{"id":1002838,"date":"2024-12-27T10:12:14","date_gmt":"2024-12-27T02:12:14","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1002838.html"},"modified":"2024-12-27T10:12:17","modified_gmt":"2024-12-27T02:12:17","slug":"python%e5%a6%82%e4%bd%95%e5%8e%bb%e6%8e%89%e7%a6%bb%e6%95%a3%e7%82%b9","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1002838.html","title":{"rendered":"python\u5982\u4f55\u53bb\u6389\u79bb\u6563\u70b9"},"content":{"rendered":"

\"python\u5982\u4f55\u53bb\u6389\u79bb\u6563\u70b9\"<\/p>\n

\u5728Python\u4e2d\u53bb\u9664\u79bb\u6563\u70b9\u7684\u65b9\u6cd5\u6709\u591a\u79cd\uff0c\u5e38\u7528\u7684\u5305\u62ec\uff1aZ-score\u65b9\u6cd5\u3001IQR\uff08\u56db\u5206\u4f4d\u8ddd\uff09\u65b9\u6cd5\u3001\u4f7f\u7528\u89c6\u89c9\u5316\u5de5\u5177\uff08\u5982\u7bb1\u7ebf\u56fe\uff09\u8bc6\u522b\u3001DBSCAN\u7b49\u805a\u7c7b\u7b97\u6cd5\u3002\u672c\u6587\u5c06\u8be6\u7ec6\u4ecb\u7ecdZ-score\u548cIQR\u65b9\u6cd5\uff0c\u5e76\u5bf9Z-score\u65b9\u6cd5\u8fdb\u884c\u8be6\u7ec6\u63cf\u8ff0\u3002<\/strong><\/p>\n<\/p>\n

Z-score\u65b9\u6cd5\u662f\u4e00\u79cd\u57fa\u4e8e\u6807\u51c6\u5dee\u7684\u79bb\u7fa4\u70b9\u68c0\u6d4b\u65b9\u6cd5\u3002\u5b83\u901a\u8fc7\u8ba1\u7b97\u6bcf\u4e2a\u6570\u636e\u70b9\u4e0e\u5747\u503c\u7684\u6807\u51c6\u5dee\u8ddd\u79bb\u6765\u8bc6\u522b\u79bb\u7fa4\u70b9\u3002\u5177\u4f53\u6765\u8bf4\uff0c\u5982\u679c\u4e00\u4e2a\u6570\u636e\u70b9\u7684Z-score\u8d85\u8fc7\u67d0\u4e2a\u9608\u503c\uff08\u901a\u5e38\u662f3\uff09\uff0c\u5219\u8ba4\u4e3a\u8be5\u70b9\u4e3a\u79bb\u7fa4\u70b9\u3002\u4f7f\u7528Z-score\u65b9\u6cd5\u7684\u4f18\u70b9\u662f\u7b80\u5355\u6613\u7528\uff0c\u5c24\u5176\u9002\u7528\u4e8e\u6570\u636e\u670d\u4ece\u6b63\u6001\u5206\u5e03\u7684\u60c5\u51b5\u3002<\/p>\n<\/p>\n

\n

\u4e00\u3001Z-SCORE\u65b9\u6cd5<\/h2>\n<\/p>\n

Z-score\u65b9\u6cd5\u662f\u4e00\u79cd\u7edf\u8ba1\u5b66\u4e2d\u5e38\u7528\u7684\u6807\u51c6\u5316\u65b9\u6cd5\uff0c\u7528\u4e8e\u68c0\u6d4b\u6570\u636e\u96c6\u4e2d\u7684\u79bb\u7fa4\u70b9\u3002Z-score\u7684\u8ba1\u7b97\u516c\u5f0f\u4e3a\uff1a<\/p>\n<\/p>\n

[ Z = \\frac{(X – \\mu)}{\\sigma} ]<\/p>\n<\/p>\n

\u5176\u4e2d\uff0c( X ) \u662f\u6570\u636e\u70b9\u7684\u503c\uff0c( \\mu ) \u662f\u6570\u636e\u7684\u5747\u503c\uff0c( \\sigma ) \u662f\u6570\u636e\u7684\u6807\u51c6\u5dee\u3002Z-score\u8868\u793a\u6570\u636e\u70b9\u8ddd\u79bb\u5747\u503c\u7684\u6807\u51c6\u5dee\u500d\u6570\u3002<\/p>\n<\/p>\n

