提升(Boosting)算法

#Adaboost
from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.ensemble import AdaBoostClassifier
filename = 'D:/0520代码+数据/第3、4次课：代码+数据/pima_data.csv'
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(filename, names=names)
array = data.values
X = array[:, 0:8]
Y = array[:, 8]
num_folds = 10
seed = 7
kfold = KFold(n_splits=num_folds, random_state=seed, shuffle=True)
num_tree = 30
model =AdaBoostClassifier()
model = AdaBoostClassifier(n_estimators=num_tree, random_state=seed)
result = cross_val_score(model, X, Y, cv=kfold)
print(result.mean())

# 随机梯度提升
from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.ensemble import GradientBoostingClassifier
filename = 'D:/0520代码+数据/第3、4次课：代码+数据/pima_data.csv'
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(filename, names=names)
array = data.values
X = array[:, 0:8]
Y = array[:, 8]
num_folds = 10
seed = 7
kfold = KFold(n_splits=num_folds, random_state=seed, shuffle=True)
num_tree = 100
model = GradientBoostingClassifier(n_estimators=num_tree, random_state=seed)
result = cross_val_score(model, X, Y, cv=kfold)
print(result.mean())

# 投票算法
from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.ensemble import VotingClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.svm import SVC
from sklearn.linear_model import LogisticRegression
filename = 'D:/0520代码+数据/第3、4次课：代码+数据/pima_data.csv'
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(filename, names=names)
array = data.values
X = array[:, 0:8]
Y = array[:, 8]
num_folds = 10
seed = 7
kfold = KFold(n_splits=num_folds, random_state=seed, shuffle=True)
cart = DecisionTreeClassifier()
models = []
model_logistic = LogisticRegression()
models.append(('logistic', model_logistic))
model_cart = DecisionTreeClassifier()
models.append(('cart', model_cart))
model_svc = SVC()
models.append(('svc', model_svc))
ensemble_model = VotingClassifier(estimators=models)
result = cross_val_score(ensemble_model, X, Y, cv=kfold)
print(result.mean())