\u5929\u6c14\u8f6f\u4ef6\u4f30\u8ba1\u660e\u5929\u7684\u6c14\u6e29，\u90ae\u7bb1\u8bc6\u522b\u5783\u573e\u90ae\u4ef6，\u8d2d\u7269\u7f51\u7ad9\u63a8\u8350\u53ef\u80fd\u611f\u5174\u8da3\u7684\u5546\u54c1，\u8fd9\u4e9b\u529f\u80fd\u80cc\u540e\u90fd\u53ef\u80fd\u7528\u5230\u673a\u5668\u5b66\u4e60\u3002\u4e0d\u8fc7，\u673a\u5668\u5b66\u4e60\u5e76\u4e0d\u662f\u8ba9\u8ba1\u7b97\u673a\u50cf\u4eba\u4e00\u6837\u201c\u51ed\u7a7a\u601d\u8003\u201d，\u5b83\u66f4\u50cf\u4e00\u79cd\u4ece\u5df2\u6709\u6570\u636e\u4e2d\u603b\u7ed3\u89c4\u5f8b\u3001\u518d\u5229\u7528\u89c4\u5f8b\u5904\u7406\u65b0\u6570\u636e\u7684\u65b9\u6cd5\u3002<\/p>\n
\u8fd9\u7bc7\u6587\u7ae0\u5148\u5efa\u7acb\u51e0\u4e2a\u6700\u5e38\u7528\u7684\u6982\u5ff5，\u518d\u7528 Python \u548c scikit-learn \u5b8c\u6210\u4e00\u4e2a\u5c0f\u578b\u56de\u5f52\u4efb\u52a1：\u6839\u636e\u5b66\u4e60\u65f6\u957f\u9884\u6d4b\u8003\u8bd5\u5206\u6570\u3002\u793a\u4f8b\u6570\u636e\u7531\u4ee3\u7801\u751f\u6210，\u4e0d\u4ee3\u8868\u771f\u5b9e\u6559\u5b66\u7814\u7a76；\u5b83\u7684\u7528\u9014\u662f\u8ba9\u6211\u4eec\u770b\u6e05\u4e00\u6b21\u673a\u5668\u5b66\u4e60\u5b9e\u9a8c\u7684\u5b8c\u6574\u8def\u5f84\u3002<\/p>\n
\u673a\u5668\u5b66\u4e60（Machine Learning）\u662f\u8ba9\u8ba1\u7b97\u673a\u4ece\u6570\u636e\u4e2d\u5b66\u4e60\u89c4\u5f8b，\u5e76\u5229\u7528\u8fd9\u4e9b\u89c4\u5f8b\u505a\u51fa\u9884\u6d4b\u6216\u51b3\u7b56\u7684\u4e00\u7c7b\u65b9\u6cd5\u3002\u8fd9\u91cc\u7684\u201c\u5b66\u4e60\u201d\u4e0d\u662f\u8bb0\u4f4f\u6807\u51c6\u7b54\u6848，\u800c\u662f\u8c03\u6574\u6a21\u578b\u5185\u90e8\u7684\u53c2\u6570，\u4f7f\u6a21\u578b\u7ed9\u51fa\u7684\u7ed3\u679c\u5c3d\u91cf\u63a5\u8fd1\u5df2\u77e5\u7ed3\u679c\u3002<\/p>\n
\u4f8b\u5982，\u6211\u4eec\u6536\u96c6\u4e00\u4e9b\u5b66\u751f\u7684\u5b66\u4e60\u65f6\u957f\u548c\u8003\u8bd5\u5206\u6570\u3002\u591a\u6570\u60c5\u51b5\u4e0b，\u5b66\u4e60\u65f6\u95f4\u589e\u52a0，\u5206\u6570\u4e5f\u4f1a\u53d1\u751f\u76f8\u5e94\u53d8\u5316\u3002\u673a\u5668\u5b66\u4e60\u6a21\u578b\u4f1a\u5c1d\u8bd5\u4ece\u8fd9\u4e9b\u6210\u5bf9\u6570\u636e\u4e2d\u627e\u51fa\u5173\u7cfb\u3002\u4e4b\u540e\u7ed9\u5b83\u4e00\u4e2a\u6ca1\u6709\u89c1\u8fc7\u7684\u5b66\u4e60\u65f6\u957f，\u5b83\u5c31\u80fd\u7ed9\u51fa\u9884\u6d4b\u5206\u6570\u3002<\/p>\n
