Comparing randomized search and grid search for hyperparameter estimation

Compare randomized search and grid search for optimizing hyperparameters of a random forest. All parameters that influence the learning are searched simultaneously (except for the number of estimators, which poses a time / quality tradeoff).

The randomized search and the grid search explore exactly the same space of parameters. The result in parameter settings is quite similar, while the run time for randomized search is drastically lower.

The performance is slightly worse for the randomized search, though this is most likely a noise effect and would not carry over to a held-out test set.

Note that in practice, one would not search over this many different parameters simultaneously using grid search, but pick only the ones deemed most important.

Python source code: randomized_search.py

print(__doc__)

import numpy as np

from time import time
from operator import itemgetter
from scipy.stats import randint as sp_randint from sklearn.grid_search import GridSearchCV, RandomizedSearchCV
from sklearn.datasets import load_digits
from sklearn.ensemble import RandomForestClassifier # get some data
iris = load_digits()
X, y = iris.data, iris.target # build a classifier
clf = RandomForestClassifier(n_estimators=20) # Utility function to report best scores
def report(grid_scores, n_top=3):
top_scores = sorted(grid_scores, key=itemgetter(1), reverse=True)[:n_top]
for i, score in enumerate(top_scores):
print("Model with rank: {0}".format(i + 1))
print("Mean validation score: {0:.3f} (std: {1:.3f})".format(
score.mean_validation_score,
np.std(score.cv_validation_scores)))
print("Parameters: {0}".format(score.parameters))
print("") # specify parameters and distributions to sample from
param_dist = {"max_depth": [3, None],
"max_features": sp_randint(1, 11),
"min_samples_split": sp_randint(1, 11),
"min_samples_leaf": sp_randint(1, 11),
"bootstrap": [True, False],
"criterion": ["gini", "entropy"]} # run randomized search
n_iter_search = 20
random_search = RandomizedSearchCV(clf, param_distributions=param_dist,
n_iter=n_iter_search) start = time()
random_search.fit(X, y)
print("RandomizedSearchCV took %.2f seconds for %d candidates"
" parameter settings." % ((time() - start), n_iter_search))
report(random_search.grid_scores_) # use a full grid over all parameters
param_grid = {"max_depth": [3, None],
"max_features": [1, 3, 10],
"min_samples_split": [1, 3, 10],
"min_samples_leaf": [1, 3, 10],
"bootstrap": [True, False],
"criterion": ["gini", "entropy"]} # run grid search
grid_search = GridSearchCV(clf, param_grid=param_grid)
start = time()
grid_search.fit(X, y) print("GridSearchCV took %.2f seconds for %d candidate parameter settings."
% (time() - start, len(grid_search.grid_scores_)))
report(grid_search.grid_scores_)

Comparing randomized search and grid search for hyperparameter estimation的更多相关文章

  1. 3.2. Grid Search: Searching for estimator parameters

    3.2. Grid Search: Searching for estimator parameters Parameters that are not directly learnt within ...

  2. scikit-learn:3.2. Grid Search: Searching for estimator parameters

    參考:http://scikit-learn.org/stable/modules/grid_search.html GridSearchCV通过(蛮力)搜索參数空间(參数的全部可能组合).寻找最好的 ...

  3. Grid search in the tidyverse

    @drsimonj here to share a tidyverse method of grid search for optimizing a model's hyperparameters. ...

  4. How to Grid Search Hyperparameters for Deep Learning Models in Python With Keras

    Hyperparameter optimization is a big part of deep learning. The reason is that neural networks are n ...

  5. Grid Search学习

    转自:https://www.cnblogs.com/ysugyl/p/8711205.html Grid Search:一种调参手段:穷举搜索:在所有候选的参数选择中,通过循环遍历,尝试每一种可能性 ...

  6. grid search 超参数寻优

    http://scikit-learn.org/stable/modules/grid_search.html 1. 超参数寻优方法 gridsearchCV 和  RandomizedSearchC ...

  7. [转载]Grid Search

    [转载]Grid Search 初学机器学习,之前的模型都是手动调参的,效果一般.同学和我说他用了一个叫grid search的方法.可以实现自动调参,顿时感觉非常高级.吃饭的时候想调参的话最差不过也 ...

  8. 【起航计划 032】2015 起航计划 Android APIDemo的魔鬼步伐 31 App->Search->Invoke Search 搜索功能 Search Dialog SearchView SearchRecentSuggestions

    Search (搜索)是Android平台的一个核心功能之一,用户可以在手机搜索在线的或是本地的信息.Android平台为所有需要提供搜索或是查询功能的应用提 供了一个统一的Search Framew ...

  9. grid search

    sklearn.metrics.make_scorer(score_func, greater_is_better=True, needs_proba=False, needs_threshold=F ...

随机推荐

  1. etrace 跟踪 nginx之HTTP请求流程

    curl 127.0.0.1 | | | \--ngx_epoll_process_events | | | | \--ngx_time_update | | | | | \--ngx_gmtime ...

  2. Entity Framework CodeFirst------使用CodeFirst方式建立数据库连接(一)

    本文分步演练介绍通过 Code First 开发建立新数据库.这个方案包括建立不存在的数据库(Code First 创建)或者空数据库(Code First 向它添加新表).借助 Code First ...

  3. [转] CSS float 浮动属性

    http://www.cnblogs.com/polk6/p/3142187.html CSS float 浮动属性 本篇主要介绍float属性:定义元素朝哪个方向浮动. 目录: 1. 页面布局方式: ...

  4. Java基础知识强化之集合框架笔记14:List集合存储字符串并遍历

    1. List集合存储学生对象并遍历: 需求:存储字符串并遍历 分析: (1)创建集合对象 (2)创建字符串对象 (3)添加字符串对象到集合中 (4)遍历集合 2. 代码示例: package cn. ...

  5. Date和TimeZone的关系

    java2平台为我们提供了丰富的日期时间API.如java.util.Date;java.util.calendar;java.text.DateFormat等.那么它们之间有什么关系呢? 首先,ja ...

  6. 使用Spring简化JDBC操作数据库

    Spring的开发初衷是为了减轻企业级开发的复杂度,其对数据库访问的支持亦如此,使用Spring访问数据库能带来以下好处: 1.1     简化代码 使用原生的JDBC访问数据库,一般总是要执行以下步 ...

  7. jquery,javascript -设置某一ul下的li下的 a的属性

    //javascriptvar ul = document.getElementById('ul); var as = ul.getElementsByTagName('a'); for(var i ...

  8. 玩转CSLA.NET小技巧系列一:跳转页面丢失session,如何解决

    很少写代码,最近在写代码被登录难倒了,这丫的一直在跟我较劲 每次登录完跳转到首页后还是未登录状态 if (ModelState.IsValid) { bool isSuccess = FI.Finan ...

  9. 关于UIScrollView属性和方法的总结

    iOS中UIScollView的总结 在iOS开发中可以说UIScollView是所有滑动类视图的基础,包括UITableView,UIWebView,UICollectionView等等,UIScr ...

  10. iOS中webView加载URL需要处理特殊字符

    今天在项目中遇到webView加载URL时,因为URL中有特殊字符,导致页面无法加载,而且在- (BOOL)webView:(UIWebView )webView shouldStartLoadWit ...