SimpleRNNClassifierSKTimeWrapper
Python template · sinapsis_sktime.templates.sktime_classifiers
Overview
Template for SkTime classification model training and inference for the deep_learning module.
SimpleRNNClassifier — inherited documentation
Simple recurrent neural network.
For a drop-in replacement based on PyTorch, see `SimpleRNNClassifierTorch`.
Parameters ---------- n_epochs : int, default = 100 the number of epochs to train the model batch_size : int, default = 1 the number of samples per gradient update. units : int, default = 6 number of units in the network callbacks : tuple of tf.keras.callbacks.Callback objects, default = None add_default_callback : bool, default = True whether to add default callback random_state : int or None, default=0 Seed for random number generation. verbose : boolean, default = False whether to output extra information loss : string, default="mean_squared_error" fit parameter for the keras model metrics : list of strings, default=["accuracy"] metrics to use in fitting the neural network activation : string or a tf callable, default="sigmoid" Activation function used in the output layer. List of available activation functions: https://keras.io/api/layers/activations/ activation_hidden : string or a tf callable, default="tanh" Activation function used in the hidden layers. List of available activation functions: https://keras.io/api/layers/activations/ use_bias : boolean, default = True whether the layer uses a bias vector. optimizer : keras.optimizers object, default = RMSprop(lr=0.001) specify the optimizer and the learning rate to be used. dropout : float, default=0.0 The dropout rate for the RNN layer.
References ---------- ..[1] benchmark forecaster in M4 forecasting competition: https://github.com/Mcompetitions/M4-methods
Examples -------- >>> from sktime.classification.deep_learning.rnn import SimpleRNNClassifier >>> from sktime.datasets import load_unit_test >>> X_train, y_train = load_unit_test(split="train") >>> clf = SimpleRNNClassifier(n_epochs=20,batch_size=20) # doctest: +SKIP >>> clf.fit(X_train, y_train) # doctest: +SKIP ResNetClassifier(...)
Capabilities
Capabilities: not setInstallation
Install the published package using pip or uv.
pip install sinapsis-sktime==1.0.0uv pip install sinapsis-sktime==1.0.0uv add sinapsis-sktime==1.0.0Configuration
Effective fields from the inspector schema, including nested Pydantic model fields.
Optional
Default: null
Optional
Default: "/sinapsis-hub/private/platform/sinapsis-hub/playground/publish"
Path where the trained model will be saved. simplernnclassifier_init n_epochs <class 'int'>: default: 100 batch_size <class 'int'>: default: 1 units <class 'int'>: default: 6 callbacks <class 'NoneType'>: default: None… Read full field description
Path where the trained model will be saved. simplernnclassifier_init n_epochs <class 'int'>: default: 100 batch_size <class 'int'>: default: 1 units <class 'int'>: default: 6 callbacks <class 'NoneType'>: default: None add_default_callback <class 'bool'>: default: True random_state <class 'int'>: default: 0 verbose <class 'bool'>: default: False loss <class 'str'>: default: mean_squared_error metrics <class 'NoneType'>: default: None activation <class 'str'>: default: sigmoid activation_hidden <class 'str'>: default: tanh use_bias <class 'bool'>: default: True optimizer <class 'NoneType'>: default: None dropout <class 'float'>: default: 0.0
Required
Default: null
Required
Default: null
Optional
Default: "mean_squared_error"
Optional
Default: 6
Optional
Default: 0
Optional
Default: null
Optional
Default: false
Optional
Default: 100
Optional
Default: true
Optional
Default: null
Optional
Default: null
Optional
Default: "sigmoid"
Optional
Default: 1
Optional
Default: 0
Optional
Default: "tanh"
Optional
Default: true
Configuration example
Generated from documented defaults. Replace any placeholders and complete required nested settings before running.
templates:
- template_name: "SimpleRNNClassifierSKTimeWrapper"
class_name: "SimpleRNNClassifierSKTimeWrapper"
attributes:
root_dir: "/sinapsis-hub/private/platform/sinapsis-hub/playground/publish"
model_save_path: "<required>"
simplernnclassifier_init:
loss: "mean_squared_error"
units: 6
dropout: 0
metrics: null
verbose: false
n_epochs: 100
use_bias: true
callbacks: null
optimizer: null
activation: "sigmoid"
batch_size: 1
random_state: 0
activation_hidden: "tanh"
add_default_callback: true
Inheritance
sinapsis_sktime.templates.sktime_classifiers.SKTimeDeepLearningClassifiersEnvironment variables
Environment definitions belong to their canonical Python modules.