Compute the log-likelihood for the Generalized Pareto Distribution (μ=0) Parameters ---------- Y : numpy.arr

Find possible roots of a scalar function Parameters ---------- fun : function scalar function

Plot the results of given by the run Parameters ---------- run_results : dict results given by t

Run SPOT on the stream Parameters ---------- with_alarm : bool (default = True) If False, SPOT will ad

Compute the GPD parameters estimation with the Grimshaw's trick Parameters ---------- epsilon : float

Compute the GPD parameters estimation with the Grimshaw's trick Parameters ---------- epsilon : float

Compute the quantile at level 1-q for a given side Parameters ---------- side : str 'up' or 'dow

Compute the quantile at level 1-q for a given side Parameters ---------- side : str 'up' or 'dow

Derive an instance of :math:`q(z|h(x))`, the variational net. Args: x: The observation `x` for the variational net.

Compute the GPD parameters estimation with the Grimshaw's trick Parameters ---------- epsilon : float

Compute the GPD parameters estimation with the Grimshaw's trick Parameters ---------- epsilon : float

Compute the quantile at level 1-q Parameters ---------- gamma : float GPD parameter sigma : fl

Compute the quantile at level 1-q Parameters ---------- gamma : float GPD parameter sigma : fl

This function allows to append data to the already fitted data Parameters ---------- data : list, numpy.array, pan

Calculate adjusted predict labels using given `score`, `threshold` (or given `pred`) and `label`. Args: score (np.ndarray): The anom

calculate f1 score by predict and actual. Args: predict (np.ndarray): the predict label actual (np.ndarray): np.ndarray

Iterate through the sliding windows of each array in `arrays`. This method is not re-entrant, i.e., calling :meth:`get_iterator`

Get the `reconstruction probability` of specified KPI observations. The larger `reconstruction probability`, the less likely a point

Derive an instance of :math:`p(x|h(z))`, the model net. Args: z: If specified, observe `z` in the model net. (default :o

Chain :math:`q(z|h(x))` and :math:`p(x,z|h(x))` together. This method chains the variational net :math:`q(z|h(x))` and the m

returns normalized and standardized data.

save the sampled z in a txt file

Construct the :class:`VAE`. Args: p_z (Distribution): :math:`p(z)`, the distribution instance. p_x_given_z:

Get a `z` sample from :math:`q(z|h(x))`, using the variational net. Args: inputs: The input `x`. n_z: Number

Find the best-f1 score by searching best `threshold` in [`start`, `end`). Returns: list: list for results float: the `thres

Calculate f1 score for a score sequence

Import data to SPOT object Parameters ---------- init_data : list, numpy.array or pandas.Series initial batc

Train the :class:`OmniAnomaly` model with given data. Args: values (np.ndarray): 1-D `float32` array, the standardized

get data from pkl files return shape: (([train_size, x_dim], [train_size] or None), ([test_size, x_dim], [test_size]))

Get the training loss for this VAE. The variational solver is automatically chosen according to `z.is_reparameterized`, and

Get :math:`h(z)`, the hidden network for :math:`p(x|h(z))`. Returns: Module: The hidden network.

Get :math:`h(x)`, the hidden network for :math:`q(z|h(x))`. Returns: Module: The hidden network.

Run the calibration (initialization) step Parameters ---------- level : float (default 0.98) Probab

Iterate through all the mini-batch slices. Args: length (int): Total length of data in an epoch. batch_size (int): Size of e

Get the factory for :math:`p(x|h(z))`. Returns: DistributionFactory: The distribution factory.

Run POT method on given score. Args: init_score (np.ndarray): The data to get init threshold. For `OmniAnomaly`, it shoul

Get the factory for :math:`q(z|h(x))`. Returns: DistributionFactory: The distribution factory.

Constructor Parameters ---------- q Detection level (risk) Returns ---------- SPOT object

Constructor Parameters ---------- q Detection level (risk) Returns ---------- biSPOT object

Construct the :class:`Lambda`. Args: f ((inputs, \**kwargs) -> outputs): The function or lambda expressi

Compute the log-likelihood for the Generalized Pareto Distribution (μ=0) Parameters ---------- Y : numpy.arr

Compute the log-likelihood for the Generalized Pareto Distribution (μ=0) Parameters ---------- Y : numpy.arr

Compute the log-likelihood for the Generalized Pareto Distribution (μ=0) Parameters ---------- Y : numpy.arr

Find possible roots of a scalar function Parameters ---------- fun : function scalar function

Find possible roots of a scalar function Parameters ---------- fun : function scalar function

Find possible roots of a scalar function Parameters ---------- fun : function scalar function

This function allows to append data to the already fitted data Parameters ---------- data : list, numpy.array, pan

This function allows to append data to the already fitted data Parameters ---------- data : list, numpy.array, pan

This function allows to append data to the already fitted data Parameters ---------- data : list, numpy.array, pan

Import data to biSPOT object Parameters ---------- init_data : list, numpy.array or pandas.Series initial ba

Import data to DSPOT object Parameters ---------- init_data : list, numpy.array or pandas.Series initial bat

Import data to biDSPOT object Parameters ---------- init_data : list, numpy.array or pandas.Series initial b

Get the reconstruction probability for `x`. The larger `reconstruction probability`, the less likely a point is anomaly. Yo

Get the training loss for `x`. Args: x (tf.Tensor): 2-D `float32` :class:`tf.Tensor`, the windows of KPI

Run the calibration (initialization) step Parameters ---------- verbose : bool (default = True) If True, giv

Run the calibration (initialization) step Parameters ---------- verbose : bool (default = True) If True, giv

Run the calibration (initialization) step Parameters ---------- verbose : bool (default = True) If True, giv

Whether or not `z` is re-parameterized?