机械学系之数据训练

# 1.评估算法
from pandas import  read_csv
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
filename = 'D:/0520代码+数据/第3、4次课：代码+数据/pima_data.csv'
names = ['preq', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(filename, names=names)
array = data.values
X = array[:, 0:8]
Y = array[:, 8]
test_size = 0.33
seed = 4
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=test_size, random_state=seed)
model = LogisticRegression()
model.fit(X_train, Y_train)
result = model.score(X_test, Y_test)
print('算法评估的结果:  %.3f %%' % (result * 100) )

#  2.K值交叉验证
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
filename = 'D:/0520代码+数据/第3、4次课：代码+数据/pima_data.csv'
names = ['preq', '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_fold = 10
seed = 7
kfold = KFold(n_splits=num_fold, random_state=seed, shuffle=True)
model = LogisticRegression(multi_class='multinomial', max_iter=3000)
result = cross_val_score(model, X, Y, cv=kfold)
print("算法结果:  %.3f%% (%.3f%%)" % (result.mean() * 100, result.std() * 100))

# 3.弃一交叉验证
from pandas import  read_csv
from sklearn.model_selection import LeaveOneOut
from sklearn.linear_model import LogisticRegression
from  sklearn.model_selection import cross_val_score
filename = 'D:/0520代码+数据/第3、4次课：代码+数据/pima_data.csv'
names = ['preq', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(filename, names=names)
array = data.values
X = array[:, 0:8]
Y = array[:, 8]
loocv = LeaveOneOut()
model = LogisticRegression(multi_class='multinomial', max_iter=3000)
result = cross_val_score(model, X, Y, cv=loocv)
print('算法评估: %.3f%% (%.3f%%)' % (result.mean() * 100, result.std() * 100))

# 4.重复随机分离数据
from pandas import  read_csv
from sklearn.model_selection import ShuffleSplit
from sklearn.linear_model import LogisticRegression
from  sklearn.model_selection import cross_val_score
filename = 'D:/0520代码+数据/第3、4次课：代码+数据/pima_data.csv'
names = ['preq', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(filename, names=names)
array = data.values
X = array[:, 0:8]
Y = array[:, 8]
n_splits = 10
test_size = 0.33
seed = 7
kfold = ShuffleSplit(n_splits=n_splits, test_size=test_size, random_state=seed)
model = LogisticRegression(multi_class='multinomial', max_iter=3000)
result = cross_val_score(model, X, Y, cv=kfold)
print('算法评估: %.3f%% (%.3f%%)' % (result.mean() * 100, result.std() * 100))