easyensemble算法的完整实现python代码

Sure, here's an example of how you can implement the EasyEnsemble algorithm using Python:

from sklearn.base import BaseEstimator, ClassifierMixin
from sklearn.utils import check_X_y, check_random_state
from sklearn.tree import DecisionTreeClassifier
from sklearn.utils import resample
from sklearn.metrics import accuracy_score

class EasyEnsemble(BaseEstimator, ClassifierMixin):
    def __init__(self, base_estimator=None, n_estimators=10, random_state=None):
        self.base_estimator = base_estimator or DecisionTreeClassifier()
        self.n_estimators = n_estimators
        self.random_state = random_state

    def fit(self, X, y):
        X, y = check_X_y(X, y)
        self.estimators_ = []
        self.estimators_weights_ = []
        random_state = check_random_state(self.random_state)

        for _ in range(self.n_estimators):
            X_resampled, y_resampled = resample(X, y, random_state=random_state)
            estimator = self.base_estimator.fit(X_resampled, y_resampled)
            self.estimators_.append(estimator)
            self.estimators_weights_.append(1.0)

        return self

    def predict(self, X):
        predictions = []

        for estimator in self.estimators_:
            predictions.append(estimator.predict(X))

        return self._majority_vote(predictions)

    def _majority_vote(self, predictions):
        return [self._mode(p) for p in zip(*predictions)]

    def _mode(self, lst):
        return max(set(lst), key=lst.count)

# Example usage:
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split

# Generate a synthetic dataset
X, y = make_classification(n_samples=1000, n_features=10, random_state=42)

# Split the dataset into train and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Create an instance of the EasyEnsemble classifier
ee = EasyEnsemble(n_estimators=10)

# Fit the EasyEnsemble classifier on the training data
ee.fit(X_train, y_train)

# Make predictions on the test data
y_pred = ee.predict(X_test)

# Calculate the accuracy of the predictions
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)

This code defines a custom `EasyEnsemble` class that inherits from `BaseEstimator` and `ClassifierMixin` from scikit-learn. It uses a base estimator (default is `DecisionTreeClassifier`) to create an ensemble of classifiers using resampled subsets of the training data. The predictions are made by majority voting of the predictions from each individual classifier in the ensemble.