Hutan Acak

import numpy as np
import matplotlib.pyplot as plt

from sklearn.datasets import make_classification
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import roc_auc_score

n_features = 20
X, y = make_classification(
    n_samples=2500,
    n_features=n_features,
    n_informative=10,
    n_classes=2,
    n_redundant=0,
    n_clusters_per_class=4,
    random_state=777,
)
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.33, random_state=777
)

model = RandomForestClassifier(
    n_estimators=50, max_depth=3, random_state=777, bootstrap=True, oob_score=True
)
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
rf_score = roc_auc_score(y_test, y_pred)
print(f"ROC-AUC @ test dataset = {rf_score}")

import japanize_matplotlib

estimator_scores = []
for i in range(10):
    estimator = model.estimators_[i]
    estimator_pred = estimator.predict(X_test)
    estimator_scores.append(roc_auc_score(y_test, estimator_pred))

plt.figure(figsize=(10, 4))
bar_index = [i for i in range(len(estimator_scores))]
plt.bar(bar_index, estimator_scores)
plt.bar([10], rf_score)
plt.xticks(bar_index + [10], bar_index + ["RF"])
plt.xlabel("tree index")
plt.ylabel("ROC-AUC")
plt.show()

plt.figure(figsize=(10, 4))
feature_index = [i for i in range(n_features)]
plt.bar(feature_index, model.feature_importances_)
plt.xlabel("Feature Index")
plt.ylabel("Feature Importance")
plt.show()

from sklearn.inspection import permutation_importance

p_imp = permutation_importance(
    model, X_train, y_train, n_repeats=10, random_state=77
).importances_mean

plt.figure(figsize=(10, 4))
plt.bar(feature_index, p_imp)
plt.xlabel("Feature Index")
plt.ylabel("Feature Importance")
plt.show()

from sklearn.tree import export_graphviz
from subprocess import call
from IPython.display import Image
from IPython.display import display

for i in range(10):
    try:
        estimator = model.estimators_[i]
        export_graphviz(
            estimator,
            out_file=f"tree{i}.dot",
            feature_names=[f"x{i}" for i in range(n_features)],
            class_names=["A", "B"],
            proportion=True,
            filled=True,
        )

        call(["dot", "-Tpng", f"tree{i}.dot", "-o", f"tree{i}.png", "-Gdpi=500"])
        display(Image(filename=f"tree{i}.png"))
    except KeyboardInterrupt:
        # TODO
        pass

from sklearn.metrics import accuracy_score

for i in range(10):
    model_i = RandomForestClassifier(
        n_estimators=50,
        max_depth=3 + i % 2,
        random_state=i,
        bootstrap=True,
        oob_score=True,
    )
    model_i.fit(X_train, y_train)
    y_pred = model_i.predict(X_test)
    oob_score = model_i.oob_score_
    test_score = accuracy_score(y_test, y_pred)
    print(f"OOB＝{oob_score} test＝{test_score}")