def test():
from pycaret.datasets import get_data
data = get_data("boston")
from pycaret.regression import setup, create_model, tune_model
s = setup(data, target="medv", silent=True, html=False, session_id=123)
gbr = create_model("gbr")
tuned_gbr = tune_model(gbr)
xgboost = create_model("xgboost")
tuned_xgboost = tune_model(xgboost)
lightgbm = create_model("lightgbm")
tuned_lightgbm = tune_model(lightgbm)
assert 1 == 1
from pycaret.regression import setup, create_model, tune_model, save_model
import pandas as pd
data = pd.read_csv('C:/tmp/insurance.csv', delimiter=',')
print(data.head())
r2 = setup(data, target='charges', session_id=123,
normalize=True,
polynomial_features=True, trigonometry_features=True,
feature_interaction=True,
bin_numeric_features=['age', 'bmi'])
lr = create_model('lr')
tuned_lr = tune_model(lr)
save_model(tuned_lr, model_name='./models/lr_deployment_20210521')
def regression_model(*, y_col, training_set, normalize, test_size, folds,
metric, model_name, testing_set, imbalanced, seed,
include_models, normalize_method):
"""
Build a regression model for prediction.
Parameters
----------
y_col : str
the name of the target column.
training_set : pd.DataFrame
DataFrame containing the training data.
normalize : bool
if True the dataset will be normalized before training.
test_size : float
Between [0.0-1.0]. The size of the split for test within the training set.
folds : int
number of folds for cross validation.
metric : str
the metric used for evaluating the best model.
model_name : str
the name to save the model.
testing_set : pd.DataFrame
the external dataset for evaluating the best model.
imbalanced
seed : int
random number to initilize the process.
include_models : List
a list of models to be included in the process.
normalize_method : str
The method used for normalizing the data.
Returns
-------
Final regression model
"""
if not metric:
metric = 'RMSE'
setup = pyreg.setup(target=y_col,
data=training_set,
normalize=normalize,
normalize_method=normalize_method,
train_size=1 - test_size,
fold=folds,
silent=True,
session_id=seed)
best_model = pyreg.compare_models(sort=metric, include=include_models)
pyreg.pull().to_csv(model_name + '_compare_models.tsv',
sep='\t',
index=False)
reg_model = pyreg.create_model(best_model)
reg_tuned_model = pyreg.tune_model(reg_model, optimize=metric)
pyreg.pull().to_csv(model_name + '_tuned_model.tsv', sep='\t', index=False)
final_model = pyreg.finalize_model(reg_tuned_model)
pyreg.plot_model(final_model, save=True)
pyreg.plot_model(final_model, plot='feature', save=True)
pyreg.plot_model(final_model, plot='error', save=True)
pyreg.save_model(final_model, model_name)
if len(testing_set.index) != 0:
unseen_predictions = test_regressor(
model_path=model_name + '.pkl',
x_set=testing_set.drop(columns=[y_col]),
y_col=testing_set[y_col],
output=model_name)
unseen_predictions.to_csv(model_name + '_external_testing_results.tsv',
sep='\t',
index=True)
return final_model
fold=3,
round=5,
)
# ---- 模型调参 ---------------------------------------------------------------------------------
# 初始化模型, 固定参数.
params = {'max_features': 'auto'}
rgsr = create_model('rf', verbose=False, **params)
# 模型调参.
params4tuning = {
"n_estimators": np.arange(30, 250, 30),
"min_samples_leaf": [10, 15, 20, 30, 40, 50],
"min_samples_split": [20, 30, 40],
}
rgsr_tuned = tune_model(rgsr,
optimize='R2',
n_iter=2,
fold=5,
round=2,
custom_grid=params4tuning)
# ---- 模型训练和预测 ---------------------------------------------------------------------------
# evaluate_model(rgsr_tuned)
# ---- 模型可解释性 -----------------------------------------------------------------------------
interpret_model(rgsr_tuned, plot='summary')