Note

Go to the end to download the full example code.

Mixture of Expert (MoE) Regression#

Installation

# To install the required package, use the following command:
# !pip install modeva

Authentication

# To get authentication, use the following command: (To get full access please replace the token to your own token)
# from modeva.utils.authenticate import authenticate
# authenticate(auth_code='eaaa4301-b140-484c-8e93-f9f633c8bacb')

Import required modules

from modeva import DataSet
from modeva import TestSuite
from modeva.models import MoMoERegressor, MoXGBRegressor

Load and prepare dataset for regression

ds = DataSet()
ds.load(name="BikeSharing")
ds.set_random_split()
ds.set_target("cnt")

ds.scale_numerical(features=("cnt",), method="log1p")
ds.preprocess()

Train models#

model = MoMoERegressor(max_depth=2)
model.fit(ds.train_x, ds.train_y)

MoMoERegressor(base_score=None, booster=None, callbacks=None,
               colsample_bylevel=None, colsample_bynode=None,
               colsample_bytree=None, device=None, early_stopping_rounds=None,
               enable_categorical=False, eval_metric=None, feature_types=None,
               gamma=None, grow_policy=None, importance_type=None,
               interaction_constraints=None, learning_rate=None, max_bin=None,
               max_cat_threshold=None, max_cat_to_onehot=None,
               max_delta_step=None, max_depth=2, max_leaves=None,
               min_child_weight=None, missing=nan, monotone_constraints=None,
               multi_strategy=None, n_estimators=None, n_jobs=None,
               name='MoMoERegressor', num_parallel_tree=None, ...)
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.


Basic accuracy analysis#

ts = TestSuite(ds, model)
results = ts.diagnose_accuracy_table()
results.table
MSE MAE R2
train 0.1051 0.2259 0.9476
test 0.1288 0.2478 0.9363
GAP 0.0237 0.0219 -0.0113


Local MOE weights interpretation#

results = ts.interpret_local_moe_weights()
results.plot()


Data drift test between cluster “1” with the rest samples#

results = ts.interpret_moe_cluster_analysis()
data_results = ds.data_drift_test(**results.value[2]["data_info"],
                                  distance_metric="PSI",
                                  psi_method="uniform",
                                  psi_bins=10)
data_results.plot("summary")


Interpret feature importance#

results = ts.interpret_fi()

Expert No. 0

results.plot("0")


Expert No. 2

results.plot("2")


Interpret effect importance#

results = ts.interpret_ei()

Expert No. 0

results.plot("0")


Expert No. 2

results.plot("2")


Interpret effects#

results = ts.interpret_effects(features="hr")

Expert No. 0

results.plot("0")


Expert No. 2

results.plot("2")


Expert of all clusters

results.plot("all")


Cluster performance analysis#

results = ts.interpret_moe_cluster_analysis()
results.plot()


Distribution difference summary between cluster-0 with the rest

data_results = ds.data_drift_test(**results.value[0]["data_info"],
                                  distance_metric="PSI",
                                  psi_method="uniform",
                                  psi_bins=10)
data_results.plot("summary")


Distributional difference for hr between cluster-0 with the rest

data_results.plot(("density", "hr"))


Local feature importance analysis#

results = ts.interpret_local_fi(dataset='train', sample_index=1)

Expert No. 0

results.plot("0")


Expert No. 2

results.plot("2")


Local effect importance analysis#

results = ts.interpret_local_ei(dataset='train', sample_index=1)

Expert No. 0

results.plot("0")


Expert No. 2

results.plot("2")


Total running time of the script: (0 minutes 17.603 seconds)

Gallery generated by Sphinx-Gallery