def is_outlier():
if not flask.request.json or not 'symptom' in flask.request.json or not 'value' in flask.request.json or not 'ts' in flask.request.json or not 'uid' in flask.request.json:
flask.abort(400)
symptom = flask.request.json["symptom"]
val = flask.request.json["value"]
ts = flask.request.json["ts"]
uid = flask.request.json["uid"]
#date_time_obj = datetime.datetime.fromisoformat(ts)
hour_before = datetime.datetime.now() - datetime.timedelta(hours=1)
print(hour_before)
if not (symptom in symptoms):
return flask.jsonify(
{'message':
f'Invalid Symptom! Accepted symptoms are {symptoms}'}), 400
select_query_1_hour = f"select timestamp,\"{symptom}\" from symptom where {symptom} is not null and \"userId\" = '{int(uid)}' and timestamp > '{hour_before}' order by timestamp desc"
#select_query = f"select timestamp,\"{symptom}\" from symptom where {symptom} is not null and \"userId\" = '{int(uid)}' order by timestamp desc"
column_names = ["timestamp", symptom]
conn = connect()
df = postgresql_to_pd(conn, select_query_1_hour, column_names)
print(df)
if len(df) == 0:
return flask.jsonify({
'isOutlier': str(False),
'noData': str(True)
}), 200
df = df.append({f"{symptom}": val, "timestamp": ts}, ignore_index=True)
df["DateTime"] = pd.to_datetime(df["timestamp"])
df = df.set_index(pd.DatetimeIndex(df["DateTime"]))
df = df.drop(["timestamp", "DateTime"], axis=1)
validate_series(df)
outlier_detector = OutlierDetector(
LocalOutlierFactor(contamination=0.05,
n_neighbors=int(round(len(df) / 2))))
anomalies = outlier_detector.fit_detect(df)
conn.close()
return flask.jsonify({'outlier': str(anomalies.iat[-1])}), 200
def isolationForestAD(self, c):
outlier_detector = OutlierDetector(IsolationForest(contamination=c))
anomalies = outlier_detector.fit_detect(self.data)
self.anomalies = anomalies
self.evaluate()
def localOutlierFactorAD(self, c):
outlier_detector = OutlierDetector(LocalOutlierFactor(contamination=c))
anomalies = outlier_detector.fit_detect(self.data)
self.anomalies = anomalies
self.evaluate()
plot(df,
anomaly_pred=anomalies,
ts_linewidth=2,
ts_markersize=3,
ap_color='red',
ap_alpha=0.3,
curve_group='all')
'''GET ACCURACY'''
found_events = len(np.where(Y[anomalies.values] == 1)[0])
accuracy = found_events / len(eventtime_incon[0])
accuracy
# !!!! PLOT ROC CURVE !!!!
'''THIS IS SUPER COOL B=) '''
from adtk.detector import OutlierDetector
from sklearn.neighbors import LocalOutlierFactor
outlier_detector = OutlierDetector(LocalOutlierFactor(contamination=0.05))
anomalies = outlier_detector.fit_detect(df)
plot(df,
anomaly_pred=anomalies,
ts_linewidth=2,
ts_markersize=3,
ap_color='red',
ap_alpha=0.3,
curve_group='all')
from adtk.detector import RegressionAD
from sklearn.linear_model import LinearRegression
regression_ad = RegressionAD(regressor=LinearRegression(),
target="data2",
c=3.0)
anomalies = regression_ad.fit_detect(df)
#TimeBins=TimeBins[TimeBins["timestamp"] < '2020-06-30 23:55:55']
TimeBins = TimeBins.set_index('timestamp')
TimeBins = validate_series(TimeBins)
#persist_ad = PersistAD(window=7, c=3, side='both')
#anomalies1 = persist_ad.fit_detect(TimeBins)
#plot(TimeBins, anomaly=anomalies1, ts_linewidth=1, ts_markersize=3, anomaly_color='red', figsize=(20,10), anomaly_tag="marker", anomaly_markersize=5)
#customized_detector = CustomizedDetectorHD(detect_func=Detector_prive)
#anomalies = customized_detector.detect(TimeBins)
#threshold_ad = ThresholdAD(high=150, low=0)
#anomalies = threshold_ad.detect(TimeBins)
