chemicalchecker.util.pipeline.tasks.task_cc_fit.CCFit

class CCFit(cc_root, cctype, molset, **params)[source]

Bases: BaseTask

Initialize CC fit task.

Parameters:
  • cc_root (str) – The CC root path (Required)

  • cctype (str) – The CC type where the fit is applied (Required)

  • molset (str) – The signature molset (e.g. full or reference) on which the fit method will be called.

  • name (str) – The name of the task (default:cctype)

  • datasets (list) – The list of dataset codes to apply the fit (Optional, by default ‘essential’ which includes all essential CC datasets)

  • sign_args (dict) – A dictionary where key is dataset code and value is a list with all dataset specific parameters for initializing the signature. (Optional)

  • sign_kwargs (dict) – A dictionary where key is dataset code and value is a dictionary with all dataset specific key-worded parameters for initializing the signature. (Optional)

  • fit_args (dict) – A dictionary where key is dataset code and value is a list with all dataset specific parameters for calling the signature fit method. (Optional)

  • fit_kwargs (dict) – A dictionary where key is dataset code and value is a dictionary with all dataset specific key-worded calling the signature fit method. (Optional)

  • hpc_kwargs (dict) – A dictionary where key is dataset code and value is a dictionary with key-worded parameters for the HPC module. (Optional)

  • ref_datasets (list) – List of reference datasets for fitting sign3. (specific for sign3)

Methods

clean

Clean the step.

custom_ready

execute

Same as run but for Airflow.

is_ready

Check if the step is already done.

mark_ready

Mark the step as done.

run

Run the task.

set_dirs

clean(substep=None)

Clean the step.

execute(context)[source]

Same as run but for Airflow.

is_ready(substep=None)

Check if the step is already done.

mark_ready(substep=None)

Mark the step as done.

run()[source]

Run the task.