first commit

backend/app/analysis/statistics.py

@@ -0,0 +1,36 @@
+"""Statistical analysis helpers."""
+
+from typing import Dict, List, Optional
+
+import numpy as np
+import pandas as pd
+from scipy import stats
+
+
+def descriptive_stats(values: List[float]) -> Dict[str, float]:
+    if not values:
+        return {"mean": 0.0, "std": 0.0, "min": 0.0, "max": 0.0, "median": 0.0}
+    arr = np.array(values, dtype=float)
+    return {
+        "mean": round(float(np.mean(arr)), 4),
+        "std": round(float(np.std(arr, ddof=1)), 4),
+        "min": round(float(np.min(arr)), 4),
+        "max": round(float(np.max(arr)), 4),
+        "median": round(float(np.median(arr)), 4),
+    }
+
+
+def anova(groups: List[List[float]]) -> Dict[str, Optional[float]]:
+    """One-way ANOVA across groups."""
+    if len(groups) < 2 or any(len(g) < 2 for g in groups):
+        return {"f_statistic": None, "p_value": None}
+    f_stat, p_value = stats.f_oneway(*groups)
+    return {"f_statistic": round(float(f_stat), 4), "p_value": round(float(p_value), 6)}
+
+
+def paired_t_test(a: List[float], b: List[float]) -> Dict[str, Optional[float]]:
+    """Paired t-test between two samples."""
+    if len(a) != len(b) or len(a) < 2:
+        return {"t_statistic": None, "p_value": None}
+    t_stat, p_value = stats.ttest_rel(a, b)
+    return {"t_statistic": round(float(t_stat), 4), "p_value": round(float(p_value), 6)}