收到了三份代碼，我覺得clf = gs.best_estimator_這種用法，應(yīng)該是比較科學(xué)和不重復(fù)的，書寫也比較規(guī)范，又不含糊，求驗證~
https://blog.csdn.net/wp_python/article/details/80255466
原始數(shù)據(jù)劃分為3份，分別為：訓(xùn)練集、驗證集和測試集；其中訓(xùn)練集用來模型訓(xùn)練，驗證集用來調(diào)整參數(shù)，而測試集用來衡量模型表現(xiàn)好壞。
那請問是不是用了GridSearchCV，就可以不用cross_val_score、cross_validate了，就也相當(dāng)于是交叉驗證了，經(jīng)過訓(xùn)練之后就只需要測試就可以了對吧？---對的
一，clf = gs.best_estimator_寫得明白
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)) # 支持向量機（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) # 訓(xùn)練，找到最優(yōu)的參數(shù)，同時使用最優(yōu)的參數(shù)實例化一個新的SVC estimator，這個就有些含糊，圖省事
#!/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循環(huán)實現(xiàn)網(wǎng)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)#對于每種參數(shù)可能的組合，進行一次訓(xùn)練；
svm.fit(X_train,y_train)
score = svm.score(X_test,y_test)
if score > best_score:#找到表現(xiàn)最好的參數(shù)
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循環(huán)實現(xiàn)網(wǎng)格搜索與交叉驗證
: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折交叉驗證
score = scores.mean() #取平均數(shù)
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類
:param X_train:
:param X_test:
:param y_train:
:param y_test:
:return:
'''
#把要調(diào)整的參數(shù)以及其候選值 列出來；
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) # 實例化一個GridSearchCV類
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) # 訓(xùn)練，找到最優(yōu)的參數(shù)，同時使用最優(yōu)的參數(shù)實例化一個新的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)#最優(yōu)模型-這個用得也太正規(guī)和重復(fù)輸入了吧
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
#下載數(shù)據(jù)
digits = datasets.load_digits()
#print(digits.images)
n_sample = len(digits.images)
#把數(shù)據(jù)轉(zhuǎn)換為二維數(shù)據(jù)，x的行數(shù)據(jù)是不同樣本數(shù)據(jù)，列是樣本屬性。
x = digits.images.reshape(n_sample, -1)#取數(shù)據(jù)的所有行第一列數(shù)據(jù)
y = digits.target
#print(x)
#以下方法確定解釋變量只能有一個，但是多個解釋變量該怎么處理呢,答案是x包含了眾多解釋變量
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()
#利用網(wǎng)格搜索算法構(gòu)建評估器模型，并且對數(shù)據(jù)進行評估
clf = GridSearchCV(SVC(C=1), tuned_parameters, cv=5, scoring='%s_macro'%score)
clf.fit(x_train, y_train)
print('最優(yōu)參數(shù)：',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('網(wǎng)格數(shù)據(jù)得分：','%0.3f (+/-%0.3f) for %r'%(mean, std, params))
#這個std有的文章乘以2，但個人不知道為什么需要乘以2，如有明白的朋友，求指點。
print()
y_true, y_pred = y_test, clf.predict(x_test)
print(y_true)
print(classification_report(y_true, y_pred))
#在獲取最優(yōu)超參數(shù)之后， 用5折交叉驗證來評估模型
clf = SVC(kernel='rbf', C=1, gamma=1e-3)#最優(yōu)模型
#對模型進行評分
scores = cross_val_score(clf, x, y, cv=5)
print(scores)
