==========
``candle``
==========

.. automodule:: candle

   .. contents::
      :local:

.. currentmodule:: candle


Functions
=========

- :py:func:`generate_cross_validation_partition`:
  This function generates partition indices of samples for cross-

- :py:func:`quantile_normalization`:
  This function does quantile normalization to input data. After

- :py:func:`load_csv_data`:
  Load data from the files specified. Columns corresponding to data

- :py:func:`load_Xy_data_noheader`:
  Load training and testing data from the files specified, with the first

- :py:func:`load_Xy_one_hot_data2`:
  Load training and testing data from the files specified, with a column

- :py:func:`select_decorrelated_features`:
  This function selects features whose mutual absolute correlation

- :py:func:`select_features_by_missing_values`:
  This function returns the indices of the features whose missing rates

- :py:func:`select_features_by_variation`:
  This function evaluates the variations of individual features and

- :py:func:`get_file`:
  Downloads a file from a URL if it not already in the cache. Passing the

- :py:func:`validate_file`:
  Validates a file against a MD5 hash.

- :py:func:`fetch_file`:
  Convert URL to file path and download the file if it is not already

- :py:func:`keras_default_config`:
  Defines parameters that intervine in different functions using the keras

- :py:func:`set_up_logger`:
  Set up the event logging system. Two handlers are created. One to send

- :py:func:`str2bool`:
  This is taken from:

- :py:func:`verify_path`:
  Verify if a directory path exists locally. If the path does not exist,

- :py:func:`add_cluster_noise`:
  Undocumented.

- :py:func:`add_column_noise`:
  Undocumented.

- :py:func:`add_gaussian_noise`:
  Undocumented.

- :py:func:`add_noise`:
  Undocumented.

- :py:func:`label_flip`:
  Undocumented.

- :py:func:`label_flip_correlated`:
  Undocumented.

- :py:func:`combat_batch_effect_removal`:
  This function corrects for batch effect in data.

- :py:func:`coxen_multi_drug_gene_selection`:
  This function uses the COXEN approach to select genes for predicting the

- :py:func:`coxen_single_drug_gene_selection`:
  This function selects genes for drug response prediction using the COXEN

- :py:func:`generate_gene_set_data`:
  This function generates genomic data summarized at the gene set level.

- :py:func:`check_flag_conflicts`:
  Check if parameters that must be exclusive are used in conjunction. The

- :py:func:`finalize_parameters`:
  Utility to parse parameters in common as well as parameters particular

- :py:func:`parse_from_dictlist`:
  Functionality to parse options.

- :py:func:`compute_empirical_calibration_interpolation`:
  Use the arrays provided to estimate an empirical mapping between

- :py:func:`compute_statistics_heteroscedastic`:
  Extracts ground truth, mean prediction, error, standard deviation of

- :py:func:`compute_statistics_homoscedastic`:
  Extracts ground truth, mean prediction, error and standard deviation of

- :py:func:`compute_statistics_homoscedastic_summary`:
  Extracts ground truth, mean prediction, error and standard deviation of

- :py:func:`compute_statistics_quantile`:
  Extracts ground truth, 50th percentile mean prediction, low percentile

- :py:func:`generate_index_distribution`:
  Generates a vector of indices to partition the data for training. NO

- :py:func:`split_data_for_empirical_calibration`:
  Extracts a portion of the arrays provided for the computation of the

- :py:func:`plot_2d_density_sigma_vs_error`:
  Functionality to plot a 2D histogram of the distribution of the standard

- :py:func:`plot_array`:
  Undocumented.

- :py:func:`plot_calibrated_std`:
  Functionality to plot values in testing set after calibration. An

- :py:func:`plot_calibration_interpolation`:
  Functionality to plot empirical calibration curves estimated by

- :py:func:`plot_contamination`:
  Functionality to plot results for the contamination model. This includes

- :py:func:`plot_decile_predictions`:
  Functionality to plot the mean of the deciles predicted. The plot

- :py:func:`plot_density_observed_vs_predicted`:
  Functionality to plot a 2D histogram of the distribution of observed

- :py:func:`plot_histogram_error_per_sigma`:
  Functionality to plot a 1D histogram of the distribution of computed errors

- :py:func:`plot_history`:
  Undocumented.

- :py:func:`plot_scatter`:
  Undocumented.

- :py:func:`clr_callback`:
  Creates keras callback for cyclical learning rate.

- :py:func:`clr_check_args`:
  Checks if the arguments for cyclical learning rate are valid.

- :py:func:`clr_set_args`:
  Undocumented.

- :py:func:`build_initializer`:
  Set the initializer to the appropriate Keras initializer function based

- :py:func:`build_optimizer`:
  Set the optimizer to the appropriate Keras optimizer function based on

- :py:func:`compute_trainable_params`:
  Extract number of parameters from the given Keras model

- :py:func:`get_function`:
  Undocumented.

- :py:func:`mae`:
  Undocumented.

- :py:func:`mse`:
  Undocumented.

