#调整随机森林的参数(调整n_estimators随机森林中树的数量默认10个树，精度递增显著，但并不是越多越好)，加上verbose=True，显示进程使用信息
#调整随机森林的参数(调整n_estimators随机森林中树的数量默认10个树，精度递增显著) from sklearn import datasets
X, y = datasets.make_classification(n_samples=10000,n_features=20,n_informative=15,flip_y=.5, weights=[.2, .8]) import numpy as np
training = np.random.choice([True, False], p=[.8, .2],size=y.shape) from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import confusion_matrix n_estimator_params = range(1, 100,5)
confusion_matrixes = {}
for n_estimator in n_estimator_params:
rf = RandomForestClassifier(n_estimators=n_estimator,n_jobs=-1, verbose=True)
rf.fit(X[training], y[training])
print ("Accuracy:\t", (rf.predict(X[~training]) == y[~training]).mean()) '''
======================== RESTART: E:/python/pp138.py ========================
[Parallel(n_jobs=-1)]: Done 1 out of 1 | elapsed: 0.0s finished
[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 0.0s finished
Accuracy: 0.590083456063
[Parallel(n_jobs=-1)]: Done 6 out of 6 | elapsed: 0.1s finished
[Parallel(n_jobs=2)]: Done 6 out of 6 | elapsed: 0.0s finished
Accuracy: 0.618065783014
[Parallel(n_jobs=-1)]: Done 11 out of 11 | elapsed: 0.3s finished
[Parallel(n_jobs=2)]: Done 11 out of 11 | elapsed: 0.0s finished
Accuracy: 0.682866961217
[Parallel(n_jobs=-1)]: Done 16 out of 16 | elapsed: 0.5s finished
[Parallel(n_jobs=2)]: Done 16 out of 16 | elapsed: 0.0s finished
Accuracy: 0.692194403535
[Parallel(n_jobs=-1)]: Done 21 out of 21 | elapsed: 0.6s finished
[Parallel(n_jobs=2)]: Done 21 out of 21 | elapsed: 0.0s finished
Accuracy: 0.702012763868
[Parallel(n_jobs=-1)]: Done 26 out of 26 | elapsed: 0.9s finished
[Parallel(n_jobs=2)]: Done 26 out of 26 | elapsed: 0.0s finished
Accuracy: 0.697594501718
[Parallel(n_jobs=-1)]: Done 31 out of 31 | elapsed: 1.0s finished
[Parallel(n_jobs=2)]: Done 31 out of 31 | elapsed: 0.0s finished
Accuracy: 0.710358370152
[Parallel(n_jobs=-1)]: Done 36 out of 36 | elapsed: 1.1s finished
[Parallel(n_jobs=2)]: Done 36 out of 36 | elapsed: 0.0s finished
Accuracy: 0.704958271969
[Parallel(n_jobs=-1)]: Done 41 out of 41 | elapsed: 1.3s finished
[Parallel(n_jobs=2)]: Done 41 out of 41 | elapsed: 0.0s finished
Accuracy: 0.707412862052
[Parallel(n_jobs=-1)]: Done 46 out of 46 | elapsed: 1.5s finished
[Parallel(n_jobs=2)]: Done 46 out of 46 | elapsed: 0.0s finished
Accuracy: 0.716740304369
[Parallel(n_jobs=-1)]: Done 46 tasks | elapsed: 1.6s
[Parallel(n_jobs=-1)]: Done 51 out of 51 | elapsed: 1.8s finished
[Parallel(n_jobs=2)]: Done 46 tasks | elapsed: 0.0s
[Parallel(n_jobs=2)]: Done 51 out of 51 | elapsed: 0.0s finished
Accuracy: 0.713303878252
[Parallel(n_jobs=-1)]: Done 46 tasks | elapsed: 1.5s
