\u793a\u4f8b\u6570\u636e<\/strong><\/h2>\nX = np.array([[1, 2], [3, 4], [5, 6], [7, 8], [9, 10]])<\/p>\n
y = np.array([1, 2, 3, 4, 5])<\/p>\n
model = LogisticRegression()<\/p>\n
scores = cross_val_score(model, X, y, cv=5)<\/p>\n
print("Cross-validation scores:", scores)<\/p>\n
<\/code><\/pre>\n<\/p>\n
2\u3001Keras\u4e2d\u7684\u4ea4\u53c9\u9a8c\u8bc1<\/h4>\n<\/p>\n
\u5bf9\u4e8e\u6df1\u5ea6\u5b66\u4e60\u6a21\u578b\uff0c\u53ef\u4ee5\u4f7f\u7528Keras\u548cScikit-learn\u7ed3\u5408\u8fdb\u884c\u4ea4\u53c9\u9a8c\u8bc1\u3002\u4e0b\u9762\u662f\u4e00\u4e2a\u4f7f\u7528K\u6298\u4ea4\u53c9\u9a8c\u8bc1\u8bc4\u4f30Keras\u6a21\u578b\u6027\u80fd\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n
from keras.models import Sequential<\/p>\nfrom keras.layers import Dense<\/p>\n
from keras.wrappers.scikit_learn import KerasClassifier<\/p>\n
from sklearn.model_selection import cross_val_score<\/p>\n
import numpy as np<\/p>\n
\u521b\u5efaKeras\u6a21\u578b\u7684\u51fd\u6570<\/strong><\/h2>\ndef create_model():<\/p>\n
model = Sequential()<\/p>\n
model.add(Dense(12, input_dim=8, activation='relu'))<\/p>\n
model.add(Dense(8, activation='relu'))<\/p>\n
model.add(Dense(1, activation='sigmoid'))<\/p>\n
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])<\/p>\n
return model<\/p>\n
\u793a\u4f8b\u6570\u636e<\/strong><\/h2>\nX = np.random.rand(100, 8)<\/p>\n
y = np.random.randint(2, size=100)<\/p>\n
model = KerasClassifier(build_fn=create_model, epochs=10, batch_size=10, verbose=0)<\/p>\n
scores = cross_val_score(model, X, y, cv=5)<\/p>\n
print("Cross-validation scores:", scores)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u516d\u3001\u4ea4\u53c9\u9a8c\u8bc1\u7684\u5e94\u7528\u573a\u666f<\/h3>\n<\/p>\n
1\u3001\u6a21\u578b\u9009\u62e9<\/h4>\n<\/p>\n
\u4ea4\u53c9\u9a8c\u8bc1\u53ef\u4ee5\u7528\u4e8e\u6a21\u578b\u9009\u62e9\uff0c\u901a\u8fc7\u8bc4\u4f30\u4e0d\u540c\u6a21\u578b\u7684\u6027\u80fd\uff0c\u9009\u62e9\u6700\u4f18\u6a21\u578b\u3002\u4f8b\u5982\uff0c\u53ef\u4ee5\u4f7f\u7528K\u6298\u4ea4\u53c9\u9a8c\u8bc1\u6bd4\u8f83\u51b3\u7b56\u6811\u3001\u968f\u673a\u68ee\u6797\u548c\u652f\u6301\u5411\u91cf\u673a\u7b49\u6a21\u578b\u7684\u6027\u80fd\uff0c\u4ece\u800c\u9009\u62e9\u6700\u9002\u5408\u4efb\u52a1\u7684\u6a21\u578b\u3002<\/p>\n<\/p>\n
from sklearn.model_selection import cross_val_score<\/p>\nfrom sklearn.tree import DecisionTreeClassifier<\/p>\n
from sklearn.ensemble import RandomForestClassifier<\/p>\n