- :py:func:`r2`:
  Undocumented.

- :py:func:`register_permanent_dropout`:
  Undocumented.

- :py:func:`set_parallelism_threads`:
  Set the number of parallel threads according to the number available on

- :py:func:`set_seed`:
  Set the random number seed to the desired value.

- :py:func:`abstention_acc_class_i_metric`:
  Function to estimate accuracy over the class i prediction after removing

- :py:func:`abstention_acc_metric`:
  Abstained accuracy: Function to estimate accuracy over the predicted

- :py:func:`abstention_class_i_metric`:
  Function to estimate fraction of the samples where the model is

- :py:func:`abstention_loss`:
  Function to compute abstention loss. It is composed by two terms: (i)

- :py:func:`abstention_metric`:
  Function to estimate fraction of the samples where the model is

- :py:func:`acc_class_i_metric`:
  Function to estimate accuracy over the ith class prediction. This

- :py:func:`add_index_to_output`:
  This function adds a column to the training output to store the indices

- :py:func:`add_model_output`:
  This function modifies the last dense layer in the passed keras model.

- :py:func:`contamination_loss`:
  Function to compute contamination loss. It is composed by two terms: (i)

- :py:func:`heteroscedastic_loss`:
  This function computes the heteroscedastic loss for the heteroscedastic

- :py:func:`mae_contamination_metric`:
  This function computes the mean absolute error (mae) for the

- :py:func:`mae_heteroscedastic_metric`:
  This function computes the mean absolute error (mae) for the

- :py:func:`meanS_heteroscedastic_metric`:
  This function computes the mean log of the variance (log S) for the

- :py:func:`modify_labels`:
  This function generates a categorical representation with a class added

- :py:func:`mse_contamination_metric`:
  This function computes the mean squared error (mse) for the

- :py:func:`mse_heteroscedastic_metric`:
  This function computes the mean squared error (mse) for the

- :py:func:`quantile_loss`:
  This function computes the quantile loss for a given quantile fraction.

- :py:func:`quantile_metric`:
  This function computes the quantile metric for a given quantile and

- :py:func:`r2_contamination_metric`:
  This function computes the r2 for the contamination model. The r2 is

- :py:func:`r2_heteroscedastic_metric`:
  This function computes the r2 for the heteroscedastic model. The r2 is

- :py:func:`sparse_abstention_acc_metric`:
  Abstained accuracy: Function to estimate accuracy over the predicted

- :py:func:`sparse_abstention_loss`:
  Function to compute abstention loss. It is composed by two terms: (i)

- :py:func:`triple_quantile_loss`:
  This function computes the quantile loss for the median and low and high

- :py:func:`plot_metrics`:
  Plots keras training curves history.

- :py:func:`build_pytorch_activation`:
  Undocumented.

- :py:func:`build_pytorch_optimizer`:
  Undocumented.

- :py:func:`get_pytorch_function`:
  Undocumented.

- :py:func:`pytorch_initialize`:
  Undocumented.

- :py:func:`pytorch_mse`:
  Undocumented.

- :py:func:`pytorch_xent`:
  Undocumented.

- :py:func:`set_pytorch_seed`:
  Set the random number seed to the desired value

- :py:func:`set_pytorch_threads`:
  Undocumented.


