From 02866790e1c26e833349351f1f998ea1f10c3aa1 Mon Sep 17 00:00:00 2001
From: Mika <kontakt@donau2space.de>
Date: Sun, 5 Apr 2026 02:07:41 +0000
Subject: [PATCH] Add data_analysis_tool/src/data_analysis_tool/core.py

---
 .../src/data_analysis_tool/core.py            | 63 +++++++++++++++++++
 1 file changed, 63 insertions(+)
 create mode 100644 data_analysis_tool/src/data_analysis_tool/core.py

diff --git a/data_analysis_tool/src/data_analysis_tool/core.py b/data_analysis_tool/src/data_analysis_tool/core.py
new file mode 100644
index 0000000..77dd449
--- /dev/null
+++ b/data_analysis_tool/src/data_analysis_tool/core.py
@@ -0,0 +1,63 @@
+from __future__ import annotations
+import json
+import pandas as pd
+from pathlib import Path
+from typing import Any
+
+
+class AnalysisResults:
+    """Speichert die Ergebnisse der Magnetfeldauswertung."""
+
+    def __init__(self, mean_Bx: float, mean_By: float, variance_Bx: float, spikes: int) -> None:
+        self.mean_Bx = float(mean_Bx)
+        self.mean_By = float(mean_By)
+        self.variance_Bx = float(variance_Bx)
+        self.spikes = int(spikes)
+
+    def to_json(self) -> str:
+        """Konvertiert die Analyseergebnisse in ein JSON-Format."""
+        result = {
+            "mean_Bx": self.mean_Bx,
+            "mean_By": self.mean_By,
+            "variance_Bx": self.variance_Bx,
+            "spikes": self.spikes,
+        }
+        return json.dumps(result, indent=2)
+
+
+def analyze_data(data_file: str) -> AnalysisResults:
+    """Analysiert Magnetometerdaten aus einer CSV-Datei und berechnet Mittelwerte, Varianzen und Anomalien."""
+    file_path = Path(data_file)
+    if not file_path.exists() or not file_path.is_file():
+        raise FileNotFoundError(f"Eingabedatei nicht gefunden: {data_file}")
+
+    # Lese CSV-Daten
+    try:
+        df = pd.read_csv(file_path)
+    except Exception as e:
+        raise ValueError(f"Fehler beim Lesen der CSV-Datei: {e}")
+
+    required_cols = {"Bx", "By", "Bz"}
+    if not required_cols.issubset(df.columns):
+        raise ValueError(f"CSV muss die Spalten {required_cols} enthalten.")
+
+    # Input-Validierung: alle numerischen Spalten prüfen
+    for col in ["Bx", "By", "Bz"]:
+        if not pd.api.types.is_numeric_dtype(df[col]):
+            raise ValueError(f"Spalte {col} muss numerisch sein.")
+
+    mean_Bx = df["Bx"].mean()
+    mean_By = df["By"].mean()
+    variance_Bx = df["Bx"].var()
+
+    # Einfache Spike-Erkennung: Werte, die mehr als 3 Standardabweichungen vom Mittelwert entfernt sind
+    std_Bx = df["Bx"].std()
+    spikes_series = (df["Bx"] - mean_Bx).abs() > 3 * std_Bx if std_Bx > 0 else pd.Series([False] * len(df))
+    spikes_count = int(spikes_series.sum())
+
+    return AnalysisResults(
+        mean_Bx=mean_Bx,
+        mean_By=mean_By,
+        variance_Bx=variance_Bx,
+        spikes=spikes_count,
+    )
\ No newline at end of file