1\u3001\u8ba1\u7b97\u5747\u503c\u4e0e\u6807\u51c6\u5dee<\/h3>\n<\/p>\n

\u5728\u4f7f\u7528Z-score\u65b9\u6cd5\u4e4b\u524d\uff0c\u9700\u8981\u8ba1\u7b97\u6570\u636e\u96c6\u7684\u5747\u503c\u548c\u6807\u51c6\u5dee\u3002\u8fd9\u4e24\u4e2a\u503c\u662f\u540e\u7eed\u8ba1\u7b97\u6bcf\u4e2a\u6570\u636e\u70b9\u7684Z-score\u7684\u57fa\u7840\u3002\u5728Python\u4e2d\uff0c\u53ef\u4ee5\u4f7f\u7528NumPy\u5e93\u6765\u65b9\u4fbf\u5730\u8ba1\u7b97\uff1a<\/p>\n<\/p>\n

import numpy as np<\/p>\n
data = [your_data_points]<\/p>\n
mean = np.mean(data)<\/p>\n
std_dev = np.std(data)<\/p>\n
<\/code><\/pre>\n<\/p>\n
2\u3001\u8ba1\u7b97Z-score\u5e76\u8bc6\u522b\u79bb\u7fa4\u70b9<\/h3>\n<\/p>\n
\u5728\u83b7\u5f97\u5747\u503c\u548c\u6807\u51c6\u5dee\u540e\uff0c\u63a5\u4e0b\u6765\u5c31\u662f\u8ba1\u7b97\u6bcf\u4e2a\u6570\u636e\u70b9\u7684Z-score\u3002\u901a\u5e38\uff0c\u7edd\u5bf9\u503c\u5927\u4e8e3\u7684Z-score\u88ab\u8ba4\u4e3a\u662f\u79bb\u7fa4\u70b9\uff1a<\/p>\n<\/p>\n
threshold = 3<\/p>\n
outliers = []<\/p>\n
for i in data:<\/p>\n
    z = (i - mean) \/ std_dev<\/p>\n
    if np.abs(z) > threshold:<\/p>\n
        outliers.append(i)<\/p>\n
<\/code><\/pre>\n<\/p>\n
3\u3001\u53bb\u9664\u79bb\u7fa4\u70b9<\/h3>\n<\/p>\n
\u8bc6\u522b\u51fa\u79bb\u7fa4\u70b9\u540e\uff0c\u5c31\u53ef\u4ee5\u4ece\u6570\u636e\u96c6\u4e2d\u53bb\u9664\u8fd9\u4e9b\u70b9\uff0c\u4ee5\u4fbf\u4e8e\u540e\u7eed\u7684\u6570\u636e\u5206\u6790\uff1a<\/p>\n<\/p>\n
cleaned_data = [i for i in data if i not in outliers]<\/p>\n
<\/code><\/pre>\n<\/p>\n
4\u3001\u5e94\u7528\u573a\u666f<\/h3>\n<\/p>\n
Z-score\u65b9\u6cd5\u9002\u7528\u4e8e\u6570\u636e\u670d\u4ece\u6b63\u6001\u5206\u5e03\u7684\u60c5\u51b5\uff0c\u7279\u522b\u662f\u5728\u6570\u636e\u70b9\u8f83\u591a\u65f6\u6548\u679c\u8f83\u597d\u3002\u5b83\u7b80\u5355\u6613\u7528\uff0c\u4e0d\u9700\u8981\u989d\u5916\u7684\u53c2\u6570\u8bbe\u5b9a\uff0c\u9002\u5408\u521d\u5b66\u8005\u548c\u5feb\u901f\u5904\u7406\u6570\u636e\u7684\u573a\u5408\u3002<\/p>\n<\/p>\n
\n
\u4e8c\u3001IQR\uff08\u56db\u5206\u4f4d\u8ddd\uff09\u65b9\u6cd5<\/h2>\n<\/p>\n
IQR\u65b9\u6cd5\u901a\u8fc7\u8ba1\u7b97\u6570\u636e\u96c6\u7684\u56db\u5206\u4f4d\u6570\u6765\u8bc6\u522b\u79bb\u7fa4\u70b9\u3002\u5b83\u901a\u8fc7\u8ba1\u7b97\u6570\u636e\u7684\u7b2c\u4e00\u56db\u5206\u4f4d\u6570\uff08Q1\uff09\u548c\u7b2c\u4e09\u56db\u5206\u4f4d\u6570\uff08Q3\uff09\uff0c\u7136\u540e\u8ba1\u7b97IQR\uff08Q3 – Q1\uff09\u3002\u4efb\u4f55\u5c0f\u4e8eQ1 – 1.5 * IQR\u6216\u5927\u4e8eQ3 + 1.5 * IQR\u7684\u6570\u636e\u70b9\u90fd\u88ab\u89c6\u4e3a\u79bb\u7fa4\u70b9\u3002<\/p>\n<\/p>\n