.. autofunction:: generate_cross_validation_partition

.. autofunction:: quantile_normalization

.. autofunction:: load_csv_data

.. autofunction:: load_Xy_data_noheader

.. autofunction:: load_Xy_one_hot_data2

.. autofunction:: select_decorrelated_features

.. autofunction:: select_features_by_missing_values

.. autofunction:: select_features_by_variation

.. autofunction:: get_file

.. autofunction:: validate_file

.. autofunction:: fetch_file

.. autofunction:: keras_default_config

.. autofunction:: set_up_logger

.. autofunction:: str2bool

.. autofunction:: verify_path

.. autofunction:: add_cluster_noise

.. autofunction:: add_column_noise

.. autofunction:: add_gaussian_noise

.. autofunction:: add_noise

.. autofunction:: label_flip

.. autofunction:: label_flip_correlated

.. autofunction:: combat_batch_effect_removal

.. autofunction:: coxen_multi_drug_gene_selection

.. autofunction:: coxen_single_drug_gene_selection

.. autofunction:: generate_gene_set_data

.. autofunction:: check_flag_conflicts

.. autofunction:: finalize_parameters

.. autofunction:: parse_from_dictlist

.. autofunction:: compute_empirical_calibration_interpolation

.. autofunction:: compute_statistics_heteroscedastic

.. autofunction:: compute_statistics_homoscedastic

.. autofunction:: compute_statistics_homoscedastic_summary

.. autofunction:: compute_statistics_quantile

.. autofunction:: generate_index_distribution

.. autofunction:: split_data_for_empirical_calibration

.. autofunction:: plot_2d_density_sigma_vs_error

.. autofunction:: plot_array

.. autofunction:: plot_calibrated_std

.. autofunction:: plot_calibration_interpolation

.. autofunction:: plot_contamination

.. autofunction:: plot_decile_predictions

.. autofunction:: plot_density_observed_vs_predicted

.. autofunction:: plot_histogram_error_per_sigma

.. autofunction:: plot_history

.. autofunction:: plot_scatter

.. autofunction:: clr_callback

.. autofunction:: clr_check_args

.. autofunction:: clr_set_args

.. autofunction:: build_initializer

.. autofunction:: build_optimizer

.. autofunction:: compute_trainable_params

.. autofunction:: get_function

.. autofunction:: mae

.. autofunction:: mse

.. autofunction:: r2

.. autofunction:: register_permanent_dropout

.. autofunction:: set_parallelism_threads

.. autofunction:: set_seed

.. autofunction:: abstention_acc_class_i_metric

.. autofunction:: abstention_acc_metric

.. autofunction:: abstention_class_i_metric

.. autofunction:: abstention_loss

.. autofunction:: abstention_metric

.. autofunction:: acc_class_i_metric

.. autofunction:: add_index_to_output

.. autofunction:: add_model_output

.. autofunction:: contamination_loss

.. autofunction:: heteroscedastic_loss

.. autofunction:: mae_contamination_metric

.. autofunction:: mae_heteroscedastic_metric

.. autofunction:: meanS_heteroscedastic_metric

.. autofunction:: modify_labels

.. autofunction:: mse_contamination_metric

.. autofunction:: mse_heteroscedastic_metric

.. autofunction:: quantile_loss

.. autofunction:: quantile_metric

.. autofunction:: r2_contamination_metric

.. autofunction:: r2_heteroscedastic_metric

.. autofunction:: sparse_abstention_acc_metric

.. autofunction:: sparse_abstention_loss

.. autofunction:: triple_quantile_loss

.. autofunction:: plot_metrics

.. autofunction:: build_pytorch_activation

.. autofunction:: build_pytorch_optimizer

.. autofunction:: get_pytorch_function

.. autofunction:: pytorch_initialize

.. autofunction:: pytorch_mse

.. autofunction:: pytorch_xent

.. autofunction:: set_pytorch_seed

.. autofunction:: set_pytorch_threads


Classes
=======

- :py:class:`Benchmark`:
  Class that implements an interface to handle configuration options for

- :py:class:`Progbar`:
  Progress bar

- :py:class:`ArgumentStruct`:
  Class that converts a python dictionary into an object with named

- :py:class:`MultiGPUCheckpoint`:
  Callback to save the Keras model or model weights at some frequency.

- :py:class:`CyclicLR`:
  This callback implements a cyclical learning rate policy (CLR). The

- :py:class:`CandleRemoteMonitor`:
  Capture Run level output and store/send for monitoring.

- :py:class:`LoggingCallback`:
  Abstract base class used to build new callbacks.

- :py:class:`PermanentDropout`:
  Applies Dropout to the input.

- :py:class:`TerminateOnTimeOut`:
  This class implements timeout on model training.

- :py:class:`AbstentionAdapt_Callback`:
  This callback is used to adapt the parameter alpha in the abstention

- :py:class:`Contamination_Callback`:
  This callback is used to update the parameters of the contamination


.. autoclass:: Benchmark
   :members:

   .. rubric:: Inheritance
   .. inheritance-diagram:: Benchmark
      :parts: 1

.. autoclass:: Progbar
   :members:

   .. rubric:: Inheritance
   .. inheritance-diagram:: Progbar
      :parts: 1

.. autoclass:: ArgumentStruct
   :members:

   .. rubric:: Inheritance
   .. inheritance-diagram:: ArgumentStruct
      :parts: 1

.. autoclass:: MultiGPUCheckpoint
   :members:

   .. rubric:: Inheritance
   .. inheritance-diagram:: MultiGPUCheckpoint
      :parts: 1

.. autoclass:: CyclicLR
   :members:

   .. rubric:: Inheritance
   .. inheritance-diagram:: CyclicLR
      :parts: 1

.. autoclass:: CandleRemoteMonitor
   :members:

   .. rubric:: Inheritance
   .. inheritance-diagram:: CandleRemoteMonitor
      :parts: 1

.. autoclass:: LoggingCallback
   :members:

   .. rubric:: Inheritance
   .. inheritance-diagram:: LoggingCallback
      :parts: 1

.. autoclass:: PermanentDropout
   :members:

   .. rubric:: Inheritance
   .. inheritance-diagram:: PermanentDropout
      :parts: 1

.. autoclass:: TerminateOnTimeOut
   :members:

   .. rubric:: Inheritance
   .. inheritance-diagram:: TerminateOnTimeOut
      :parts: 1

.. autoclass:: AbstentionAdapt_Callback
   :members:

   .. rubric:: Inheritance
   .. inheritance-diagram:: AbstentionAdapt_Callback
      :parts: 1

.. autoclass:: Contamination_Callback
   :members:

   .. rubric:: Inheritance
   .. inheritance-diagram:: Contamination_Callback
      :parts: 1