装袋(Bagging)算法

# 背包基模型
from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.ensemble import BaggingClassifier
from sklearn.tree import DecisionTreeClassifier
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()
num_tree = 100
model = BaggingClassifier(n_estimators=num_tree, random_state=seed)
result = cross_val_score(model, X, Y, cv=kfold)
print(result.mean())

# 随机森林
from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.ensemble import RandomForestClassifier
from sklearn.tree import DecisionTreeClassifier
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
max_features = 3
model = RandomForestClassifier(n_estimators=num_tree, random_state=seed, max_features=max_features)
result = cross_val_score(model, X, Y, cv=kfold)
print(result.mean())

# 极端随机数
from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.ensemble import ExtraTreesClassifier
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
max_features = 7
model = ExtraTreesClassifier(n_estimators=num_tree, random_state=seed, max_features=max_features)
result = cross_val_score(model, X, Y, cv=kfold)
print(result.mean())