1\u3001\u8ba1\u7b97\u56db\u5206\u4f4d\u6570<\/h3>\n<\/p>\n
\u5728\u4f7f\u7528IQR\u65b9\u6cd5\u4e4b\u524d\uff0c\u9700\u8981\u8ba1\u7b97\u6570\u636e\u7684\u7b2c\u4e00\u548c\u7b2c\u4e09\u56db\u5206\u4f4d\u6570\u3002\u5728Python\u4e2d\uff0c\u53ef\u4ee5\u4f7f\u7528NumPy\u6216Pandas\u5e93\uff1a<\/p>\n<\/p>\n
import numpy as np<\/p>\n
data = [your_data_points]<\/p>\n
Q1 = np.percentile(data, 25)<\/p>\n
Q3 = np.percentile(data, 75)<\/p>\n
IQR = Q3 - Q1<\/p>\n
<\/code><\/pre>\n<\/p>\n
2\u3001\u8bc6\u522b\u79bb\u7fa4\u70b9<\/h3>\n<\/p>\n
\u6839\u636eIQR\u7684\u8ba1\u7b97\u7ed3\u679c\uff0c\u8bc6\u522b\u51fa\u79bb\u7fa4\u70b9\uff1a<\/p>\n<\/p>\n
lower_bound = Q1 - 1.5 * IQR<\/p>\n
upper_bound = Q3 + 1.5 * IQR<\/p>\n
outliers = [i for i in data if i < lower_bound or i > upper_bound]<\/p>\n
<\/code><\/pre>\n<\/p>\n
3\u3001\u53bb\u9664\u79bb\u7fa4\u70b9<\/h3>\n<\/p>\n
\u4e0eZ-score\u65b9\u6cd5\u7c7b\u4f3c\uff0c\u8bc6\u522b\u51fa\u79bb\u7fa4\u70b9\u540e\u53ef\u4ee5\u5c06\u5176\u4ece\u6570\u636e\u96c6\u4e2d\u53bb\u9664\uff1a<\/p>\n<\/p>\n
cleaned_data = [i for i in data if i >= lower_bound and i <= upper_bound]<\/p>\n
<\/code><\/pre>\n<\/p>\n
4\u3001\u5e94\u7528\u573a\u666f<\/h3>\n<\/p>\n
IQR\u65b9\u6cd5\u4e0d\u4f9d\u8d56\u6570\u636e\u7684\u5206\u5e03\u5f62\u5f0f\uff0c\u56e0\u6b64\u5bf9\u975e\u6b63\u6001\u5206\u5e03\u7684\u6570\u636e\u4e5f\u6709\u6548\u3002\u9002\u7528\u4e8e\u6570\u636e\u91cf\u8f83\u5927\u3001\u5206\u5e03\u590d\u6742\u7684\u6570\u636e\u96c6\uff0c\u662f\u5904\u7406\u5f02\u5e38\u503c\u7684\u5e38\u7528\u65b9\u6cd5\u4e4b\u4e00\u3002<\/p>\n<\/p>\n
\n
\u4e09\u3001\u4f7f\u7528\u53ef\u89c6\u5316\u5de5\u5177\u8bc6\u522b\u79bb\u7fa4\u70b9<\/h2>\n<\/p>\n
\u53ef\u89c6\u5316\u5de5\u5177\u662f\u4e00\u79cd\u76f4\u63a5\u4e14\u6709\u6548\u7684\u8bc6\u522b\u79bb\u7fa4\u70b9\u7684\u65b9\u6cd5\u3002\u5e38\u7528\u7684\u53ef\u89c6\u5316\u5de5\u5177\u5305\u62ec\u7bb1\u7ebf\u56fe\u548c\u6563\u70b9\u56fe\uff0c\u8fd9\u4e9b\u5de5\u5177\u80fd\u591f\u76f4\u89c2\u5730\u5c55\u793a\u6570\u636e\u5206\u5e03\uff0c\u4ece\u800c\u5e2e\u52a9\u8bc6\u522b\u79bb\u7fa4\u70b9\u3002<\/p>\n<\/p>\n
1\u3001\u7bb1\u7ebf\u56fe<\/h3>\n<\/p>\n
