Intel DAAL AI加速 ——传统决策树和随机森林
# file: dt_cls_dense_batch.py
#===============================================================================
# Copyright 2014-2018 Intel Corporation.
#
# This software and the related documents are Intel copyrighted materials, and
# your use of them is governed by the express license under which they were
# provided to you (License). Unless the License provides otherwise, you may not
# use, modify, copy, publish, distribute, disclose or transmit this software or
# the related documents without Intel's prior written permission.
#
# This software and the related documents are provided as is, with no express
# or implied warranties, other than those that are expressly stated in the
# License.
#=============================================================================== ## <a name="DAAL-EXAMPLE-PY-DT_CLS_DENSE_BATCH"></a>
## \example dt_cls_dense_batch.py import os
import sys from daal.algorithms.decision_tree.classification import prediction, training
from daal.algorithms import classifier
from daal.data_management import (
FileDataSource, DataSourceIface, NumericTableIface, HomogenNumericTable, MergedNumericTable
)
utils_folder = os.path.realpath(os.path.abspath(os.path.dirname(os.path.dirname(__file__))))
if utils_folder not in sys.path:
sys.path.insert(0, utils_folder)
from utils import printNumericTables DAAL_PREFIX = os.path.join('..', 'data') # Input data set parameters
trainDatasetFileName = os.path.join(DAAL_PREFIX, 'batch', 'decision_tree_train.csv')
pruneDatasetFileName = os.path.join(DAAL_PREFIX, 'batch', 'decision_tree_prune.csv')
testDatasetFileName = os.path.join(DAAL_PREFIX, 'batch', 'decision_tree_test.csv') nFeatures = 5
nClasses = 5 # Model object for the decision tree classification algorithm
model = None
predictionResult = None
testGroundTruth = None def trainModel():
global model # Initialize FileDataSource<CSVFeatureManager> to retrieve the input data from a .csv file
trainDataSource = FileDataSource(
trainDatasetFileName,
DataSourceIface.notAllocateNumericTable,
DataSourceIface.doDictionaryFromContext
) # Create Numeric Tables for training data and labels
trainData = HomogenNumericTable(nFeatures, 0, NumericTableIface.notAllocate)
trainGroundTruth = HomogenNumericTable(1, 0, NumericTableIface.notAllocate)
mergedData = MergedNumericTable(trainData, trainGroundTruth) # Retrieve the data from the input file
trainDataSource.loadDataBlock(mergedData) # Initialize FileDataSource<CSVFeatureManager> to retrieve the input data from a .csv file
pruneDataSource = FileDataSource(
pruneDatasetFileName,
DataSourceIface.notAllocateNumericTable,
DataSourceIface.doDictionaryFromContext
) # Create Numeric Tables for pruning data and labels
pruneData = HomogenNumericTable(nFeatures, 0, NumericTableIface.notAllocate)
pruneGroundTruth = HomogenNumericTable(1, 0, NumericTableIface.notAllocate)
pruneMergedData = MergedNumericTable(pruneData, pruneGroundTruth) # Retrieve the data from the input file
pruneDataSource.loadDataBlock(pruneMergedData) # Create an algorithm object to train the decision tree classification model
algorithm = training.Batch(nClasses) # Pass the training data set and dependent values to the algorithm
algorithm.input.set(classifier.training.data, trainData)
algorithm.input.set(classifier.training.labels, trainGroundTruth)
algorithm.input.setTable(training.dataForPruning, pruneData)
algorithm.input.setTable(training.labelsForPruning, pruneGroundTruth) # Train the decision tree classification model and retrieve the results of the training algorithm
trainingResult = algorithm.compute()
model = trainingResult.get(classifier.training.model) def testModel():
global testGroundTruth, predictionResult # Initialize FileDataSource<CSVFeatureManager> to retrieve the test data from a .csv file
testDataSource = FileDataSource(
testDatasetFileName,
DataSourceIface.notAllocateNumericTable,
DataSourceIface.doDictionaryFromContext
) # Create Numeric Tables for testing data and labels
testData = HomogenNumericTable(nFeatures, 0, NumericTableIface.notAllocate)
testGroundTruth = HomogenNumericTable(1, 0, NumericTableIface.notAllocate)
mergedData = MergedNumericTable(testData, testGroundTruth) # Retrieve the data from input file
testDataSource.loadDataBlock(mergedData) # Create algorithm objects for decision tree classification prediction with the default method
algorithm = prediction.Batch() # Pass the testing data set and trained model to the algorithm
#print("Number of columns: {}".format(testData.getNumberOfColumns()))
algorithm.input.setTable(classifier.prediction.data, testData)
algorithm.input.setModel(classifier.prediction.model, model) # Compute prediction results and retrieve algorithm results
# (Result class from classifier.prediction)
predictionResult = algorithm.compute() def printResults(): printNumericTables(
testGroundTruth,
predictionResult.get(classifier.prediction.prediction),
"Ground truth", "Classification results",
"Decision tree classification results (first 20 observations):",
20, flt64=False
) if __name__ == "__main__": trainModel()
testModel()
printResults()
随机森林的:
