机械学系之数据评估

# 一, 算法评估矩阵
# 1.分类准确度
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))

# 2.对数损失函数 （预测值和真实值差异的程度）
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]
model = LogisticRegression(multi_class='multinomial', max_iter=3000)
num_flods = 10
seed = 7
kfold = KFold(n_splits=num_flods, random_state=seed,shuffle= True)
model = LogisticRegression(multi_class='multinomial', max_iter=3000)
Scoring = 'neg_log_loss'
result = cross_val_score(model, X, Y, cv=kfold, scoring=Scoring)
print('LogLoss: %.3f (%.3f)' % (result.mean(),result.std()))

# AUC图
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_flods = 10
seed = 7
kfold = KFold(n_splits=num_flods, random_state=seed,shuffle= True)
model = LogisticRegression(multi_class='multinomial', max_iter=3000)
scoring = 'roc_auc'
result = cross_val_score(model, X, Y, cv=kfold, scoring= scoring)
print('AUC %.3f (%.3f)' %(result.mean(), result.std()))

# 混淆矩阵 Confusion Matrix
import pandas as pd
from pandas import  read_csv
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from  sklearn.metrics import confusion_matrix
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(multi_class='multinomial', max_iter=3000)
model.fit(X_train, Y_train)
predicted = model.predict(X_test)
matrix = confusion_matrix(Y_test, predicted)
classes = ['0', '1']
datafeame = pd.DataFrame(data=matrix, index=classes, columns=classes)
print(datafeame)

# 结果报告
import pandas as pd
from pandas import  read_csv
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from  sklearn.metrics import classification_report
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(multi_class='multinomial', max_iter=3000)
model.fit(X_train, Y_train)
predicted = model.predict(X_test)
report = classification_report(Y_test, predicted)
print(report)