import numpy as np
from sklearn.datasets import load_boston
from sklearn.tree import DecisionTreeRegressor
from sklearn.ensemble import RandomForestRegressor as skRandomForestRegressor

def r2_score(y_true, y_pred):
    numerator = np.sum((y_true - y_pred) ** 2)
    denominator = np.sum((y_true - np.mean(y_true)) ** 2)
    return 1 - numerator / denominator

class RandomForestRegressor():
    def __init__(self, n_estimators=100, max_depth=None, max_features="auto",
                 oob_score=False, random_state=0):
        self.n_estimators = n_estimators
        self.max_depth = max_depth
        self.max_features = max_features
        self.oob_score = oob_score
        self.random_state = random_state

    def fit(self, X, y):
        self.n_features_ = X.shape[1]
        MAX_INT = np.iinfo(np.int32).max
        rng = np.random.RandomState(self.random_state)
        self.estimators_ = []
        for i in range(self.n_estimators):
            est = DecisionTreeRegressor(max_depth=self.max_depth,
                                        max_features=self.max_features,
                                        random_state=rng.randint(MAX_INT))
            sample_rng = np.random.RandomState(est.random_state)
            sample_indices = sample_rng.randint(0, X.shape[0], X.shape[0])
            sample_counts = np.bincount(sample_indices, minlength=X.shape[0])
            est.fit(X, y, sample_weight=sample_counts)
            self.estimators_.append(est)
        if self.oob_score:
            self._set_oob_score(X, y)
        return self

    def _set_oob_score(self, X, y):
        predictions = np.zeros(X.shape[0])
        n_predictions = np.zeros(X.shape[0])
        for i in range(self.n_estimators):
            sample_rng = np.random.RandomState(self.estimators_[i].random_state)
            sample_indices = sample_rng.randint(0, X.shape[0], X.shape[0])
            mask = np.ones(X.shape[0], dtype=bool)
            mask[sample_indices] = False
            predictions[mask] += self.estimators_[i].predict(X[mask])
            n_predictions[mask] += 1
        predictions /= n_predictions
        self.oob_prediction_ = predictions
        self.oob_score_ = r2_score(y, predictions)

    def predict(self, X):
        pred = np.zeros(X.shape[0])
        for i in range(self.n_estimators):
            pred += self.estimators_[i].predict(X)
        pred /= self.n_estimators
        return pred

    @property
    def feature_importances_(self):
        all_importances = np.zeros(self.n_features_)
        for i in range(self.n_estimators):
            all_importances += self.estimators_[i].feature_importances_
        all_importances /= self.n_estimators   
        return all_importances / np.sum(all_importances)

X, y = load_boston(return_X_y=True)
clf1 = RandomForestRegressor(random_state=0, oob_score=True).fit(X, y)
clf2 = skRandomForestRegressor(random_state=0, oob_score=True).fit(X, y)
pred1 = clf1.predict(X)
pred2 = clf2.predict(X)
assert np.allclose(pred1, pred2)
assert np.allclose(clf1.oob_prediction_, clf2.oob_prediction_)
assert np.allclose(clf1.oob_score_, clf2.oob_score_)
assert np.allclose(clf1.feature_importances_, clf2.feature_importances_)