Machine Learning: 決定木とランダムフォレスト — 高精度な分類・回帰のためのアンサンブル思考

from sklearn.ensemble import RandomForestClassifier

rf = RandomForestClassifier(n_estimators=100, oob_score=True, random_state=42)
rf.fit(X_train, y_train)
print(f"OOB Accuracy: {rf.oob_score_:.3f}")
print(f"Top feature: {feature_names[rf.feature_importances_.argmax()]}")

from sklearn.tree import DecisionTreeClassifier, plot_tree
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, classification_report
import matplotlib.pyplot as plt

iris = load_iris()
X_train, X_test, y_train, y_test = train_test_split(
    iris.data, iris.target, test_size=0.3, random_state=42, stratify=iris.target
)

# Train with pre-pruning
tree = DecisionTreeClassifier(max_depth=3, min_samples_leaf=5, random_state=42)
tree.fit(X_train, y_train)

y_pred = tree.predict(X_test)
print(f"Accuracy: {accuracy_score(y_test, y_pred):.4f}")
print(f"Tree depth: {tree.get_depth()}")
print(f"Number of leaves: {tree.get_n_leaves()}")

# Visualize tree
fig, ax = plt.subplots(figsize=(14, 8))
plot_tree(tree, feature_names=iris.feature_names,
          class_names=iris.target_names, filled=True, rounded=True, ax=ax)
plt.title("Decision Tree (max_depth=3)")
plt.tight_layout()
plt.savefig("decision_tree.png", dpi=150)

# Runs successfully

from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import cross_val_score
from sklearn.datasets import load_iris

X, y = load_iris(return_X_y=True)

configs = {
    "No pruning": DecisionTreeClassifier(random_state=42),
    "max_depth=2": DecisionTreeClassifier(max_depth=2, random_state=42),
    "max_depth=3": DecisionTreeClassifier(max_depth=3, random_state=42),
    "min_samples_leaf=5": DecisionTreeClassifier(min_samples_leaf=5, random_state=42),
    "max_depth=3 + min_samples_leaf=5": DecisionTreeClassifier(
        max_depth=3, min_samples_leaf=5, random_state=42),
}

for name, model in configs.items():
    scores = cross_val_score(model, X, y, cv=5, scoring="accuracy")
    model.fit(X, y)
    print(f"{name:35s}: Accuracy={scores.mean():.3f}, Leaves={model.get_n_leaves()}")

# Runs successfully

from sklearn.ensemble import RandomForestClassifier
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

X, y = load_iris(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

rf = RandomForestClassifier(
    n_estimators=100,
    max_depth=None,
    oob_score=True,
    random_state=42,
)
rf.fit(X_train, y_train)

print(f"OOB Score: {rf.oob_score_:.4f}")
print(f"Test Accuracy: {accuracy_score(y_test, rf.predict(X_test)):.4f}")
print(f"Number of trees: {rf.n_estimators}")

# Runs successfully

from sklearn.ensemble import RandomForestRegressor
from sklearn.model_selection import train_test_split, cross_val_score
from sklearn.metrics import mean_absolute_error, r2_score
import numpy as np

rng = np.random.default_rng(42)
n = 500
X = rng.uniform(0, 100, (n, 6))
y = 50 + 0.8 * X[:, 0] + 1.2 * X[:, 1] - 0.5 * X[:, 2] + rng.normal(0, 5, n)

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Compare different n_estimators
for n_est in [10, 50, 100, 200]:
    rf = RandomForestRegressor(n_estimators=n_est, random_state=42, n_jobs=-1)
    rf.fit(X_train, y_train)
    score = rf.score(X_test, y_test)
    mae = mean_absolute_error(y_test, rf.predict(X_test))
    print(f"n_estimators={n_est:3d}: R²={score:.4f}, MAE={mae:.2f}")

# Runs successfully

from sklearn.ensemble import RandomForestClassifier
from sklearn.inspection import permutation_importance
from sklearn.datasets import load_iris
import matplotlib.pyplot as plt
import numpy as np

X, y = load_iris(return_X_y=True)
feature_names = load_iris().feature_names

rf = RandomForestClassifier(n_estimators=100, random_state=42)
rf.fit(X, y)

# Method 1: MDI (built-in, fast but biased)
mdi_importance = rf.feature_importances_

# Method 2: Permutation importance (slower but more reliable)
perm_result = permutation_importance(rf, X, y, n_repeats=30, random_state=42, n_jobs=-1)
perm_importance = perm_result.importances_mean

# Compare
fig, axes = plt.subplots(1, 2, figsize=(14, 5))

y_pos = np.arange(len(feature_names))
axes[0].barh(y_pos, mdi_importance, color="#2196F3")
axes[0].set_yticks(y_pos)
axes[0].set_yticklabels(feature_names)
axes[0].set_title("MDI Feature Importance")

axes[1].barh(y_pos, perm_importance, color="#4CAF50")
axes[1].set_yticks(y_pos)
axes[1].set_yticklabels(feature_names)
axes[1].set_title("Permutation Feature Importance")

plt.tight_layout()
plt.savefig("feature_importance.png", dpi=150)

# Runs successfully

from sklearn.ensemble import RandomForestClassifier
import pandas as pd
import numpy as np

rng = np.random.default_rng(42)
n = 1000
df = pd.DataFrame({
    "price_usd": rng.uniform(10, 200, n),
    "first_week_sales": rng.integers(10, 2000, n),
    "category_trend_score": rng.uniform(0, 1, n),
    "ad_budget_k": rng.uniform(1, 50, n),
    "review_score": rng.uniform(1, 5, n),
    "return_rate": rng.uniform(0, 0.3, n),
    "stock_depth": rng.integers(10, 500, n),
})

df["is_hit"] = (
    (df["first_week_sales"] > 500)
    & (df["category_trend_score"] > 0.6)
    & (df["price_usd"] < 100)
).astype(int) | (rng.random(n) < 0.05)  # Add 5% noise

X = df.drop(columns=["is_hit"])
y = df["is_hit"]

rf = RandomForestClassifier(n_estimators=200, random_state=42)
rf.fit(X, y)

importance = pd.DataFrame({
    "feature": X.columns,
    "importance": rf.feature_importances_,
}).sort_values("importance", ascending=False)

print("Feature Importance for Hit Product Prediction:")
print(importance.to_string(index=False))

Feature Importance for Hit Product Prediction: