5分钟掌握手动优化机器学习模型超参数
Python中文社区
共 23747字,需浏览 48分钟
·
2021-04-29 21:19
可以使用随机优化算法代替网格和随机搜索来进行超参数优化。 如何使用随机爬山算法调整 Perceptron 算法的超参数。 如何手动优化 XGBoost 梯度提升算法的超参数。
手动超参数优化 感知器超参数优化 XGBoost 超参数优化
https://machinelearningmastery.com/hyperparameter-optimization-with-random-search-and-grid-search/
make_classification()
函数来定义一个包含1,000行和五个输入变量的二进制分类问题。下面的示例创建数据集并总结数据的形状。# define a binary classification dataset
from sklearn.datasets import make_classification
# define dataset
X, y = make_classification(n_samples=1000, n_features=5, n_informative=2, n_redundant=1, random_state=1)
# summarize the shape of the dataset
print(X.shape, y.shape)
(1000, 5) (1000,)
# perceptron default hyperparameters for binary classification
from numpy import mean
from numpy import std
from sklearn.datasets import make_classification
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import RepeatedStratifiedKFold
from sklearn.linear_model import Perceptron
# define dataset
X, y = make_classification(n_samples=1000, n_features=5, n_informative=2, n_redundant=1, random_state=1)
# define model
model = Perceptron()
# define evaluation procedure
cv = RepeatedStratifiedKFold(n_splits=10, n_repeats=3, random_state=1)
# evaluate model
scores = cross_val_score(model, X, y, scoring='accuracy', cv=cv, n_jobs=-1)
# report result
print('Mean Accuracy: %.3f (%.3f)' % (mean(scores), std(scores)))
Mean Accuracy: 0.786 (0.069)
学习率(eta0) 正则化(alpha)
Objective()
函数实现了这一点,采用了数据集和配置值列表。将配置值(学习率和正则化权重)解压缩,用于配置模型,然后对模型进行评估,并返回平均准确度。# objective function
def objective(X, y, cfg):
# unpack config
eta, alpha = cfg
# define model
model = Perceptron(penalty='elasticnet', alpha=alpha, eta0=eta)
# define evaluation procedure
cv = RepeatedStratifiedKFold(n_splits=10, n_repeats=3, random_state=1)
# evaluate model
scores = cross_val_score(model, X, y, scoring='accuracy', cv=cv, n_jobs=-1)
# calculate mean accuracy
result = mean(scores)
return result
randn()
,NumPy函数生成具有高斯分布的随机数。下面的step()
函数实现了这一点,并将在搜索空间中迈出一步,并使用现有配置生成新配置。# take a step in the search space
def step(cfg, step_size):
# unpack the configuration
eta, alpha = cfg
# step eta
new_eta = eta + randn() * step_size
# check the bounds of eta
if new_eta <= 0.0:
new_eta = 1e-8
# step alpha
new_alpha = alpha + randn() * step_size
# check the bounds of alpha
if new_alpha < 0.0:
new_alpha = 0.0
# return the new configuration
return [new_eta, new_alpha]
Objective()
函数来评估候选解,而我们的step()
函数将在搜索空间中迈出一步。搜索首先生成一个随机初始解,在这种情况下,eta和alpha值在0到1范围内。然后评估初始解并将其视为当前最佳工作解。# starting point for the search
solution = [rand(), rand()]
# evaluate the initial point
solution_eval = objective(X, y, solution)
# take a step
candidate = step(solution, step_size)
# evaluate candidate point
candidte_eval = objective(X, y, candidate)
# check if we should keep the new point
if candidte_eval >= solution_eval:
# store the new point
solution, solution_eval = candidate, candidte_eval
# report progress
print('>%d, cfg=%s %.5f' % (i, solution, solution_eval))
hillclimbing()
函数以数据集,目标函数,迭代次数和步长为参数,实现了用于调整 Perceptron 算法的随机爬山算法。# hill climbing local search algorithm
def hillclimbing(X, y, objective, n_iter, step_size):
# starting point for the search
solution = [rand(), rand()]
# evaluate the initial point
solution_eval = objective(X, y, solution)
# run the hill climb
for i in range(n_iter):
# take a step
candidate = step(solution, step_size)
# evaluate candidate point
candidte_eval = objective(X, y, candidate)
# check if we should keep the new point
if candidte_eval >= solution_eval:
# store the new point
solution, solution_eval = candidate, candidte_eval
# report progress
print('>%d, cfg=%s %.5f' % (i, solution, solution_eval))
return [solution, solution_eval]
# define the total iterations
n_iter = 100
# step size in the search space
step_size = 0.1
# perform the hill climbing search
cfg, score = hillclimbing(X, y, objective, n_iter, step_size)
print('Done!')