\u673a\u5668\u5b66\u4e60\u9002\u5408\u89c4\u5f8b\u5b58\u5728\u3001\u4f46\u5f88\u96be\u624b\u5199\u6210\u5927\u91cf\u7cbe\u786e\u89c4\u5219\u7684\u95ee\u9898\u3002\u5b83\u4e5f\u6709\u8fb9\u754c：\u8bad\u7ec3\u6570\u636e\u6709\u504f\u5dee，\u6a21\u578b\u901a\u5e38\u4f1a\u7ee7\u627f\u8fd9\u79cd\u504f\u5dee；\u6570\u636e\u592a\u5c11\u6216\u8f93\u5165\u4e0e\u76ee\u6807\u6ca1\u6709\u7a33\u5b9a\u5173\u7cfb，\u9884\u6d4b\u4e5f\u4e0d\u4f1a\u53ef\u9760\u3002<\/p>\n
\u4f20\u7edf\u7f16\u7a0b\u901a\u5e38\u662f\u201c\u6570\u636e + \u4eba\u5199\u7684\u89c4\u5219 \u2192 \u7ed3\u679c\u201d\u3002\u4f8b\u5982，\u89c4\u5b9a\u6210\u7ee9\u5927\u4e8e\u7b49\u4e8e 60 \u5206\u5c31\u662f\u53ca\u683c，\u7a0b\u5e8f\u53ea\u9700\u5fe0\u5b9e\u6267\u884c\u8fd9\u6761\u89c4\u5219\u3002<\/p>\n
\u76d1\u7763\u5f0f\u673a\u5668\u5b66\u4e60\u66f4\u63a5\u8fd1\u201c\u6570\u636e + \u5df2\u77e5\u7b54\u6848 \u2192 \u6a21\u578b\u201d\u3002\u6211\u4eec\u4e0d\u76f4\u63a5\u544a\u8bc9\u7a0b\u5e8f\u5b66\u4e60 1 \u5c0f\u65f6\u5e94\u5f97\u591a\u5c11\u5206，\u800c\u662f\u63d0\u4f9b\u591a\u7ec4\u5b66\u4e60\u65f6\u957f\u548c\u5bf9\u5e94\u5206\u6570，\u8ba9\u7b97\u6cd5\u81ea\u5df1\u4f30\u8ba1\u4e24\u8005\u7684\u5173\u7cfb\u3002\u8bad\u7ec3\u5b8c\u6210\u540e，\u518d\u4f7f\u7528\u201c\u65b0\u6570\u636e + \u6a21\u578b \u2192 \u9884\u6d4b\u7ed3\u679c\u201d\u3002<\/p>\n
\u4e24\u8005\u5e76\u4e0d\u662f\u4e92\u76f8\u66ff\u4ee3\u3002\u89c4\u5219\u660e\u786e\u3001\u7a33\u5b9a\u5e76\u4e14\u5fc5\u987b\u4e25\u683c\u6267\u884c\u65f6，\u4f20\u7edf\u7a0b\u5e8f\u5f80\u5f80\u66f4\u5408\u9002；\u89c4\u5219\u96be\u4ee5\u9010\u6761\u63cf\u8ff0，\u5374\u6709\u8db3\u591f\u7684\u4ee3\u8868\u6027\u6570\u636e\u65f6，\u53ef\u4ee5\u8003\u8651\u673a\u5668\u5b66\u4e60\u3002\u5b9e\u9645\u7cfb\u7edf\u4e5f\u7ecf\u5e38\u628a\u4e24\u8005\u7ec4\u5408\u8d77\u6765\u3002<\/p>\n
\u6309\u7167\u83b7\u5f97\u53cd\u9988\u7684\u65b9\u5f0f，\u673a\u5668\u5b66\u4e60\u5e38\u88ab\u5206\u4e3a\u4e09\u7c7b：<\/p>\n
\u4e09\u8005\u89e3\u51b3\u7684\u95ee\u9898\u4e0d\u540c\u3002\u521d\u5b66\u65f6\u4e0d\u5fc5\u6025\u7740\u8bb0\u4f4f\u5927\u91cf\u7b97\u6cd5，\u5148\u5224\u65ad\u201c\u6709\u6ca1\u6709\u7b54\u6848\u201d\u201c\u5e0c\u671b\u9884\u6d4b\u4ec0\u4e48\u201d\u66f4\u91cd\u8981\u3002<\/p>\n
\u8fd9\u56db\u4e2a\u8bcd\u4f1a\u8d2f\u7a7f\u540e\u7eed\u6587\u7ae0：<\/p>\n
\u5728 scikit-learn \u4e2d，\u7279\u5f81\u901a\u5e38\u8bb0\u4e3a X，\u6807\u7b7e\u901a\u5e38\u8bb0\u4e3a y\u3002\u5373\u4f7f\u53ea\u6709\u4e00\u4e2a\u7279\u5f81，X \u4e5f\u901a\u5e38\u5199\u6210\u201c\u6837\u672c\u6570 \u00d7 \u7279\u5f81\u6570\u201d\u7684\u4e8c\u7ef4\u6570\u7ec4\u3002<\/p>\n