from sklearn.svm import SVC<\/p>\n
\u793a\u4f8b\u6570\u636e<\/strong><\/h2>\nX = np.random.rand(100, 10)<\/p>\n
y = np.random.randint(2, size=100)<\/p>\n
models = {<\/p>\n
'Decision Tree': DecisionTreeClassifier(),<\/p>\n
'Random Forest': RandomForestClassifier(),<\/p>\n
'SVM': SVC()<\/p>\n
}<\/p>\n
for name, model in models.items():<\/p>\n
scores = cross_val_score(model, X, y, cv=5)<\/p>\n
print(f"{name} Cross-validation scores: {scores.mean()}")<\/p>\n
<\/code><\/pre>\n<\/p>\n
2\u3001\u8d85\u53c2\u6570\u8c03\u4f18<\/h4>\n<\/p>\n
\u4ea4\u53c9\u9a8c\u8bc1\u8fd8\u53ef\u4ee5\u7528\u4e8e\u6a21\u578b\u7684\u8d85\u53c2\u6570\u8c03\u4f18\uff0c\u901a\u8fc7\u4ea4\u53c9\u9a8c\u8bc1\u8bc4\u4f30\u4e0d\u540c\u8d85\u53c2\u6570\u7ec4\u5408\u7684\u6027\u80fd\uff0c\u4ece\u800c\u627e\u5230\u6700\u4f18\u8d85\u53c2\u6570\u3002\u4f8b\u5982\uff0c\u53ef\u4ee5\u4f7f\u7528\u7f51\u683c\u641c\u7d22\uff08Grid Search\uff09\u7ed3\u5408K\u6298\u4ea4\u53c9\u9a8c\u8bc1\u8fdb\u884c\u8d85\u53c2\u6570\u8c03\u4f18\u3002<\/p>\n<\/p>\n
from sklearn.model_selection import GridSearchCV<\/p>\nfrom sklearn.ensemble import RandomForestClassifier<\/p>\n
\u793a\u4f8b\u6570\u636e<\/strong><\/h2>\nX = np.random.rand(100, 10)<\/p>\n
y = np.random.randint(2, size=100)<\/p>\n
param_grid = {<\/p>\n
'n_estimators': [10, 50, 100],<\/p>\n
'max_depth': [None, 10, 20]<\/p>\n
}<\/p>\n
model = RandomForestClassifier()<\/p>\n
grid_search = GridSearchCV(model, param_grid, cv=5)<\/p>\n
grid_search.fit(X, y)<\/p>\n
print("Best parameters:", grid_search.best_params_)<\/p>\n
<\/code><\/pre>\n<\/p>\n
3\u3001\u6a21\u578b\u8bc4\u4f30<\/h4>\n<\/p>\n
\u4ea4\u53c9\u9a8c\u8bc1\u662f\u6a21\u578b\u8bc4\u4f30\u7684\u91cd\u8981\u5de5\u5177\uff0c\u901a\u8fc7\u4ea4\u53c9\u9a8c\u8bc1\u53ef\u4ee5\u5f97\u5230\u6a21\u578b\u5728\u4e0d\u540c\u6570\u636e\u96c6\u4e0a\u7684\u6027\u80fd\u8868\u73b0\uff0c\u4ece\u800c\u66f4\u51c6\u786e\u5730\u8bc4\u4f30\u6a21\u578b\u7684\u6cdb\u5316\u80fd\u529b\u3002\u4f8b\u5982\uff0c\u53ef\u4ee5\u4f7f\u7528K\u6298\u4ea4\u53c9\u9a8c\u8bc1\u8bc4\u4f30\u6a21\u578b\u7684\u51c6\u786e\u7387\u3001\u7cbe\u786e\u7387\u3001\u53ec\u56de\u7387\u7b49\u6307\u6807\u3002<\/p>\n<\/p>\n
from sklearn.model_selection import cross_val_score<\/p>\nfrom sklearn.metrics import accuracy_score, precision_score, recall_score<\/p>\n
from sklearn.linear_model import LogisticRegression<\/p>\n
\u793a\u4f8b\u6570\u636e<\/strong><\/h2>\nX = np.random.rand(100, 10)<\/p>\n
y = np.random.randint(2, size=100)<\/p>\n
