{"id":1179376,"date":"2025-01-15T18:22:53","date_gmt":"2025-01-15T10:22:53","guid":{"rendered":""},"modified":"2025-01-15T18:22:57","modified_gmt":"2025-01-15T10:22:57","slug":"python%e5%a6%82%e4%bd%95%e5%af%bc%e5%87%ba%e5%9b%9e%e5%bd%92%e7%9a%84%e7%b3%bb%e6%95%b0","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1179376.html","title":{"rendered":"python\u5982\u4f55\u5bfc\u51fa\u56de\u5f52\u7684\u7cfb\u6570"},"content":{"rendered":"

\"python\u5982\u4f55\u5bfc\u51fa\u56de\u5f52\u7684\u7cfb\u6570\"<\/p>\n

Python\u4e2d\u53ef\u4ee5\u4f7f\u7528\u591a\u79cd\u5e93\u6765\u8fdb\u884c\u56de\u5f52\u5206\u6790\u5e76\u5bfc\u51fa\u56de\u5f52\u7cfb\u6570\uff0c\u5982scikit-learn\u3001statsmodels\u7b49\u3002\u5177\u4f53\u65b9\u6cd5\u5305\u62ec\uff1a\u4f7f\u7528scikit-learn\u7684LinearRegression\u7c7b\u3001\u4f7f\u7528statsmodels\u7684OLS\u7c7b\u3001\u901a\u8fc7\u5c5e\u6027\u8bbf\u95ee\u7cfb\u6570\u3002<\/strong><\/p>\n<\/p>\n

\u4e0b\u9762\u6211\u4eec\u8be6\u7ec6\u4ecb\u7ecd\u5982\u4f55\u4f7f\u7528scikit-learn\u548cstatsmodels\u6765\u5bfc\u51fa\u56de\u5f52\u7cfb\u6570\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u4f7f\u7528Scikit-learn\u8fdb\u884c\u56de\u5f52\u5206\u6790<\/h3>\n<\/p>\n

Scikit-learn\u662f\u4e00\u4e2a\u975e\u5e38\u5f3a\u5927\u7684\u673a\u5668\u5b66\u4e60<\/a>\u5e93\uff0c\u63d0\u4f9b\u4e86\u591a\u79cd\u56de\u5f52\u6a21\u578b\u3002\u6700\u5e38\u7528\u7684\u7ebf\u6027\u56de\u5f52\u6a21\u578b\u53ef\u4ee5\u901a\u8fc7LinearRegression<\/code>\u7c7b\u6765\u5b9e\u73b0\u3002\u4ee5\u4e0b\u662f\u5177\u4f53\u6b65\u9aa4\uff1a<\/p>\n<\/p>\n

1\u3001\u5bfc\u5165\u5fc5\u8981\u7684\u5e93<\/h4>\n<\/p>\n

\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u5bfc\u5165\u5fc5\u8981\u7684\u5e93\uff0c\u5305\u62ecscikit-learn\u548cnumpy\u7b49\u3002<\/p>\n<\/p>\n

import numpy as np<\/p>\n
import pandas as pd<\/p>\n
from sklearn.linear_model import LinearRegression<\/p>\n
<\/code><\/pre>\n<\/p>\n
2\u3001\u51c6\u5907\u6570\u636e<\/h4>\n<\/p>\n
\u6211\u4eec\u9700\u8981\u51c6\u5907\u597d\u8bad\u7ec3\u6570\u636e\u96c6\uff0c\u8fd9\u91cc\u5047\u8bbe\u6211\u4eec\u6709\u4e00\u4e2a\u7b80\u5355\u7684\u7ebf\u6027\u56de\u5f52\u95ee\u9898\u3002<\/p>\n<\/p>\n
# \u521b\u5efa\u6837\u672c\u6570\u636e<\/p>\n
X = np.array([[1, 1], [1, 2], [2, 2], [2, 3]])<\/p>\n
y = np.dot(X, np.array([1, 2])) + 3<\/p>\n
<\/code><\/pre>\n<\/p>\n
3\u3001\u521b\u5efa\u548c\u8bad\u7ec3\u6a21\u578b<\/h4>\n<\/p>\n
\u521b\u5efa\u4e00\u4e2aLinearRegression<\/code>\u5bf9\u8c61\uff0c\u5e76\u4f7f\u7528\u8bad\u7ec3\u6570\u636e\u8fdb\u884c\u62df\u5408\u3002<\/p>\n<\/p>\n