\u7bb1\u7ebf\u56fe\u901a\u8fc7\u663e\u793a\u6570\u636e\u7684\u56db\u5206\u4f4d\u6570\u3001\u6700\u5c0f\u503c\u548c\u6700\u5927\u503c\uff0c\u80fd\u591f\u76f4\u89c2\u5730\u5c55\u793a\u6570\u636e\u7684\u5206\u5e03\u60c5\u51b5\u548c\u79bb\u7fa4\u70b9\u3002\u5728Python\u4e2d\uff0c\u53ef\u4ee5\u4f7f\u7528Matplotlib\u6216Seaborn\u5e93\u7ed8\u5236\u7bb1\u7ebf\u56fe\uff1a<\/p>\n<\/p>\n
import matplotlib.pyplot as plt<\/p>\n
import seaborn as sns<\/p>\n
data = [your_data_points]<\/p>\n
plt.figure(figsize=(10, 6))<\/p>\n
sns.boxplot(data)<\/p>\n
plt.show()<\/p>\n
<\/code><\/pre>\n<\/p>\n
2\u3001\u6563\u70b9\u56fe<\/h3>\n<\/p>\n
\u6563\u70b9\u56fe\u901a\u8fc7\u5c55\u793a\u6570\u636e\u70b9\u7684\u5206\u5e03\uff0c\u80fd\u591f\u5e2e\u52a9\u8bc6\u522b\u79bb\u7fa4\u70b9\u7279\u522b\u662f\u5728\u4e8c\u7ef4\u6216\u4e09\u7ef4\u6570\u636e\u96c6\u4e2d\u7684\u79bb\u7fa4\u70b9\u3002\u5728Python\u4e2d\uff0c\u53ef\u4ee5\u4f7f\u7528Matplotlib\u5e93\u7ed8\u5236\u6563\u70b9\u56fe\uff1a<\/p>\n<\/p>\n
plt.figure(figsize=(10, 6))<\/p>\n
plt.scatter(range(len(data)), data)<\/p>\n
plt.show()<\/p>\n
<\/code><\/pre>\n<\/p>\n
3\u3001\u5e94\u7528\u573a\u666f<\/h3>\n<\/p>\n
\u53ef\u89c6\u5316\u5de5\u5177\u9002\u7528\u4e8e\u6570\u636e\u91cf\u9002\u4e2d\u4e14\u9700\u8981\u76f4\u89c2\u8bc6\u522b\u79bb\u7fa4\u70b9\u7684\u573a\u5408\u3002\u901a\u8fc7\u53ef\u89c6\u5316\u56fe\u5f62\uff0c\u80fd\u591f\u5feb\u901f\u8bc6\u522b\u6570\u636e\u4e2d\u7684\u5f02\u5e38\u503c\uff0c\u9002\u5408\u521d\u6b65\u6570\u636e\u5206\u6790\u548c\u63a2\u7d22\u3002<\/p>\n<\/p>\n
\n
\u56db\u3001DBSCAN\u805a\u7c7b\u7b97\u6cd5<\/h2>\n<\/p>\n
DBSCAN\uff08Density-Based Spatial Clustering of Applications with Noise\uff09\u662f\u4e00\u79cd\u57fa\u4e8e\u5bc6\u5ea6\u7684\u805a\u7c7b\u7b97\u6cd5\uff0c\u80fd\u591f\u6709\u6548\u5730\u8bc6\u522b\u79bb\u7fa4\u70b9\u3002DBSCAN\u901a\u8fc7\u5bc6\u5ea6\u805a\u7c7b\u7684\u65b9\u5f0f\uff0c\u5c06\u5bc6\u5ea6\u8f83\u4f4e\u7684\u70b9\u89c6\u4e3a\u566a\u58f0\u70b9\uff0c\u5373\u79bb\u7fa4\u70b9\u3002<\/p>\n<\/p>\n
1\u3001DBSCAN\u7b97\u6cd5\u539f\u7406<\/h3>\n<\/p>\n
DBSCAN\u7b97\u6cd5\u7684\u57fa\u672c\u601d\u60f3\u662f\u57fa\u4e8e\u5bc6\u5ea6\u7684\u533a\u57df\u6269\u5c55\u3002\u5b83\u901a\u8fc7\u5728\u6570\u636e\u7a7a\u95f4\u4e2d\u5bfb\u627e\u5bc6\u5ea6\u8f83\u9ad8\u7684\u533a\u57df\uff0c\u5c06\u8fd9\u4e9b\u533a\u57df\u4e2d\u7684\u70b9\u5f52\u4e3a\u4e00\u4e2a\u7c07\uff0c\u5e76\u5c06\u5bc6\u5ea6\u8f83\u4f4e\u7684\u70b9\u89c6\u4e3a\u566a\u58f0\u70b9\u3002<\/p>\n<\/p>\n
2\u3001\u4f7f\u7528DBSCAN\u8bc6\u522b\u79bb\u7fa4\u70b9<\/h3>\n<\/p>\n
\u5728Python\u4e2d\uff0c\u53ef\u4ee5\u4f7f\u7528Scikit-learn\u5e93\u4e2d\u7684DBSCAN\u5b9e\u73b0\u79bb\u7fa4\u70b9\u68c0\u6d4b\uff1a<\/p>\n<\/p>\n
