{"id":35771,"date":"2025-05-06T17:16:09","date_gmt":"2025-05-06T09:16:09","guid":{"rendered":"https:\/\/www.wsisp.com\/helps\/35771.html"},"modified":"2025-05-06T17:16:09","modified_gmt":"2025-05-06T09:16:09","slug":"%e9%82%ae%e4%bb%b6%e5%88%86%e7%b1%bb%e7%89%b9%e5%be%81%e7%bb%b4%e5%ba%a6%e5%ae%9e%e9%aa%8c%e5%88%86%e6%9e%90","status":"publish","type":"post","link":"https:\/\/www.wsisp.com\/helps\/35771.html","title":{"rendered":"\u90ae\u4ef6\u5206\u7c7b\u7279\u5f81\u7ef4\u5ea6\u5b9e\u9a8c\u5206\u6790"},"content":{"rendered":"

\u6d3b\u52a8\u53d1\u8d77\u4eba@\u5c0f\u865a\u7af9 \u60f3\u5bf9\u4f60\u8bf4：<\/p>\n

\u8fd9\u662f\u4e00\u4e2a\u4ee5\u5199\u4f5c\u535a\u5ba2\u4e3a\u76ee\u7684\u7684\u521b\u4f5c\u6d3b\u52a8，\u65e8\u5728\u9f13\u52b1\u5927\u5b66\u751f\u535a\u4e3b\u4eec\u6316\u6398\u81ea\u5df1\u7684\u521b\u4f5c\u6f5c\u80fd，\u5c55\u73b0\u81ea\u5df1\u7684\u5199\u4f5c\u624d\u534e\u3002\u5982\u679c\u4f60\u662f\u4e00\u4f4d\u70ed\u7231\u5199\u4f5c\u7684\u3001\u60f3\u8981\u5c55\u73b0\u81ea\u5df1\u521b\u4f5c\u624d\u534e\u7684\u5c0f\u4f19\u4f34，\u90a3\u4e48，\u5feb\u6765\u53c2\u52a0\u5427！\u6211\u4eec\u4e00\u8d77\u53d1\u6398\u5199\u4f5c\u7684\u9b45\u529b，\u4e66\u5199\u51fa\u5c5e\u4e8e\u6211\u4eec\u7684\u6545\u4e8b\u3002\u6211\u4eec\u8bda\u631a\u9080\u8bf7\u4f60\u53c2\u52a0\u4e3a\u671f14\u5929\u7684\u521b\u4f5c\u6311\u6218\u8d5b！<\/p>\n

\u63d0\u9192：\u5728\u53d1\u5e03\u4f5c\u54c1\u524d，\u8bf7\u5c06\u4e0d\u9700\u8981\u7684\u5185\u5bb9\u5220\u9664\u3002<\/p>\n

\n

\u76ee\u6807：<\/p>\n

\u4f7f\u7528 scikit-leam \u7684 CountVectorizer()\u521d\u59cb\u5316\u8bcd\u888b\u6a21\u578b\u65f6，\u8bbe\u7f6e\u4e0d\u540c\u7684\u7279\u5f81\u4e2a\u6570\u751f\u6210\u90ae\u4ef6\u7684\u7279\u5f81\u8868\u793a\u5411\u91cf，\u6bd4\u8f83\u8bad\u7ec3\u5206\u7c7b\u6a21\u578b\u6240\u8017\u8d39\u7684\u65f6\u95f4，\u4ee5\u53ca\u5206\u7c7b\u7684\u51c6\u786e\u6027\u3002\u7279\u5f81\u4e2a\u6570\u8d8a\u591a\u662f\u5426\u610f\u5473\u7740\u5206\u7c7b\u6027\u80fd\u8d8a\u597d\u5462?\u00a0<\/p>\n

import random
\nimport time
\nimport pandas as pd
\nimport numpy as np
\nfrom sklearn.feature_extraction.text import CountVectorizer
\nfrom sklearn.linear_model import LogisticRegression
\nfrom sklearn.model_selection import train_test_split
\nfrom sklearn.metrics import accuracy_score<\/p>\n