#plot(TimeBins, anomaly=anomalies, ts_linewidth=1, ts_markersize=5, anomaly_color='red', anomaly_alpha=0.3, curve_group='all');
outlier_detector = OutlierDetector(
LocalOutlierFactor(n_neighbors=1, p=1, contamination=0.05))
anomalies = outlier_detector.fit_detect(TimeBins)
plot(TimeBins,
anomaly=anomalies,
ts_linewidth=1,
ts_markersize=5,
anomaly_color='red',
anomaly_alpha=0.3,
curve_group='all')
plt.ylim(top=460)
plt.savefig('%d_%d.pdf' % Input2 % elem, bbox_inches='tight')
plt.close()
del TimeBins
del rslt_df
del boolean_condition
def adtk_init(model, colname=None):
if model == 'iqr':
from adtk.detector import InterQuartileRangeAD
clf = InterQuartileRangeAD()
elif model == 'ar':
from adtk.detector import AutoregressionAD
clf = AutoregressionAD()
elif model == 'esd':
from adtk.detector import GeneralizedESDTestAD
clf = GeneralizedESDTestAD()
elif model == 'level':
from adtk.detector import LevelShiftAD
clf = LevelShiftAD(15)
elif model == 'persist':
from adtk.detector import PersistAD
clf = PersistAD(15)
elif model == 'quantile':
from adtk.detector import QuantileAD
clf = QuantileAD()
elif model == 'seasonal':
from adtk.detector import SeasonalAD
clf = SeasonalAD()
elif model == 'volatility':
from adtk.detector import VolatilityShiftAD
clf = VolatilityShiftAD(15)
elif model == 'kmeans':
from adtk.detector import MinClusterDetector
from sklearn.cluster import KMeans
clf = MinClusterDetector(KMeans(n_clusters=2))
elif model == 'birch':
from adtk.detector import MinClusterDetector
from sklearn.cluster import Birch
clf = MinClusterDetector(Birch(threshold=0.25, branching_factor=25))
elif model == 'gmm':
from adtk.detector import MinClusterDetector
from sklearn.mixture import GaussianMixture
clf = MinClusterDetector(GaussianMixture(n_components=2, max_iter=50))
elif model == 'vbgmm':
from adtk.detector import MinClusterDetector
from sklearn.mixture import BayesianGaussianMixture
clf = MinClusterDetector(BayesianGaussianMixture(n_components=2, max_iter=50))
elif model == 'eliptic':
from adtk.detector import OutlierDetector
from sklearn.covariance import EllipticEnvelope
clf = OutlierDetector(EllipticEnvelope())
elif model == 'mcdad':
from adtk.detector import OutlierDetector
from sklearn.covariance import MinCovDet
clf = OutlierDetector(MinCovDet())
elif model == 'isof':
from adtk.detector import OutlierDetector
from sklearn.ensemble import IsolationForest
clf = OutlierDetector(IsolationForest())
elif model == 'lofad':
from adtk.detector import OutlierDetector
from sklearn.neighbors import LocalOutlierFactor
clf = OutlierDetector(LocalOutlierFactor())
elif model == 'pcaad':
from adtk.detector import PcaAD
clf = PcaAD()
elif model == 'linear':
from adtk.detector import RegressionAD
from sklearn.linear_model import LinearRegression
clf = RegressionAD(LinearRegression(), target=colname)
elif model == 'rf':
from adtk.detector import RegressionAD
from sklearn.ensemble import RandomForestRegressor
clf = RegressionAD(RandomForestRegressor(), target=colname)
elif model == 'huber':
from adtk.detector import RegressionAD
from sklearn.linear_model import HuberRegressor
clf = RegressionAD(HuberRegressor(), target=colname)
elif model == 'knnad':
from adtk.detector import RegressionAD
from sklearn.neighbors import KNeighborsRegressor
clf = RegressionAD(KNeighborsRegressor(), target=colname)
elif model == 'kernridge':
from adtk.detector import RegressionAD
from sklearn.kernel_ridge import KernelRidge
clf = RegressionAD(KernelRidge(), target=colname)
else:
clf = ADTKDefault()
return clf