{"id":1011774,"date":"2024-12-27T11:33:02","date_gmt":"2024-12-27T03:33:02","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1011774.html"},"modified":"2024-12-27T11:33:05","modified_gmt":"2024-12-27T03:33:05","slug":"python%e5%a6%82%e4%bd%95%e5%ae%9e%e7%8e%b0knn%e7%ae%97%e6%b3%95","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1011774.html","title":{"rendered":"python\u5982\u4f55\u5b9e\u73b0knn\u7b97\u6cd5"},"content":{"rendered":"

\"python\u5982\u4f55\u5b9e\u73b0knn\u7b97\u6cd5\"<\/p>\n

Python\u5b9e\u73b0KNN\u7b97\u6cd5\u7684\u65b9\u6cd5\u5305\u62ec\u4ee5\u4e0b\u51e0\u6b65\uff1a\u6570\u636e\u51c6\u5907\u3001\u8ba1\u7b97\u8ddd\u79bb\u3001\u9009\u62e9\u6700\u8fd1\u7684k\u4e2a\u90bb\u5c45\u3001\u8fdb\u884c\u6295\u7968\u9884\u6d4b\u3002<\/strong>\u5728\u8fd9\u4e9b\u6b65\u9aa4\u4e2d\uff0c\u9009\u62e9\u5408\u9002\u7684k\u503c<\/strong>\u662f\u975e\u5e38\u91cd\u8981\u7684\uff0c\u56e0\u4e3a\u5b83\u76f4\u63a5\u5f71\u54cd\u6a21\u578b\u7684\u6027\u80fd\u3002\u4e00\u822c\u6765\u8bf4\uff0ck\u503c\u8fc7\u5c0f\u53ef\u80fd\u5bfc\u81f4\u8fc7\u62df\u5408\uff0c\u800c\u8fc7\u5927\u5219\u53ef\u80fd\u5bfc\u81f4\u6b20\u62df\u5408\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u5c06\u8be6\u7ec6\u63a2\u8ba8\u6bcf\u4e00\u4e2a\u6b65\u9aa4\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u6570\u636e\u51c6\u5907<\/p>\n<\/p>\n

\u5728\u4f7f\u7528KNN\u7b97\u6cd5\u524d\uff0c\u9996\u5148\u9700\u8981\u51c6\u5907\u597d\u6570\u636e\u96c6\u3002\u901a\u5e38\uff0c\u6570\u636e\u96c6\u4f1a\u5206\u4e3a\u7279\u5f81\u548c\u6807\u7b7e\u4e24\u90e8\u5206\u3002\u7279\u5f81\u662f\u7528\u4e8e\u9884\u6d4b\u7684\u8f93\u5165\u6570\u636e\uff0c\u800c\u6807\u7b7e\u662f\u6211\u4eec\u5e0c\u671b\u9884\u6d4b\u7684\u8f93\u51fa\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Python\u4e2d\u7684\u5e93\u5982Pandas\u6765\u52a0\u8f7d\u548c\u5904\u7406\u6570\u636e\u3002<\/p>\n<\/p>\n

import pandas as pd<\/p>\n
\u52a0\u8f7d\u6570\u636e<\/strong><\/h2>\n
data = pd.read_csv('data.csv')<\/p>\n
\u5206\u79bb\u7279\u5f81\u548c\u6807\u7b7e<\/strong><\/h2>\n
X = data.drop('target', axis=1)<\/p>\n
y = data['target']<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u5904\u7406\u6570\u636e\u65f6\uff0c\u6807\u51c6\u5316\u662f\u4e00\u4e2a\u91cd\u8981\u7684\u6b65\u9aa4\uff0c\u56e0\u4e3aKNN\u7b97\u6cd5\u57fa\u4e8e\u8ddd\u79bb\u5ea6\u91cf\uff0c\u7279\u5f81\u7684\u91cf\u7eb2\u5dee\u5f02\u53ef\u80fd\u4f1a\u5f71\u54cd\u7ed3\u679c\u3002\u53ef\u4ee5\u4f7f\u7528Scikit-learn\u7684\u6807\u51c6\u5316\u65b9\u6cd5\uff1a<\/p>\n<\/p>\n