# \u521b\u5efa\u7ebf\u6027\u56de\u5f52\u5bf9\u8c61<\/p>\n
model = LinearRegression()<\/p>\n
\u8bad\u7ec3\u6a21\u578b<\/strong><\/h2>\n
model.fit(X, y)<\/p>\n
<\/code><\/pre>\n<\/p>\n
4\u3001\u5bfc\u51fa\u56de\u5f52\u7cfb\u6570<\/h4>\n<\/p>\n
\u4f7f\u7528coef_<\/code>\u548cintercept_<\/code>\u5c5e\u6027\u6765\u83b7\u53d6\u56de\u5f52\u7cfb\u6570\u548c\u622a\u8ddd\u3002<\/p>\n<\/p>\n
# \u83b7\u53d6\u56de\u5f52\u7cfb\u6570<\/p>\n
coefficients = model.coef_<\/p>\n
intercept = model.intercept_<\/p>\n
print("\u56de\u5f52\u7cfb\u6570:", coefficients)<\/p>\n
print("\u622a\u8ddd:", intercept)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e8c\u3001\u4f7f\u7528Statsmodels\u8fdb\u884c\u56de\u5f52\u5206\u6790<\/h3>\n<\/p>\n
Statsmodels\u662f\u4e00\u4e2a\u4e13\u95e8\u7528\u4e8e\u7edf\u8ba1\u5efa\u6a21\u7684\u5e93\uff0c\u63d0\u4f9b\u4e86\u66f4\u8be6\u7ec6\u7684\u7edf\u8ba1\u4fe1\u606f\u3002\u4ee5\u4e0b\u662f\u4f7f\u7528statsmodels\u8fdb\u884c\u56de\u5f52\u5206\u6790\u7684\u6b65\u9aa4\uff1a<\/p>\n<\/p>\n
1\u3001\u5bfc\u5165\u5fc5\u8981\u7684\u5e93<\/h4>\n<\/p>\n
import statsmodels.api as sm<\/p>\n
import numpy as np<\/p>\n
import pandas as pd<\/p>\n
<\/code><\/pre>\n<\/p>\n
2\u3001\u51c6\u5907\u6570\u636e<\/h4>\n<\/p>\n
\u4e0e\u4e0a\u9762\u7c7b\u4f3c\uff0c\u6211\u4eec\u9700\u8981\u51c6\u5907\u597d\u8bad\u7ec3\u6570\u636e\u96c6\u3002<\/p>\n<\/p>\n
# \u521b\u5efa\u6837\u672c\u6570\u636e<\/p>\n
X = np.array([[1, 1], [1, 2], [2, 2], [2, 3]])<\/p>\n
y = np.dot(X, np.array([1, 2])) + 3<\/p>\n
\u6dfb\u52a0\u5e38\u6570\u9879<\/strong><\/h2>\n
X = sm.add_constant(X)<\/p>\n
<\/code><\/pre>\n<\/p>\n
3\u3001\u521b\u5efa\u548c\u8bad\u7ec3\u6a21\u578b<\/h4>\n<\/p>\n
\u4f7f\u7528OLS<\/code>\u7c7b\u6765\u521b\u5efa\u548c\u8bad\u7ec3\u56de\u5f52\u6a21\u578b\u3002<\/p>\n<\/p>\n
# \u521b\u5efaOLS\u6a21\u578b<\/p>\n
model = sm.OLS(y, X)<\/p>\n
\u8bad\u7ec3\u6a21\u578b<\/strong><\/h2>\n
results = model.fit()<\/p>\n
<\/code><\/pre>\n<\/p>\n
4\u3001\u5bfc\u51fa\u56de\u5f52\u7cfb\u6570<\/h4>\n<\/p>\n
\u4f7f\u7528params<\/code>\u5c5e\u6027\u6765\u83b7\u53d6\u56de\u5f52\u7cfb\u6570\u3002<\/p>\n<\/p>\n
# \u83b7\u53d6\u56de\u5f52\u7cfb\u6570<\/p>\n
coefficients = results.params<\/p>\n
print("\u56de\u5f52\u7cfb\u6570:", coefficients)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e09\u3001\u5176\u4ed6\u56de\u5f52\u6a21\u578b<\/h3>\n<\/p>\n
\u9664\u4e86\u7ebf\u6027\u56de\u5f52\uff0cscikit-learn\u548cstatsmodels\u8fd8\u63d0\u4f9b\u4e86\u5176\u4ed6\u56de\u5f52\u6a21\u578b\uff0c\u5982\u5cad\u56de\u5f52\u3001Lasso\u56de\u5f52\u7b49\u3002\u8fd9\u91cc\u7b80\u8981\u4ecb\u7ecd\u5982\u4f55\u4f7f\u7528scikit-learn\u5b9e\u73b0\u5cad\u56de\u5f52\u3002<\/p>\n<\/p>\n
