一键导入
active-learning-system
Эксперт active learning. Используй для ML с участием человека, uncertainty sampling, annotation workflows и labeling optimization.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Эксперт active learning. Используй для ML с участием человека, uncertainty sampling, annotation workflows и labeling optimization.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Find high-value SEO keywords: search volume, difficulty, intent classification, topic clusters. 关键词研究/内容选题
Expert SEO covering technical SEO, content optimization, link building, keyword research, and search analytics. Use when auditing technical SEO issues, researching keywords by intent and difficulty, optimizing on-page elements, building link acquisition strategies, or analyzing organic search performance.
Эксперт A/B тестирования. Используй для статистических тестов, экспериментов и ML-оптимизации.
Эксперт ABM. Используй для account-based marketing, target account selection и personalized campaigns.
Эксперт по accessibility дизайну. Используй для WCAG, a11y чеклистов и inclusive design.
Эксперт по a11y тестированию. Используй для axe-core, automated testing и accessibility audits.
| name | active-learning-system |
| description | Эксперт active learning. Используй для ML с участием человека, uncertainty sampling, annotation workflows и labeling optimization. |
Эксперт по системам активного обучения для машинного обучения.
from modAL import ActiveLearner
from modAL.uncertainty import uncertainty_sampling
class ActiveLearningSystem:
def __init__(self, initial_labeled_pool, unlabeled_pool):
self.labeled_X, self.labeled_y = initial_labeled_pool
self.unlabeled_X = unlabeled_pool
self.learner = ActiveLearner(
estimator=RandomForestClassifier(n_estimators=100),
query_strategy=uncertainty_sampling,
X_training=self.labeled_X,
y_training=self.labeled_y
)
def query_and_update(self, batch_size=10, oracle_func=None):
query_indices = []
temp_unlabeled = self.unlabeled_X.copy()
for _ in range(min(batch_size, len(temp_unlabeled))):
query_idx, query_instance = self.learner.query(temp_unlabeled)
query_indices.append(query_idx)
temp_unlabeled = np.delete(temp_unlabeled, query_idx, axis=0)
queried_X = self.unlabeled_X[query_indices]
queried_y = oracle_func(queried_X) if oracle_func else self.simulate_oracle(queried_X)
self.learner.teach(queried_X, queried_y)
self.unlabeled_X = np.delete(self.unlabeled_X, query_indices, axis=0)
return query_indices, queried_X, queried_y
class CommitteeActiveLearner:
def __init__(self, X_initial, y_initial):
self.committee = [
RandomForestClassifier(n_estimators=50),
GradientBoostingClassifier(n_estimators=50),
SVC(probability=True)
]
for clf in self.committee:
clf.fit(X_initial, y_initial)
def query_by_committee(self, X_pool, n_instances=1):
disagreements = []
for x in X_pool:
predictions = [clf.predict_proba([x])[0] for clf in self.committee]
avg_pred = np.mean(predictions, axis=0)
disagreement = -np.sum(avg_pred * np.log(avg_pred + 1e-10))
disagreements.append(disagreement)
selected_indices = np.argsort(disagreements)[-n_instances:]
return selected_indices, X_pool[selected_indices]
class ActiveLearningMonitor:
def track_performance(self, model, X_test, y_test, n_annotations):
accuracy = accuracy_score(y_test, model.predict(X_test))
self.performance_history.append(accuracy)
self.annotation_costs.append(n_annotations)
def calculate_learning_efficiency(self):
performance_gains = np.diff(self.performance_history)
annotation_increments = np.diff(self.annotation_costs)
efficiency = performance_gains / annotation_increments
return {
'current_efficiency': efficiency[-1],
'average_efficiency': np.mean(efficiency),
'efficiency_trend': np.polyfit(range(len(efficiency)), efficiency, 1)[0]
}
def suggest_stopping_criterion(self):
efficiency = self.calculate_learning_efficiency()
if efficiency['current_efficiency'] < 0.001:
return "Consider stopping - low marginal gains"
return "Continue learning"