import numpy as np
from sklearn.ensemble import IsolationForest

row_names = np.array(
    [
        "baseline-01",
        "baseline-02",
        "baseline-03",
        "baseline-04",
        "baseline-05",
        "baseline-06",
        "spike-01",
    ]
)

readings = np.array(
    [
        [10.0, 200.0],
        [10.4, 198.0],
        [9.8, 202.0],
        [10.2, 201.0],
        [10.1, 199.0],
        [10.5, 203.0],
        [42.0, 410.0],
    ]
)

detector = IsolationForest(contamination=0.15, random_state=42)
detector.fit(readings)

labels = detector.predict(readings)
scores = detector.decision_function(readings)

print("Training rows")
for row_name, label, score in zip(row_names, labels, scores):
    state = "outlier" if label == -1 else "inlier"
    print(f"{row_name:11s} {state:7s} label={label:2d} score={score: .3f}")

outliers = row_names[labels == -1]
print(f"Detected training outliers: {', '.join(outliers)}")

new_rows = np.array(
    [
        [10.3, 200.5],
        [35.0, 390.0],
    ]
)
new_names = np.array(["incoming-normal", "incoming-spike"])
new_labels = detector.predict(new_rows)
new_scores = detector.decision_function(new_rows)

print("\nNew rows")
for row_name, label, score in zip(new_names, new_labels, new_scores):
    state = "outlier" if label == -1 else "inlier"
    print(f"{row_name:15s} {state:7s} label={label:2d} score={score: .3f}")

assert "spike-01" in outliers
assert "incoming-spike" in new_names[new_labels == -1]
print("\nSmoke check passed: expected spike rows are outliers")