标签:适应 zip kernel blank 测试 import params 链接 round
一、概述
机器学习算法在近几年大数据点燃的热火熏陶下已经变得被人所“熟知”,就算不懂得其中各算法理论,叫你喊上一两个著名算法的名字,你也能昂首挺胸脱口而出。当然了,算法之林虽大,但能者还是有限,能适应某些环境并取得较好效果的算法会脱颖而出,而表现平平者则被历史所淡忘。随着机器学习社区的发展和实践验证,这群脱颖而出者也逐渐被人所认可和青睐,同时获得了更多社区力量的支持、改进和推广。
以最广泛的分类算法为例,大致可以分为线性和非线性两大派别。线性算法有著名的逻辑回归、朴素贝叶斯、最大熵等,非线性算法有随机森林、决策树、神经网络、核机器等等。线性算法举的大旗是训练和预测的效率比较高,但最终效果对特征的依赖程度较高,需要数据在特征层面上是线性可分的。因此,使用线性算法需要在特征工程上下不少功夫,尽量对特征进行选择、变换或者组合等使得特征具有区分性。而非线性算法则牛逼点,可以建模复杂的分类面,从而能更好的拟合数据。
那在我们选择了特征的基础上,哪个机器学习算法能取得更好的效果呢?谁也不知道。实践是检验哪个好的不二标准。那难道要苦逼到写五六个机器学习的代码吗?No,机器学习社区的力量是强大的,码农界的共识是不重复造轮子!因此,对某些较为成熟的算法,总有某些优秀的库可以直接使用,省去了大伙调研的大部分时间。
基于目前使用python较多,而python界中远近闻名的机器学习库要数scikit-learn莫属了。这个库优点很多。简单易用,接口抽象得非常好,而且文档支持实在感人。本文中,我们可以封装其中的很多机器学习算法,然后进行一次性测试,从而便于分析取优。当然了,针对具体算法,超参调优也非常重要。
二、Scikit-learn的python实践
2.1、Python的准备工作
Python一个备受欢迎的点是社区支持很多,有非常多优秀的库或者模块。但是某些库之间有时候也存在依赖,所以要安装这些库也是挺繁琐的过程。但总有人忍受不了这种繁琐,都会开发出不少自动化的工具来节省各位客官的时间。其中,个人总结,安装一个python的库有以下三种方法:
1)Anaconda
这是一个非常齐全的python发行版本,最新的版本提供了多达195个流行的python包,包含了我们常用的numpy、scipy等等科学计算的包。有了它,妈妈再也不用担心我焦头烂额地安装一个又一个依赖包了。Anaconda在手,轻松我有!下载地址如下:http://www.continuum.io/downloads
2)Pip
可参考:http://www.cnblogs.com/kylinsblog/p/7754697.html
使用过Ubuntu的人,对apt-get的爱只有自己懂。其实对Python的库的下载和安装可以借助pip工具的。需要安装什么库,直接下载和安装一条龙服务。在pip官网https://pypi.python.org/pypi/pip下载安装即可。未来的需求就在#pip install xx 中。
SaintKings-Mac-mini:nlp saintking$ pip install sklearn
3)源码包
如果上述两种方法都没有找到你的库,那你直接把库的源码下载回来,解压,然后在目录中会有个setup.py文件。执行#python setup.py install 即可把这个库安装到python的默认库目录中。
2.2、Scikit-learn的测试
scikit-learn已经包含在Anaconda中。也可以在官方下载源码包进行安装。本文代码里封装了如下机器学习算法,我们修改数据加载函数,即可一键测试:
classifiers = {‘NB‘:naive_bayes_classifier, ‘KNN‘:knn_classifier, ‘LR‘:logistic_regression_classifier, ‘RF‘:random_forest_classifier, ‘DT‘:decision_tree_classifier, ‘SVM‘:svm_classifier, ‘SVMCV‘:svm_cross_validation, ‘GBDT‘:gradient_boosting_classifier }
train_test.py
#!usr/bin/env python #-*- coding: utf-8 -*- import sys import os import time from sklearn import metrics import numpy as np import cPickle as pickle reload(sys) sys.setdefaultencoding(‘utf8‘) # Multinomial Naive Bayes Classifier def naive_bayes_classifier(train_x, train_y): from sklearn.naive_bayes import MultinomialNB model = MultinomialNB(alpha=0.01) model.fit(train_x, train_y) return model # KNN Classifier def knn_classifier(train_x, train_y): from sklearn.neighbors import KNeighborsClassifier model = KNeighborsClassifier() model.fit(train_x, train_y) return model # Logistic Regression Classifier def logistic_regression_classifier(train_x, train_y): from sklearn.linear_model import LogisticRegression model = LogisticRegression(penalty=‘l2‘) model.fit(train_x, train_y) return model # Random Forest Classifier def random_forest_classifier(train_x, train_y): from sklearn.ensemble import RandomForestClassifier model = RandomForestClassifier(n_estimators=8) model.fit(train_x, train_y) return model # Decision Tree Classifier def decision_tree_classifier(train_x, train_y): from sklearn import tree model = tree.DecisionTreeClassifier() model.fit(train_x, train_y) return model # GBDT(Gradient Boosting Decision Tree) Classifier def gradient_boosting_classifier(train_x, train_y): from sklearn.ensemble import GradientBoostingClassifier model = GradientBoostingClassifier(n_estimators=200) model.fit(train_x, train_y) return model # SVM Classifier def svm_classifier(train_x, train_y): from sklearn.svm import SVC model = SVC(kernel=‘rbf‘, probability=True) model.fit(train_x, train_y) return model # SVM Classifier using cross validation def svm_cross_validation(train_x, train_y): from sklearn.grid_search