초기 커밋

app/processing/utils/dataframe_utils.py

@@ -0,0 +1,26 @@
+from __future__ import annotations
+
+from datetime import datetime
+
+import polars as pl
+
+
+def filter_time_range(
+    df: pl.DataFrame, column: str, start: datetime, end: datetime
+) -> pl.DataFrame:
+    return df.filter(
+        (pl.col(column) >= start) & (pl.col(column) <= end)
+    )
+
+
+def resample(df: pl.DataFrame, time_column: str, interval: str) -> pl.DataFrame:
+    numeric_cols = [
+        c for c in df.columns if c != time_column and df[c].dtype.is_numeric()
+    ]
+    return df.sort(time_column).group_by_dynamic(time_column, every=interval).agg(
+        [pl.col(c).mean().alias(c) for c in numeric_cols]
+    )
+
+
+def to_records(df: pl.DataFrame) -> list[dict]:
+    return df.to_dicts()

app/processing/utils/statistics.py

@@ -0,0 +1,39 @@
+from __future__ import annotations
+
+import numpy as np
+
+
+def moving_average(values: list[float], window: int = 5) -> list[float]:
+    if len(values) < window:
+        return values
+    arr = np.array(values, dtype=float)
+    return np.convolve(arr, np.ones(window) / window, mode="valid").tolist()
+
+
+def detect_anomalies(
+    values: list[float], threshold: float = 2.0
+) -> list[dict]:
+    """Detect anomalies using Z-score method."""
+    arr = np.array(values, dtype=float)
+    mean = np.mean(arr)
+    std = np.std(arr)
+
+    if std == 0:
+        return []
+
+    z_scores = np.abs((arr - mean) / std)
+    anomalies = []
+    for i, (val, z) in enumerate(zip(values, z_scores)):
+        if z > threshold:
+            anomalies.append({"index": i, "value": val, "z_score": float(z)})
+    return anomalies
+
+
+def percentile_stats(values: list[float]) -> dict:
+    arr = np.array(values, dtype=float)
+    return {
+        "p50": float(np.percentile(arr, 50)),
+        "p90": float(np.percentile(arr, 90)),
+        "p95": float(np.percentile(arr, 95)),
+        "p99": float(np.percentile(arr, 99)),
+    }