交叉验证（Cross Validation）与网格搜索（Grid
2022-05-03 本文已影响0人
万州客
收到了三份代码，我觉得clf = gs.best_estimator_这种用法，应该是比较科学和不重复的，书写也比较规范，又不含糊，求验证~
https://blog.csdn.net/wp_python/article/details/80255466
原始数据划分为3份，分别为：训练集、验证集和测试集；其中训练集用来模型训练，验证集用来调整参数，而测试集用来衡量模型表现好坏。
那请问是不是用了GridSearchCV，就可以不用cross_val_score、cross_validate了，就也相当于是交叉验证了，经过训练之后就只需要测试就可以了对吧？---对的
一，clf = gs.best_estimator_写得明白
from sklearn.model_selection import validation_curve
import pandas as pd
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import make_pipeline
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import GridSearchCV
from sklearn.svm import SVC
df = pd.read_csv('xxx\\wdbc.data',
header=None)
print(df.head())
X = df.loc[:, 2:].values
y = df.loc[:, 1].values
le = LabelEncoder()
y = le.fit_transform(y)
X_train, X_test, y_train, y_test = train_test_split(X, y,
test_size=0.20,
stratify=y,
random_state=1)
print(len(X_train))
pipe_svc = make_pipeline(StandardScaler(),
SVC(random_state=1)) # 支持向量机（SVM）
param_range = [0.0001, 0.001, 0.01, 0.1, 1.0, 10.0, 100.0, 1000.0]
param_grid = [{'svc__C': param_range,
'svc__kernel': ['linear']},
{'svc__C': param_range,
'svc__gamma': param_range,
'svc__kernel': ['rbf']}]
gs = GridSearchCV(estimator=pipe_svc,
param_grid=param_grid,
scoring='accuracy',
cv=10,
n_jobs=-1)
gs = gs.fit(X_train, y_train)
print(gs.best_score_)
print(gs.best_params_)
clf = gs.best_estimator_
clf.fit(X_train, y_train)
print('Test accuracy: %.3f' % clf.score(X_test, y_test))
二，grid_search.fit(X_train, y_train) # 训练，找到最优的参数，同时使用最优的参数实例化一个新的SVC estimator，这个就有些含糊，图省事
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
__author__ = 'WF'
from sklearn.datasets import load_iris
from sklearn.svm import SVC
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.model_selection import cross_val_score
def simpleGridSearch(X_train, X_test, y_train, y_test):
'''
使用for循环实现网格搜索
:param X_train:
:param X_test:
:param y_train:
:param y_test:
:return:
'''
# grid search start
best_score = 0
for gamma in [0.001, 0.01, 0.1, 1, 10, 100]:
for C in [0.001, 0.01, 0.1, 1, 10, 100]:
svm = SVC(gamma=gamma,C=C)#对于每种参数可能的组合，进行一次训练；
svm.fit(X_train,y_train)
score = svm.score(X_test,y_test)
if score > best_score:#找到表现最好的参数
best_score = score
best_parameters = {'gamma':gamma,'C':C}
print("Best score:{:.2f}".format(best_score))
print("Best parameters:{}".format(best_parameters))
def gridSearchCv(X_train, X_test, y_train, y_test):
'''
使用for循环实现网格搜索与交叉验证
:param X_train:
:param X_test:
:param y_train:
:param y_test:
:return:
'''
best_score = 0.0
for gamma in [0.001,0.01,0.1,1,10,100]:
for C in [0.001,0.01,0.1,1,10,100]:
svm = SVC(gamma=gamma, C=C)
scores = cross_val_score(svm, X_train, y_train, cv=5) #5折交叉验证
score = scores.mean() #取平均数
if score > best_score:
best_score = score
best_parameters = {"gamma": gamma, "C": C}
svm = SVC(**best_parameters)
svm.fit(X_train, y_train)
test_score = svm.score(X_test,y_test)
print("Best score on validation set:{:.2f}".format(best_score))
print("Best parameters:{}".format(best_parameters))
print("Score on testing set:{:.2f}".format(test_score))
def skGridSearchCv(X_train, X_test, y_train, y_test):
'''
利用sklearn中的GridSearchCV类
:param X_train:
:param X_test:
:param y_train:
:param y_test:
:return:
'''
#把要调整的参数以及其候选值 列出来；
param_grid = {"gamma": [0.001,0.01,0.1,1,10,100],
"C": [0.001,0.01,0.1,1,10,100]}
print("Parameters:{}".format(param_grid))
grid_search = GridSearchCV(SVC(),param_grid,cv=5) # 实例化一个GridSearchCV类
X_train, X_test, y_train, y_test = train_test_split(iris.data,iris.target, random_state=10)
grid_search.fit(X_train, y_train) # 训练，找到最优的参数，同时使用最优的参数实例化一个新的SVC estimator。
print("Test set score:{:.2f}".format(grid_search.score(X_test, y_test)))
print("Best parameters:{}".format(grid_search.best_params_))
print("Best score on train set:{:.2f}".format(grid_search.best_score_))
if __name__ == '__main__':
iris = load_iris()
X_train, X_test, y_train, y_test = train_test_split(iris.data, iris.target, random_state=0)
print("Size of training set:{} size of testing set:{}".format(X_train.shape[0], X_test.shape[0]))
# simpleGridSearch(X_train, X_test, y_train, y_test)
# gridSearchCv(X_train, X_test, y_train, y_test)
skGridSearchCv(X_train, X_test, y_train, y_test)
三，clf = SVC(kernel='rbf', C=1, gamma=1e-3)#最优模型-这个用得也太正规和重复输入了吧
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.model_selection import GridSearchCV
from sklearn.model_selection import cross_val_score
from sklearn.metrics import classification_report
from sklearn.svm import SVC
#下载数据
digits = datasets.load_digits()
#print(digits.images)
n_sample = len(digits.images)
#把数据转换为二维数据，x的行数据是不同样本数据，列是样本属性。
x = digits.images.reshape(n_sample, -1)#取数据的所有行第一列数据
y = digits.target
#print(x)
#以下方法确定解释变量只能有一个，但是多个解释变量该怎么处理呢,答案是x包含了众多解释变量
x_train, x_test, y_train, y_test = train_test_split(x, y, train_size=0.7, random_state=0)
tuned_parameters = [{'kernel': ['rbf'], 'gamma': [1e-3, 1e-4],
'C': [1, 10, 100, 1000]},
{'kernel': ['linear'], 'C': [1, 10, 100, 1000]}]
scores = ['precision', 'recall']
for score in scores:
print('Tuning hyper-parameters for %s'%score)
print()
#利用网格搜索算法构建评估器模型，并且对数据进行评估
clf = GridSearchCV(SVC(C=1), tuned_parameters, cv=5, scoring='%s_macro'%score)
clf.fit(x_train, y_train)
print('最优参数：',clf.best_params_)
print()
means = clf.cv_results_['mean_test_score']
stds = clf.cv_results_['std_test_score']
for mean, std, params in zip(means, stds, clf.cv_results_['params']):
print('网格数据得分：','%0.3f (+/-%0.3f) for %r'%(mean, std, params))
#这个std有的文章乘以2，但个人不知道为什么需要乘以2，如有明白的朋友，求指点。
print()
y_true, y_pred = y_test, clf.predict(x_test)
print(y_true)
print(classification_report(y_true, y_pred))
#在获取最优超参数之后， 用5折交叉验证来评估模型
clf = SVC(kernel='rbf', C=1, gamma=1e-3)#最优模型
#对模型进行评分
scores = cross_val_score(clf, x, y, cv=5)
print(scores)