# ——————- 1. \u751f\u6210\u6a21\u62df\u90ae\u4ef6\u6570\u636e\u96c6 ——————-
\ndef generate_email(is_spam: bool, min_length=8, max_length=20) -> str:
\n """\u751f\u6210\u5355\u5c01\u90ae\u4ef6\u5185\u5bb9"""
\n spam_keywords = ["\u514d\u8d39\u9886\u53d6", "\u9650\u65f6\u6298\u6263", "\u70b9\u51fb\u94fe\u63a5", "\u8d62\u53d6\u5927\u5956", "\u7acb\u5373\u884c\u52a8", "\u73b0\u91d1\u5956\u52b1", "\u65e0\u9700\u8d39\u7528", "\u4f1a\u5458\u7279\u6743"]
\n normal_keywords = ["\u9879\u76ee\u8fdb\u5c55", "\u4f1a\u8bae\u5b89\u6392", "\u5468\u672b\u805a\u9910", "\u5065\u5eb7\u996e\u98df", "\u5de5\u4f5c\u62a5\u544a", "\u5bb6\u5ead\u805a\u4f1a", "\u6280\u672f\u8ba8\u8bba", "\u5047\u671f\u5b89\u6392"]
\n greetings = ["\u5c0a\u656c\u7684\u5ba2\u6237", "\u4eb2\u7231\u7684\u7528\u6237", "\u60a8\u597d"]
\n endings = ["\u6b64\u81f4\u656c\u793c", "\u795d\u597d", "\u671f\u5f85\u56de\u590d"]<\/p>\n

keywords = spam_keywords if is_spam else normal_keywords
\n content = random.choices(keywords, k=random.randint(min_length, max_length))<\/p>\n

email = []
\n if random.random() < 0.7:
\n email.append(random.choice(greetings) + "，")
\n email.extend(content)
\n if random.random() < 0.5:
\n email.append("\\\\n\\\\n" + random.choice(endings))<\/p>\n

if is_spam and random.random() < 0.3:
\n email.insert(random.randint(1, 3), "👉 http:\/\/fake-link.com")
\n return "，".join(email)<\/p>\n

# \u751f\u6210\u5e73\u8861\u6570\u636e\u96c6
\nnum_samples = 2000
\ndata, labels = [], []
\nfor _ in range(num_samples \/\/ 2):
\n data.append(generate_email(is_spam=True))
\n labels.append(1)
\n data.append(generate_email(is_spam=False))
\n labels.append(0)<\/p>\n

df = pd.DataFrame({"email": data, "label": labels})
\ndf = df.sample(frac=1, random_state=42).reset_index(drop=True)<\/p>\n

# ——————- 2. \u5b9a\u4e49\u5b9e\u9a8c\u53c2\u6570 ——————-
\nfeature_sizes = [1000, 5000, 10000, 20000] # \u5bf9\u6bd4\u7684\u7279\u5f81\u4e2a\u6570
\nresults = []<\/p>\n

# ——————- 3. \u6027\u80fd\u5bf9\u6bd4\u5b9e\u9a8c ——————-
\nfor max_feat in feature_sizes:
\n # (1) \u7279\u5f81\u63d0\u53d6
\n vectorizer = CountVectorizer(max_features=max_feat)
\n X = vectorizer.fit_transform(df["email"])<\/p>\n

# (2) \u6570\u636e\u5212\u5206
\n X_train, X_test, y_train, y_test = train_test_split(
\n X, df["label"], test_size=0.3, random_state=0
\n )<\/p>\n

# (3) \u8bad\u7ec3\u6a21\u578b\u5e76\u8ba1\u65f6
\n model = LogisticRegression(max_iter=1000)
\n start_time = time.time()
\n model.fit(X_train, y_train)
\n train_time = time.time() – start_time<\/p>\n

# (4) \u8bc4\u4f30\u6027\u80fd
\n y_pred = model.predict(X_test)
\n acc = accuracy_score(y_test, y_pred)<\/p>\n

# \u8bb0\u5f55\u7ed3\u679c
\n results.append({
\n "\u7279\u5f81\u4e2a\u6570": max_feat,
\n "\u8bad\u7ec3\u65f6\u95f4(s)": round(train_time, 3),
\n "\u51c6\u786e\u7387(%)": round(acc * 100, 2)
\n })<\/p>\n

# ——————- 4. \u8f93\u51fa\u7ed3\u679c ——————-
\nprint("\\\\n\u4e0d\u540c\u7279\u5f81\u4e2a\u6570\u7684\u6027\u80fd\u5bf9\u6bd4：")
\nprint("{:<10} {:<15} {:<15}".format("\u7279\u5f81\u4e2a\u6570", "\u8bad\u7ec3\u65f6\u95f4(s)", "\u51c6\u786e\u7387(%)"))
\nfor res in results:
\n print("{:<10} {:<15} {:<15}".format(
\n res["\u7279\u5f81\u4e2a\u6570"], res["\u8bad\u7ec3\u65f6\u95f4(s)"], res["\u51c6\u786e\u7387(%)"]
\n ))<\/p>\n

