pycaret.classification.ClassificationExperiment

class pycaret.classification.ClassificationExperiment

__init__() → None

Methods

__init__()
add_metric(id, name, score_func[, target, ...])	Adds a custom metric to be used in the experiment.
automl([optimize, use_holdout, turbo, ...])	This function returns the best model out of all trained models in current session based on the optimize parameter.
blend_models(estimator_list[, fold, round, ...])	This function trains a Soft Voting / Majority Rule classifier for select models passed in the estimator_list param.
calibrate_model(estimator[, method, ...])	This function calibrates the probability of a given estimator using isotonic or logistic regression.
check_drift([reference_data, current_data, ...])	This function generates a drift report file using the evidently library.
check_fairness(estimator, sensitive_features)	There are many approaches to conceptualizing fairness.
compare_models([include, exclude, fold, ...])	This function trains and evaluates performance of all estimators available in the model library using cross validation.
convert_model(estimator[, language])	This function transpiles trained machine learning models into native inference script in different programming languages (Python, C, Java, Go, JavaScript, Visual Basic, C#, PowerShell, R, PHP, Dart, Haskell, Ruby, F#).
create_api(estimator, api_name[, host, port])	This function takes an input estimator and creates a POST API for inference.
create_app(estimator, app_kwargs)	This function creates a basic gradio app for inference.
create_docker(api_name[, base_image, ...])	This function creates a Dockerfile and requirements.txt for productionalizing API end-point.
create_model(estimator[, fold, round, ...])	This function trains and evaluates the performance of a given estimator using cross validation.
dashboard(estimator[, display_format, ...])	This function generates the interactive dashboard for a trained model.
deploy_model(model, model_name, authentication)	This function deploys the transformation pipeline and trained model on cloud.
ensemble_model(estimator[, method, fold, ...])	This function ensembles a given estimator.
evaluate_model(estimator[, fold, ...])	This function displays a user interface for analyzing performance of a trained model.
finalize_model(estimator[, fit_kwargs, ...])	This function trains a given estimator on the entire dataset including the holdout set.
get_allowed_engines(estimator)	Get all the allowed engines for the specified estimator
get_config([variable])	This function is used to access global environment variables.
get_engine(estimator)	Gets the model engine currently set in the experiment for the specified model.
get_leaderboard([finalize_models, ...])	generates leaderboard for all models run in current run.
get_logs([experiment_name, save])	Returns a table of experiment logs.
get_metrics([reset, include_custom, ...])	Returns table of available metrics used in the experiment.
interpret_model(estimator[, plot, feature, ...])	This function takes a trained model object and returns an interpretation plot based on the test / hold-out set.
load_experiment(path_or_file[, data, ...])	Load an experiment saved with save_experiment from path or file.
load_model(model_name[, platform, ...])	This function loads a previously saved pipeline.
models([type, internal, raise_errors])	Returns table of models available in the model library.
optimize_threshold(estimator[, optimize, ...])	This function optimizes probability threshold for a trained classifier.
plot_model(estimator[, plot, scale, save, ...])	This function analyzes the performance of a trained model on holdout set.
plot_model_check_display_format_(display_format)	Checks if the display format is in the allowed list
predict_model(estimator[, data, ...])	This function predicts Label and Score (probability of predicted class) using a trained model.
pull([pop])	Returns the latest displayed table.
remove_metric(name_or_id)	Removes a metric from the experiment.
save_experiment(path_or_file, ...)	Saves the experiment to a pickle file.
save_model(model, model_name[, model_only, ...])	This function saves the transformation pipeline and trained model object into the current working directory as a pickle file for later use.
set_config([variable, value])	This function is used to reset global environment variables.
setup([data, data_func, target, index, ...])	This function initializes the training environment and creates the transformation pipeline.
stack_models(estimator_list[, meta_model, ...])	This function trains a meta model over select estimators passed in the estimator_list parameter.
tune_model(estimator[, fold, round, n_iter, ...])	This function tunes the hyperparameters of a given estimator.

Attributes

X	Feature set.
X_test	Feature set of the test set.
X_test_transformed	Transformed feature set of the test set.
X_train	Feature set of the training set.
X_train_transformed	Transformed feature set of the training set.
X_transformed	Transformed feature set.
dataset	Complete dataset without ignored columns.
dataset_transformed	Transformed dataset.
gpu_n_jobs_param
is_multiclass	Method to check if the problem is multiclass.
test	Test set.
test_transformed	Transformed test set.
train	Training set.
train_transformed	Transformed training set.
variable_and_property_keys
variables
y	Target column.
y_test	Target column of the test set.
y_test_transformed	Transformed target column of the test set.
y_train	Target column of the training set.
y_train_transformed	Transformed target column of the training set.
y_transformed	Transformed target column.