\u5982\u679c\u628a\u6240\u6709\u6570\u636e\u90fd\u4ea4\u7ed9\u6a21\u578b\u8bad\u7ec3，\u518d\u7528\u540c\u4e00\u6279\u6570\u636e\u8003\u8bd5，\u5f97\u5230\u7684\u5206\u6570\u5bb9\u6613\u8fc7\u4e8e\u4e50\u89c2\u3002\u56e0\u6b64，\u6211\u4eec\u901a\u5e38\u5148\u62c6\u5206\u6570\u636e：<\/p>\n
\u672c\u6587\u628a 75% \u7684\u6837\u672c\u7528\u4e8e\u8bad\u7ec3，25% \u7559\u4f5c\u6d4b\u8bd5，\u5e76\u7ed9 train_test_split \u8bbe\u7f6e random_state=42\u3002\u56fa\u5b9a\u968f\u673a\u79cd\u5b50\u610f\u5473\u7740\u6bcf\u6b21\u8fd0\u884c\u90fd\u4f1a\u5f97\u5230\u76f8\u540c\u7684\u62c6\u5206，\u4fbf\u4e8e\u590d\u73b0\u548c\u6838\u5bf9\u3002\u6d4b\u8bd5\u96c6\u4e0d\u53c2\u4e0e fit，\u5426\u5219\u5c31\u5931\u53bb\u4e86\u6a21\u62df\u201c\u65b0\u6570\u636e\u201d\u7684\u610f\u4e49\u3002<\/p>\n
\u6211\u4eec\u7528\u4ee3\u7801\u6784\u9020 20 \u6761\u6a21\u62df\u6570\u636e：\u5b66\u4e60\u65f6\u957f\u4ece 1.0 \u5c0f\u65f6\u589e\u52a0\u5230 10.5 \u5c0f\u65f6，\u5206\u6570\u603b\u4f53\u968f\u65f6\u957f\u4e0a\u5347，\u540c\u65f6\u52a0\u5165\u5c11\u91cf\u968f\u673a\u6ce2\u52a8\u3002\u968f\u673a\u6570\u751f\u6210\u5668\u4e5f\u56fa\u5b9a\u4e3a 42，\u6240\u4ee5\u6570\u636e\u672c\u8eab\u6bcf\u6b21\u90fd\u4e00\u81f4\u3002<\/p>\n
\u4efb\u52a1\u6d41\u7a0b\u662f：\u751f\u6210\u6570\u636e \u2192 \u62c6\u5206\u8bad\u7ec3\u96c6\u548c\u6d4b\u8bd5\u96c6 \u2192 \u8bad\u7ec3\u7ebf\u6027\u56de\u5f52\u6a21\u578b \u2192 \u9884\u6d4b\u6d4b\u8bd5\u96c6 \u2192 \u8ba1\u7b97\u8bc4\u4f30\u6307\u6807 \u2192 \u9884\u6d4b\u4e00\u4e2a\u65b0\u7684 6.5 \u5c0f\u65f6\u6837\u672c\u3002<\/p>\n
\u5c06\u4e0b\u9762\u4ee3\u7801\u4fdd\u5b58\u4e3a 01_demo.py，\u5728\u88c5\u6709 NumPy \u548c scikit-learn \u7684 Python 3 \u73af\u5883\u4e2d\u8fd0\u884c：<\/p>\n
"""\u6839\u636e\u5b66\u4e60\u65f6\u957f\u9884\u6d4b\u8003\u8bd5\u5206\u6570\u3002"""<\/p>\n
import sys<\/p>\n
def check_environment():
\n """\u68c0\u67e5 Python \u7248\u672c\u548c\u793a\u4f8b\u4f9d\u8d56，\u5e76\u7ed9\u51fa\u53ef\u8bfb\u7684\u9519\u8bef\u4fe1\u606f\u3002"""
\n if sys.version_info < (3, 8):
\n raise RuntimeError("\u672c\u793a\u4f8b\u9700\u8981 Python 3.8 \u6216\u66f4\u9ad8\u7248\u672c\u3002")<\/p>\n
try:
\n import numpy as np
\n import sklearn
\n except ImportError as exc:
\n raise RuntimeError(