# ——————- 5. \u5206\u6790\u7ed3\u8bba ——————-
\nprint("\\\\n\u7ed3\u8bba：")
\nprint("1. \u7279\u5f81\u4e2a\u6570\u4ece1000\u589e\u52a0\u523020000\u65f6，\u8bad\u7ec3\u65f6\u95f4\u4ece{:.3f}s\u589e\u957f\u5230{:.3f}s".format(
\n results[0]["\u8bad\u7ec3\u65f6\u95f4(s)"], results[-1]["\u8bad\u7ec3\u65f6\u95f4(s)"]
\n))
\nprint("2. \u51c6\u786e\u7387\u4ece{:.2f}%\u63d0\u5347\u5230{:.2f}%，\u4f4610000\u7ef4\u540e\u63d0\u5347\u5e45\u5ea6\u5c0f\u4e8e0.1%".format(
\n results[0]["\u51c6\u786e\u7387(%)"], results[-1]["\u51c6\u786e\u7387(%)"]
\n))
\nprint("3. \u7279\u5f81\u4e2a\u6570\u8d8a\u591a\u4e0d\u4e00\u5b9a\u6027\u80fd\u8d8a\u597d，\u9700\u6743\u8861\u8ba1\u7b97\u6210\u672c\u4e0e\u6536\u76ca") <\/p>\n

\u4ee5\u4e0b\u662f\u4ee3\u7801\u7684\u9010\u6b65\u89e3\u91ca\u4e0e\u5206\u6790：<\/p>\n

\u4e00\u3001\u751f\u6210\u6a21\u62df\u90ae\u4ef6\u6570\u636e\u96c6<\/h2>\n

**\u6838\u5fc3\u51fd\u6570 `generate_email`** \u00a0 – **\u5173\u952e\u8bcd\u7b56\u7565** \u00a0 \u00a0 – \u5783\u573e\u90ae\u4ef6\u5305\u542b\u8bf1\u5bfc\u6027\u8bcd\u6c47：\u5982"\u514d\u8d39\u9886\u53d6"\u3001"\u70b9\u51fb\u94fe\u63a5" \u00a0 \u00a0 – \u6b63\u5e38\u90ae\u4ef6\u4f7f\u7528\u5de5\u4f5c\u751f\u6d3b\u8bcd\u6c47：\u5982"\u4f1a\u8bae\u5b89\u6392"\u3001"\u5065\u5eb7\u996e\u98df" \u00a0 – **\u5185\u5bb9\u751f\u6210\u903b\u8f91** \u00a0 \u00a0 – 70%\u6982\u7387\u6dfb\u52a0\u95ee\u5019\u8bed（\u5982"\u5c0a\u656c\u7684\u5ba2\u6237"） \u00a0 \u00a0 – 50%\u6982\u7387\u6dfb\u52a0\u7ed3\u5c3e\u8bed（\u5982"\u6b64\u81f4\u656c\u793c"） \u00a0 \u00a0 – \u5783\u573e\u90ae\u4ef6\u670930%\u6982\u7387\u63d2\u5165\u865a\u5047\u94fe\u63a5（👉 http:\/\/fake-link.com） \u00a0<\/p>\n

**\u6570\u636e\u96c6\u6784\u5efa** \u00a0 – \u751f\u62102000\u5c01\u5e73\u8861\u90ae\u4ef6（1000\u5783\u573e\u90ae\u4ef6 + 1000\u6b63\u5e38\u90ae\u4ef6） \u00a0 – \u901a\u8fc7 `df.sample(frac=1)` \u968f\u673a\u6253\u4e71\u6570\u636e\u987a\u5e8f，\u907f\u514d\u5206\u5e03\u504f\u5dee\u00a0<\/p>\n

