Detección de anomalías para el monitoreo de aplicaciones

import numpy as np
from dataclasses import dataclass
 
@dataclass
class AnomalyResult:
    value: float
    mean: float
    std: float
    z_score: float
    is_anomaly: bool
 
def detect_zscore_anomaly(
    values: list[float],
    current: float,
    threshold: float = 3.0
) -> AnomalyResult:
    """Detect anomalies using z-score on recent history."""
    arr = np.array(values)
    mean = float(np.mean(arr))
    std = float(np.std(arr))
 
    # Avoid division by zero for constant metrics
    if std == 0:
        z_score = 0.0 if current == mean else float('inf')
    else:
        z_score = abs(current - mean) / std
 
    return AnomalyResult(
        value=current,
        mean=mean,
        std=std,
        z_score=z_score,
        is_anomaly=z_score > threshold
    )
 
# Example: error rate over the last 24 hours (1-minute intervals)
error_rates = [0.02, 0.018, 0.022, 0.019, ...]  # 1440 data points
current_rate = 0.085
 
result = detect_zscore_anomaly(error_rates, current_rate)
# z_score: 8.2, is_anomaly: True
# Mean 2%, current 8.5% → clearly anomalous

class EMADetector {
  private ema: number | null = null;
  private emaVariance: number = 0;
 
  constructor(
    private alpha: number = 0.1,
    private threshold: number = 3.0
  ) {}
 
  update(
    value: number
  ): { isAnomaly: boolean; expected: number; deviation: number } {
    if (this.ema === null) {
      this.ema = value;
      return { isAnomaly: false, expected: value, deviation: 0 };
    }
 
    // Update EMA (exponentially weighted moving average)
    const prevEma = this.ema;
    this.ema = this.alpha * value + (1 - this.alpha) * this.ema;
 
    // Update variance estimate
    const diff = value - prevEma;
    this.emaVariance =
      this.alpha * diff * diff +
      (1 - this.alpha) * this.emaVariance;
 
    const stdDev = Math.sqrt(this.emaVariance);
    const deviation =
      stdDev > 0 ? Math.abs(value - prevEma) / stdDev : 0;
 
    return {
      isAnomaly: deviation > this.threshold,
      expected: prevEma,
      deviation,
    };
  }
}
 
// Usage: detect latency anomalies
const latencyDetector = new EMADetector(0.05, 3.0);
 
// Feed in normal values to establish baseline
for (const latency of normalLatencies) {
  latencyDetector.update(latency);
}
 
// Then check new values
const result = latencyDetector.update(850);
// { isAnomaly: true, expected: 120, deviation: 4.2 }

from dataclasses import dataclass
import numpy as np
 
@dataclass
class SeasonalBaseline:
    hourly_means: np.ndarray  # 24 values (one per hour)
    hourly_stds: np.ndarray   # 24 values
    day_of_week_factors: np.ndarray  # 7 values
 
def build_seasonal_baseline(
    timestamps: list[float],
    values: list[float],
    min_weeks: int = 2
) -> SeasonalBaseline:
    """Build hourly baselines from historical data."""
    from datetime import datetime
 
    # Group values by hour-of-day
    hourly_buckets: dict[int, list[float]] = {h: [] for h in range(24)}
    dow_buckets: dict[int, list[float]] = {d: [] for d in range(7)}
 
    for ts, val in zip(timestamps, values):
        dt = datetime.fromtimestamp(ts)
        hourly_buckets[dt.hour].append(val)
        dow_buckets[dt.weekday()].append(val)
 
    hourly_means = np.array([
        np.mean(hourly_buckets[h]) if hourly_buckets[h] else 0
        for h in range(24)
    ])
    hourly_stds = np.array([
        np.std(hourly_buckets[h]) if len(hourly_buckets[h]) > 1 else 1
        for h in range(24)
    ])
 
    global_mean = np.mean(values) if values else 1
    day_factors = np.array([
        np.mean(dow_buckets[d]) / global_mean if dow_buckets[d] else 1
        for d in range(7)
    ])
 
