Python機(jī)器學(xué)習(xí)入門(mén)(四)之Python選擇模型

from pandas import read_csv
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import LeaveOneOut
from sklearn.model_selection import ShuffleSplit
 
 
filename = 'pima_data.csv'
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(filename, names=names)
# print(data.head(10))
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(max_iter=3000)
model.fit(X_train, Y_train)
result = model.score(X_test, Y_test)
print("算法評(píng)估結(jié)果：%3f%%" % (result * 100))

# K折交叉驗(yàn)證分離
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("算法評(píng)估結(jié)果：%.3f%% (%.3f%%)" % (result.mean() * 100, result.std() * 100))

# 棄一交叉驗(yàn)證分離
# 計(jì)算量非常大!!
loocv = LeaveOneOut()
model = LogisticRegression(max_iter=3000)
result = cross_val_score(model,X,Y,cv = loocv)
print("算法評(píng)估結(jié)果：%.3f%% (%.3f%%)"% (result.mean()*100,result.std()*100))

n_splits = 10
test_size = 0.33
seed = 7
kfold = ShuffleSplit(n_splits=n_splits, test_size=test_size, random_state=seed)
model = LogisticRegression(max_iter=3000)
result = cross_val_score(model, X, Y, cv=kfold)
print("算法評(píng)估結(jié)果：%.3f%% (%.3f%%)" % (result.mean() * 100, result.std() * 100))

from pandas import read_csv
import pandas as pd
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
 
#分類(lèi)準(zhǔn)確度
filename = 'pima_data.csv'
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(filename,names=names)
#print(data.head(10))
#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]
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("算法評(píng)估結(jié)果準(zhǔn)確度：%.3f(%.3f)" % (result.mean(),result.std()))

from pandas import read_csv
import pandas as pd
from sklearn.model_selection import KFold
from sklearn.metrics import classification_report
 
#分類(lèi)準(zhǔn)確度
filename = 'pima_data.csv'
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(filename,names=names)
print(data.head(10))
#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]
num_folds = 10
seed = 7
kfold = KFold(n_splits=num_folds,random_state=seed,shuffle=True)
model = LogisticRegression(max_iter=3000)
model.fit(X_train,Y_train)
predicted = model.predict(X_test)
report = classification_report(Y_test, predicted)
print(report)

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)
model = LinearRegression()
 
#平均絕對(duì)誤差
scoring = 'neg_mean_absolute_error'
result = cross_val_score(model, X, Y, cv=kfold, scoring=scoring)
print('MAE:%.3f(%.3f)'%  (result.mean(),result.std()))

#均方誤差
scoring = 'neg_mean_squared_error'
result = cross_val_score(model, X, Y, cv=kfold, scoring=scoring)
print('MSE:%.3f(%.3f)'%  (result.mean(),result.std()))

#決定系數(shù)
scoring = 'r2'
result = cross_val_score(model, X, Y, cv=kfold, scoring=scoring)
print('R2:%.3f(%.3f)'%  (result.mean(),result.std()))