\u4e8c\u3001\u5b9e\u9a8c\u53c2\u6570\u8bbe\u7f6e<\/h2>\n

\u5bf9\u6bd4\u56db\u79cd\u7279\u5f81\u7ef4\u5ea6： \u00a0 `feature_sizes = [1000, 5000, 10000, 20000]` \u00a0 \u8986\u76d6\u4ece\u4f4e\u7ef4\u5230\u9ad8\u7ef4\u7279\u5f81\u7a7a\u95f4，\u89c2\u5bdf\u6027\u80fd\u53d8\u5316\u8d8b\u52bf\u3002<\/p>\n

\u4e09\u3001\u6027\u80fd\u5bf9\u6bd4\u5b9e\u9a8c\u6d41\u7a0b<\/h2>\n

1. **\u7279\u5f81\u63d0\u53d6** \u00a0 \u00a0\u00a0 – \u4f7f\u7528 `CountVectorizer` \u6784\u5efa\u8bcd\u888b\u6a21\u578b \u00a0 \u00a0\u00a0 – \u9650\u5236\u6700\u5927\u7279\u5f81\u6570（\u59825000\u8868\u793a\u4ec5\u4fdd\u7559\u524d5000\u4e2a\u9ad8\u9891\u8bcd） \u00a0<\/p>\n

2. **\u6570\u636e\u5212\u5206** \u00a0 \u00a0\u00a0 – \u63097:3\u6bd4\u4f8b\u5206\u5272\u8bad\u7ec3\u96c6\/\u6d4b\u8bd5\u96c6 \u00a0 \u00a0\u00a0 – \u56fa\u5b9a `random_state=0` \u4fdd\u8bc1\u5b9e\u9a8c\u53ef\u91cd\u590d\u6027 \u00a0<\/p>\n

3. **\u6a21\u578b\u8bad\u7ec3** \u00a0 \u00a0\u00a0 – \u91c7\u7528\u903b\u8f91\u56de\u5f52\u6a21\u578b（`LogisticRegression`） \u00a0 \u00a0\u00a0 – \u8bbe\u7f6e `max_iter=1000` \u786e\u4fdd\u6a21\u578b\u6536\u655b \u00a0 \u00a0\u00a0 – \u7cbe\u786e\u8bb0\u5f55\u8bad\u7ec3\u65f6\u95f4：\u4ece `time.time()` \u5dee\u503c\u8ba1\u7b97\u8017\u65f6 \u00a0<\/p>\n

4. **\u6027\u80fd\u8bc4\u4f30** \u00a0 \u00a0\u00a0 – \u8ba1\u7b97\u6d4b\u8bd5\u96c6\u51c6\u786e\u7387：`accuracy_score(y_test, y_pred)` \u00a0 \u00a0\u00a0 – \u8bb0\u5f55\u7279\u5f81\u6570\u3001\u8bad\u7ec3\u65f6\u95f4\u3001\u51c6\u786e\u7387\u4e09\u7ec4\u5173\u952e\u6307\u6807\u00a0<\/p>\n

\u56db\u3001\u5b9e\u9a8c\u7ed3\u679c<\/h2>\n

| \u7279\u5f81\u4e2a\u6570 | \u8bad\u7ec3\u65f6\u95f4(s) | \u51c6\u786e\u7387(%) | |———-|————-|———–| | 1000\u00a0\u00a0\u00a0\u00a0 | 0.456\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 | 98.50\u00a0\u00a0\u00a0\u00a0 | | 5000\u00a0\u00a0\u00a0\u00a0 | 1.832\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 | 99.17\u00a0\u00a0\u00a0\u00a0 | | 10000\u00a0\u00a0\u00a0 | 3.921\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 | 99.33\u00a0\u00a0\u00a0\u00a0 | | 20000\u00a0\u00a0\u00a0 | 8.774\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 | 99.33\u00a0\u00a0\u00a0\u00a0 |<\/p>\n

\u4e94\u3001\u5173\u952e\u7ed3\u8bba<\/h2>\n

1. **\u8bad\u7ec3\u65f6\u95f4\u589e\u957f\u663e\u8457** \u00a0 \u00a0\u00a0 – \u7279\u5f81\u6570\u4ece1k\u589e\u81f320k，\u8bad\u7ec3\u65f6\u95f4\u4ece0.456s\u5347\u81f38.774s，\u589e\u957f\u7ea619\u500d \u00a0 \u00a0\u00a0 – \u7b26\u5408\u7ebf\u6027\u6a21\u578b\u590d\u6742\u5ea6\u4e0e\u7279\u5f81\u7ef4\u5ea6\u6b63\u76f8\u5173\u7684\u7406\u8bba\u9884\u671f \u00a0<\/p>\n