[Parallel(n_jobs=-1)]: Done 56 out of 56 | elapsed: 1.8s finished
[Parallel(n_jobs=2)]: Done 46 tasks | elapsed: 0.0s
[Parallel(n_jobs=2)]: Done 56 out of 56 | elapsed: 0.0s finished
Accuracy: 0.713303878252
[Parallel(n_jobs=-1)]: Done 46 tasks | elapsed: 1.5s
[Parallel(n_jobs=-1)]: Done 61 out of 61 | elapsed: 2.0s finished
[Parallel(n_jobs=2)]: Done 46 tasks | elapsed: 0.0s
[Parallel(n_jobs=2)]: Done 61 out of 61 | elapsed: 0.0s finished
Accuracy: 0.717231222386
[Parallel(n_jobs=-1)]: Done 46 tasks | elapsed: 1.5s
[Parallel(n_jobs=-1)]: Done 66 out of 66 | elapsed: 2.3s finished
[Parallel(n_jobs=2)]: Done 46 tasks | elapsed: 0.0s
[Parallel(n_jobs=2)]: Done 66 out of 66 | elapsed: 0.0s finished
Accuracy: 0.711340206186
[Parallel(n_jobs=-1)]: Done 46 tasks | elapsed: 1.6s
[Parallel(n_jobs=-1)]: Done 71 out of 71 | elapsed: 2.5s finished
[Parallel(n_jobs=2)]: Done 46 tasks | elapsed: 0.0s
[Parallel(n_jobs=2)]: Done 71 out of 71 | elapsed: 0.0s finished
Accuracy: 0.720667648503
[Parallel(n_jobs=-1)]: Done 46 tasks | elapsed: 1.5s
[Parallel(n_jobs=-1)]: Done 76 out of 76 | elapsed: 2.4s finished
[Parallel(n_jobs=2)]: Done 46 tasks | elapsed: 0.0s
[Parallel(n_jobs=2)]: Done 76 out of 76 | elapsed: 0.0s finished
Accuracy: 0.721649484536
[Parallel(n_jobs=-1)]: Done 46 tasks | elapsed: 1.7s
[Parallel(n_jobs=-1)]: Done 81 out of 81 | elapsed: 3.0s finished
[Parallel(n_jobs=2)]: Done 46 tasks | elapsed: 0.0s
[Parallel(n_jobs=2)]: Done 81 out of 81 | elapsed: 0.0s finished
Accuracy: 0.721649484536
[Parallel(n_jobs=-1)]: Done 46 tasks | elapsed: 1.5s
[Parallel(n_jobs=-1)]: Done 86 out of 86 | elapsed: 2.8s finished
[Parallel(n_jobs=2)]: Done 46 tasks | elapsed: 0.0s
[Parallel(n_jobs=2)]: Done 86 out of 86 | elapsed: 0.0s finished
Accuracy: 0.716740304369
[Parallel(n_jobs=-1)]: Done 46 tasks | elapsed: 1.5s
[Parallel(n_jobs=-1)]: Done 91 out of 91 | elapsed: 3.1s finished
[Parallel(n_jobs=2)]: Done 46 tasks | elapsed: 0.0s
[Parallel(n_jobs=2)]: Done 91 out of 91 | elapsed: 0.0s finished
Accuracy: 0.72410407462
[Parallel(n_jobs=-1)]: Done 46 tasks | elapsed: 1.4s
[Parallel(n_jobs=-1)]: Done 96 out of 96 | elapsed: 3.1s finished
[Parallel(n_jobs=2)]: Done 46 tasks | elapsed: 0.0s
[Parallel(n_jobs=2)]: Done 96 out of 96 | elapsed: 0.0s finished
Accuracy: 0.718213058419
'''
#调整随机森林的参数(调整n_estimators随机森林中树的数量默认10个树，精度递增显著，但并不是越多越好)，加上verbose=True，显示进程使用信息的更多相关文章
- #调整随机森林的参数(调整max_features，结果未见明显差异)
#调整随机森林的参数(调整max_features,结果未见明显差异) from sklearn import datasets X, y = datasets.make_classification ...
- Linux 查找指定名称的进程并显示进程详细信息
实际应用中可能有这样的场景:给定一个进程名称特征串,查找所有匹配该进程名称的进程的详细信息. 解决的办法是: (1) 先用pgrep [str] 命令进行模糊匹配,找到匹配该特征串的进程ID: (2) ...