from sklearn.cluster import DBSCAN<\/p>\n
import numpy as np<\/p>\n
data = np.array(your_data_points).reshape(-1, 1)<\/p>\n
db = DBSCAN(eps=0.5, min_samples=5).fit(data)<\/p>\n
labels = db.labels_<\/p>\n
-1\u6807\u7b7e\u8868\u793a\u566a\u58f0\u70b9\uff0c\u5373\u79bb\u7fa4\u70b9<\/strong><\/h2>\n
outliers = data[labels == -1]<\/p>\n
<\/code><\/pre>\n<\/p>\n
3\u3001\u53bb\u9664\u79bb\u7fa4\u70b9<\/h3>\n<\/p>\n
\u8bc6\u522b\u51fa\u79bb\u7fa4\u70b9\u540e\uff0c\u53ef\u4ee5\u5c06\u5176\u4ece\u6570\u636e\u96c6\u4e2d\u53bb\u9664\uff1a<\/p>\n<\/p>\n
cleaned_data = data[labels != -1]<\/p>\n
<\/code><\/pre>\n<\/p>\n
4\u3001\u5e94\u7528\u573a\u666f<\/h3>\n<\/p>\n
DBSCAN\u9002\u7528\u4e8e\u6570\u636e\u91cf\u5927\u4e14\u7ed3\u6784\u590d\u6742\u7684\u6570\u636e\u96c6\uff0c\u5c24\u5176\u5728\u975e\u7ebf\u6027\u5206\u5e03\u7684\u6570\u636e\u4e2d\u6548\u679c\u826f\u597d\u3002\u5b83\u4e0d\u9700\u8981\u6307\u5b9a\u7c07\u7684\u6570\u91cf\uff0c\u80fd\u591f\u81ea\u52a8\u8bc6\u522b\u79bb\u7fa4\u70b9\uff0c\u662f\u4e00\u79cd\u7075\u6d3b\u4e14\u5f3a\u5927\u7684\u805a\u7c7b\u7b97\u6cd5\u3002<\/p>\n<\/p>\n
\n
\u901a\u8fc7\u4ee5\u4e0a\u65b9\u6cd5\uff0c\u53ef\u4ee5\u5728Python\u4e2d\u6709\u6548\u5730\u53bb\u9664\u79bb\u7fa4\u70b9\uff0c\u4ece\u800c\u63d0\u9ad8\u6570\u636e\u5206\u6790\u7684\u51c6\u786e\u6027\u548c\u53ef\u9760\u6027\u3002\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0c\u53ef\u4ee5\u6839\u636e\u6570\u636e\u7684\u7279\u6027\u548c\u9700\u6c42\u9009\u62e9\u5408\u9002\u7684\u65b9\u6cd5\u8fdb\u884c\u79bb\u7fa4\u70b9\u68c0\u6d4b\u548c\u53bb\u9664\u3002<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
 \u5982\u4f55\u5224\u65ad\u54ea\u4e9b\u6570\u636e\u70b9\u662f\u79bb\u6563\u70b9\uff1f<\/strong>
\u79bb\u6563\u70b9\u901a\u5e38\u662f\u6307\u4e0e\u5176\u4ed6\u6570\u636e\u70b9\u76f8\u8ddd\u8f83\u8fdc\u7684\u70b9\u3002\u5728Python\u4e2d\uff0c\u53ef\u4ee5\u4f7f\u7528\u7edf\u8ba1\u65b9\u6cd5\u5982Z-score\u3001IQR\uff08\u56db\u5206\u4f4d\u8ddd\uff09\u6216\u673a\u5668\u5b66\u4e60<\/a>\u7b97\u6cd5\u5982\u5b64\u7acb\u68ee\u6797\u6765\u8bc6\u522b\u8fd9\u4e9b\u79bb\u6563\u70b9\u3002Z-score\u53ef\u4ee5\u901a\u8fc7\u8ba1\u7b97\u6bcf\u4e2a\u6570\u636e\u70b9\u4e0e\u6570\u636e\u96c6\u5747\u503c\u7684\u6807\u51c6\u5dee\u8ddd\u79bb\u6765\u8bc6\u522b\uff0c\u800cIQR\u5219\u901a\u8fc7\u8ba1\u7b97\u6570\u636e\u7684\u7b2c\u4e00\u548c\u7b2c\u4e09\u56db\u5206\u4f4d\u6570\u6765\u786e\u5b9a\u5f02\u5e38\u503c\u7684\u8303\u56f4\u3002<\/p>\n