from sklearn.preprocessing import StandardScaler<\/p>\n
scaler = StandardScaler()<\/p>\n
X_scaled = scaler.fit_transform(X)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e8c\u3001\u8ba1\u7b97\u8ddd\u79bb<\/p>\n<\/p>\n
KNN\u7b97\u6cd5\u7684\u6838\u5fc3\u662f\u8ba1\u7b97\u6837\u672c\u70b9\u4e4b\u95f4\u7684\u8ddd\u79bb\u3002\u5e38\u7528\u7684\u8ddd\u79bb\u5ea6\u91cf\u65b9\u6cd5\u6709\u6b27\u6c0f\u8ddd\u79bb\u3001\u66fc\u54c8\u987f\u8ddd\u79bb\u7b49\u3002\u6b27\u6c0f\u8ddd\u79bb\u662f\u6700\u5e38\u7528\u7684\u65b9\u6cd5\uff0c\u8ba1\u7b97\u516c\u5f0f\u5982\u4e0b\uff1a<\/p>\n<\/p>\n
[<\/p>\n
d(x_i, x_j) = \\sqrt{\\sum_{k=1}^{n} (x_{ik} – x_{jk})^2}<\/p>\n
]<\/p>\n<\/p>\n
\u5728Python\u4e2d\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Numpy\u6765\u8ba1\u7b97\uff1a<\/p>\n<\/p>\n
import numpy as np<\/p>\n
def euclidean_distance(x1, x2):<\/p>\n
    return np.sqrt(np.sum((x1 - x2)  2))<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e09\u3001\u9009\u62e9\u6700\u8fd1\u7684k\u4e2a\u90bb\u5c45<\/p>\n<\/p>\n
\u5728\u8ba1\u7b97\u51fa\u6240\u6709\u6837\u672c\u70b9\u7684\u8ddd\u79bb\u540e\uff0c\u9700\u8981\u9009\u62e9\u8ddd\u79bb\u6700\u8fd1\u7684k\u4e2a\u90bb\u5c45\u3002\u8fd9\u53ef\u4ee5\u901a\u8fc7\u5bf9\u8ddd\u79bb\u6392\u5e8f\u6765\u5b9e\u73b0\u3002Python\u63d0\u4f9b\u4e86\u65b9\u4fbf\u7684\u6392\u5e8f\u65b9\u6cd5\uff1a<\/p>\n<\/p>\n
def get_k_neighbors(X_trAI<\/a>n, x_test, k):<\/p>\n
    distances = [euclidean_distance(x_test, x_train) for x_train in X_train]<\/p>\n
    sorted_indices = np.argsort(distances)<\/p>\n
    return sorted_indices[:k]<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u56db\u3001\u8fdb\u884c\u6295\u7968\u9884\u6d4b<\/p>\n<\/p>\n
\u6709\u4e86\u6700\u8fd1\u7684k\u4e2a\u90bb\u5c45\u4e4b\u540e\uff0c\u5c31\u53ef\u4ee5\u8fdb\u884c\u6295\u7968\u9884\u6d4b\u3002\u5bf9\u4e8e\u5206\u7c7b\u95ee\u9898\uff0cKNN\u901a\u8fc7\u9009\u62e9k\u4e2a\u90bb\u5c45\u4e2d\u51fa\u73b0\u9891\u7387\u6700\u9ad8\u7684\u7c7b\u522b\u4f5c\u4e3a\u9884\u6d4b\u7ed3\u679c\uff1b\u5bf9\u4e8e\u56de\u5f52\u95ee\u9898\uff0c\u5219\u662f\u8ba1\u7b97k\u4e2a\u90bb\u5c45\u7684\u5e73\u5747\u503c\u3002<\/p>\n<\/p>\n