- Sysctl命令及linux内核参数调整
一.Sysctl命令用来配置与显示在/proc/sys目录中的内核参数．如果想使参数长期保存,可以通过编辑/etc/sysctl.conf文件来实现. 命令格式: sysctl [-n ...
- sklearn中随机森林的参数
一:sklearn中决策树的参数: 1,criterion: ”gini” or “entropy”(default=”gini”)是计算属性的gini(基尼不纯度)还是entropy(信息增益),来 ...
- XGBoost中参数调整的完整指南（包含Python中的代码）
(搬运)XGBoost中参数调整的完整指南(包含Python中的代码) AARSHAY JAIN, 2016年3月1日 介绍 如果事情不适合预测建模,请使用XGboost.XGBoost算法已 ...
- TensorFlow实现超参数调整
TensorFlow实现超参数调整 正如你目前所看到的,神经网络的性能非常依赖超参数.因此,了解这些参数如何影响网络变得至关重要. 常见的超参数是学习率.正则化器.正则化系数.隐藏层的维数.初始权重值 ...
- Galera集群server.cnf参数调整--Innodb存储引擎内存相关参数（一）
在innodb引擎中,内存的组成主要有三部分:缓冲池(buffer pool),重做日志缓存(redo log buffer),额外的内存池(additional memory pool).
- paip.提升性能----jvm参数调整.txt
paip.提升性能----jvm参数调整.txt 作者Attilax 艾龙, EMAIL:1466519819@qq.com 来源:attilax的专栏 地址:http://blog.csdn.n ...
- Storm集群参数调整
Supervisor 参数调整 修改${STORM_HOME}conf/storm.yaml文件内容 supervisor变更参数 slots 配置: 若storm host仅仅执行superviso ...
随机推荐
- C#使用Sockets操作FTP
http://blog.csdn.net/foart/article/details/6824551 using System; using System.Collections; using Sys ...
- QT 布局时使用 addStretch 可伸缩设置
今天在使用addStretch,布局的时候,发现addStretch竟然是可以平均分配的,有意思.比如: QVBoxLayout *buttonLayout = new QVBoxLayout; bu ...
- sql 触发器回顾
一: 触发器是一种特殊的存储过程﹐它不能被显式地调用﹐而是在往表中插入记录﹑更新记录或者删除记录时被自动地激活.所以触发器可以用来实现对表实施复杂的完整性约束. 二: SQL Server为每个触发器 ...
- 获得Version和Build版本号
[[NSBundle mainBundle] infoDictionary][@"CFBundleShortVersionString"] ?: [[NSBundle mainBu ...
- 初学者的Node.js学习历程
废话篇: 对于我这个新手的不能再白菜的人来说,nodejs的大名都有耳闻,所以说他是一项不可不克服的技能也是可以说的.但是之前没有搞清楚的情况之下胡乱的猜测,是的我对node.js没有一个具体的概念的 ...
- 四种launchMode
注意:如果在一个singleTop或者singleInstance的ActivityA中通过startActivityForResult()方法来启动另外一个ActivityB,那么系统将直接返回Ac ...
- SQL-主键与外键
1.PRIMARY KEY 主键,唯一标识一行或多行,不允许重复值,也不允许未NULL. 语法:[CONSTRAINT <约束名>] PRIMARY KEY [(列名1,列名2...)] ...
- (转)Linux sort命令
Linux 的 ‘sort’命令的14个有用的范例(一) 2015-5-2 10:29 评论: 3 收藏: 10 编译自:http://www.tecmint.com/sort-command- ...
- 让camera实现类似cs第一人称视角旋转和位移
直接把这个脚本挂在摄像机上就可: using System.Collections; using System.Collections.Generic; using UnityEngine; /* * ...
- bzoj 4299 Codechef FRBSUM
定义一个集合的神秘数为不能表示成这个集合的某个子集和的最小正整数,给一个数列,多次求区间神秘数 $n \leq 100000$ sol: 考虑这个神秘数的性质,可以发现,如果神秘数是 $x$,那么 $ ...