اكتشاف الشذوذ والقيم المتطرفة

from sklearn.ensemble import IsolationForest
from sklearn.neighbors import LocalOutlierFactor
from sklearn.svm import OneClassSVM
from sklearn.preprocessing import StandardScaler
from sklearn.datasets import make_classification
import numpy as np

class="tok-comment"># ── Sample data (class="tok-num">5% anomalies) ─────────────────────────────────────────
X_normal, _ = make_classification(n_samples=class="tok-num">475, n_features=class="tok-num">10, random_state=class="tok-num">42)
X_anom  = np.random.randn(class="tok-num">25, class="tok-num">10) * class="tok-num">4    class="tok-comment"># class="tok-num">25 clear outliers
X = np.vstack([X_normal, X_anom])
y_true = np.array([class="tok-num">0]*class="tok-num">475 + [class="tok-num">1]*class="tok-num">25)       class="tok-comment"># class="tok-num">0=normal, class="tok-num">1=anomaly

X_scaled = StandardScaler().fit_transform(X)

class="tok-comment"># ── Isolation Forest ───────────────────────────────────────────────
iso = IsolationForest(
    n_estimators=class="tok-num">200,
    contamination=class="tok-num">0.05,   class="tok-comment"># expected fraction of outliers
    random_state=class="tok-num">42
)
labels_iso = iso.fit_predict(X_scaled)  class="tok-comment"># class="tok-num">1=inlier, -class="tok-num">1=outlier
scores_iso = iso.score_samples(X_scaled)  class="tok-comment"># lower = more anomalous

class="tok-comment"># ── Local Outlier Factor ────────────────────────────────────────────
lof = LocalOutlierFactor(n_neighbors=class="tok-num">20, contamination=class="tok-num">0.05)
labels_lof = lof.fit_predict(X_scaled)

class="tok-comment"># ── Z-Score (univariate, per-feature) ──────────────────────────────
from scipy import stats
z_scores = np.abs(stats.zscore(X))
outlier_mask = (z_scores > class="tok-num">3).any(axis=class="tok-num">1)

class="tok-comment"># ── Evaluate with known labels ─────────────────────────────────────
from sklearn.metrics import roc_auc_score, average_precision_score
class="tok-comment"># Convert: class="tok-num">1=inlier → class="tok-num">0=normal,  -class="tok-num">1=outlier → class="tok-num">1=anomaly
y_pred = (labels_iso == -class="tok-num">1).astype(int)
print(fclass="tok-str">"AUC-ROC: {roc_auc_score(y_true, -scores_iso):.3f}")
print(fclass="tok-str">"AP:      {average_precision_score(y_true, -scores_iso):.3f}")