\n "\u7f3a\u5c11 NumPy \u6216 scikit-learn，\u8bf7\u5148\u5728\u5f53\u524d\u73af\u5883\u5b89\u88c5 requirements.txt \u4e2d\u7684\u4f9d\u8d56\u3002"
\n ) from exc<\/p>\n
return np, sklearn<\/p>\n
def main():
\n np, sklearn = check_environment()<\/p>\n
from sklearn.linear_model import LinearRegression
\n from sklearn.metrics import mean_absolute_error, r2_score
\n from sklearn.model_selection import train_test_split<\/p>\n
# \u6784\u9020\u4e00\u7ec4\u6559\u5b66\u7528\u7684\u6a21\u62df\u6570\u636e\u3002\u56fa\u5b9a\u79cd\u5b50\u4f7f\u6bcf\u6b21\u751f\u6210\u7684\u6570\u636e\u5b8c\u5168\u4e00\u81f4\u3002
\n random_seed = 42
\n rng = np.random.default_rng(random_seed)
\n study_hours = np.arange(1.0, 11.0, 0.5).reshape(-1, 1)
\n scores = 30.0 + 6.2 * study_hours.ravel() + rng.normal(
\n loc=0.0, scale=2.0, size=study_hours.shape[0]
\n )<\/p>\n
if study_hours.shape[0] != scores.shape[0] or not np.isfinite(scores).all():
\n raise ValueError("\u793a\u4f8b\u6570\u636e\u65e0\u6548：\u7279\u5f81\u548c\u6807\u7b7e\u6570\u91cf\u4e0d\u4e00\u81f4，\u6216\u6807\u7b7e\u5305\u542b\u975e\u6709\u9650\u503c\u3002")<\/p>\n
# \u7559\u51fa 25% \u7684\u6837\u672c\u4f5c\u4e3a\u6d4b\u8bd5\u96c6，\u6a21\u578b\u8bad\u7ec3\u65f6\u4e0d\u4f1a\u770b\u5230\u5b83\u4eec\u3002
\n x_train, x_test, y_train, y_test = train_test_split(
\n study_hours,
\n scores,
\n test_size=0.25,
\n random_state=random_seed,
\n )<\/p>\n
model = LinearRegression()
\n model.fit(x_train, y_train)
\n y_pred = model.predict(x_test)<\/p>\n
mae = mean_absolute_error(y_test, y_pred)
\n r2 = r2_score(y_test, y_pred)
\n new_prediction = model.predict(np.array([[6.5]]))[0]<\/p>\n
print(f"Python: {sys.version.split()[0]}")
\n print(f"NumPy: {np.__version__}")
\n print(f"scikit-learn: {sklearn.__version__}")
\n print(f"\u8bad\u7ec3\u96c6\u6837\u672c\u6570: {len(x_train)}")
\n print(f"\u6d4b\u8bd5\u96c6\u6837\u672c\u6570: {len(x_test)}")
\n print("\\\\n\u6d4b\u8bd5\u96c6\u9884\u6d4b\u7ed3\u679c:")
\n for hours, actual, predicted in zip(x_test.ravel(), y_test, y_pred):
\n print(
\n f"\u5b66\u4e60 {hours:>4.1f} \u5c0f\u65f6 | \u5b9e\u9645\u5206\u6570 {actual:>5.2f} | "
\n f"\u9884\u6d4b\u5206\u6570 {predicted:>5.2f}"
\n )
\n print(f"\\\\n\u5e73\u5747\u7edd\u5bf9\u8bef\u5dee（MAE）: {mae:.2f}")
\n print(f"\u51b3\u5b9a\u7cfb\u6570（R2）: {r2:.3f}")