import GridSearchCV from sklearn.svm import SVC model = SVC(kernel=‘rbf‘, probability=True) param_grid = {‘C‘: [1e-3, 1e-2, 1e-1, 1, 10, 100, 1000], ‘gamma‘: [0.001, 0.0001]} grid_search = GridSearchCV(model, param_grid, n_jobs = 1, verbose=1) grid_search.fit(train_x, train_y) best_parameters = grid_search.best_estimator_.get_params() for para, val in best_parameters.items(): print para, val model = SVC(kernel=‘rbf‘, C=best_parameters[‘C‘], gamma=best_parameters[‘gamma‘], probability=True) model.fit(train_x, train_y) return model def read_data(data_file): import gzip f = gzip.open(data_file, "rb") train, val, test = pickle.load(f) f.close() train_x = train[0] train_y = train[1] test_x = test[0] test_y = test[1] return train_x, train_y, test_x, test_y if __name__ == ‘__main__‘: data_file = "mnist.pkl.gz" thresh = 0.5 model_save_file = None model_save = {} test_classifiers = [‘NB‘, ‘KNN‘, ‘LR‘, ‘RF‘, ‘DT‘, ‘SVM‘, ‘GBDT‘] classifiers = {‘NB‘:naive_bayes_classifier, ‘KNN‘:knn_classifier, ‘LR‘:logistic_regression_classifier, ‘RF‘:random_forest_classifier, ‘DT‘:decision_tree_classifier, ‘SVM‘:svm_classifier, ‘SVMCV‘:svm_cross_validation, ‘GBDT‘:gradient_boosting_classifier } print ‘reading training and testing data...‘ train_x, train_y, test_x, test_y = read_data(data_file) num_train, num_feat = train_x.shape num_test, num_feat = test_x.shape is_binary_class = (len(np.unique(train_y)) == 2) print ‘******************** Data Info *********************‘ print ‘#training data: %d, #testing_data: %d, dimension: %d‘ % (num_train, num_test, num_feat) for classifier in test_classifiers: print ‘******************* %s ********************‘ % classifier start_time = time.time() model = classifiers[classifier](train_x, train_y) print ‘training took %fs!‘ % (time.time() - start_time) predict = model.predict(test_x) if model_save_file != None: model_save[classifier] = model if is_binary_class: precision = metrics.precision_score(test_y, predict) recall = metrics.recall_score(test_y, predict) print ‘precision: %.2f%%, recall: %.2f%%‘ % (100 * precision, 100 * recall) accuracy = metrics.accuracy_score(test_y, predict) print ‘accuracy: %.2f%%‘ % (100 * accuracy) if model_save_file != None: pickle.dump(model_save, open(model_save_file, ‘wb‘))
四、测试结果
本次使用mnist手写体库进行实验:http://deeplearning.net/data/mnist/mnist.pkl.gz。共5万训练样本和1万测试样本。
http://yann.lecun.com/exdb/mnist/
链接: https://pan.baidu.com/s/1dEKHD8d 密码: 83b9
代码运行结果如下:
reading training and testing data... ******************** Data Info ********************* #training data: 50000, #testing_data: 10000, dimension: 784 ******************* NB ******************** training took 0.287000s! accuracy: 83.69% ******************* KNN ******************** training took 31.991000s! accuracy: 96.64% ******************* LR ******************** training took 101.282000s! accuracy: 91.99% ******************* RF ******************** training took 5.442000s! accuracy: 93.78% ******************* DT ******************** training took 28.326000s! accuracy: 87.23% ******************* SVM ******************** training took 3152.369000s! accuracy: 94.35% ******************* GBDT ******************** training took 7623.761000s! accuracy: 96.18%
在这个数据集中,由于数据分布的团簇性较好(如果对这个数据库了解的话,看它的t-SNE映射图就可以看出来。由于任务简单,其在deep learning界已被认为是toy dataset),因此KNN的效果不赖。GBDT是个非常不错的算法,在kaggle等大数据比赛中,状元探花榜眼之列经常能见其身影。三个臭皮匠赛过诸葛亮,还是被验证有道理的,特别是三个臭皮匠还能力互补的时候!
还有一个在实际中非常有效的方法,就是融合这些分类器,再进行决策。例如简单的投票,效果都非常不错。建议在实践中,大家都可以尝试下。
标签:适应 zip kernel blank 测试 import params 链接 round
原文地址:http://www.cnblogs.com/kylinsblog/p/7777351.html