model = LogisticRegression()<\/p>\n
scores = cross_val_score(model, X, y, cv=5, scoring='accuracy')<\/p>\n
print("Cross-validation accuracy scores:", scores)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e03\u3001\u6ce8\u610f\u4e8b\u9879<\/h3>\n<\/p>\n
1\u3001\u6570\u636e\u6cc4\u6f0f<\/h4>\n<\/p>\n
\u5728\u8fdb\u884c\u4ea4\u53c9\u9a8c\u8bc1\u65f6\uff0c\u9700\u8981\u6ce8\u610f\u907f\u514d\u6570\u636e\u6cc4\u6f0f\uff08Data Leakage\uff09\u3002\u6570\u636e\u6cc4\u6f0f\u6307\u7684\u662f\u8bad\u7ec3\u96c6\u4e2d\u7684\u4fe1\u606f\u6cc4\u9732\u5230\u9a8c\u8bc1\u96c6\u4e2d\uff0c\u4ece\u800c\u5bfc\u81f4\u6a21\u578b\u8bc4\u4f30\u7ed3\u679c\u8fc7\u4e8e\u4e50\u89c2\u3002\u4e3a\u4e86\u907f\u514d\u6570\u636e\u6cc4\u6f0f\uff0c\u9700\u8981\u5728\u5212\u5206\u6570\u636e\u96c6\u4e4b\u524d\u8fdb\u884c\u6570\u636e\u9884\u5904\u7406\uff0c\u4f8b\u5982\u6807\u51c6\u5316\u3001\u5f52\u4e00\u5316\u7b49\u3002<\/p>\n<\/p>\n
2\u3001\u8ba1\u7b97\u5f00\u9500<\/h4>\n<\/p>\n
\u4ea4\u53c9\u9a8c\u8bc1\u7684\u8ba1\u7b97\u5f00\u9500\u8f83\u5927\uff0c\u5c24\u5176\u662f\u5728\u5927\u6570\u636e\u96c6\u548c\u590d\u6742\u6a21\u578b\u4e2d\u3002\u4e3a\u4e86\u51cf\u5c11\u8ba1\u7b97\u5f00\u9500\uff0c\u53ef\u4ee5\u9009\u62e9\u8f83\u5c0f\u7684K\u503c\uff0c\u6216\u8005\u4f7f\u7528\u5e76\u884c\u8ba1\u7b97\u52a0\u901f\u4ea4\u53c9\u9a8c\u8bc1\u8fc7\u7a0b\u3002\u4f8b\u5982\uff0c\u5728Scikit-learn\u4e2d\u53ef\u4ee5\u901a\u8fc7\u8bbe\u7f6en_jobs<\/code>\u53c2\u6570\u542f\u7528\u5e76\u884c\u8ba1\u7b97\u3002<\/p>\n<\/p>\nfrom sklearn.model_selection import cross_val_score<\/p>\nfrom sklearn.linear_model import LogisticRegression<\/p>\n
\u793a\u4f8b\u6570\u636e<\/strong><\/h2>\nX = np.random.rand(100, 10)<\/p>\n
y = np.random.randint(2, size=100)<\/p>\n
model = LogisticRegression()<\/p>\n
scores = cross_val_score(model, X, y, cv=5, n_jobs=-1)<\/p>\n
print("Cross-validation scores:", scores)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u516b\u3001\u603b\u7ed3<\/h3>\n<\/p>\n
\u5728Python\u4e2d\u9009\u62e9\u5408\u9002\u7684\u4ea4\u53c9\u9a8c\u8bc1\u65b9\u6cd5\u662f\u63d0\u5347\u6a21\u578b\u6027\u80fd\u548c\u6cdb\u5316\u80fd\u529b\u7684\u91cd\u8981\u6b65\u9aa4\u3002\u901a\u8fc7\u9009\u62e9\u5408\u9002\u7684\u4ea4\u53c9\u9a8c\u8bc1\u65b9\u6cd5\u3001\u5747\u8861\u6570\u636e\u5206\u5e03\u3001\u5408\u7406\u8bbe\u7f6e\u4ea4\u53c9\u9a8c\u8bc1\u7684\u6298\u6570\u4ee5\u53ca\u8003\u8651\u6a21\u578b\u7684\u590d\u6742\u5ea6\uff0c\u53ef\u4ee5\u