add Final Infrastructure Setup

evaluation/05_visualize_runs.py

@@ -0,0 +1,157 @@
+"""
+05_visualize_runs.py – Detaillierte Zeitreihen-Visualisierung der Läufe
+======================================================================
+Visualisiert pro Lauf:
+  - Durchsatz (Net_out / network_sent_mb_s)
+  - Net_in (network_recv_mb_s)
+  - CPU-Auslastung (%)
+  - RAM-Verbrauch (MB)
+  - Injektions-Fenster (Hintergrund-Shading)
+  - Detektierte Anomalien (Marker)
+"""
+
+import sys
+
+import matplotlib.dates as mdates
+import matplotlib.pyplot as plt
+import pandas as pd
+
+sys.path.insert(0, ".")
+from config import *
+
+
+def _to_utc(ts):
+    ts = pd.Timestamp(ts)
+    return ts.tz_localize("UTC") if ts.tzinfo is None else ts.tz_convert("UTC")
+
+
+def plot_run_details(run_key: str, windows_df: pd.DataFrame):
+    print(f"  Erstelle Plot für {run_key}...")
+
+    # 1. Daten laden
+    try:
+        bm = load_baseline_metrics(run_key)
+        anom = load_anomalies(run_key)
+    except Exception as e:
+        print(f"    Fehler beim Laden der Daten für {run_key}: {e}")
+        return
+
+    # Zeitstempel normalisieren
+    bm["timestamp"] = bm["timestamp"].apply(_to_utc)
+    anom["timestamp"] = anom["timestamp"].apply(_to_utc)
+
+    # Injektionen für diesen Lauf filtern
+    inj = windows_df[windows_df["run"] == run_key].copy()
+
+    # Plot-Setup: 3 Subplots (Netzwerk, CPU, RAM)
+    fig, (ax1, ax2, ax3) = plt.subplots(3, 1, figsize=(16, 10), sharex=True)
+
+    # --- Subplot 1: Netzwerk ---
+    ax1.plot(
+        bm["timestamp"],
+        bm["network_sent_mb_s"],
+        color="tab:blue",
+        lw=1.2,
+        label="Net Out (Throughput)",
+    )
+    ax1.plot(
+        bm["timestamp"],
+        bm["network_recv_mb_s"],
+        color="tab:cyan",
+        lw=0.8,
+        alpha=0.6,
+        label="Net In",
+    )
+    ax1.set_ylabel("Durchsatz [MB/s]")
+    ax1.set_title(f"Detaillierter Laufverlauf: {run_key}")
+    ax1.legend(loc="upper right", fontsize=8)
+
+    # --- Subplot 2: CPU ---
+    ax2.plot(
+        bm["timestamp"],
+        bm["cpu_percent"],
+        color="tab:green",
+        lw=1.0,
+        label="CPU Auslastung",
+    )
+    # Detektierte Anomalien einzeichnen (als Punkte auf der CPU-Linie)
+    detected_only = anom[anom["is_anomaly"] == True]
+    if not detected_only.empty:
+        ax2.scatter(
+            detected_only["timestamp"],
+            [2] * len(detected_only),
+            color="red",
+            s=25,
+            label="Pipeline Alarm",
+            zorder=5,
+            marker="^",
+        )
+
+    ax2.set_ylabel("CPU [%]")
+    ax2.set_ylim(0, 100)
+    ax2.legend(loc="upper right", fontsize=8)
+
+    # --- Subplot 3: RAM ---
+    ax3.plot(
+        bm["timestamp"],
+        bm["memory_used_mb"],
+        color="tab:purple",
+        lw=1.2,
+        label="RAM Used",
+    )
+    ax3.set_ylabel("RAM [MB]")
+    ax3.set_xlabel("Zeit [UTC]")
+    ax3.legend(loc="upper right", fontsize=8)
+
+    # --- Anomalie-Bänder über alle Subplots ---
+    for _, row in inj.iterrows():
+        t0, t1 = _to_utc(row["t_inj"]), _to_utc(row["t_stop"])
+        for ax in [ax1, ax2, ax3]:
+            ax.axvspan(t0, t1, color="red", alpha=0.1, zorder=0)
+            if ax == ax1:
+                ax.text(
+                    t0,
+                    ax.get_ylim()[1] * 0.9,
+                    row["scenario"],
+                    rotation=90,
+                    color="darkred",
+                    fontsize=7,
+                    va="top",
+                    alpha=0.7,
+                )
+
+    for ax in [ax1, ax2, ax3]:
+        ax.xaxis.set_major_formatter(mdates.DateFormatter("%H:%M:%S"))
+        ax.grid(True, alpha=0.3)
+
+    plt.tight_layout()
+    save_fig(f"05_details_{run_key}")
+
+
+def main():
+    print_section("05 – Detaillierte Zeitreihen-Visualisierung")
+
+    try:
+        windows_df = pd.read_csv(OUTPUT_DIR / "injection_windows.csv")
+    except:
+        print(
+            "  Fehler: injection_windows.csv nicht gefunden. Bitte erst 01_ground_truth.py ausführen."
+        )
+        return
+
+    sample_runs = [
+        "full_cycle_run1",
+        "high_bw_run1",
+        "high_iops_run1",
+        "batch_out_run1",
+    ]
+
+    for run_key in sample_runs:
+        if run_key in RUNS:
+            plot_run_details(run_key, windows_df)
+
+    print(f"\n→ Detaillierte Plots unter {OUTPUT_DIR}/05_details_*.png gespeichert.")
+
+
+if __name__ == "__main__":
+    main()