pycaret

# Import dataset from pycaret repository
from pycaret.datasets import get_data
insurance = get_data('insurance')

# Initialize environment
from pycaret.regression import *
r1 = setup(insurance, target = 'charges', session_id = 123,
           normalize = True,
           polynomial_features = True, trigonometry_features = True,
           feature_interaction=True, 

pycaret

from pycaret.clustering import *
clu1 = setup(data, ignore_features = ['Country Name', 'Indicator Name'])

pycaret

# import regression module
from pycaret.regression import *

# init setup
reg1 = setup(data, target = 'charges', silent=True, 
            categorical_features=['sex', 'smoker', 'region', 'children'], 
            numeric_features=['age', 'bmi'])

pycaret

#tune with default n_iter i.e. 10
tuned_dt1 = tune_model('dt')

#tune with n_iter = 50
tuned_dt2 = tune_model('dt', n_iter = 50)

pycaret

tuned_lda = tune_model(model='lda', supervised_target='status', estimator='xgboost')

pycaret

predict_model(xgboost, probability_threshold=0.2)

pycaret

# train a catboost model
catboost = create_model('catboost')

# predict on holdout set (when no data is passed)
pred_holdout = predict_model(catboost)

# predict on new dataset
new_data = pd.read_csv('new-data.csv')
pred_new = predict_model(catboost, data = new_data)

pycaret

# Import module
from pycaret.classification import *

# Initialize setup (when using Notebook environment)
clf1 = setup(data, target = 'target-variable')

# Initialize setup (outside of Notebook environment)
clf1 = setup(data, target = 'target-variable', html = False)

# Initialize setup (When using remote execution such as Kaggle / GitHub actions / CI-CD pipelines)

pycaret

# import classification module
from pycaret.classification import *

# init setup
clf1 = setup(data, target = 'name-of-target')

# train a decision tree model
dt = create_model('dt')

# tune hyperparameters of decision tree

pycaret

# import classification module
from pycaret.classification import *

# init setup
clf1 = setup(data, target = 'name-of-target', log_experiment = True, experiment_name = 'exp-name-here')

# compare models
best = compare_models()

# start mlflow server on localhost:5000 (when using notebook)