Tree Classification (TaiwanCredit)

Experiment initialization and data preparation

from piml import Experiment
from piml.models import TreeClassifier

exp = Experiment()
exp.data_loader(data="TaiwanCredit", silent=True)
exp.data_summary(feature_exclude=["LIMIT_BAL", "SEX", "EDUCATION", "MARRIAGE", "AGE"], silent=True)
exp.data_prepare(target="FlagDefault", task_type="classification", silent=True)

Train Model

exp.model_train(model=TreeClassifier(max_depth=6), name="Tree")

Evaluate predictive performance

exp.model_diagnose(model="Tree", show="accuracy_table")

          ACC      AUC       F1 LogLoss   Brier

Train  0.8248   0.7716   0.4872  0.4281  0.1334
Test   0.8255   0.7605   0.4715  0.4537  0.1342
Gap    0.0007  -0.0111  -0.0157  0.0256  0.0008

Global interpretation starting from the root node

exp.model_interpret(model="Tree", show="tree_global", root=0, depth=3,
                    original_scale=True, figsize=(16, 10))

Global interpretation starting from the 10-th node

exp.model_interpret(model="Tree", show="tree_global", root=2, depth=3,
                    original_scale=True, figsize=(16, 10))

Local interpretation

exp.model_interpret(model="Tree", show="tree_local", sample_id=0,
                    original_scale=True, figsize=(16, 10))

Estimated memory usage: 34 MB