LostTech.TensorFlow : API Documentation

Type TimeSeriesModel

Namespace tensorflow_estimator.python.estimator.canned.timeseries.model

Parent PythonObjectContainer

Interfaces ITimeSeriesModel

Methods

Properties

Public instance methods

object define_loss(IDictionary<object, object> features, string mode)

object define_loss(object features, string mode)

object define_loss_dyn(object features, object mode)

void generate(object number_of_series, object series_length, object model_parameters, object seed)

object generate_dyn(object number_of_series, object series_length, object model_parameters, object seed)

Sample synthetic data from model parameters, with optional substitutions.

Returns `number_of_series` possible sequences of future values, sampled from the generative model with each conditioned on the previous. Samples are based on trained parameters, except for those parameters explicitly overridden in `model_parameters`.

For distributions over future observations, see predict().
Parameters
object number_of_series
Number of time series to create.
object series_length
Length of each time series.
object model_parameters
A dictionary mapping model parameters to values, which replace trained parameters when generating data.
object seed
If specified, return deterministic time series according to this value.
Returns
object
A dictionary with keys TrainEvalFeatures.TIMES (mapping to an array with shape [number_of_series, series_length]) and TrainEvalFeatures.VALUES (mapping to an array with shape [number_of_series, series_length, num_features]).

object get_batch_loss(object features, string mode, PythonClassContainer state)

object get_batch_loss(object features, string mode, IGraphNodeBase state)

object get_batch_loss(IDictionary<object, object> features, string mode, IEnumerable<object> state)

object get_batch_loss(IDictionary<object, object> features, string mode, IGraphNodeBase state)

object get_batch_loss(IDictionary<object, object> features, string mode, PythonClassContainer state)

object get_batch_loss(object features, string mode, IEnumerable<object> state)

object get_batch_loss_dyn(object features, object mode, object state)

Computes predictions and a loss.
Parameters
object features
A dictionary (such as is produced by a chunker) with the following key/value pairs (shapes are given as required for training): TrainEvalFeatures.TIMES: A [batch size, self.window_size] integer Tensor with times for each observation. To train on longer sequences, the data should first be chunked. TrainEvalFeatures.VALUES: A [batch size, self.window_size, self.num_features] Tensor with values for each observation. When evaluating, `TIMES` and `VALUES` must have a window size of at least self.window_size, but it may be longer, in which case the last window_size - self.input_window_size times (or fewer if this is not divisible by self.output_window_size) will be evaluated on with non-overlapping output windows (and will have associated predictions). This is primarily to support qualitative evaluation/plotting, and is not a recommended way to compute evaluation losses (since there is no overlap in the output windows, which for window-based models is an undesirable bias).
object mode
The tf.estimator.ModeKeys mode to use (TRAIN or EVAL).
object state
Unused
Returns
object
A model.ModelOutputs object.

ValueTuple<Tensor, object, object> get_start_state()

Returns a tuple of state for the start of the time series.

For example, a mean and covariance. State should not have a batch dimension, and will often be TensorFlow Variables to be learned along with the rest of the model parameters.

object get_start_state_dyn()

Returns a tuple of state for the start of the time series.

For example, a mean and covariance. State should not have a batch dimension, and will often be TensorFlow Variables to be learned along with the rest of the model parameters.

void initialize_graph(object input_statistics)

Define ops for the model, not depending on any previously defined ops.
Parameters
object input_statistics
A math_utils.InputStatistics object containing input statistics. If None, data-independent defaults are used, which may result in longer or unstable training.

object initialize_graph_dyn(object input_statistics)

Define ops for the model, not depending on any previously defined ops.
Parameters
object input_statistics
A math_utils.InputStatistics object containing input statistics. If None, data-independent defaults are used, which may result in longer or unstable training.

IDictionary<string, object> predict(IDictionary<object, object> features)

Computes predictions multiple steps into the future.
Parameters
IDictionary<object, object> features
A dictionary with the following key/value pairs:
Returns
IDictionary<string, object>
A dictionary with keys, "mean", "covariance". The values are Tensors of shape [batch_size, predict window size, num_features] and correspond to the values passed in `TIMES`.

Public properties

DType dtype get; set;

IList<object> exogenous_feature_columns get;

object exogenous_feature_columns_dyn get;

object num_features get; set;

object PythonObject get;