ट्री-आधारित मॉडल: निर्णय वृक्ष और रैंडम फ़ॉरेस्ट

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

X, y = load_iris(return_X_y=True)
model = DecisionTreeClassifier(max_depth=3, random_state=0).fit(X, y)
print("Depth:", model.get_depth())
print("Leaves:", model.get_n_leaves())

from sklearn.tree import DecisionTreeClassifier
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split

X, y = make_classification(random_state=0)
X_tr, X_te, y_tr, y_te = train_test_split(X, y, random_state=0)

model = DecisionTreeClassifier(max_depth=5, min_samples_leaf=5)
model.fit(X_tr, y_tr)
print("Test acc:", model.score(X_te, y_te))

from sklearn.tree import DecisionTreeRegressor
from sklearn.datasets import make_regression
from sklearn.metrics import mean_squared_error

X, y = make_regression(noise=15, random_state=0)
model = DecisionTreeRegressor(max_depth=4).fit(X, y)
print("RMSE:", mean_squared_error(y, model.predict(X))**0.5)

from sklearn.tree import DecisionTreeClassifier
from sklearn.datasets import load_iris
import numpy as np

X, y = load_iris(return_X_y=True)
feature_names = load_iris().feature_names
model = DecisionTreeClassifier().fit(X, y)
for name, imp in sorted(zip(feature_names, model.feature_importances_), key=lambda x: -x[1]):
    print(f"{name}: {imp:.3f}")

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

X, y = make_classification(random_state=0)
X_tr, X_te, y_tr, y_te = train_test_split(X, y, random_state=0)

model = RandomForestClassifier(n_estimators=100, random_state=0)
model.fit(X_tr, y_tr)
print("Test acc:", model.score(X_te, y_te))

from sklearn.ensemble import RandomForestRegressor
from sklearn.datasets import make_regression
from sklearn.metrics import r2_score

X, y = make_regression(noise=10, random_state=0)
model = RandomForestRegressor(n_estimators=100, random_state=0).fit(X, y)
print("R²:", r2_score(y, model.predict(X)))

from sklearn.ensemble import RandomForestClassifier
from sklearn.datasets import make_classification

X, y = make_classification(random_state=0)
model = RandomForestClassifier(n_estimators=100, oob_score=True, random_state=0).fit(X, y)
print("OOB score:", model.oob_score_)

from sklearn.ensemble import GradientBoostingClassifier
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split

X, y = make_classification(random_state=0)
X_tr, X_te, y_tr, y_te = train_test_split(X, y, random_state=0)
model = GradientBoostingClassifier(n_estimators=100).fit(X_tr, y_tr)
print("Test acc:", model.score(X_te, y_te))

# pip install xgboost lightgbm
from xgboost import XGBClassifier
from lightgbm import LGBMClassifier
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split

X, y = make_classification(random_state=0)
X_tr, X_te, y_tr, y_te = train_test_split(X, y, random_state=0)

xgb = XGBClassifier(n_estimators=100, eval_metric="logloss").fit(X_tr, y_tr)
print("XGB acc:", xgb.score(X_te, y_te))

from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import cross_val_score
from sklearn.datasets import make_classification
import numpy as np

X, y = make_classification(random_state=0)
for n in [10, 50, 100, 200]:
    scores = cross_val_score(RandomForestClassifier(n_estimators=n, random_state=0), X, y, cv=5)
    print(f"n={n}: {scores.mean():.3f}")

from sklearn.tree import DecisionTreeClassifier, export_text, plot_tree
from sklearn.datasets import load_iris

X, y = load_iris(return_X_y=True)
model = DecisionTreeClassifier(max_depth=2).fit(X, y)
print(export_text(model, feature_names=load_iris().feature_names.tolist()))