\n print(f"\u5b66\u4e60 6.5 \u5c0f\u65f6\u7684\u9884\u6d4b\u5206\u6570: {new_prediction:.2f}")<\/p>\n
if __name__ == "__main__":
\n try:
\n main()
\n except (RuntimeError, ValueError) as exc:
\n print(f"\u7a0b\u5e8f\u65e0\u6cd5\u7ee7\u7eed：{exc}", file=sys.stderr)
\n sys.exit(1)<\/p>\n
check_environment \u5148\u786e\u8ba4 Python \u7248\u672c，\u518d\u5c1d\u8bd5\u5bfc\u5165 NumPy \u548c scikit-learn\u3002\u5982\u679c\u4f9d\u8d56\u7f3a\u5931，\u7a0b\u5e8f\u4f1a\u7ed9\u51fa\u660e\u786e\u63d0\u793a\u5e76\u6b63\u5e38\u8fdb\u5165\u9519\u8bef\u5904\u7406，\u800c\u4e0d\u662f\u5728\u540e\u7eed\u6b65\u9aa4\u4ea7\u751f\u96be\u61c2\u7684\u5f02\u5e38\u3002<\/p>\n
np.arange(…).reshape(-1, 1) \u751f\u6210\u5b66\u4e60\u65f6\u957f，\u5e76\u628a\u4e00\u7ef4\u6570\u636e\u6539\u4e3a scikit-learn \u9700\u8981\u7684\u4e8c\u7ef4\u7279\u5f81\u77e9\u9635\u3002rng.normal \u751f\u6210\u5747\u503c\u4e3a 0 \u7684\u5c0f\u5e45\u968f\u673a\u6ce2\u52a8\u3002\u8fd9\u91cc\u660e\u786e\u5199\u51fa\u5b83\u662f\u6a21\u62df\u6570\u636e，\u4e0d\u80fd\u628a\u7ed3\u679c\u89e3\u91ca\u6210\u771f\u5b9e\u5b66\u751f\u7fa4\u4f53\u7684\u89c4\u5f8b\u3002<\/p>\n
train_test_split \u5b8c\u6210\u968f\u673a\u62c6\u5206\u3002model.fit(x_train, y_train) \u662f\u8bad\u7ec3\u6b65\u9aa4，\u7ebf\u6027\u56de\u5f52\u4f1a\u6839\u636e 15 \u4e2a\u8bad\u7ec3\u6837\u672c\u4f30\u8ba1\u76f4\u7ebf\u7684\u659c\u7387\u548c\u622a\u8ddd\u3002model.predict(x_test) \u5219\u628a 5 \u4e2a\u672a\u53c2\u4e0e\u8bad\u7ec3\u7684\u5b66\u4e60\u65f6\u957f\u653e\u5165\u6a21\u578b，\u5f97\u5230\u9884\u6d4b\u5206\u6570\u3002<\/p>\n
\u6700\u540e，\u4ee3\u7801\u8ba1\u7b97\u6d4b\u8bd5\u96c6\u4e0a\u7684 MAE \u548c R\u00b2，\u5e76\u9884\u6d4b\u5b66\u4e60 6.5 \u5c0f\u65f6\u7684\u5206\u6570\u3002\u4f20\u5165 [[6.5]] \u800c\u4e0d\u662f 6.5，\u662f\u56e0\u4e3a\u6a21\u578b\u671f\u5f85\u7684\u8f93\u5165\u5f62\u72b6\u4ecd\u7136\u662f\u201c1 \u4e2a\u6837\u672c\u30011 \u4e2a\u7279\u5f81\u201d\u3002<\/p>\n
\u8fd9\u4efd\u4ee3\u7801\u5df2\u5728 Conda \u7684 base \u73af\u5883\u4e2d\u5b9e\u9645\u8fd0\u884c，\u7248\u672c\u4e3a Python 3.11.4\u3001NumPy 1.24.3 \u548c scikit-learn 1.3.0\u3002\u7a0b\u5e8f\u6b63\u5e38\u7ed3\u675f，\u672c\u6b21\u56fa\u5b9a\u6570\u636e\u4e0e\u62c6\u5206\u5f97\u5230：\u8bad\u7ec3\u96c6 15 \u6761\u3001\u6d4b\u8bd5\u96c6 5 \u6761，MAE \u4e3a 1.66，R\u00b2 \u4e3a 0.992，\u5b66\u4e60 6.5 \u5c0f\u65f6\u7684\u9884\u6d4b\u5206\u6570\u4e3a 70.67\u3002\u56e0\u4e3a\u968f\u673a\u79cd\u5b50\u548c\u5e93\u7248\u672c\u90fd\u56fa\u5b9a，\u5728\u76f8\u540c\u73af\u5883\u4e2d\u5e94\u5f97\u5230\u76f8\u540c\u7ed3\u679c；\u4e0d\u540c\u5e93\u7248\u672c\u53ef\u80fd\u51fa\u73b0\u5f88\u5c0f\u7684\u6d6e\u70b9\u5dee\u5f02\u3002<\/p>\n
\u53ea\u770b\u67d0\u4e00\u6761\u9884\u6d4b\u5e76\u4e0d\u591f，\u56e0\u6b64\u9700\u8981\u8bc4\u4f30\u6307\u6807（Evaluation Metric），\u4e5f\u5c31\u662f\u628a\u4e00\u7ec4\u9884\u6d4b\u8d28\u91cf\u538b\u7f29\u6210\u6570\u503c\u7684\u65b9\u6cd5\u3002<\/p>\n
\u5e73\u5747\u7edd\u5bf9\u8bef\u5dee（Mean Absolute Error，MAE）\u4f1a\u8ba1\u7b97\u6bcf\u6761\u9884\u6d4b\u4e0e\u771f\u5b9e\u503c\u4e4b\u5dee\u7684\u7edd\u5bf9\u503c，\u518d\u53d6\u5e73\u5747\u3002\u8fd9\u91cc MAE \u4e3a 1.66，\u53ef\u4ee5\u76f4\u89c2\u7406\u89e3\u4e3a：\u5728\u8fd9 5 \u6761\u6d4b\u8bd5\u6837\u672c\u4e0a，\u9884\u6d4b\u5206\u6570\u5e73\u5747\u76f8\u5dee\u7ea6 1.66 \u5206\u3002MAE \u8d8a\u63a5\u8fd1 0 \u8d8a\u597d\u3002<\/p>\n
\u51b3\u5b9a\u7cfb\u6570（R-squared，R\u00b2）\u8861\u91cf\u6a21\u578b\u76f8\u5bf9\u4e8e\u201c\u603b\u662f\u9884\u6d4b\u5e73\u5747\u503c\u201d\u7684\u65b9\u6cd5\u89e3\u91ca\u4e86\u591a\u5c11\u53d8\u5316\u3002\u5b83\u901a\u5e38\u8d8a\u63a5\u8fd1 1 \u8d8a\u597d，0 \u8868\u793a\u6ca1\u6709\u4f18\u4e8e\u7b80\u5355\u7684\u5e73\u5747\u503c\u57fa\u7ebf，\u4e5f\u53ef\u80fd\u51fa\u73b0\u8d1f\u6570\u3002\u672c\u4f8b\u7684 0.992 \u63a5\u8fd11，\u662f\u56e0\u4e3a\u6a21\u62df\u6570\u636e\u672c\u6765\u5c31\u63a5\u8fd1\u76f4\u7ebf；\u8fd9\u4e0d\u80fd\u8bc1\u660e\u6a21\u578b\u5728\u771f\u5b9e\u8003\u8bd5\u6570\u636e\u4e0a\u4e5f\u4f1a\u540c\u6837\u51c6\u786e\u3002<\/p>\n
\u6d4b\u8bd5\u96c6\u53ea\u6709 5 \u6761，\u6240\u4ee5\u8fd9\u4e2a\u6570\u503c\u4e3b\u8981\u7528\u4e8e\u6f14\u793a\u6d41\u7a0b，\u4e0d\u80fd\u636e\u6b64\u4f5c\u73b0\u5b9e\u51b3\u7b56\u3002\u771f\u5b9e\u9879\u76ee\u8fd8\u8981\u4f7f\u7528\u66f4\u591a\u6709\u4ee3\u8868\u6027\u7684\u6570\u636e，\u5e76\u68c0\u67e5\u5f02\u5e38\u503c\u3001\u504f\u5dee\u548c\u91cd\u590d\u5b9e\u9a8c\u7ed3\u679c\u3002<\/p>\n
\u5165\u95e8\u9636\u6bb5\u53ef\u4ee5\u5148\u7406\u89e3\u6570\u636e\u3001\u8bad\u7ec3\u548c\u8bc4\u4f30\u7684\u6d41\u7a0b\u3002\u968f\u7740\u4efb\u52a1\u6df1\u5165，\u7ebf\u6027\u4ee3\u6570\u3001\u6982\u7387\u7edf\u8ba1\u548c\u5fae\u79ef\u5206\u4f1a\u5e2e\u52a9\u4f60\u7406\u89e3\u7b97\u6cd5\u4e3a\u4ec0\u4e48\u6709\u6548，\u4f46\u4e0d\u5fc5\u7b49\u5230\u5b66\u5b8c\u6240\u6709\u6570\u5b66\u624d\u5f00\u59cb\u5b9e\u8df5\u3002<\/p>\n
