Python机器学习入门(五)之Python算法审查

from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.linear_model import LogisticRegression#逻辑回归
 
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]
 
#逻辑回归
num_folds = 10
seed = 7
kfold = KFold(n_splits=num_folds, random_state=seed, shuffle=True)
model = LogisticRegression(max_iter=3000)
result = cross_val_score(model, X, Y, cv=kfold)
print(result.mean())

from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
 
#相同代码不再赘述
 
#线性判别分析
model = LinearDiscriminantAnalysis()
result = cross_val_score(model, X, Y, cv=kfold)
print(result.mean())

from sklearn.neighbors import KNeighborsClassifier
 
#相同代码不再赘述
 
#K近邻
model = KNeighborsClassifier()
result = cross_val_score(model, X, Y,cv=kfold)
print(result.mean())

from sklearn.naive_bayes import GaussianNB
 
#贝叶斯分类器
model = GaussianNB()
result = cross_val_score(model, X, Y,cv=kfold)
print(result.mean())

from sklearn.tree import DecisionTreeClassifier
 
#分类与回归树
model = DecisionTreeClassifier()
result = cross_val_score(model, X, Y,cv=kfold)
print(result.mean())

from sklearn.svm import SVC
 
#支持向量机
model = SVC()
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.linear_model import LinearRegression
 
filename = 'housing.csv'
names = ['CRIM','ZN','INDUS','CHAS','NOX','RM','AGE','DIS','RAD','TAX','PRTATIO','B','LSTAT','MEDV']
data = read_csv(filename,names=names,delim_whitespace=True)
array = data.values
X = array[:,0:13]
Y = array[:,13]
n_splits = 10
seed = 7
kfold = KFold(n_splits=n_splits,random_state=seed,shuffle=True)
 
#线性回归算法
model = LinearRegression()
scoring = 'neg_mean_squared_error'
result = cross_val_score(model, X, Y, cv=kfold, scoring=scoring)
print("线性回归算法：%.3f" % result.mean())

from sklearn.linear_model import Ridge
 
#岭回归算法
model = Ridge()
scoring = 'neg_mean_squared_error'
result = cross_val_score(model, X, Y, cv=kfold, scoring=scoring)
print("岭回归算法：%.3f" % result.mean())

from sklearn.linear_model import Lasso
 
#套索回归算法
model = Lasso()
scoring = 'neg_mean_squared_error'
result = cross_val_score(model, X, Y, cv=kfold, scoring=scoring)
print("套索回归算法：%.3f" % result.mean())

from sklearn.linear_model import ElasticNet
 
#弹性网络回归算法
model = ElasticNet()
scoring = 'neg_mean_squared_error'
result = cross_val_score(model, X, Y, cv=kfold, scoring=scoring)
print("弹性网络回归算法：%.3f" % result.mean())

from sklearn.neighbors import KNeighborsRegressor
 
#K近邻算法
model = KNeighborsRegressor()
scoring = 'neg_mean_squared_error'
result = cross_val_score(model, X, Y, cv=kfold, scoring=scoring)
print("K近邻算法：%.3f" % result.mean())

from sklearn.tree import DecisionTreeRegressor
 
#分类与回归树算法
model = DecisionTreeRegressor()
scoring = 'neg_mean_squared_error'
result = cross_val_score(model, X, Y, cv=kfold, scoring=scoring)
print("分类与回归树算法：%.3f" % result.mean())

from sklearn.svm import SVR
 
#支持向量机
model = SVR()
scoring = 'neg_mean_squared_error'
result = cross_val_score(model, X, Y, cv=kfold, scoring=scoring)
print("支持向量机:%.3f" % result.mean())

from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import cross_val_score
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.neighbors import KNeighborsRegressor
from sklearn.tree import DecisionTreeRegressor
from sklearn.svm import SVC
from sklearn.naive_bayes import GaussianNB
from matplotlib import pyplot
 
 
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,random_state=seed,shuffle=True)
models={}
models['LR'] = LogisticRegression(max_iter=3000)
models['LDA'] = LinearDiscriminantAnalysis()
models['KNN'] = KNeighborsRegressor()
models['CART'] = DecisionTreeRegressor()
models['SVM'] = SVC()
models['NB'] = GaussianNB()
results = []
for name in models:
    result = cross_val_score(models[name], X, Y, cv=kfold)
    results.append(result)
    msg = '%s: %.3f (%.3f)' % (name, result.mean(), result.std())
    print(msg)
 
#图表显示
fig = pyplot.figure()
fig.suptitle('Algorithm Comparison')
ax = fig.add_subplot(111)
pyplot.boxplot(results)
ax.set_xticklabels(models.keys())
pyplot.show()