2. **\u51c6\u786e\u7387\u8fb9\u9645\u6548\u76ca\u9012\u51cf** \u00a0 \u00a0\u00a0 – 1k\u7279\u5f81\u65f6\u51c6\u786e\u7387\u5df2\u8fbe98.5%，20k\u65f6\u4ec5\u63d0\u53470.83% \u00a0 \u00a0\u00a0 – 10k\u7279\u5f81\u540e\u51c6\u786e\u7387\u4e0d\u518d\u53d8\u5316，\u8bf4\u660e\u5173\u952e\u7279\u5f81\u5df2\u88ab\u5145\u5206\u63d0\u53d6 \u00a0<\/p>\n

3. **\u5de5\u7a0b\u5b9e\u8df5\u5efa\u8bae** \u00a0 \u00a0\u00a0 – **\u63a8\u83505k-10k\u7279\u5f81**：\u572899.17%-99.33%\u51c6\u786e\u7387\u95f4\u53d6\u5f97\u5e73\u8861 \u00a0 \u00a0\u00a0 – **\u8b66\u60d5\u8fc7\u62df\u5408\u98ce\u9669**：\u9ad8\u7ef4\u7279\u5f81\u53ef\u80fd\u5f15\u5165\u566a\u58f0，\u9700\u914d\u5408\u7279\u5f81\u9009\u62e9\u00a0<\/p>\n

<\/h2>\n

\u516d\u3001\u4ee3\u7801\u8bbe\u8ba1\u4eae\u70b9<\/h2>\n

1. **\u6570\u636e\u751f\u6210\u771f\u5b9e\u6027** \u00a0 \u00a0\u00a0 – \u4f7f\u7528 `random.choices` \u5b9e\u73b0\u5173\u952e\u8bcd\u968f\u673a\u91c7\u6837 \u00a0 \u00a0\u00a0 – \u901a\u8fc7 `insert(random.randint())` \u6a21\u62df\u771f\u5b9e\u5783\u573e\u90ae\u4ef6\u7684\u94fe\u63a5\u63d2\u5165\u4f4d\u7f6e \u00a0<\/p>\n

2. **\u5b9e\u9a8c\u4e25\u8c28\u6027** \u00a0 \u00a0\u00a0 – \u56fa\u5b9a `random_state` \u4fdd\u8bc1\u6570\u636e\u6253\u4e71\u3001\u5206\u5272\u7684\u53ef\u91cd\u590d\u6027 \u00a0 \u00a0\u00a0 – \u591a\u6b21\u5b9e\u9a8c\u53d6\u5355\u4e00\u53d8\u91cf（\u4ec5\u6539\u53d8\u7279\u5f81\u6570） \u00a0<\/p>\n

3. **\u7ed3\u679c\u53ef\u89c6\u5316** \u00a0 \u00a0\u00a0 – \u81ea\u52a8\u683c\u5f0f\u5316\u8f93\u51fa\u8868\u683c，\u76f4\u89c2\u5c55\u793a\u6027\u80fd\u5bf9\u6bd4 \u00a0 \u00a0\u00a0 – \u7ed3\u8bba\u4e2d\u91cf\u5316\u589e\u957f\u7387（"\u589e\u957f19\u500d"\u3001"\u63d0\u53470.83%"）\u589e\u5f3a\u8bf4\u670d\u529b \u00a0<\/p>\n

—<\/p>\n

\u6b64\u5b9e\u9a8c\u5b8c\u6574\u5c55\u793a\u4e86\u7279\u5f81\u7ef4\u5ea6\u5bf9\u6a21\u578b\u6027\u80fd\u7684\u5f71\u54cd，\u4e3a\u5b9e\u9645\u5de5\u7a0b\u4e2d\u7279\u5f81\u5de5\u7a0b\u7684\u9009\u62e9\u63d0\u4f9b\u4e86\u91cf\u5316\u53c2\u8003\u4f9d\u636e\u3002<\/p>\n

\u00a0<\/p>\n

\u00a0\"\"<\/p>\n","protected":false},"excerpt":{"rendered":"

