Description:

autotab 0.11

autotab
optimize pipeline for any machine learning mdoel using hierarchical optimization
method for tabular datasets.
Installation
This package can be installed using pip from pypi using following command
pip install autotab

or using github link for the latest code
python -m pip install git+https://github.com/Sara-Iftikhar/autotab.git

or using setup file, go to folder where this repoitory is downloaded
python setup.py install

Example
Click here to

or cick here to

from ai4water.datasets import busan_beach
from skopt.plots import plot_objective
from autotab import OptimizePipeline

data = busan_beach()
input_features = data.columns.tolist()[0:-1]
output_features = data.columns.tolist()[-1:]

transformations = ['minmax', 'zscore', 'log', 'log10', 'sqrt', 'robust', 'quantile', 'none', 'scale']

pl = OptimizePipeline(
inputs_to_transform=data.columns.tolist()[0:-1],
parent_iterations=400,
child_iterations=20,
parent_algorithm='bayes',
child_algorithm="random",
cv_parent_hpo=True,
eval_metric='mse',
monitor=['r2', 'nse'],
input_transformations = transformations,
output_transformations = transformations,
models=[ "LinearRegression",
"LassoLars",
"Lasso",
"RandomForestRegressor",
"HistGradientBoostingRegressor",
"CatBoostRegressor",
"XGBRegressor",
"LGBMRegressor",
"GradientBoostingRegressor",
"ExtraTreeRegressor",
"ExtraTreesRegressor"
],

input_features=data.columns.tolist()[0:-1],
output_features=data.columns.tolist()[-1:],
cross_validator={"KFold": {"n_splits": 5}},
split_random=True,
)

get version information
pl._version_info()

perform optimization
results = pl.fit(data=data, process_results=False)

print optimization report
print(pl.report())

show convergence plot
pl.optimizer_._plot_convergence(save=False)

pl.optimizer_._plot_parallel_coords(figsize=(16, 8), save=False)

_ = pl.optimizer_._plot_distributions(save=False)

pl.optimizer_.plot_importance(save=False)

pl.optimizer_.plot_importance(save=False, plot_type="bar")

_ = plot_objective(results)

pl.optimizer._plot_evaluations(save=False)

pl.optimizer._plot_edf(save=False)

pl.dumbbell_plot(data=data)

pl.dumbbell_plot(data=data, metric_name='r2')

pl.taylor_plot(data=data, save=False, figsize=(6,6))

pl.compare_models()

pl.compare_models(plot_type="bar_chart")

pl.compare_models("r2", plot_type="bar_chart")

get best pipeline with respect to evaluation metric
pl.get_best_pipeline_by_metric('r2')

build fit and evaluate the best pipeline
model = pl.bfe_best_model_from_scratch(data=data)

pl.evaluate_model(model, data=data)

pl.evaluate_model(model, data=data, metric_name='nse')

pl.evaluate_model(model, data=data, metric_name='r2')

get best pipeline with respect to R2
pl.get_best_pipeline_by_metric('r2')

model = pl.bfe_best_model_from_scratch(data=data, metric_name='r2')

pl.evaluate_model(model, data=data, metric_name='r2')

print(f"all results are save in {pl.path} folder")

License

For personal and professional use. You cannot resell or redistribute these repositories in their original state.

Share

• Share on Facebook
• Share on Twitter