NLP Academy · 课时

重采样与类别权重

用代码而不是更多数据来重新平衡

重采样与类别权重 是 CoddyKit 上的免费 NLP Academy 课时。这是第 2 节课，共 4 节。你可以在下方免费阅读本课时的完整内容 — 然后在浏览器中使用内置代码编辑器和全天候 AI 导师进行实践。这是 NLP Academy 学习路径的一部分，你的进度在网页和 CoddyKit 应用中同步。 NLP Academy 课程共包含 4 节课。

本课时的部分内容尚未翻译，以英文显示。

Two Ways to Rebalance

You can fix skew by changing the data with resampling, or by changing the math with class weights. Both nudge attention to the rare class.

Oversampling the Minority

Oversampling copies or synthesizes more rare examples so the classes meet in the middle, giving the model more to learn from.

Undersampling the Majority

Undersampling drops some majority examples instead. It is fast and lean, but you risk throwing away useful signal.

SMOTE for Text Features

SMOTE invents new minority points between real ones in feature space, rather than duplicating, so the model sees fresh variety.

from imblearn.over_sampling import SMOTE
X_bal, y_bal = SMOTE().fit_resample(X, y)

Resample Training Only

Always rebalance the training set alone. Touching your test set fakes good scores and hides the real performance.

The Weighting Idea

Instead of moving data, you can make each rare mistake hurt more. Higher class weights push the loss to respect the minority.

Balanced in One Line

Many scikit-learn models accept class_weight. Set it to balanced and weights are computed inversely to class frequency.

clf = LogisticRegression(class_weight='balanced')

How Balanced Weights Work

Balanced weighting scales each class by the inverse of its frequency, so a rare label effectively counts many times more.

Weights vs Resampling

Class weights are cheap and keep your data intact, while resampling can capture richer patterns. Try weights first.

Watch for Overfitting

Aggressive oversampling can make a model memorize rare examples. Validate on untouched data to catch this overfitting early.

Pick One, Measure It

There is no universal winner. Choose a method, then judge it by minority recall, not by raw accuracy. 🎯

Quick Check

Pick the safest rebalancing habit.

Recap

Fight skew with resampling or class weights, rebalance training data only, and judge results on minority recall. ✅

常见问题解答

「重采样与类别权重」课时是免费的吗？

是的 — 「重采样与类别权重」的完整文本可在网页上免费阅读。要进行交互式练习（内置代码编辑器和全天候 AI 导师）并解锁 NLP Academy 课程的其余内容，请升级到 CoddyKit PRO。 NLP Academy 课程共包含 4 节课。

「重采样与类别权重」这节课中我会学到什么？

用代码而不是更多数据来重新平衡你通过在浏览器中直接运行的动手代码来练习 NLP Academy，全天候 AI 导师会在你学习这节课的过程中回答你的问题。

学习 NLP Academy 需要有经验吗？

无需任何先前经验。CoddyKit 上的 NLP Academy 课程适合初学者到高级学习者，你可以从这里开始或从头开始，按照自己的节奏学习。这是第 2 节课，共 4 节。

「重采样与类别权重」课时需要多长时间？

大多数 CoddyKit 课程大约需要 5–10 分钟。每节课都很精短且互动，所以你能稳步进步，并在网页和应用中从离开的地方继续。

我能在这节 NLP Academy 课中编写并运行代码吗？

能。每节 NLP Academy 课都包含内置代码编辑器，你可以在浏览器中直接编写并运行真实代码，并获得即时 AI 反馈 — 无需本地设置。

此课程中的所有课时

← 返回 NLP Academy