from collections import Counter<\/p>\n
def predict(X_train, y_train, x_test, k):<\/p>\n
    neighbors = get_k_neighbors(X_train, x_test, k)<\/p>\n
    k_nearest_labels = [y_train[i] for i in neighbors]<\/p>\n
    return Counter(k_nearest_labels).most_common(1)[0][0]<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e94\u3001\u9009\u62e9\u5408\u9002\u7684k\u503c<\/p>\n<\/p>\n
\u9009\u62e9\u5408\u9002\u7684k\u503c\u662fKNN\u7b97\u6cd5\u7684\u4e00\u4e2a\u5173\u952e\u6b65\u9aa4\u3002\u4e00\u822c\u6765\u8bf4\uff0c\u53ef\u4ee5\u901a\u8fc7\u4ea4\u53c9\u9a8c\u8bc1\u6765\u9009\u62e9\u6700\u4f73\u7684k\u503c\u3002\u8f83\u5c0f\u7684k\u503c\u4f7f\u6a21\u578b\u5177\u6709\u8f83\u9ad8\u7684\u65b9\u5dee\uff0c\u8f83\u5927\u7684k\u503c\u5219\u964d\u4f4e\u6a21\u578b\u7684\u65b9\u5dee\uff0c\u4f46\u53ef\u80fd\u589e\u52a0\u504f\u5dee\u3002<\/p>\n<\/p>\n
from sklearn.model_selection import cross_val_score<\/p>\n
from sklearn.neighbors import KNeighborsClassifier<\/p>\n
def choose_best_k(X_train, y_train):<\/p>\n
    k_values = range(1, 30)<\/p>\n
    scores = []<\/p>\n
    for k in k_values:<\/p>\n
        knn = KNeighborsClassifier(n_neighbors=k)<\/p>\n
        score = cross_val_score(knn, X_train, y_train, cv=5)<\/p>\n
        scores.append(score.mean())<\/p>\n
    best_k = k_values[np.argmax(scores)]<\/p>\n
    return best_k<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u516d\u3001KNN\u7b97\u6cd5\u7684\u4f18\u52bf\u4e0e\u5c40\u9650\u6027<\/p>\n<\/p>\n
KNN\u7b97\u6cd5\u7b80\u5355\u6613\u61c2\u4e14\u6613\u4e8e\u5b9e\u73b0\uff0c\u5bf9\u4e8e\u5c0f\u89c4\u6a21\u6570\u636e\u96c6\u6548\u679c\u8f83\u597d\u3002\u7136\u800c\uff0c\u5b83\u4e5f\u6709\u4e00\u4e9b\u5c40\u9650\u6027\u3002\u4f8b\u5982\uff0cKNN\u5bf9\u9ad8\u7ef4\u6570\u636e\u8868\u73b0\u4e0d\u4f73\uff0c\u56e0\u4e3a\u968f\u7740\u7ef4\u5ea6\u589e\u52a0\uff0c\u6837\u672c\u95f4\u7684\u8ddd\u79bb\u53d8\u5f97\u4e0d\u518d\u6709\u533a\u5206\u5ea6\u3002\u6b64\u5916\uff0cKNN\u7684\u8ba1\u7b97\u590d\u6742\u5ea6\u8f83\u9ad8\uff0c\u5c24\u5176\u5728\u5927\u89c4\u6a21\u6570\u636e\u96c6\u4e0a\uff0c\u56e0\u4e3a\u9700\u8981\u8ba1\u7b97\u6bcf\u4e2a\u6837\u672c\u70b9\u7684\u8ddd\u79bb\u3002<\/p>\n<\/p>\n
\u4e03\u3001\u5e94\u7528\u4e0e\u4f18\u5316<\/p>\n<\/p>\n