    return SeasonalBaseline(hourly_means, hourly_stds, day_factors)
 
def is_seasonal_anomaly(
    baseline: SeasonalBaseline,
    current_value: float,
    hour: int,
    day_of_week: int,
    threshold: float = 3.0
) -> bool:
    """Check if value is anomalous for this time and day."""
    expected = baseline.hourly_means[hour] * baseline.day_of_week_factors[day_of_week]
    std = baseline.hourly_stds[hour]
 
    if std == 0:
        return current_value != expected
 
    z = abs(current_value - expected) / std
    return z > threshold

// ❌ Alerting on raw anomaly detection output
// Every z-score > 3 triggers a page
// Result: 15 alerts per day, most are benign blips
// On-call engineer ignores all alerts after 2 days
 
// ✅ Multi-stage alerting pipeline
interface AlertPipeline {
  stage1_detection: {
    description: "Raw anomaly detection on 1-minute data";
    output: "Boolean: is this data point anomalous?";
  };
  stage2_confirmation: {
    description: "Require N consecutive anomalous points";
    config: { consecutiveRequired: 3; windowMinutes: 5 };
    output: "Boolean: sustained anomaly confirmed?";
  };
  stage3_severity: {
    description: "Classify severity based on deviation magnitude";
    config: {
      warning: "z-score 3-5 OR error rate increase 2-5x";
      critical: "z-score > 5 OR error rate increase > 5x";
    };
  };
  stage4_dedup: {
    description: "Suppress duplicate alerts for same incident";
    config: { silenceMinutes: 30; groupBy: "metric_name + service" };
  };
}

class AlertManager {
  private activeAlerts = new Map<string, { since: Date; count: number }>();
 
  shouldAlert(
    metricKey: string,
    isAnomaly: boolean,
    severity: "warning" | "critical"
  ): { alert: boolean; action: "page" | "slack" | "none" } {
    const existing = this.activeAlerts.get(metricKey);
 
    if (!isAnomaly) {
      // Anomaly resolved
      if (existing) {
        this.activeAlerts.delete(metricKey);
        return { alert: true, action: "slack" }; // Resolution notification
      }
      return { alert: false, action: "none" };
    }
 
    if (existing) {
      existing.count++;
      // Already alerted, suppress until silence window expires
      return { alert: false, action: "none" };
    }
 
    // New anomaly
    this.activeAlerts.set(metricKey, { since: new Date(), count: 1 });
 
    return {
      alert: true,
      action: severity === "critical" ? "page" : "slack",
    };
  }
}

interface CorrelatedCheck {
  primary: { metric: string; isAnomaly: boolean };
  supporting: Array<{ metric: string; isAnomaly: boolean }>;
  confidence: number;
}
 
function correlatedAnomalyCheck(
  checks: CorrelatedCheck
): { isReal: boolean; confidence: number } {
  if (!checks.primary.isAnomaly) {
    return { isReal: false, confidence: 0 };
  }
 
  const supportingAnomaly = checks.supporting.filter(
    (s) => s.isAnomaly
  ).length;
  const totalSupporting = checks.supporting.length;
 
  // Higher confidence when multiple related metrics are anomalous
  const correlationScore =
    totalSupporting > 0 ? supportingAnomaly / totalSupporting : 0;
 
  const confidence = 0.5 + 0.5 * correlationScore;
 
  return {
    isReal: confidence > 0.6,
    confidence,
  };
}
 
// Example: high error rate is more likely real if:
// - Latency is also elevated (correlated)
// - Traffic volume is normal (not a traffic spike causing errors)
// - CPU usage is elevated (resource pressure)
const check: CorrelatedCheck = {
  primary: { metric: "error_rate", isAnomaly: true },
  supporting: [
    { metric: "p99_latency", isAnomaly: true },
    { metric: "request_rate", isAnomaly: false },
    { metric: "cpu_usage", isAnomaly: true },
  ],
  confidence: 0,
};
// 2/3 supporting anomalies → confidence: 0.83 → alert