1\u3001\u5bfc\u5165\u5fc5\u8981\u7684\u5e93<\/h4>\n<\/p>\n
from sklearn.linear_model import Ridge<\/p>\n
<\/code><\/pre>\n<\/p>\n
2\u3001\u521b\u5efa\u548c\u8bad\u7ec3\u6a21\u578b<\/h4>\n<\/p>\n
\u521b\u5efa\u4e00\u4e2aRidge<\/code>\u5bf9\u8c61\uff0c\u5e76\u4f7f\u7528\u8bad\u7ec3\u6570\u636e\u8fdb\u884c\u62df\u5408\u3002<\/p>\n<\/p>\n
# \u521b\u5efa\u5cad\u56de\u5f52\u5bf9\u8c61<\/p>\n
ridge_model = Ridge(alpha=1.0)<\/p>\n
\u8bad\u7ec3\u6a21\u578b<\/strong><\/h2>\n
ridge_model.fit(X, y)<\/p>\n
<\/code><\/pre>\n<\/p>\n
3\u3001\u5bfc\u51fa\u56de\u5f52\u7cfb\u6570<\/h4>\n<\/p>\n
\u540c\u6837\u4f7f\u7528coef_<\/code>\u548cintercept_<\/code>\u5c5e\u6027\u6765\u83b7\u53d6\u56de\u5f52\u7cfb\u6570\u548c\u622a\u8ddd\u3002<\/p>\n<\/p>\n
# \u83b7\u53d6\u56de\u5f52\u7cfb\u6570<\/p>\n
ridge_coefficients = ridge_model.coef_<\/p>\n
ridge_intercept = ridge_model.intercept_<\/p>\n
print("\u5cad\u56de\u5f52\u7cfb\u6570:", ridge_coefficients)<\/p>\n
print("\u5cad\u56de\u5f52\u622a\u8ddd:", ridge_intercept)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u56db\u3001\u603b\u7ed3<\/h3>\n<\/p>\n
\u901a\u8fc7\u4ee5\u4e0a\u65b9\u6cd5\uff0c\u6211\u4eec\u53ef\u4ee5\u8f7b\u677e\u5730\u5728Python\u4e2d\u8fdb\u884c\u56de\u5f52\u5206\u6790\u5e76\u5bfc\u51fa\u56de\u5f52\u7cfb\u6570\u3002Scikit-learn\u9002\u5408\u5feb\u901f\u5efa\u6a21\u548c\u9884\u6d4b\uff0c\u63d0\u4f9b\u4e86\u4e00\u81f4\u7684API\u548c\u9ad8\u6548\u7684\u5b9e\u73b0\uff1bStatsmodels\u5219\u9002\u5408\u9700\u8981\u8be6\u7ec6\u7edf\u8ba1\u4fe1\u606f\u7684\u573a\u666f\uff0c\u63d0\u4f9b\u4e86\u66f4\u4e30\u5bcc\u7684\u7edf\u8ba1\u68c0\u9a8c\u548c\u7ed3\u679c\u89e3\u8bfb\u529f\u80fd\u3002<\/strong>\u6839\u636e\u5177\u4f53\u9700\u6c42\u9009\u62e9\u5408\u9002\u7684\u5de5\u5177\uff0c\u53ef\u4ee5\u66f4\u597d\u5730\u5b8c\u6210\u6570\u636e\u5206\u6790\u548c\u5efa\u6a21\u4efb\u52a1\u3002<\/p>\n<\/p>\n
\u4e94\u3001\u9644\u52a0\u4fe1\u606f<\/h3>\n<\/p>\n
\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0c\u6570\u636e\u9884\u5904\u7406\u548c\u6a21\u578b\u8bc4\u4f30\u540c\u6837\u91cd\u8981\u3002\u4ee5\u4e0b\u662f\u4e00\u4e9b\u5e38\u7528\u7684\u6280\u5de7\u548c\u65b9\u6cd5\uff1a<\/p>\n<\/p>\n
1\u3001\u6570\u636e\u9884\u5904\u7406<\/h4>\n<\/p>\n
\u5728\u8fdb\u884c\u56de\u5f52\u5206\u6790\u524d\uff0c\u901a\u5e38\u9700\u8981\u5bf9\u6570\u636e\u8fdb\u884c\u9884\u5904\u7406\uff0c\u5305\u62ec\u7f3a\u5931\u503c\u5904\u7406\u3001\u7279\u5f81\u7f29\u653e\u3001\u7c7b\u522b\u7f16\u7801\u7b49\u3002<\/p>\n<\/p>\n
from sklearn.preprocessing import StandardScaler<\/p>\n