KNN\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\u88ab\u5e7f\u6cdb\u7528\u4e8e\u6a21\u5f0f\u8bc6\u522b\u3001\u56fe\u50cf\u5206\u7c7b\u7b49\u9886\u57df\u3002\u4e3a\u4e86\u63d0\u9ad8KNN\u7684\u6027\u80fd\uff0c\u53ef\u4ee5\u8003\u8651\u4ee5\u4e0b\u4f18\u5316\u7b56\u7565\uff1a<\/p>\n<\/p>\n
    \n
  1. \u7ef4\u5ea6\u7f29\u51cf<\/strong>\uff1a\u901a\u8fc7PCA\u7b49\u65b9\u6cd5\u964d\u4f4e\u6570\u636e\u7684\u7ef4\u5ea6\uff0c\u4ee5\u51cf\u5c0f\u8ba1\u7b97\u590d\u6742\u5ea6\u3002<\/li>\n
  2. \u52a0\u6743KNN<\/strong>\uff1a\u4e3a\u90bb\u5c45\u8d4b\u4e88\u4e0d\u540c\u7684\u6743\u91cd\uff0c\u8ddd\u79bb\u8d8a\u8fd1\u7684\u90bb\u5c45\u6743\u91cd\u8d8a\u5927\uff0c\u4ee5\u63d0\u9ad8\u9884\u6d4b\u7684\u51c6\u786e\u6027\u3002<\/li>\n
  3. \u4f7f\u7528KD\u6811\u6216Ball\u6811<\/strong>\uff1a\u8fd9\u662f\u4e00\u79cd\u6570\u636e\u7ed3\u6784\u4f18\u5316\u65b9\u6cd5\uff0c\u7528\u4e8e\u52a0\u901f\u8ddd\u79bb\u8ba1\u7b97\u3002<\/li>\n
  4. \u7279\u5f81\u9009\u62e9<\/strong>\uff1a\u9009\u62e9\u6700\u5177\u4fe1\u606f\u91cf\u7684\u7279\u5f81\uff0c\u4ee5\u63d0\u9ad8\u6a21\u578b\u7684\u6027\u80fd\u3002<\/li>\n<\/ol>\n
    \u603b\u4e4b\uff0cKNN\u662f\u4e00\u79cd\u5f3a\u5927\u7684\u975e\u53c2\u6570\u5b66\u4e60\u7b97\u6cd5\uff0c\u9002\u7528\u4e8e\u591a\u79cd\u5e94\u7528\u573a\u666f\u3002\u901a\u8fc7\u5408\u7406\u7684\u6570\u636e\u9884\u5904\u7406\u3001\u53c2\u6570\u9009\u62e9\u548c\u4f18\u5316\u7b56\u7565\uff0c\u53ef\u4ee5\u663e\u8457\u63d0\u5347\u5176\u6027\u80fd\u3002<\/p>\n<\/p>\n
    \u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
     \u5982\u4f55\u5728Python\u4e2d\u5b9e\u73b0KNN\u7b97\u6cd5\uff1f<\/strong>
    \u8981\u5728Python\u4e2d\u5b9e\u73b0KNN\uff08K-Nearest Neighbors\uff09\u7b97\u6cd5\uff0c\u60a8\u53ef\u4ee5\u4f7f\u7528scikit-learn<\/code>\u5e93\uff0c\u8fd9\u662f\u4e00\u79cd\u6d41\u884c\u7684    \u673a\u5668\u5b66\u4e60<\/a>\u5e93\u3002\u60a8\u9700\u8981\u9996\u5148\u5b89\u88c5\u8be5\u5e93\uff0c\u7136\u540e\u5bfc\u5165\u6240\u9700\u7684\u6a21\u5757\uff0c\u51c6\u5907\u6570\u636e\u96c6\uff0c\u9009\u62e9K\u503c\uff0c\u8bad\u7ec3\u6a21\u578b\u5e76\u8fdb\u884c\u9884\u6d4b\u3002\u5177\u4f53\u6b65\u9aa4\u5305\u62ec\u52a0\u8f7d\u6570\u636e\u3001\u5206\u5272\u6570\u636e\u96c6\u3001\u521b\u5efaKNN\u6a21\u578b\u3001\u8bad\u7ec3\u6a21\u578b\u4ee5\u53ca\u4f7f\u7528\u6a21\u578b\u8fdb\u884c\u9884\u6d4b\u3002<\/p>\n
