Python机器学习入门(六)之Python优化模型

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 = '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,shuffle=True,random_state=seed)
 
#袋装决策树
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)
print(result.mean())

from sklearn.ensemble import RandomForestClassifier
 
#随机森林
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())

from sklearn.ensemble import ExtraTreesClassifier
 
#极端随机树
num_tree = 100
max_features = 3
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())

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 = '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,shuffle=True,random_state=seed)
 
#AdaBost
num_tree = 100
model = AdaBoostClassifier(n_estimators=num_tree,random_state=seed)
result = cross_val_score(model, X, Y, cv=kfold)
print(result.mean())

from sklearn.ensemble import GradientBoostingClassifier
 
#随机 梯度提升
num_tree = 100
model = GradientBoostingClassifier(n_estimators=num_tree,random_state=seed)
result = cross_val_score(model, X, Y, cv=kfold)
print(result.mean())

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 = '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,shuffle=True,random_state=seed)
 
#投票算法
models=[]
model_logistic = LogisticRegression(max_iter=3000)
model_cart = DecisionTreeClassifier()
model_svc = SVC()
models.append(('logistic',model_logistic))
models.append(('cart',model_cart))
models.append(('svc',model_svc))
ensemble_model = VotingClassifier(estimators=models)
result = cross_val_score(ensemble_model, X, Y, cv=kfold)
print(result.mean())

from pandas import read_csv
from sklearn.linear_model import Ridge
from sklearn.model_selection import GridSearchCV
 
#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]
#算法实例化
model = Ridge()
#设置要遍历的参数
param_grid = {'alpha':[1,0.1,0.01,0.001,0]}
#通过网格搜索查询最优参数
grid = GridSearchCV(model, param_grid)
grid.fit(X,Y)
#搜索结果
print('max_score:%.3f'% grid.best_score_)
print('best_para:%.3f'% grid.best_estimator_.alpha)

from sklearn.model_selection import RandomizedSearchCV
from scipy.stats import unifORM
 
#随即搜索优化参数
grid = RandomizedSearchCV(model, param_grid,100,random_state=7)
grid.fit(X,Y)
#搜索结果
print('max_score:%.3f'% grid.best_score_)
print('best_para:%.3f'% grid.best_estimator_.alpha)