Base Model¶
- class dataprofiler.labelers.base_model.AutoSubRegistrationMeta(clsname, bases, attrs)¶
Bases:
abc.ABCMeta
- mro()¶
Return a type’s method resolution order.
- register(subclass)¶
Register a virtual subclass of an ABC.
Returns the subclass, to allow usage as a class decorator.
- class dataprofiler.labelers.base_model.BaseModel(label_mapping, parameters)¶
Bases:
object
Base Model Initializer. Only model and model parameters are stored here :param parameters: Contains all the appropriate parameters for the model.
Must contain num_labels.
- Returns
None
- requires_zero_mapping = False¶
- property label_mapping¶
mapping of labels to their encoded values
- Type
return
- property reverse_label_mapping¶
Reversed order of current labels, useful for when needed to extract Labels via indices
- Type
return
- property labels¶
Retrieves the label :return: list of labels
- property num_labels¶
- classmethod get_class(class_name)¶
- get_parameters(param_list=None)¶
Returns a dict of parameters from the model given a list. :param param_list: list of parameters to retrieve from the model. :type param_list: list :return: dict of parameters
- set_params(**kwargs)¶
Given kwargs, set the parameters if they exist.
- add_label(label, same_as=None)¶
Adds a label to the data labeler.
- Parameters
label (str) – new label being added to the data labeler
same_as (str) – label to have the same encoding index as for multi-label to single encoding index.
- Returns
None
- set_label_mapping(label_mapping)¶
Sets the labels for the model
- Parameters
label_mapping (Union[list, dict]) – label mapping of the model or list of labels to be converted into the label mapping
- Returns
None
- classmethod help()¶
Help function describing alterable parameters.
- Returns
None
- abstract reset_weights()¶
Reset the weights of the model.
- Returns
None
- abstract predict(data, batch_size, show_confidences, verbose)¶
Predict the data with the current model :param data: model input data to predict on :type data: iterator of data to process :param batch_size: number of samples in the batch of data :type batch_size: int :param show_confidences: whether user wants prediction confidences :type show_confidences: bool :param verbose: Flag to determine whether to print status or not :type verbose: bool :return: char level predictions and confidences :rtype: dict
- abstract classmethod load_from_disk(dirpath)¶
Loads whole model from disk with weights :param dirpath: directory path where you want to load the model from :type dirpath: str :return: None
- abstract save_to_disk(dirpath)¶
Saves whole model to disk with weights :param dirpath: directory path where you want to save the model to :type dirpath: str :return: None
- class dataprofiler.labelers.base_model.BaseTrainableModel(label_mapping, parameters)¶
Bases:
dataprofiler.labelers.base_model.BaseModel
Base Model Initializer. Only model and model parameters are stored here :param parameters: Contains all the appropriate parameters for the model.
Must contain num_labels.
- Returns
None
- abstract fit(train_data, val_data, batch_size=32, epochs=1, label_mapping=None, reset_weights=False)¶
Train the current model with the training data and validation data :param train_data: Training data used to train model :type train_data: Union[pd.DataFrame, pd.Series, np.ndarray] :param val_data: Validation data used to validate the training :type val_data: Union[pd.DataFrame, pd.Series, np.ndarray] :param batch_size: Used to determine number of samples in each batch :type batch_size: int :param epochs: Used to determine how many epochs to run :type epochs: int :param label_mapping: Mapping of the labels :type label_mapping: dict :param reset_weights: Flag to determine whether or not to reset the
model’s weights
- Returns
None
- add_label(label, same_as=None)¶
Adds a label to the data labeler.
- Parameters
label (str) – new label being added to the data labeler
same_as (str) – label to have the same encoding index as for multi-label to single encoding index.
- Returns
None
- classmethod get_class(class_name)¶
- get_parameters(param_list=None)¶
Returns a dict of parameters from the model given a list. :param param_list: list of parameters to retrieve from the model. :type param_list: list :return: dict of parameters
- classmethod help()¶
Help function describing alterable parameters.
- Returns
None
- property label_mapping¶
mapping of labels to their encoded values
- Type
return
- property labels¶
Retrieves the label :return: list of labels
- abstract classmethod load_from_disk(dirpath)¶
Loads whole model from disk with weights :param dirpath: directory path where you want to load the model from :type dirpath: str :return: None
- property num_labels¶
- abstract predict(data, batch_size, show_confidences, verbose)¶
Predict the data with the current model :param data: model input data to predict on :type data: iterator of data to process :param batch_size: number of samples in the batch of data :type batch_size: int :param show_confidences: whether user wants prediction confidences :type show_confidences: bool :param verbose: Flag to determine whether to print status or not :type verbose: bool :return: char level predictions and confidences :rtype: dict
- requires_zero_mapping = False¶
- abstract reset_weights()¶
Reset the weights of the model.
- Returns
None
- property reverse_label_mapping¶
Reversed order of current labels, useful for when needed to extract Labels via indices
- Type
return
- abstract save_to_disk(dirpath)¶
Saves whole model to disk with weights :param dirpath: directory path where you want to save the model to :type dirpath: str :return: None
- set_label_mapping(label_mapping)¶
Sets the labels for the model
- Parameters
label_mapping (Union[list, dict]) – label mapping of the model or list of labels to be converted into the label mapping
- Returns
None
- set_params(**kwargs)¶
Given kwargs, set the parameters if they exist.