print('cfg=%s: Mean Accuracy: %f' % (cfg, score))
# manually search perceptron hyperparameters for binary classification
from numpy import mean
from numpy.random import randn
from numpy.random import rand
from sklearn.datasets import make_classification
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import RepeatedStratifiedKFold
from sklearn.linear_model import Perceptron
# objective function
def objective(X, y, cfg):
# unpack config
eta, alpha = cfg
# define model
model = Perceptron(penalty='elasticnet', alpha=alpha, eta0=eta)
# define evaluation procedure
cv = RepeatedStratifiedKFold(n_splits=10, n_repeats=3, random_state=1)
# evaluate model
scores = cross_val_score(model, X, y, scoring='accuracy', cv=cv, n_jobs=-1)
# calculate mean accuracy
result = mean(scores)
return result
# take a step in the search space
def step(cfg, step_size):
# unpack the configuration
eta, alpha = cfg
# step eta
new_eta = eta + randn() * step_size
# check the bounds of eta
if new_eta <= 0.0:
new_eta = 1e-8
# step alpha
new_alpha = alpha + randn() * step_size
# check the bounds of alpha
if new_alpha < 0.0:
new_alpha = 0.0
# return the new configuration
return [new_eta, new_alpha]
# hill climbing local search algorithm
def hillclimbing(X, y, objective, n_iter, step_size):
# starting point for the search
solution = [rand(), rand()]
# evaluate the initial point
solution_eval = objective(X, y, solution)
# run the hill climb
for i in range(n_iter):
# take a step
candidate = step(solution, step_size)
# evaluate candidate point
candidte_eval = objective(X, y, candidate)
# check if we should keep the new point
if candidte_eval >= solution_eval:
# store the new point
solution, solution_eval = candidate, candidte_eval
# report progress
print('>%d, cfg=%s %.5f' % (i, solution, solution_eval))
return [solution, solution_eval]
# define dataset
X, y = make_classification(n_samples=1000, n_features=5, n_informative=2, n_redundant=1, random_state=1)
# define the total iterations
n_iter = 100
# step size in the search space
step_size = 0.1
# perform the hill climbing search
cfg, score = hillclimbing(X, y, objective, n_iter, step_size)
print('Done!')
print('cfg=%s: Mean Accuracy: %f' % (cfg, score))
>0, cfg=[0.5827274503894747, 0.260872709578015] 0.70533
>4, cfg=[0.5449820307807399, 0.3017271170801444] 0.70567
>6, cfg=[0.6286475606495414, 0.17499090243915086] 0.71933
>7, cfg=[0.5956196828965779, 0.0] 0.78633
>8, cfg=[0.5878361167354715, 0.0] 0.78633
>10, cfg=[0.6353507984485595, 0.0] 0.78633
>13, cfg=[0.5690530537610675, 0.0] 0.78633
>17, cfg=[0.6650936023999641, 0.0] 0.78633
>22, cfg=[0.9070451625704087, 0.0] 0.78633
>23, cfg=[0.9253366187387938, 0.0] 0.78633
>26, cfg=[0.9966143540220266, 0.0] 0.78633
>31, cfg=[1.0048613895650054, 0.002162219228449132] 0.79133
Done!
cfg=[1.0048613895650054, 0.002162219228449132]: Mean Accuracy: 0.791333
sudo pip install xgboost
# xgboost
import xgboost
print("xgboost", xgboost.__version__)
xgboost 1.0.1
# define model
model = XGBClassifier()
# xgboost with default hyperparameters for binary classification
from numpy import mean
from numpy import std
from sklearn.datasets import make_classification
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import RepeatedStratifiedKFold
from xgboost import XGBClassifier
# define dataset
X, y = make_classification(n_samples=1000, n_features=5, n_informative=2, n_redundant=1, random_state=1)
# define model
model = XGBClassifier()
# define evaluation procedure
cv = RepeatedStratifiedKFold(n_splits=10, n_repeats=3, random_state=1)
# evaluate model
scores = cross_val_score(model, X, y, scoring='accuracy', cv=cv, n_jobs=-1)
# report result
print('Mean Accuracy: %.3f (%.3f)' % (mean(scores), std(scores)))
Mean Accuracy: 0.849 (0.040)
https://machinelearningmastery.com/configure-gradient-boosting-algorithm/
学习率( learning_rate
)树数( n_estimators
)子样本百分比(子样本) 树深(最大深度)
Objective()
函数以解包XGBoost模型的超参数,对其进行配置,然后评估平均分类精度。# objective function
def objective(X, y, cfg):
# unpack config
lrate, n_tree, subsam, depth = cfg
# define model
model = XGBClassifier(learning_rate=lrate, n_estimators=n_tree, subsample=subsam, max_depth=depth)
# define evaluation procedure
cv = RepeatedStratifiedKFold(n_splits=10, n_repeats=3, random_state=1)
# evaluate model
scores = cross_val_score(model, X, y, scoring='accuracy', cv=cv, n_jobs=-1)
# calculate mean accuracy
result = mean(scores)
return result
