ADTK lanjutan

1
2
3
4
5
6
7
8

import numpy as np
import pandas as pd
from adtk.data import validate_series

s_train = pd.read_csv("./training.csv", index_col="timestamp", parse_dates=True)
s_train = validate_series(s_train)
s_train["value2"] = s_train["value"].apply(lambda v: np.sin(v) + np.cos(v))
s_train

1
2
3

from adtk.visualization import plot

plot(s_train)

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25

import matplotlib.pyplot as plt
from adtk.detector import OutlierDetector, PcaAD, RegressionAD
from sklearn.linear_model import LinearRegression
from sklearn.neighbors import LocalOutlierFactor

model_dict = {
    "OutlierDetector": OutlierDetector(LocalOutlierFactor(contamination=0.05)),
    "RegressionAD": RegressionAD(regressor=LinearRegression(), target="value2", c=3.0),
    "PcaAD": PcaAD(k=2),
}

for model_name, model in model_dict.items():
    anomalies = model.fit_detect(s_train)

    plot(
        s_train,
        anomaly=anomalies,
        ts_linewidth=1,
        ts_markersize=3,
        anomaly_color="red",
        anomaly_alpha=0.3,
        curve_group="all",
    )
    plt.title(model_name)
    plt.show()