金融风控08

模型融合

投票器模型融合

from sklearn import model_selection
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.svm import SVC
from sklearn.ensemble import VotingClassifier
import pandas
import warnings
warnings.filterwarnings('ignore')

data = "pima-indians-diabetes.data.csv"
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']#class是类别标签
df = pandas.read_csv(data, names=names)
df.head()

df['class'].unique()

array = df.values
X = array[:,0:8]
Y = array[:,8]
kfold = model_selection.KFold(n_splits=5, random_state=2018)

# 创建投票器的子模型
estimators = []
model_1 = LogisticRegression()
estimators.append(('logistic', model_1))

model_2 = DecisionTreeClassifier()
estimators.append(('dt', model_2))

model_3 = SVC()
estimators.append(('svm', model_3))

# 构建投票器融合
ensemble = VotingClassifier(estimators)
result = model_selection.cross_val_score(ensemble, X, Y, cv=kfold)
print(result.mean())

#Bagging
from sklearn.ensemble import BaggingClassifier

dt = DecisionTreeClassifier()
num = 100
kfold = model_selection.KFold(n_splits=5, random_state=2018)
model = BaggingClassifier(base_estimator=dt, n_estimators=num, random_state=2018)
result = model_selection.cross_val_score(model, X, Y, cv=kfold)
print(result.mean())

#RandomForest
from sklearn.ensemble import RandomForestClassifier
num_trees = 100
max_feature_num = 5
kfold = model_selection.KFold(n_splits=5, random_state=2018)
model = RandomForestClassifier(n_estimators=num_trees, max_features=max_feature_num)
result = model_selection.cross_val_score(model, X, Y, cv=kfold)
print(result.mean())

#Adaboost
from sklearn.ensemble import AdaBoostClassifier
num_trees = 25
kfold = model_selection.KFold(n_splits=5, random_state=2018)
model = AdaBoostClassifier(n_estimators=num_trees, random_state=2018)
result = model_selection.cross_val_score(model, X, Y, cv=kfold)
print(result.mean())