Logistic Regression (Classification)

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 MoLogisticRegression

Load and prepare dataset

ds = DataSet()
ds.load(name="TaiwanCredit")
ds.set_random_split()
ds.set_target("FlagDefault")

Train model

model = MoLogisticRegression(name="GLM",
                             feature_names=ds.feature_names,
                             feature_types=ds.feature_types)
model.fit(ds.train_x, ds.train_y)


# Basic accuracy analysis
# ----------------------------------------------------------
ts = TestSuite(ds, model)
results = ts.diagnose_accuracy_table()
results.table

	AUC	ACC	F1	LogLoss	Precision	Recall	Brier
train	0.7369	0.8019	0.3466	0.4647	0.6510	0.2362	0.1470
test	0.7371	0.8075	0.3389	0.4537	0.6578	0.2282	0.1429
GAP	0.0002	0.0056	-0.0078	-0.0110	0.0068	-0.0080	-0.0040

Coefficient interpretation

results = ts.interpret_coef(features=("PAY_1", "PAY_2", "PAY_3", "EDUCATION", "SEX"))
results.plot()

Feature importance

results = ts.interpret_fi()
results.plot()

Main effect plot

results = ts.interpret_effects(features="PAY_1")
results.plot()

Local feature importance analysis

results = ts.interpret_local_fi(dataset="train",
                                sample_index=15,
                                centered=True)
results.plot()

Local feature importance with linear coefficients

results = ts.interpret_local_linear_fi(dataset="test",
                                       sample_index=15,
                                       centered=True)
results.plot()