\u6a21\u578b\u9700\u8981\u5728\u6ca1\u6709\u89c1\u8fc7\u7684\u6570\u636e\u4e0a\u63a5\u53d7\u68c0\u67e5\u3002\u5982\u679c\u6ca1\u6709\u6d4b\u8bd5\u96c6，\u6211\u4eec\u5f88\u96be\u5206\u8fa8\u6a21\u578b\u662f\u771f\u6b63\u5b66\u5230\u4e86\u89c4\u5f8b，\u8fd8\u662f\u53ea\u8bb0\u4f4f\u4e86\u8bad\u7ec3\u6570\u636e\u3002<\/p>\n
\u4e0d\u4e00\u5b9a\u3002\u6307\u6807\u8fd8\u4f1a\u53d7\u5230\u6570\u636e\u89c4\u6a21\u3001\u62c6\u5206\u65b9\u5f0f\u3001\u6570\u636e\u6cc4\u6f0f\u548c\u6570\u636e\u4ee3\u8868\u6027\u7684\u5f71\u54cd\u3002\u672c\u4f8b\u662f\u523b\u610f\u8bbe\u8ba1\u7684\u7b80\u5355\u6a21\u62df\u6570\u636e，\u56e0\u6b64\u7ed3\u679c\u8f83\u9ad8\u3002\u73b0\u5b9e\u4efb\u52a1\u5fc5\u987b\u7ed3\u5408\u4e1a\u52a1\u76ee\u6807\u548c\u6570\u636e\u6765\u6e90\u5224\u65ad\u3002<\/p>\n
\u968f\u673a\u62c6\u5206\u548c\u968f\u673a\u751f\u6210\u6570\u636e\u53ef\u80fd\u8ba9\u6bcf\u6b21\u7ed3\u679c\u4e0d\u540c\u3002\u56fa\u5b9a\u79cd\u5b50\u53ef\u4ee5\u8ba9\u5b9e\u9a8c\u66f4\u5bb9\u6613\u590d\u73b0\u548c\u6392\u67e5\u3002\u56fa\u5b9a\u79cd\u5b50\u4e0d\u4f1a\u81ea\u52a8\u4fdd\u8bc1\u6a21\u578b\u6b63\u786e，\u5b83\u53ea\u662f\u56fa\u5b9a\u4e86\u968f\u673a\u8fc7\u7a0b\u3002<\/p>\n
\u4e0d\u80fd\u3002\u672c\u4f8b\u53ea\u4f7f\u7528\u5b66\u4e60\u65f6\u957f\u8fd9\u4e00\u9879\u6a21\u62df\u7279\u5f81，\u4e5f\u6ca1\u6709\u771f\u5b9e\u5b66\u751f\u6570\u636e\u3002\u5b83\u662f\u7f16\u7a0b\u6559\u5b66\u6848\u4f8b，\u4e0d\u9002\u5408\u8bc4\u4ef7\u4e2a\u4eba\u3001\u6307\u5bfc\u6559\u5b66\u6216\u4f5c\u51fa\u5b9e\u9645\u51b3\u5b9a\u3002<\/p>\n
\u5148\u786e\u8ba4\u7ec8\u7aef\u4f7f\u7528\u7684\u662f\u9884\u671f\u7684 Conda \u73af\u5883，\u518d\u5728\u8be5\u73af\u5883\u4e2d\u5b89\u88c5\u4e0e\u9879\u76ee\u5339\u914d\u7684 scikit-learn\u3002\u5305\u7684\u5b89\u88c5\u540d\u662f scikit-learn，\u4ee3\u7801\u4e2d\u7684\u5bfc\u5165\u540d\u662f sklearn\u3002\u4e0d\u8981\u4e3a\u4e86\u4e00\u4e2a\u793a\u4f8b\u76f2\u76ee\u5347\u7ea7\u6574\u4e2a\u73af\u5883\u3002<\/p>\n
