u9635\u7b49\u3002<\/p>\n\n\n\n
                  \n
                • \u4ea4\u53c9\u9a8c\u8bc1<\/strong>\uff08Cross Validation\uff09\uff1a\u7528\u4e8e\u8bc4\u4f30\u6a21\u578b\u7684\u6cdb\u5316\u80fd\u529b\u3002<\/li>\n<\/ul>\n\n\n\n
                    from sklearn.model_selection import cross_val_score\n  scores = cross_val_score(model, X, y, cv=5)  # 5\u6298\u4ea4\u53c9\u9a8c\u8bc1\n  print(scores)<\/code><\/pre>\n\n\n\n
                    \n
                  • \u6df7\u6dc6\u77e9\u9635<\/strong>\uff08Confusion Matrix\uff09\uff1a\u7528\u4e8e\u5206\u7c7b\u6a21\u578b\u8bc4\u4f30\uff0c\u663e\u793a\u9884\u6d4b\u4e0e\u771f\u5b9e\u6807\u7b7e\u7684\u5339\u914d\u60c5\u51b5\u3002<\/li>\n<\/ul>\n\n\n\n
                      from sklearn.metrics import confusion_matrix\n  cm = confusion_matrix(y_true, y_pred)\n  print(cm)<\/code><\/pre>\n\n\n\n
                      \n
                    • \u51c6\u786e\u7387\u3001\u7cbe\u786e\u7387\u3001\u53ec\u56de\u7387\u3001F1\u503c<\/strong>\uff1a<\/li>\n<\/ul>\n\n\n\n
                        from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score\n  print(accuracy_score(y_true, y_pred))\n  print(precision_score(y_true, y_pred))\n  print(recall_score(y_true, y_pred))\n  print(f1_score(y_true, y_pred))<\/code><\/pre>\n\n\n\n
                      5. \u7279\u5f81\u9009\u62e9\u4e0e\u6a21\u578b\u8c03\u4f18<\/strong><\/h4>\n\n\n\n
                        \n
                      • \u7279\u5f81\u9009\u62e9<\/strong>\uff1a\u5e2e\u52a9\u9009\u62e9\u5bf9\u6a21\u578b\u6709\u6700\u5927\u5f71\u54cd\u7684\u7279\u5f81\u3002<\/li>\n<\/ul>\n\n\n\n
                          from sklearn.feature_selection import SelectKBest, f_classif\n  selector = SelectKBest(score_func=f_classif, k=10)\n  X_new = selector.fit_transform(X, y)<\/code><\/pre>\n\n\n\n
                          \n
                        • \u7f51\u683c\u641c\u7d22\u8c03\u53c2<\/strong>\uff1a\u901a\u8fc7\u7f51\u683c\u641c\u7d22\u627e\u5230\u6700\u4f18\u7684\u8d85\u53c2\u6570\u7ec4\u5408\u3002<\/li>\n<\/ul>\n\n\n\n
                            from sklearn.model_selection import GridSearchCV\n  param_grid = {'C': [0.1, 1, 10], 'kernel': ['linear', 'rbf']}\n  grid_search = GridSearchCV(SVC(), param_grid, cv=5)\n  grid_search.fit(X_train, y_train)\n  print(grid_search.best_params_)<\/code><\/pre>\n\n\n\n
                          6. Pipeline\uff08\u7ba1\u9053\uff09<\/strong><\/h4>\n\n\n\n
                          Scikit-learn \u63d0\u4f9b\u4e86 Pipeline<\/code> \u7c7b\uff0c\u53ef\u4ee5\u5c06\u591a\u4e2a\u5904\u7406\u6b65\u9aa4\u548c\u6a21\u578b\u7ec4\u5408\u6210\u4e00\u4e2a\u53ef\u590d\u7528\u7684\u6d41\u7a0b\u3002\u8fd9\u6837\u505a\u53ef\u4ee5\u51cf\u5c11\u4ee3\u7801\u5197\u4f59\u5e76\u63d0\u5347\u53ef\u7ef4\u62a4\u6027\u3002<\/p>\n\n\n\n
                          from sklearn.pipeline import Pipeline\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.svm import SVC\n\npipeline = Pipeline([\n    ('scaler', StandardScaler()),\n    ('svm', SVC())\n])\n\npipeline.fit(X_train, y_train)<\/code><\/pre>\n\n\n\n
                          \u56db\u3001Scikit-learn\u7684\u5e94\u7528\u5b9e\u4f8b<\/h3>\n\n\n\n
                          1. \u5206\u7c7b\u4efb\u52a1\uff08\u9e22\u5c3e\u82b1\u6570\u636e\u96c6\uff09<\/strong><\/h4>\n\n\n\n