66f4\u51c6\u786e\u5730\u8bc4\u4f30\u6a21\u578b\u7684\u6027\u80fd\uff0c\u4ece\u800c\u4f18\u5316\u6a21\u578b\u7684\u8868\u73b0\u3002\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0c\u53ef\u4ee5\u7ed3\u5408Scikit-learn\u3001Keras\u7b49\u5de5\u5177\u8fdb\u884c\u4ea4\u53c9\u9a8c\u8bc1\uff0c\u5e94\u7528\u4e8e\u6a21\u578b\u9009\u62e9\u3001\u8d85\u53c2\u6570\u8c03\u4f18\u548c\u6a21\u578b\u8bc4\u4f30\u7b49\u573a\u666f\u3002\u9700\u8981\u6ce8\u610f\u907f\u514d\u6570\u636e\u6cc4\u6f0f\u548c\u8ba1\u7b97\u5f00\u9500\u8fc7\u5927\u7684\u95ee\u9898\uff0c\u4ece\u800c\u786e\u4fdd\u4ea4\u53c9\u9a8c\u8bc1\u7684\u6709\u6548\u6027\u548c\u9ad8\u6548\u6027\u3002<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n \u5728\u8fdb\u884c\u4ea4\u53c9\u9a8c\u8bc1\u65f6\uff0c\u5982\u4f55\u9009\u62e9\u5408\u9002\u7684\u9a8c\u8bc1\u7b56\u7565\uff1f<\/strong>
\u9009\u62e9\u4ea4\u53c9\u9a8c\u8bc1\u7b56\u7565\u65f6\uff0c\u9700\u8003\u8651\u6570\u636e\u96c6\u7684\u7279\u6027\u548c\u6a21\u578b\u7684\u9700\u6c42\u3002\u5e38\u89c1\u7684\u7b56\u7565\u6709K\u6298\u4ea4\u53c9\u9a8c\u8bc1\u3001\u7559\u4e00\u4ea4\u53c9\u9a8c\u8bc1\u548c\u5206\u5c42K\u6298\u4ea4\u53c9\u9a8c\u8bc1\u3002K\u6298\u4ea4\u53c9\u9a8c\u8bc1\u9002\u5408\u5927\u591a\u6570\u573a\u666f\uff0c\u7559\u4e00\u4ea4\u53c9\u9a8c\u8bc1\u9002\u5408\u6570\u636e\u91cf\u8f83\u5c0f\u7684\u60c5\u51b5\uff0c\u800c\u5206\u5c42K\u6298\u4ea4\u53c9\u9a8c\u8bc1\u5219\u9002\u7528\u4e8e\u5206\u7c7b\u95ee\u9898\uff0c\u786e\u4fdd\u6bcf\u4e2a\u6298\u4e2d\u7c7b\u7684\u5206\u5e03\u4e0e\u6574\u4f53\u6570\u636e\u4e00\u81f4\u3002\u6839\u636e\u6570\u636e\u7684\u89c4\u6a21\u548c\u7c7b\u522b\u5206\u5e03\u9009\u62e9\u5408\u9002\u7684\u7b56\u7565\uff0c\u53ef\u4ee5\u63d0\u9ad8\u6a21\u578b\u7684\u6cdb\u5316\u80fd\u529b\u3002<\/p>\n\u5982\u4f55\u5728Python\u4e2d\u5b9e\u73b0\u4ea4\u53c9\u9a8c\u8bc1\uff1f<\/strong>
\u5728Python\u4e2d\uff0c\u53ef\u4ee5\u4f7f\u7528scikit-learn<\/code>\u5e93\u4e2d\u7684cross_val_score<\/code>\u51fd\u6570\u6765\u5b9e\u73b0\u4ea4\u53c9\u9a8c\u8bc1\u3002\u9996\u5148\u9700\u8981\u51c6\u5907\u597d\u6570\u636e\u96c6\u548c\u6a21\u578b\uff0c\u7136\u540e\u8c03\u7528\u8be5\u51fd\u6570\uff0c\u5e76\u6307\u5b9a\u4ea4\u53c9\u9a8c\u8bc1\u7684\u6298\u6570\u548c\u8bc4\u5206\u6307\u6807\u3002\u4f8b\u5982\uff0c\u4f7f\u7528cross_val_score(model, X, y, cv=5)<\/code>\u53ef\u4ee5\u5c06\u6570\u636e\u96c6\u5206\u4e3a5\u4e2a\u6298\u8fdb\u884c\u4ea4\u53c9\u9a8c\u8bc1\uff0c\u8fd4\u56de\u6bcf\u4e2a\u6298\u7684\u8bc4\u5206\u7ed3\u679c\u3002\u901a\u8fc7\u8c03\u6574\u53c2\u6570\uff0c\u8fd8\u53ef\u4ee5\u5b9e\u73b0\u66f4\u590d\u6742\u7684\u4ea4\u53c9\u9a8c\u8bc1\u7b56\u7565\u3002<\/p>\n\u4ea4\u53c9\u9a8c\u8bc1\u7684\u7ed3\u679c\u5982\u4f55\u89e3\u8bfb\u548c\u5e94\u7528\u4e8e\u6a21\u578b\u4f18\u5316\uff1f<\/strong>