\u673a\u5668\u5b66\u4e60\u7684\u6838\u5fc3\u4e0d\u662f\u67d0\u4e2a\u795e\u79d8\u51fd\u6570，\u800c\u662f\u4e00\u5957\u4ece\u6570\u636e\u4e2d\u5b66\u4e60\u5e76\u7528\u65b0\u6570\u636e\u68c0\u9a8c\u7684\u8fc7\u7a0b\u3002\u672c\u6587\u533a\u5206\u4e86\u4f20\u7edf\u7f16\u7a0b\u4e0e\u673a\u5668\u5b66\u4e60，\u8ba4\u8bc6\u4e86\u4e09\u7c7b\u5e38\u89c1\u5b66\u4e60\u65b9\u5f0f，\u4e5f\u660e\u786e\u4e86\u6837\u672c\u3001\u7279\u5f81\u3001\u6807\u7b7e\u3001\u6a21\u578b\u3001\u8bad\u7ec3\u96c6\u548c\u6d4b\u8bd5\u96c6\u3002\u968f\u540e，\u6211\u4eec\u5b8c\u6210\u4e86\u4e00\u4e2a\u53ef\u590d\u73b0\u7684\u7ebf\u6027\u56de\u5f52\u6848\u4f8b，\u5e76\u7528 MAE \u4e0e R\u00b2 \u68c0\u67e5\u9884\u6d4b\u6548\u679c\u3002<\/p>\n
\u8bb0\u4f4f\u4e00\u4e2a\u57fa\u672c\u987a\u5e8f\u5373\u53ef：\u660e\u786e\u95ee\u9898，\u51c6\u5907\u6570\u636e，\u62c6\u5206\u6570\u636e，\u8bad\u7ec3\u6a21\u578b，\u8bc4\u4f30\u6a21\u578b，\u518d\u8c28\u614e\u4f7f\u7528\u9884\u6d4b\u7ed3\u679c\u3002<\/p>\n
\u4e0b\u4e00\u7bc7\u5c06\u4ecb\u7ecd Anaconda\u3001Python \u4e0e\u673a\u5668\u5b66\u4e60\u5f00\u53d1\u73af\u5883，\u5305\u62ec\u5982\u4f55\u7406\u89e3 Conda \u73af\u5883\u3001\u9009\u62e9\u89e3\u91ca\u5668\u3001\u5b89\u88c5\u4f9d\u8d56，\u4ee5\u53ca\u907f\u5f00\u201c\u5305\u88c5\u597d\u4e86\u5374\u8fd0\u884c\u4e0d\u4e86\u201d\u7684\u5e38\u89c1\u95ee\u9898\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"
\u524d\u8a00\u5929\u6c14\u8f6f\u4ef6\u4f30\u8ba1\u660e\u5929\u7684\u6c14\u6e29，\u90ae\u7bb1\u8bc6\u522b\u5783\u573e\u90ae\u4ef6，\u8d2d\u7269\u7f51\u7ad9\u63a8\u8350\u53ef\u80fd\u611f\u5174\u8da3\u7684\u5546\u54c1，\u8fd9\u4e9b\u529f\u80fd\u80cc\u540e\u90fd\u53ef\u80fd\u7528\u5230\u673a\u5668\u5b66\u4e60\u3002\u4e0d\u8fc7，\u673a\u5668\u5b66\u4e60\u5e76\u4e0d\u662f\u8ba9\u8ba1\u7b97\u673a\u50cf\u4eba\u4e00\u6837\u201c\u51ed\u7a7a\u601d\u8003\u201d，\u5b83\u66f4\u50cf\u4e00\u79cd\u4ece\u5df2\u6709\u6570\u636e\u4e2d\u603b\u7ed3\u89c4\u5f8b\u3001\u518d\u5229\u7528\u89c4\u5f8b\u5904\u7406\u65b0\u6570\u636e\u7684\u65b9\u6cd5\u3002\u8fd9\u7bc7\u6587\u7ae0\u5148\u5efa\u7acb\u51e0\u4e2a\u6700\u5e38\u7528\u7684\u6982\u5ff5，\u518d\u7528 Python \u548c scikit-learn \u5b8c\u6210\u4e00\u4e2a\u5c0f\u578b\u56de\u5f52\u4efb\u52a1：\u6839\u636e\u5b66\u4e60\u65f6\u957f\u9884\u6d4b\u8003\u8bd5\u5206\u6570\u3002\u793a\u4f8b\u6570\u636e\u7531\u4ee3\u7801\u751f\u6210，<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[81,737,50,207],"topic":[],"class_list":["post-91574","post","type-post","status-publish","format-standard","hentry","category-server","tag-python","tag-scikit-learn","tag-50","tag-207"],"yoast_head":"\n