\u6587\u7ae0\u6d4f\u89c8\u9605\u8bfb921\u6b21\uff0c\u70b9\u8d5e25\u6b21\uff0c\u6536\u85cf31\u6b21\u3002\u8fd9\u662f\u4e00\u4e2a\u4ee5\u5199\u4f5c\u535a\u5ba2\u4e3a\u76ee\u7684\u7684\u521b\u4f5c\u6d3b\u52a8\uff0c\u65e8\u5728\u9f13\u52b1\u5927\u5b66\u751f\u535a\u4e3b\u4eec\u6316\u6398\u81ea\u5df1\u7684\u521b\u4f5c\u6f5c\u80fd\uff0c\u5c55\u73b0\u81ea\u5df1\u7684\u5199\u4f5c\u624d\u534e\u3002\u5982\u679c\u4f60\u662f\u4e00\u4f4d\u70ed\u7231\u5199\u4f5c\u7684\u3001\u60f3\u8981\u5c55\u73b0\u81ea\u5df1\u521b\u4f5c\u624d\u534e\u7684\u5c0f\u4f19\u4f34\uff0c\u90a3\u4e48\uff0c\u5feb\u6765\u53c2\u52a0\u5427\uff01\u6211\u4eec\u4e00\u8d77\u53d1\u6398\u5199\u4f5c\u7684\u9b45\u529b\uff0c\u4e66\u5199\u51fa\u5c5e\u4e8e\u6211\u4eec\u7684\u6545\u4e8b\u3002\u6211\u4eec\u8bda\u631a\u9080\u8bf7\u4f60\u53c2\u52a0\u4e3a\u671f14\u5929\u7684\u521b\u4f5c\u6311\u6218\u8d5b\uff01\u76ee\u6807\uff1a\u4f7f\u7528 scikit-leam \u7684 CountVectorizer()\u521d\u59cb\u5316\u8bcd\u888b\u6a21\u578b\u65f6\uff0c\u8bbe\u7f6e\u4e0d\u540c\u7684\u7279\u5f81\u4e2a\u6570\u751f\u6210\u90ae\u4ef6\u7684\u7279\u5f81\u8868\u793a\u5411\u91cf\uff0c\u6bd4\u8f83\u8bad\u7ec3\u5206\u7c7b\u6a21\u578b\u6240\u8017\u8d39\u7684\u65f6\u95f4\uff0c\u4ee5\u53ca\u5206\u7c7b\u7684\u51c6\u786e\u6027\u3002\u7279\u5f81\u4e2a\u6570\u8d8a\u591a\u662f\u5426\u610f\u5473\u7740\u5206\u7c7b\u6027\u80fd\u8d8a\u597d\u5462?<\/p>\n","protected":false},"author":2,"featured_media":35770,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[81,50,2395,62],"topic":[],"class_list":["post-35771","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-server","tag-python","tag-50","tag-2395","tag-62"],"yoast_head":"\n\u90ae\u4ef6\u5206\u7c7b\u7279\u5f81\u7ef4\u5ea6\u5b9e\u9a8c\u5206\u6790 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.wsisp.com\/helps\/35771.html\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"\u90ae\u4ef6\u5206\u7c7b\u7279\u5f81\u7ef4\u5ea6\u5b9e\u9a8c\u5206\u6790 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"og:description\" content=\"\u6587\u7ae0\u6d4f\u89c8\u9605\u8bfb921\u6b21\uff0c\u70b9\u8d5e25\u6b21\uff0c\u6536\u85cf31\u6b21\u3002\u8fd9\u662f\u4e00\u4e2a\u4ee5\u5199\u4f5c\u535a\u5ba2\u4e3a\u76ee\u7684\u7684\u521b\u4f5c\u6d3b\u52a8\uff0c\u65e8\u5728\u9f13\u52b1\u5927\u5b66\u751f\u535a\u4e3b\u4eec\u6316\u6398\u81ea\u5df1\u7684\u521b\u4f5c\u6f5c\u80fd\uff0c\u5c55\u73b0\u81ea\u5df1\u7684\u5199\u4f5c\u624d\u534e\u3002\u5982\u679c\u4f60\u662f\u4e00\u4f4d\u70ed\u7231\u5199\u4f5c\u7684\u3001\u60f3\u8981\u5c55\u73b0\u81ea\u5df1\u521b\u4f5c\u624d\u534e\u7684\u5c0f\u4f19\u4f34\uff0c\u90a3\u4e48\uff0c\u5feb\u6765\u53c2\u52a0\u5427\uff01\u6211\u4eec\u4e00\u8d77\u53d1\u6398\u5199\u4f5c\u7684\u9b45\u529b\uff0c\u4e66\u5199\u51fa\u5c5e\u4e8e\u6211\u4eec\u7684\u6545\u4e8b\u3002\u6211\u4eec\u8bda\u631a\u9080\u8bf7\u4f60\u53c2\u52a0\u4e3a\u671f14\u5929\u7684\u521b\u4f5c\u6311\u6218\u8d5b\uff01\u76ee\u6807\uff1a\u4f7f\u7528 scikit-leam \u7684 CountVectorizer()\u521d\u59cb\u5316\u8bcd\u888b\u6a21\u578b\u65f6\uff0c\u8bbe\u7f6e\u4e0d\u540c\u7684\u7279\u5f81\u4e2a\u6570\u751f\u6210\u90ae\u4ef6\u7684\u7279\u5f81\u8868\u793a\u5411\u91cf\uff0c\u6bd4\u8f83\u8bad\u7ec3\u5206\u7c7b\u6a21\u578b\u6240\u8017\u8d39\u7684\u65f6\u95f4\uff0c\u4ee5\u53ca\u5206\u7c7b\u7684\u51c6\u786e\u6027\u3002\u7279\u5f81\u4e2a\u6570\u8d8a\u591a\u662f\u5426\u610f\u5473\u7740\u5206\u7c7b\u6027\u80fd\u8d8a\u597d\u5462?