\u4ea4\u53c9\u9a8c\u8bc1\u7684\u7ed3\u679c\u901a\u5e38\u4ee5\u5e73\u5747\u8bc4\u5206\u548c\u6807\u51c6\u5dee\u7684\u5f62\u5f0f\u5448\u73b0\u3002\u5e73\u5747\u8bc4\u5206\u53cd\u6620\u4e86\u6a21\u578b\u5728\u4e0d\u540c\u6570\u636e\u6298\u4e0a\u7684\u8868\u73b0\uff0c\u800c\u6807\u51c6\u5dee\u5219\u8868\u793a\u6a21\u578b\u6027\u80fd\u7684\u7a33\u5b9a\u6027\u3002\u9ad8\u5e73\u5747\u8bc4\u5206\u548c\u4f4e\u6807\u51c6\u5dee\u8868\u660e\u6a21\u578b\u5177\u6709\u826f\u597d\u7684\u6cdb\u5316\u80fd\u529b\u3002\u6839\u636e\u4ea4\u53c9\u9a8c\u8bc1\u7684\u7ed3\u679c\uff0c\u53ef\u4ee5\u8fdb\u884c\u6a21\u578b\u7684\u53c2\u6570\u8c03\u6574\u548c\u9009\u62e9\uff0c\u5e2e\u52a9\u627e\u5230\u6700\u4f73\u7684\u6a21\u578b\u914d\u7f6e\uff0c\u5e76\u6700\u7ec8\u63d0\u5347\u6a21\u578b\u7684\u9884\u6d4b\u6027\u80fd\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u5728\u9009\u62e9Python\u7684\u4ea4\u53c9\u9a8c\u8bc1\u65f6\uff0c\u53ef\u4ee5\u8003\u8651\u4ee5\u4e0b\u51e0\u4e2a\u5173\u952e\u70b9\uff1a\u9009\u62e9\u5408\u9002\u7684\u4ea4\u53c9\u9a8c\u8bc1\u65b9\u6cd5\u3001\u6570\u636e\u5206\u5e03\u7684\u5747\u8861\u3001\u4ea4\u53c9\u9a8c\u8bc1\u7684\u6298\u6570 […]","protected":false},"author":3,"featured_media":1187025,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[37],"tags":[],"acf":[],"_links":{"self":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1187023"}],"collection":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/comments?post=1187023"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1187023\/revisions"}],"predecessor-version":[{"id":1187026,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1187023\/revisions\/1187026"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1187025"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1187023"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1187023"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1187023"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
![\"python\u5982\u4f55\u9009\u62e9\u4ea4\u53c9\u9a8c\u8bc1\"](\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/25135647\/c6a3ac1d-5823-42ff-b1c9-ea78c957923e.webp\")
<\/p>\n