\u4f7f\u7528Python\u53bb\u9664\u79bb\u6563\u70b9\u7684\u6700\u4f73\u5e93\u6709\u54ea\u4e9b\uff1f<\/strong>
\u5728Python\u4e2d\uff0c\u5e38\u7528\u7684\u5e93\u6709Pandas\u548cNumPy\u7528\u4e8e\u6570\u636e\u5904\u7406\uff0cSciPy\u63d0\u4f9b\u4e86\u7edf\u8ba1\u529f\u80fd\uff0c\u800cScikit-learn\u5219\u53ef\u7528\u4e8e\u5e94\u7528\u673a\u5668\u5b66\u4e60\u6a21\u578b\u6765\u68c0\u6d4b\u79bb\u6563\u70b9\u3002\u7ed3\u5408\u8fd9\u4e9b\u5e93\uff0c\u53ef\u4ee5\u6709\u6548\u5730\u8bc6\u522b\u548c\u53bb\u9664\u6570\u636e\u4e2d\u7684\u79bb\u6563\u70b9\u3002<\/p>\n
\u53bb\u9664\u79bb\u6563\u70b9\u540e\u6570\u636e\u7684\u5b8c\u6574\u6027\u662f\u5426\u4f1a\u53d7\u5230\u5f71\u54cd\uff1f<\/strong>
\u53bb\u9664\u79bb\u6563\u70b9\u53ef\u80fd\u4f1a\u5bf9\u6570\u636e\u96c6\u7684\u5b8c\u6574\u6027\u4ea7\u751f\u5f71\u54cd\uff0c\u5c24\u5176\u662f\u5f53\u8fd9\u4e9b\u70b9\u5b9e\u9645\u4e0a\u662f\u6709\u6548\u7684\u89c2\u6d4b\u503c\u65f6\u3002\u56e0\u6b64\uff0c\u5728\u53bb\u6389\u79bb\u6563\u70b9\u4e4b\u524d\uff0c\u5e94\u4ed4\u7ec6\u5206\u6790\u8fd9\u4e9b\u70b9\u7684\u6027\u8d28\uff0c\u5e76\u8003\u8651\u662f\u5426\u6709\u5fc5\u8981\u4fdd\u7559\u5b83\u4eec\u3002\u6267\u884c\u53bb\u9664\u64cd\u4f5c\u540e\uff0c\u5efa\u8bae\u8fdb\u884c\u6570\u636e\u53ef\u89c6\u5316\uff0c\u4ee5\u786e\u4fdd\u6570\u636e\u7684\u6574\u4f53\u7ed3\u6784\u548c\u8d8b\u52bf\u672a\u88ab\u7834\u574f\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u5728Python\u4e2d\u53bb\u9664\u79bb\u6563\u70b9\u7684\u65b9\u6cd5\u6709\u591a\u79cd\uff0c\u5e38\u7528\u7684\u5305\u62ec\uff1aZ-score\u65b9\u6cd5\u3001IQR\uff08\u56db\u5206\u4f4d\u8ddd\uff09\u65b9\u6cd5\u3001\u4f7f\u7528\u89c6\u89c9\u5316\u5de5\u5177 […]","protected":false},"author":3,"featured_media":1002847,"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\/1002838"}],"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=1002838"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1002838\/revisions"}],"predecessor-version":[{"id":1002852,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1002838\/revisions\/1002852"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1002847"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1002838"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1002838"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1002838"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}