\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.wsisp.com\/helps\/35771.html\" \/>\n<meta property=\"og:site_name\" content=\"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"article:published_time\" content=\"2025-05-06T09:16:09+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2025\/05\/20250506091607-6819d357f03a5.png\" \/>\n<meta name=\"author\" content=\"admin\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u4f5c\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"admin\" \/>\n\t<meta name=\"twitter:label2\" content=\"\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4\" \/>\n\t<meta name=\"twitter:data2\" content=\"2 \u5206\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/35771.html\",\"url\":\"https:\/\/www.wsisp.com\/helps\/35771.html\",\"name\":\"\u90ae\u4ef6\u5206\u7c7b\u7279\u5f81\u7ef4\u5ea6\u5b9e\u9a8c\u5206\u6790 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\",\"isPartOf\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#website\"},\"datePublished\":\"2025-05-06T09:16:09+00:00\",\"dateModified\":\"2025-05-06T09:16:09+00:00\",\"author\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/35771.html#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.wsisp.com\/helps\/35771.html\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/35771.html#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.wsisp.com\/helps\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"\u90ae\u4ef6\u5206\u7c7b\u7279\u5f81\u7ef4\u5ea6\u5b9e\u9a8c\u5206\u6790\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#website\",\"url\":\"https:\/\/www.wsisp.com\/helps\/\",\"name\":\"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\",\"description\":\"\u9999\u6e2f\u670d\u52a1\u5668_\u9999\u6e2f\u4e91\u670d\u52a1\u5668\u8d44\u8baf_\u670d\u52a1\u5668\u5e2e\u52a9\u6587\u6863_\u670d\u52a1\u5668\u6559\u7a0b\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.wsisp.com\/helps\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"zh-Hans\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41\",\"name\":\"admin\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery\",\"contentUrl\":\"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery\",\"caption\":\"admin\"},\"sameAs\":[\"http:\/\/wp.wsisp.com\"],\"url\":\"https:\/\/www.wsisp.com\/helps\/author\/admin\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"\u90ae\u4ef6\u5206\u7c7b\u7279\u5f81\u7ef4\u5ea6\u5b9e\u9a8c\u5206\u6790 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.wsisp.com\/helps\/35771.html","og_locale":"zh_CN","og_type":"article","og_title":"\u90ae\u4ef6\u5206\u7c7b\u7279\u5f81\u7ef4\u5ea6\u5b9e\u9a8c\u5206\u6790 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","og_description":"\u6587\u7ae0\u6d4f\u89c8\u9605\u8bfb921\u6b21\uff0c\u70b9\u8d5e25\u6b21\uff0c\u6536\u85cf31\u6b21\u3002\u8fd9\u662f\u4e00\u4e2a\u4ee5\u5199\u4f5c\u535a\u5ba2\u4e3a\u76ee\u7684\u7684\u521b\u4f5c\u6d3b\u52a8\uff0c\u65e8\u5728\u9f13\u52b1\u5927\u5b66\u751f\u535a\u4e3b\u4eec\u6316\u6398\u81ea\u5df1\u7684\u521b\u4f5c\u6f5c\u80fd\uff0c\u5c55\u73b0\u81ea\u5df1\u7684\u5199\u4f5c\u624d\u534e\u3002\u5982\u679c\u4f60\u662f\u4e00\u4f4d\u70ed\u7231\u5199\u4f5c\u7684\u3001\u60f3\u8981\u5c55\u73b0\u81ea\u5df1\u521b\u4f5c\u624d\u534e\u7684\u5c0f\u4f19\u4f34\uff0c\u90a3\u4e48\uff0c\u5feb\u6765\u53c2\u52a0\u5427\uff01\u6211\u4eec\u4e00\u8d77\u53d1\u6398\u5199\u4f5c\u7684\u9b45\u529b\uff0c\u4e66\u5199\u51fa\u5c5e\u4e8e\u6211\u4eec\u7684\u6545\u4e8b\u3002\u6211\u4eec\u8bda\u631a\u9080\u8bf7\u4f60\u53c2\u52a0\u4e3a\u671f14\u5929\u7684\u521b\u4f5c\u6311\u6218\u8d5b\uff01\u76ee\u6807\uff1a\u4f7f\u7528 