step()
函数。# take a step in the search space
def step(cfg):
# unpack config
lrate, n_tree, subsam, depth = cfg
# learning rate
lrate = lrate + randn() * 0.01
if lrate <= 0.0:
lrate = 1e-8
if lrate > 1:
lrate = 1.0
# number of trees
n_tree = round(n_tree + randn() * 50)
if n_tree <= 0.0:
n_tree = 1
# subsample percentage
subsam = subsam + randn() * 0.1
if subsam <= 0.0:
subsam = 1e-8
if subsam > 1:
subsam = 1.0
# max tree depth
depth = round(depth + randn() * 7)
if depth <= 1:
depth = 1
# return new config
return [lrate, n_tree, subsam, depth]
hillclimbing()
算法,以定义具有适当值的初始解。在这种情况下,我们将使用合理的默认值,匹配默认的超参数或接近它们来定义初始解决方案。# starting point for the search
solution = step([0.1, 100, 1.0, 7])
# xgboost manual hyperparameter optimization for binary classification
from numpy import mean
from numpy.random import randn
from numpy.random import rand
from numpy.random import randint
from sklearn.datasets import make_classification
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import RepeatedStratifiedKFold
from xgboost import XGBClassifier
# objective function
def objective(X, y, cfg):
# unpack config
lrate, n_tree, subsam, depth = cfg
# define model
model = XGBClassifier(learning_rate=lrate, n_estimators=n_tree, subsample=subsam, max_depth=depth)
# define evaluation procedure
cv = RepeatedStratifiedKFold(n_splits=10, n_repeats=3, random_state=1)
# evaluate model
scores = cross_val_score(model, X, y, scoring='accuracy', cv=cv, n_jobs=-1)
# calculate mean accuracy
result = mean(scores)
return result
# take a step in the search space
def step(cfg):
# unpack config
lrate, n_tree, subsam, depth = cfg
# learning rate
lrate = lrate + randn() * 0.01
if lrate <= 0.0:
lrate = 1e-8
if lrate > 1:
lrate = 1.0
# number of trees
n_tree = round(n_tree + randn() * 50)
if n_tree <= 0.0:
n_tree = 1
# subsample percentage
subsam = subsam + randn() * 0.1
if subsam <= 0.0:
subsam = 1e-8
if subsam > 1:
subsam = 1.0
# max tree depth
depth = round(depth + randn() * 7)
if depth <= 1:
depth = 1
# return new config
return [lrate, n_tree, subsam, depth]
# hill climbing local search algorithm
def hillclimbing(X, y, objective, n_iter):
# starting point for the search
solution = step([0.1, 100, 1.0, 7])
# evaluate the initial point
solution_eval = objective(X, y, solution)
# run the hill climb
for i in range(n_iter):
# take a step
candidate = step(solution)
# evaluate candidate point
candidte_eval = objective(X, y, candidate)
# check if we should keep the new point
if candidte_eval >= solution_eval:
# store the new point
solution, solution_eval = candidate, candidte_eval
# report progress
print('>%d, cfg=[%s] %.5f' % (i, solution, solution_eval))
return [solution, solution_eval]
# define dataset
X, y = make_classification(n_samples=1000, n_features=5, n_informative=2, n_redundant=1, random_state=1)
# define the total iterations
n_iter = 200
# perform the hill climbing search
cfg, score = hillclimbing(X, y, objective, n_iter)
print('Done!')
print('cfg=[%s]: Mean Accuracy: %f' % (cfg, score))
>0, cfg=[[0.1058242692126418, 67, 0.9228490731610172, 12]] 0.85933
>1, cfg=[[0.11060813799692253, 51, 0.859353656735739, 13]] 0.86100
>4, cfg=[[0.11890247679234153, 58, 0.7135275461723894, 12]] 0.86167
>5, cfg=[[0.10226257987735601, 61, 0.6086462443373852, 17]] 0.86400
>15, cfg=[[0.11176962034280596, 106, 0.5592742266405146, 13]] 0.86500
>19, cfg=[[0.09493587069112454, 153, 0.5049124222437619, 34]] 0.86533
>23, cfg=[[0.08516531024154426, 88, 0.5895201311518876, 31]] 0.86733
>46, cfg=[[0.10092590898175327, 32, 0.5982811365027455, 30]] 0.86867
>75, cfg=[[0.099469211050998, 20, 0.36372573610040404, 32]] 0.86900
>96, cfg=[[0.09021536590375884, 38, 0.4725379807796971, 20]] 0.86900
>100, cfg=[[0.08979482274655906, 65, 0.3697395430835758, 14]] 0.87000
>110, cfg=[[0.06792737273465625, 89, 0.33827505722318224, 17]] 0.87000
>118, cfg=[[0.05544969684589669, 72, 0.2989721608535262, 23]] 0.87200
>122, cfg=[[0.050102976159097, 128, 0.2043203965148931, 24]] 0.87200
>123, cfg=[[0.031493266763680444, 120, 0.2998819062922256, 30]] 0.87333
>128, cfg=[[0.023324201169625292, 84, 0.4017169945431015, 42]] 0.87333
>140, cfg=[[0.020224220443108752, 52, 0.5088096815056933, 53]] 0.87367
Done!
cfg=[[0.020224220443108752, 52, 0.5088096815056933, 53]]: Mean Accuracy: 0.873667
作者:沂水寒城,CSDN博客专家,个人研究方向:机器学习、深度学习、NLP、CV
Blog: http://yishuihancheng.blog.csdn.net
赞 赏 作 者
更多阅读
特别推荐
点击下方阅读原文加入社区会员
评论