Python機(jī)器學(xué)習(xí)入門(六)之Python優(yōu)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)
 
#袋裝決策樹
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
 
#隨機(jī)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
 
#極端隨機(jī)樹
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
 
#隨機(jī) 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
 
#導(dǎo)入數(shù)據(jù)
filename = 'pima_data.csv'
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(filename, names=names)
#將數(shù)據(jù)分為輸入數(shù)據(jù)和輸出結(jié)果
array = data.values
X = array[:,0:8]
Y = array[:,8]
#算法實(shí)例化
model = Ridge()
#設(shè)置要遍歷的參數(shù)
param_grid = {'alpha':[1,0.1,0.01,0.001,0]}
#通過網(wǎng)格搜索查詢最優(yōu)參數(shù)
grid = GridSearchCV(model, param_grid)
grid.fit(X,Y)
#搜索結(jié)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
 
#隨即搜索優(yōu)化參數(shù)
grid = RandomizedSearchCV(model, param_grid,100,random_state=7)
grid.fit(X,Y)
#搜索結(jié)果
print('max_score:%.3f'% grid.best_score_)
print('best_para:%.3f'% grid.best_estimator_.alpha)