                          from sklearn.datasets import load_iris\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.svm import SVC\nfrom sklearn.metrics import accuracy_score\n\n# \u52a0\u8f7d\u6570\u636e\u96c6\ndata = load_iris()\nX = data.data\ny = data.target\n\n# \u5212\u5206\u6570\u636e\u96c6\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)\n\n# \u8bad\u7ec3\u6a21\u578b\nmodel = SVC(kernel='linear')\nmodel.fit(X_train, y_train)\n\n# \u9884\u6d4b\ny_pred = model.predict(X_test)\n\n# \u8bc4\u4f30\naccuracy = accuracy_score(y_test, y_pred)\nprint(f'Accuracy: {accuracy:.2f}')<\/code><\/pre>\n\n\n\n
                          2. \u56de\u5f52\u4efb\u52a1\uff08\u6ce2\u58eb\u987f\u623f\u4ef7\u6570\u636e\u96c6\uff09<\/strong><\/h4>\n\n\n\n
                          from sklearn.datasets import load_boston\nfrom sklearn.linear_model import LinearRegression\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import mean_squared_error\n\n# \u52a0\u8f7d\u6570\u636e\u96c6\ndata = load_boston()\nX = data.data\ny = data.target\n\n# \u5212\u5206\u6570\u636e\u96c6\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)\n\n# \u8bad\u7ec3\u6a21\u578b\nmodel = LinearRegression()\nmodel.fit(X_train, y_train)\n\n# \u9884\u6d4b\ny_pred = model.predict(X_test)\n\n# \u8bc4\u4f30\nmse = mean_squared_error(y_test\n\n, y_pred)\nprint(f'Mean Squared Error: {mse:.2f}')<\/code><\/pre>\n\n\n\n
                          \u4e94\u3001\u603b\u7ed3<\/h3>\n\n\n\n
                          Scikit-learn \u662f\u673a\u5668\u5b66\u4e60\u9886\u57df\u4e2d\u6700\u5e38\u7528\u7684\u5de5\u5177\u4e4b\u4e00\uff0c\u5177\u6709\u6613\u7528\u7684API\u548c\u4e30\u5bcc\u7684\u529f\u80fd\uff0c\u652f\u6301\u4ece\u6570\u636e\u9884\u5904\u7406\u3001\u6a21\u578b\u8bad\u7ec3\u3001\u8bc4\u4f30\u5230\u8d85\u53c2\u6570\u8c03\u4f18\u7684\u6574\u4e2a\u673a\u5668\u5b66\u4e60\u6d41\u7a0b\u3002\u5b83\u9002\u5408\u65b0\u624b\u548c\u4e13\u4e1a\u4eba\u58eb\uff0c\u5e2e\u52a9\u4f60\u5728\u673a\u5668\u5b66\u4e60\u4e2d\u53d6\u5f97\u66f4\u597d\u7684\u6210\u679c\u3002\u5982\u679c\u4f60\u6b63\u5728\u5b66\u4e60\u673a\u5668\u5b66\u4e60\u6216\u6570\u636e\u79d1\u5b66\uff0c\u638c\u63e1 Scikit-learn \u5c06\u662f\u4f60\u5fc5\u5907\u7684\u6280\u80fd\u4e4b\u4e00\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"
                          Scikit-learn \u662f\u4e00\u4e2a\u7528\u4e8e\u6570\u636e\u5206\u6790\u548c\u673a\u5668\u5b66\u4e60\u7684\u5f00\u6e90 Python \u5e93\uff0c\u5b83\u63d0\u4f9b\u4e86\u8bb8\u591a\u5f3a\u5927\u800c\u6613\u4e8e\u4f7f\u7528\u7684\u5de5 […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[54],"tags":[],"class_list":["post-908","post","type-post","status-publish","format-standard","hentry","category-python"],"_links":{"self":[{"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/posts\/908","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/comments?post=908"}],"version-history":[{"count":1,"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/posts\/908\/revisions"}],"predecessor-version":[{"id":909,"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/posts\/908\/revisions\/909"}],"wp:attachment":[{"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/media?parent=908"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/categories?post=908"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/tags?post=908"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}