def train_cosmo(self,
                    data,
                    w_martingale=15,
                    non_conformity="median",
                    k=20):

        df = data

        self.model = IndividualAnomalyInductive(w_martingale=w_martingale,
                                                non_conformity=non_conformity,
                                                k=k)

        # Fit the model to a fixed subset of the data
        X_fit = data.to_numpy()
        self.model.fit(X_fit)
Exemplo n.º 2
0
    def __init__(self,
                 nb_units,
                 ids_target_units,
                 w_ref_group="7days",
                 w_martingale=15,
                 non_conformity="median",
                 k=20,
                 dev_threshold=.6,
                 transform=False,
                 w_transform=20):
        self.nb_units = nb_units
        self.ids_target_units = ids_target_units
        self.w_ref_group = w_ref_group
        self.w_martingale = w_martingale
        self.non_conformity = non_conformity
        self.k = k
        self.dev_threshold = dev_threshold
        self.transform = transform
        self.w_transform = w_transform

        self.dfs_original = [
            pd.DataFrame(data=[], index=[]) for _ in range(nb_units)
        ]
        self.dfs = [pd.DataFrame(data=[], index=[]) for _ in range(nb_units)]
        self.pg = PeerGrouping(self.w_ref_group)
        self.detectors = [
            IndividualAnomalyInductive(w_martingale, non_conformity, k,
                                       dev_threshold) for _ in range(nb_units)
        ]
        self.transformers = [
            Transformer(w=w_transform) for _ in range(nb_units)
        ]
 def test_predict_input_wrong(self):
     indev = IndividualAnomalyInductive(w_martingale=15, non_conformity="median", k=20, dev_threshold=0.6)
     indev.fit(np.array([[1,2,3], [4,5,6], [7,8,9]]))
     
     with self.assertRaises(InputValidationError):
         indev.predict(None, [])
         
     with self.assertRaises(InputValidationError):
         indev.predict(None, "foo")
 def test_init(self):
     with self.assertRaises(InputValidationError):
         IndividualAnomalyInductive(w_martingale=0, non_conformity="median", k=20, dev_threshold=0.6)
     
     with self.assertRaises(InputValidationError):
         IndividualAnomalyInductive(w_martingale=-1, non_conformity="median", k=20, dev_threshold=0.6)
     
     with self.assertRaises(InputValidationError):
         IndividualAnomalyInductive(w_martingale=15, non_conformity="foo", k=20, dev_threshold=0.6)
     
     with self.assertRaises(InputValidationError):
         IndividualAnomalyInductive(w_martingale=15, non_conformity="knn", k=0, dev_threshold=0.6)
     
     with self.assertRaises(InputValidationError):
         IndividualAnomalyInductive(w_martingale=15, non_conformity="knn", k=-1, dev_threshold=0.6)
     
     with self.assertRaises(InputValidationError):
         IndividualAnomalyInductive(w_martingale=15, non_conformity="median", k=20, dev_threshold=-1)
     
     with self.assertRaises(InputValidationError):
         IndividualAnomalyInductive(w_martingale=15, non_conformity="median", k=20, dev_threshold=2)
 def test_predict_not_fitted(self):
     indev = IndividualAnomalyInductive(w_martingale=15, non_conformity="median", k=20, dev_threshold=0.6)
     with self.assertRaises(NotFittedError):
         indev.predict(None, [1,1,1])
 def test_predict_median_w3(self):
     indev = IndividualAnomalyInductive(w_martingale=3, non_conformity="median", k=20, dev_threshold=0.6)
     indev.fit(np.array([[1,2,3], [4,5,6], [7,8,9]]))
     res = indev.predict(None, [1,1,1])
     expected = DeviationContext((3**2+4**2+5**2)**0.5, 0, 1/3, False)
     self.assertEqual(res, expected)
 def test_fit_knn_k2(self):
     indev = IndividualAnomalyInductive(w_martingale=15, non_conformity="knn", k=2, dev_threshold=0.6)
     indev.fit(np.array([[1,2,3], [4,5,6], [7,8,9]]))
     expected = [ (0 + 3**(3/2)) / 2, (3**(3/2) + 0) / 2, (3**(3/2) + 0) / 2 ]
     self.assertEqual(indev.scores, expected)
     self.assertTrue(np.allclose(indev.scores, expected))
 def test_fit_median(self):
     indev = IndividualAnomalyInductive(w_martingale=15, non_conformity="median", k=20, dev_threshold=0.6)
     indev.fit(np.array([[1,2,3], [4,5,6], [7,8,9]]))
     expected = [3**(3/2), 0, 3**(3/2)]
     self.assertEqual(indev.scores, expected)
     self.assertTrue(np.allclose(indev.scores, expected))
 def test_fit_input_empty(self):
     indev = IndividualAnomalyInductive(w_martingale=15, non_conformity="median", k=20, dev_threshold=0.6)
     with self.assertRaises(InputValidationError):
         indev.fit([])
Exemplo n.º 10
0
generator = bb.generate_samples( cam=args.cam_id, rs=args.resample_time )

# Choose between the Transductive or Inductive version.
ref_groups_list = args.ref_group.split(",")
if args.type == "T":
    indev = IndividualAnomalyTransductive(w_martingale=args.martingale,  # Window size for computing the deviation level
                                          non_conformity=args.measure,   # Strangeness measure: "median","knn","lof"
                                          k=15,                          # Used if non_conformity is "knn"
                                          dev_threshold=args.dev_threshold, # Threshold on the deviation level
                                          ref_group=ref_groups_list,
                                          #ref_group="external",
    ) # reference group construction: "week", "month", "season", "external"
else:
    indev = IndividualAnomalyInductive( w_martingale=args.martingale,# Window size for computing the deviation level
                                        non_conformity=args.measure, # Strangeness measure: "median" or "knn" or "lof"
                                        k=50,                        # Used if non_conformity is "knn"
                                        dev_threshold=args.dev_threshold)

