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
# 导入数据
filename = 'pima_data.csv'
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(filename, names=names)
data.head()preg plas pres skin test mass pedi age class 0 6 148 72 35 0 33.6 0.627 50 1 1 1 85 66 29 0 26.6 0.351 31 0 2 8 183 64 0 0 23.3 0.672 32 1 3 1 89 66 23 94 28.1 0.167 21 0 4 0 137 40 35 168 43.1 2.288 33 1
# 将数据分为输入数据和输出结果
array = data.values
X = array[:, 0:8]
Y = array[:, 8]
num_folds = 10
seed = 7
kfold = KFold(n_splits=num_folds, random_state=seed)
cart = DecisionTreeClassifier()
num_tree = 100
model = BaggingClassifier(base_estimator=cart, n_estimators=num_tree, random_state=seed)
result = cross_val_score(model, X, Y, cv=kfold)
result
array([0.67532468, 0.81818182, 0.75324675, 0.63636364, 0.81818182,
0.81818182, 0.85714286, 0.85714286, 0.69736842, 0.77631579])
result.mean()
0.770745044429255from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.ensemble import RandomForestClassifier
# 导入数据
filename = 'pima_data.csv'
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(filename, names=names)
# 将数据分为输入数据和输出结果
array = data.values
X = array[:, 0:8]
Y = array[:, 8]
num_folds = 10
seed = 7
kfold = KFold(n_splits=num_folds, random_state=seed)
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())
0.7733766233766234from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.ensemble import ExtraTreesClassifier
# 导入数据
filename = 'pima_data.csv'
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(filename, names=names)
# 将数据分为输入数据和输出结果
array = data.values
X = array[:, 0:8]
Y = array[:, 8]
num_folds = 10
seed = 7
kfold = KFold(n_splits=num_folds, random_state=seed)
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())
0.762987012987013from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.ensemble import AdaBoostClassifier
# 导入数据
filename = 'pima_data.csv'
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(filename, names=names)
# 将数据分为输入数据和输出结果
array = data.values
X = array[:, 0:8]
Y = array[:, 8]
num_folds = 10
seed = 7
kfold = KFold(n_splits=num_folds, random_state=seed)
num_tree = 30
model = AdaBoostClassifier(n_estimators=num_tree, random_state=seed)
result = cross_val_score(model, X, Y, cv=kfold)
print(result.mean())
0.760457963089542from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.ensemble import GradientBoostingClassifier
# 导入数据
filename = 'pima_data.csv'
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(filename, names=names)
# 将数据分为输入数据和输出结果
array = data.values
X = array[:, 0:8]
Y = array[:, 8]
num_folds = 10
seed = 7
kfold = KFold(n_splits=num_folds, random_state=seed)
num_tree = 100
model = GradientBoostingClassifier(n_estimators=num_tree, random_state=seed)
result = cross_val_score(model, X, Y, cv=kfold)
print(result.mean())
0.7681989063568012from 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
# 导入数据
filename = 'pima_data.csv'
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(filename, names=names)
# 将数据分为输入数据和输出结果
array = data.values
X = array[:, 0:8]
Y = array[:, 8]
num_folds = 10
seed = 7
kfold = KFold(n_splits=num_folds, random_state=seed)
cart = DecisionTreeClassifier()
models = []
model_logistic = LogisticRegression()
models.append(('logistic', model_logistic))
model_cart = DecisionTreeClassifier()
models.append(('cart', model_cart))
model_svc = SVC()
models.append(('svm', model_svc))
ensemble_model = VotingClassifier(estimators=models)
result = cross_val_score(ensemble_model, X, Y, cv=kfold)
print(result.mean())
0.7329630895420369
数据集下载地址：https://intumu.com/auth/send_fi