from sklearn.impute import SimpleImputer<\/p>\n
from sklearn.pipeline import Pipeline<\/p>\n
\u521b\u5efa\u6570\u636e\u9884\u5904\u7406\u7ba1\u9053<\/strong><\/h2>\n
preprocessing_pipeline = Pipeline([<\/p>\n
    ('imputer', SimpleImputer(strategy='mean')),<\/p>\n
    ('scaler', StandardScaler())<\/p>\n
])<\/p>\n
\u9884\u5904\u7406\u6570\u636e<\/strong><\/h2>\n
X_preprocessed = preprocessing_pipeline.fit_transform(X)<\/p>\n
<\/code><\/pre>\n<\/p>\n
2\u3001\u6a21\u578b\u8bc4\u4f30<\/h4>\n<\/p>\n
\u5728\u8bad\u7ec3\u6a21\u578b\u540e\uff0c\u8bc4\u4f30\u6a21\u578b\u7684\u6027\u80fd\u662f\u975e\u5e38\u91cd\u8981\u7684\u3002\u5e38\u7528\u7684\u8bc4\u4f30\u6307\u6807\u5305\u62ec\u5747\u65b9\u8bef\u5dee\uff08MSE\uff09\u3001\u51b3\u5b9a\u7cfb\u6570\uff08R^2\uff09\u7b49\u3002<\/p>\n<\/p>\n
from sklearn.metrics import mean_squared_error, r2_score<\/p>\n
\u9884\u6d4b<\/strong><\/h2>\n
y_pred = model.predict(X)<\/p>\n
\u8ba1\u7b97\u8bc4\u4f30\u6307\u6807<\/strong><\/h2>\n
mse = mean_squared_error(y, y_pred)<\/p>\n
r2 = r2_score(y, y_pred)<\/p>\n
print("\u5747\u65b9\u8bef\u5dee:", mse)<\/p>\n
print("\u51b3\u5b9a\u7cfb\u6570:", r2)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u901a\u8fc7\u4e0a\u8ff0\u65b9\u6cd5\uff0c\u6211\u4eec\u4e0d\u4ec5\u80fd\u591f\u5bfc\u51fa\u56de\u5f52\u7cfb\u6570\uff0c\u8fd8\u80fd\u5bf9\u6a21\u578b\u8fdb\u884c\u5168\u9762\u7684\u8bc4\u4f30\uff0c\u4ece\u800c\u786e\u4fdd\u6a21\u578b\u7684\u6709\u6548\u6027\u548c\u51c6\u786e\u6027\u3002<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
 \u5982\u4f55\u5728Python\u4e2d\u83b7\u53d6\u7ebf\u6027\u56de\u5f52\u6a21\u578b\u7684\u7cfb\u6570\uff1f<\/strong>
\u5728Python\u4e2d\uff0c\u4f7f\u7528scikit-learn<\/code>\u5e93\u8fdb\u884c\u7ebf\u6027\u56de\u5f52\u65f6\uff0c\u53ef\u4ee5\u901a\u8fc7\u8bbf\u95ee\u6a21\u578b\u7684coef_<\/code>\u5c5e\u6027\u6765\u83b7\u53d6\u56de\u5f52\u7cfb\u6570\u3002\u9996\u5148\uff0c\u60a8\u9700\u8981\u5bfc\u5165\u5fc5\u8981\u7684\u5e93\uff0c\u521b\u5efa\u6a21\u578b\u5e76\u62df\u5408\u6570\u636e\u3002\u62df\u5408\u540e\uff0c\u60a8\u53ef\u4ee5\u76f4\u63a5\u8c03\u7528\u6a21\u578b\u7684coef_<\/code>\u5c5e\u6027\u6765\u67e5\u770b\u5404\u4e2a\u7279\u5f81\u7684\u7cfb\u6570\u3002<\/p>\n
\u4f7f\u7528\u54ea\u4e9b\u5e93\u53ef\u4ee5\u8fdb\u884c\u56de\u5f52\u5206\u6790\u5e76\u5bfc\u51fa\u7cfb\u6570\uff1f<\/strong>