# Train
# Training consists of pushing one week of data through the algorithm.
# (Pretending we are "live")
# Can be switched off.
#
if args.do_train:
    print( "--------" )
    print( "Training" )
    print( "--------" )
    inside    = False
    processed = 0
    training  = []
    sequence  = 0
Exemplo n.º 11
0
class AnomalyDetection:
    def __init__(self):
        pass

    def deviation_detection(self, data, mu, sigma, l1=4, l2=8, l3=12):
        z_s = self.zscore(data, mu, sigma)
        if (len(z_s.shape) > 1):
            z_s = z_s[:, 0]
        t = np.linspace(0, len(z_s) - 1, len(z_s))
        thres1 = l1 * sigma
        thres2 = l2 * sigma
        thres3 = l3 * sigma
        plt.scatter(t[np.where(z_s <= thres1)],
                    z_s[np.where(z_s <= thres1)],
                    color='y',
                    label='Normal',
                    alpha=0.3,
                    edgecolors='none')
        plt.scatter(t[np.where((z_s > thres1) & (z_s <= thres2))],
                    z_s[np.where((z_s > thres1) & (z_s <= thres2))],
                    color='b',
                    label='L1 Threshold',
                    alpha=0.3,
                    edgecolors='none')
        plt.scatter(t[np.where((z_s > thres2) & (z_s <= thres3))],
                    z_s[np.where((z_s > thres2) & (z_s <= thres3))],
                    color='g',
                    label='L2 Threshold',
                    alpha=0.3,
                    edgecolors='none')
        plt.scatter(t[np.where(z_s > thres3)],
                    z_s[np.where(z_s > thres3)],
                    color='r',
                    label='Anomalous points',
                    alpha=0.3,
                    edgecolors='none')
        plt.xlabel('Observation Signal (in samples)')
        plt.ylabel('Anomaly Score')
        plt.title('Anomaly Score Estimation')
        plt.legend()
        return z_s, sigma

    def train_cosmo(self,
                    data,
                    w_martingale=15,
                    non_conformity="median",
                    k=20):

        df = data

        self.model = IndividualAnomalyInductive(w_martingale=w_martingale,
                                                non_conformity=non_conformity,
                                                k=k)

        # Fit the model to a fixed subset of the data
        X_fit = data.to_numpy()
        self.model.fit(X_fit)

    def test_cosmo(self, data):
        cols = ['Strangeness', 'P-Values', 'Deviation']
        lst_dict = []
        df = data
        for t, x in zip(df.index, df.values):
            info = self.model.predict(t, x)

            lst_dict.append({
                'Strangeness': info.strangeness,
                'P-Values': info.pvalue,
                'Deviation': info.deviation
            })

        # Plot strangeness and deviation level over time
        # gr = model.plot_deviations(figsize=(2000,2000))

        df1 = pd.DataFrame(lst_dict, columns=cols)

        return df1['Strangeness'].to_numpy(), df1['P-Values'].to_numpy()

    def nonstationary_AD_cosmo(self,
                               data,
                               n,
                               w_martingale,
                               k,
                               non_conformity="median",
                               ref_group=["hour-of-day"]):

        df = self.data
        cols = ['Strangeness', 'P-Values', 'Deviation']
        lst_dict = []

        model = IndividualAnomalyTransductive(
            w_martingale=
            w_martingale,  # Window size for computing the deviation level
            non_conformity=
            non_conformity,  # Strangeness measure: "median" or "knn"
            k=k,  # Used if non_conformity is "knn"
            ref_group=ref_group  # Criteria for reference group construction
        )

        for t, x in zip(df.index, df.values):
            info = model.predict(t, x)

            lst_dict.append({
                'Strangeness': info.strangeness,
                'P-Values': info.pvalue,
                'Deviation': info.deviation
            })

        # Plot strangeness and deviation level over time
        gr = model.plot_deviations(figsize=(2000, 2000))

        df1 = pd.DataFrame(lst_dict, columns=cols)

        return df1, gr
from grand.datasets import load_vehicles, load_artificial_toy
from grand import IndividualAnomalyInductive

if __name__ == '__main__':

    # Get data from one unit (vehicle)
    dataset = load_artificial_toy(0)  #load_vehicles()
    unit1_train = [x for dt, x in dataset.stream_unit(1)
                   ]  # we use unit number 1 for training

    # Create an instance of IndividualAnomalyInductive
    indev = IndividualAnomalyInductive(
        w_martingale=15,  # Window size for computing the deviation level
        non_conformity=
        "median",  # Strangeness measure: "median" or "knn" or "lof"
        k=50,  # Used if non_conformity is "knn"
        dev_threshold=.6)  # Threshold on the deviation level

    # Fit the IndividualAnomalyInductive detector to unit1_train
    indev.fit(unit1_train)

    # At each time step dt, a data-point x comes from the stream of unit number 0
    for dt, x in dataset.stream_unit(0):
        devContext = indev.predict(dt, x)

        st, pv, dev, isdev = devContext.strangeness, devContext.pvalue, devContext.deviation, devContext.is_deviating
        print("Time: {} ==> strangeness: {}, p-value: {}, deviation: {} ({})".
              format(dt, st, pv, dev, "high" if isdev else "low"))

    # Plot p-values and deviation level over time
    indev.plot_deviations()