集成模型python实现，随机森林，梯度提升决策树

import pandas as pd;

titanic = pd.read_csv('http://biostat.mc.vanderbilt.edu/wiki/pub/Main/DataSets/titanic.txt')

X = titanic[['pclass', 'age', 'sex']]
y = titanic['survived']

X['age'].fillna(X['age'].mean(), inplace = True)

from sklearn.cross_validation import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, random_state = 33)

from sklearn.feature_extraction import DictVectorizer

vec = DictVectorizer(sparse = False)

X_train = vec.fit_transform(X_train.to_dict(orient = 'record'))
X_test = vec.transform(X_test.to_dict(orient = 'record'))

from sklearn.tree import DecisionTreeClassifier

dtc = DecisionTreeClassifier()
dtc.fit(X_train, y_train)
dtc_y_pred = dtc.predict(X_test)

from sklearn.ensemble import RandomForestClassifier

rfc = RandomForestClassifier()
rfc.fit(X