\u5e38\u7528\u7684\u5e93\u5305\u62ecscikit-learn<\/code>\u3001statsmodels<\/code>\u548cnumpy<\/code>\u3002\u5176\u4e2d\uff0cscikit-learn<\/code>\u9002\u5408\u5feb\u901f\u6784\u5efa\u548c\u8bc4\u4f30\u6a21\u578b\uff0c\u800cstatsmodels<\/code>\u63d0\u4f9b\u66f4\u8be6\u7ec6\u7684\u7edf\u8ba1\u8f93\u51fa\uff0c\u5305\u62ec\u56de\u5f52\u7cfb\u6570\u548c\u76f8\u5173\u7684\u7edf\u8ba1\u68c0\u9a8c\u4fe1\u606f\u3002\u9009\u62e9\u5408\u9002\u7684\u5e93\u53ef\u4ee5\u5e2e\u52a9\u60a8\u66f4\u597d\u5730\u7406\u89e3\u6a21\u578b\u7684\u8868\u73b0\u3002<\/p>\n
\u5982\u4f55\u5c06\u56de\u5f52\u7cfb\u6570\u5bfc\u51fa\u5230CSV\u6587\u4ef6\u4e2d\uff1f<\/strong>
\u60a8\u53ef\u4ee5\u4f7f\u7528pandas<\/code>\u5e93\u6765\u521b\u5efaDataFrame\u5e76\u5c06\u56de\u5f52\u7cfb\u6570\u5bfc\u51fa\u4e3aCSV\u6587\u4ef6\u3002\u9996\u5148\uff0c\u5c06\u56de\u5f52\u7cfb\u6570\u548c\u7279\u5f81\u540d\u79f0\u7ec4\u6210\u4e00\u4e2aDataFrame\uff0c\u7136\u540e\u4f7f\u7528to_csv()<\/code>\u65b9\u6cd5\u5c06\u5176\u4fdd\u5b58\u4e3aCSV\u683c\u5f0f\u3002\u8fd9\u79cd\u65b9\u5f0f\u4e0d\u4ec5\u65b9\u4fbf\u5b58\u50a8\uff0c\u8fd8\u53ef\u4ee5\u65b9\u4fbf\u540e\u7eed\u7684\u6570\u636e\u5206\u6790\u548c\u53ef\u89c6\u5316\u3002<\/p>\n
\u56de\u5f52\u6a21\u578b\u7cfb\u6570\u7684\u89e3\u91ca\u662f\u4ec0\u4e48\uff1f<\/strong>
\u56de\u5f52\u7cfb\u6570\u8868\u793a\u6bcf\u4e2a\u81ea\u53d8\u91cf\u5bf9\u56e0\u53d8\u91cf\u7684\u5f71\u54cd\u7a0b\u5ea6\u3002\u5177\u4f53\u6765\u8bf4\uff0c\u7cfb\u6570\u7684\u5927\u5c0f\u548c\u7b26\u53f7\u6307\u793a\u4e86\u81ea\u53d8\u91cf\u53d8\u5316\u4e00\u4e2a\u5355\u4f4d\u65f6\uff0c\u56e0\u53d8\u91cf\u7684\u53d8\u5316\u91cf\u3002\u6b63\u7cfb\u6570\u8868\u660e\u81ea\u53d8\u91cf\u4e0e\u56e0\u53d8\u91cf\u6b63\u76f8\u5173\uff0c\u800c\u8d1f\u7cfb\u6570\u5219\u8868\u660e\u4e8c\u8005\u8d1f\u76f8\u5173\u3002\u4e86\u89e3\u7cfb\u6570\u7684\u542b\u4e49\u5bf9\u4e8e\u6a21\u578b\u89e3\u91ca\u548c\u7ed3\u679c\u5206\u6790\u81f3\u5173\u91cd\u8981\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u4e2d\u53ef\u4ee5\u4f7f\u7528\u591a\u79cd\u5e93\u6765\u8fdb\u884c\u56de\u5f52\u5206\u6790\u5e76\u5bfc\u51fa\u56de\u5f52\u7cfb\u6570\uff0c\u5982scikit-learn\u3001statsmodels\u7b49 […]","protected":false},"author":3,"featured_media":1179384,"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\/1179376"}],"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=1179376"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1179376\/revisions"}],"predecessor-version":[{"id":1179387,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1179376\/revisions\/1179387"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1179384"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1179376"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1179376"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1179376"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}