    KNN\u7b97\u6cd5\u9002\u7528\u4e8e\u54ea\u4e9b\u7c7b\u578b\u7684\u6570\u636e\uff1f<\/strong>
    KNN\u7b97\u6cd5\u9002\u7528\u4e8e\u5404\u79cd\u7c7b\u578b\u7684\u6570\u636e\uff0c\u5305\u62ec\u5206\u7c7b\u548c\u56de\u5f52\u95ee\u9898\u3002\u5b83\u7279\u522b\u9002\u5408\u5904\u7406\u5c0f\u578b\u6570\u636e\u96c6\uff0c\u7279\u522b\u662f\u5728\u7279\u5f81\u4e4b\u95f4\u6709\u660e\u663e\u7684\u76f8\u4f3c\u6027\u65f6\u3002\u5e38\u89c1\u7684\u5e94\u7528\u573a\u666f\u5305\u62ec\u56fe\u50cf\u8bc6\u522b\u3001\u63a8\u8350\u7cfb\u7edf\u548c\u5f02\u5e38\u68c0\u6d4b\u3002<\/p>\n
    \u5728\u4f7f\u7528KNN\u65f6\uff0c\u5982\u4f55\u9009\u62e9\u5408\u9002\u7684K\u503c\uff1f<\/strong>
    \u9009\u62e9\u5408\u9002\u7684K\u503c\u5bf9KNN\u7b97\u6cd5\u7684\u8868\u73b0\u81f3\u5173\u91cd\u8981\u3002\u8f83\u5c0f\u7684K\u503c\u53ef\u80fd\u5bfc\u81f4\u6a21\u578b\u5bf9\u566a\u58f0\u654f\u611f\uff0c\u800c\u8f83\u5927\u7684K\u503c\u53ef\u80fd\u4f1a\u5bfc\u81f4\u6a21\u578b\u8fc7\u4e8e\u5e73\u6ed1\uff0c\u4ece\u800c\u4e27\u5931\u5bf9\u6570\u636e\u7ec6\u8282\u7684\u654f\u611f\u6027\u3002\u5e38\u7528\u7684\u65b9\u6cd5\u662f\u4f7f\u7528\u4ea4\u53c9\u9a8c\u8bc1\u6765\u8bc4\u4f30\u4e0d\u540cK\u503c\u4e0b\u6a21\u578b\u7684\u6027\u80fd\uff0c\u901a\u5e38\u9009\u62e9\u80fd\u63d0\u4f9b\u6700\u4f73\u51c6\u786e\u7387\u7684K\u503c\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u5b9e\u73b0KNN\u7b97\u6cd5\u7684\u65b9\u6cd5\u5305\u62ec\u4ee5\u4e0b\u51e0\u6b65\uff1a\u6570\u636e\u51c6\u5907\u3001\u8ba1\u7b97\u8ddd\u79bb\u3001\u9009\u62e9\u6700\u8fd1\u7684k\u4e2a\u90bb\u5c45\u3001\u8fdb\u884c\u6295\u7968\u9884\u6d4b\u3002\u5728\u8fd9\u4e9b\u6b65\u9aa4 […]","protected":false},"author":3,"featured_media":1011785,"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\/1011774"}],"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=1011774"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1011774\/revisions"}],"predecessor-version":[{"id":1011789,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1011774\/revisions\/1011789"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1011785"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1011774"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1011774"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1011774"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}