集成学习算法模板

# 下面针对多个模型进行集成操作
from sklearn.svm import SVC, LinearSVC
from sklearn.naive_bayes import GaussianNB
from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier
from sklearn.neural_network import MLPClassifier
from sklearn.kernel_approximation import Nystroem
from sklearn.kernel_approximation import RBFSampler
from sklearn.pipeline import make_pipeline

SEED=666
def get_models():
    """Generate a library of base learners."""
    nb = GaussianNB()
    svc = SVC(C=100, probability=True)
    knn = KNeighborsClassifier(n_neighbors=3)
    lr = LogisticRegression(C=100, random_state=SEED)
    nn = MLPClassifier((80, 10), early_stopping=False, random_state=SEED)
    gb = GradientBoostingClassifier(n_estimators=100, random_state=SEED)
    rf = RandomForestClassifier(n_estimators=10, max_features=3, random_state=SEED)

    models = {'svm': svc,
              'knn': knn,
              'naive bayes': nb,
              'mlp-nn': nn,
              'random forest': rf,
              'gbm': gb,
              'logistic': lr,
              }

    return models
def train_predict(model_list):
    """Fit models in list on training set and return preds"""
    P = np.zeros((y_test.shape[0], len(model_list)))
    P = pd.DataFrame(P)

    print("Fitting models.")
    cols = list()
    for i, (name, m) in enumerate(models.items()):
        print("%s..." % name, end=" ", flush=False)
        m.fit(X_train, y_train)
        P.iloc[:, i] = m.predict_proba(X_test)[:, 1]
        cols.append(name)
        print("done")

    P.columns = cols
    print("Done.\n")
    return P
def score_models(P, y):
    """Score model in prediction DF"""
    print("Scoring models.")
    for m in P.columns:
        score = roc_auc_score(y, P.loc[:, m])
        print("%-26s: %.3f" % (m, score))
    print("Done.\n")

meta_learner = GradientBoostingClassifier(
n_estimators=1000,
loss="exponential",
max_features=4,
max_depth=3,
subsample=0.5,
learning_rate=0.005,
random_state=SEED
)

from mlens.ensemble import SuperLearner

# Instantiate the ensemble with 10 folds
sl = SuperLearner(
    folds=5,
    random_state=SEED,
    verbose=2,
    backend="multiprocessing"
)

# Add the base learners and the meta learner
sl.add(list(get_models().values()), proba=True) 
sl.add_meta(meta_learner, proba=True)

# Train the ensemble
sl.fit(Stan_X,y_train)

# Predict the test set
p_sl = sl.predict_proba(Stan_X_test)

 效果查看：

from sklearn.metrics import roc_auc_score
print("\nSuper Learner ROC-AUC score: %.3f" % roc_auc_score(y_test, p_sl[:, 1]))

根据预测结果，取出标签

import numpy
Y_prelast=numpy.argmax(p_sl,axis=1)