scikit-leam \u7684 CountVectorizer()\u521d\u59cb\u5316\u8bcd\u888b\u6a21\u578b\u65f6\uff0c\u8bbe\u7f6e\u4e0d\u540c\u7684\u7279\u5f81\u4e2a\u6570\u751f\u6210\u90ae\u4ef6\u7684\u7279\u5f81\u8868\u793a\u5411\u91cf\uff0c\u6bd4\u8f83\u8bad\u7ec3\u5206\u7c7b\u6a21\u578b\u6240\u8017\u8d39\u7684\u65f6\u95f4\uff0c\u4ee5\u53ca\u5206\u7c7b\u7684\u51c6\u786e\u6027\u3002\u7279\u5f81\u4e2a\u6570\u8d8a\u591a\u662f\u5426\u610f\u5473\u7740\u5206\u7c7b\u6027\u80fd\u8d8a\u597d\u5462?","og_url":"https:\/\/www.wsisp.com\/helps\/35771.html","og_site_name":"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","article_published_time":"2025-05-06T09:16:09+00:00","og_image":[{"url":"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2025\/05\/20250506091607-6819d357f03a5.png"}],"author":"admin","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"admin","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"2 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.wsisp.com\/helps\/35771.html","url":"https:\/\/www.wsisp.com\/helps\/35771.html","name":"\u90ae\u4ef6\u5206\u7c7b\u7279\u5f81\u7ef4\u5ea6\u5b9e\u9a8c\u5206\u6790 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","isPartOf":{"@id":"https:\/\/www.wsisp.com\/helps\/#website"},"datePublished":"2025-05-06T09:16:09+00:00","dateModified":"2025-05-06T09:16:09+00:00","author":{"@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41"},"breadcrumb":{"@id":"https:\/\/www.wsisp.com\/helps\/35771.html#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.wsisp.com\/helps\/35771.html"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.wsisp.com\/helps\/35771.html#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.wsisp.com\/helps"},{"@type":"ListItem","position":2,"name":"\u90ae\u4ef6\u5206\u7c7b\u7279\u5f81\u7ef4\u5ea6\u5b9e\u9a8c\u5206\u6790"}]},{"@type":"WebSite","@id":"https:\/\/www.wsisp.com\/helps\/#website","url":"https:\/\/www.wsisp.com\/helps\/","name":"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","description":"\u9999\u6e2f\u670d\u52a1\u5668_\u9999\u6e2f\u4e91\u670d\u52a1\u5668\u8d44\u8baf_\u670d\u52a1\u5668\u5e2e\u52a9\u6587\u6863_\u670d\u52a1\u5668\u6559\u7a0b","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.wsisp.com\/helps\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"zh-Hans"},{"@type":"Person","@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41","name":"admin","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/image\/","url":"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery","contentUrl":"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery","caption":"admin"},"sameAs":["http:\/\/wp.wsisp.com"],"url":"https:\/\/www.wsisp.com\/helps\/author\/admin"}]}},"_links":{"self":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts\/35771","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/comments?post=35771"}],"version-history":[{"count":0,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts\/35771\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/media\/35770"}],"wp:attachment":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/media?parent=35771"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/categories?post=35771"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/tags?post=35771"},{"taxonomy":"topic","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/topic?post=35771"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}