# file: df_cls_dense_batch.py
#===============================================================================
# Copyright 2014-2018 Intel Corporation.
#
# This software and the related documents are Intel copyrighted materials, and
# your use of them is governed by the express license under which they were
# provided to you (License). Unless the License provides otherwise, you may not
# use, modify, copy, publish, distribute, disclose or transmit this software or
# the related documents without Intel's prior written permission.
#
# This software and the related documents are provided as is, with no express
# or implied warranties, other than those that are expressly stated in the
# License.
#=============================================================================== ## <a name="DAAL-EXAMPLE-PY-DF_CLS_DENSE_BATCH"></a>
## \example df_cls_dense_batch.py import os
import sys from daal.algorithms import decision_forest
from daal.algorithms.decision_forest.classification import prediction, training
from daal.algorithms import classifier
from daal.data_management import (
FileDataSource, DataSourceIface, NumericTableIface, HomogenNumericTable,
MergedNumericTable, features
) utils_folder = os.path.realpath(os.path.abspath(os.path.dirname(os.path.dirname(__file__))))
if utils_folder not in sys.path:
sys.path.insert(0, utils_folder)
from utils import printNumericTable, printNumericTables DAAL_PREFIX = os.path.join('..', 'data') # Input data set parameters
trainDatasetFileName = os.path.join(DAAL_PREFIX, 'batch', 'df_classification_train.csv')
testDatasetFileName = os.path.join(DAAL_PREFIX, 'batch', 'df_classification_test.csv') nFeatures = 3
nClasses = 5 # Decision forest parameters
nTrees = 10
minObservationsInLeafNode = 8 # Model object for the decision forest classification algorithm
model = None
predictionResult = None
testGroundTruth = None def trainModel():
global model # Initialize FileDataSource<CSVFeatureManager> to retrieve the input data from a .csv file
trainDataSource = FileDataSource(
trainDatasetFileName,
DataSourceIface.notAllocateNumericTable,
DataSourceIface.doDictionaryFromContext
) # Create Numeric Tables for training data and labels
trainData = HomogenNumericTable(nFeatures, 0, NumericTableIface.notAllocate)
trainGroundTruth = HomogenNumericTable(1, 0, NumericTableIface.notAllocate)
mergedData = MergedNumericTable(trainData, trainGroundTruth) # Retrieve the data from the input file
trainDataSource.loadDataBlock(mergedData) # Get the dictionary and update it with additional information about data
dict = trainData.getDictionary() # Add a feature type to the dictionary
dict[0].featureType = features.DAAL_CONTINUOUS
dict[1].featureType = features.DAAL_CONTINUOUS
dict[2].featureType = features.DAAL_CATEGORICAL # Create an algorithm object to train the decision forest classification model
algorithm = training.Batch(nClasses)
algorithm.parameter.nTrees = nTrees
algorithm.parameter.minObservationsInLeafNode = minObservationsInLeafNode
algorithm.parameter.featuresPerNode = nFeatures
algorithm.parameter.varImportance = decision_forest.training.MDI
algorithm.parameter.resultsToCompute = decision_forest.training.computeOutOfBagError # Pass the training data set and dependent values to the algorithm
algorithm.input.set(classifier.training.data, trainData)
algorithm.input.set(classifier.training.labels, trainGroundTruth) # Train the decision forest classification model and retrieve the results of the training algorithm
trainingResult = algorithm.compute()
model = trainingResult.get(classifier.training.model)
printNumericTable(trainingResult.getTable(training.variableImportance), "Variable importance results: ")
printNumericTable(trainingResult.getTable(training.outOfBagError), "OOB error: ") def testModel():
global testGroundTruth, predictionResult # Initialize FileDataSource<CSVFeatureManager> to retrieve the test data from a .csv file
testDataSource = FileDataSource(
testDatasetFileName,
DataSourceIface.notAllocateNumericTable,
DataSourceIface.doDictionaryFromContext
) # Create Numeric Tables for testing data and labels
testData = HomogenNumericTable(nFeatures, 0, NumericTableIface.notAllocate)
testGroundTruth = HomogenNumericTable(1, 0, NumericTableIface.notAllocate)
mergedData = MergedNumericTable(testData, testGroundTruth) # Retrieve the data from input file
testDataSource.loadDataBlock(mergedData) # Get the dictionary and update it with additional information about data
dict = testData.getDictionary() # Add a feature type to the dictionary
dict[0].featureType = features.DAAL_CONTINUOUS
dict[1].featureType = features.DAAL_CONTINUOUS
dict[2].featureType = features.DAAL_CATEGORICAL # Create algorithm objects for decision forest classification prediction with the default method
algorithm = prediction.Batch(nClasses) # Pass the testing data set and trained model to the algorithm
algorithm.input.setTable(classifier.prediction.data, testData)
algorithm.input.setModel(classifier.prediction.model, model) # Compute prediction results and retrieve algorithm results
# (Result class from classifier.prediction)
predictionResult = algorithm.compute() def printResults():
printNumericTable(predictionResult.get(classifier.prediction.prediction),"Decision forest prediction results (first 10 rows):",10)
printNumericTable(testGroundTruth, "Ground truth (first 10 rows):", 10); if __name__ == "__main__": trainModel()
testModel()
printResults()
Intel DAAL AI加速 ——传统决策树和随机森林的更多相关文章
- Intel DAAL AI加速——支持从数据预处理到模型预测,数据源必须使用DAAL的底层封装库
数据源加速见官方文档(必须使用DAAL自己的库): Data Management Numeric Tables Tensors Data Sources Data Dictionaries Data ...
- Intel DAAL AI加速——神经网络
# file: neural_net_dense_batch.py #================================================================= ...
- R语言︱决策树族——随机森林算法
每每以为攀得众山小,可.每每又切实来到起点,大牛们,缓缓脚步来俺笔记葩分享一下吧,please~ --------------------------- 笔者寄语:有一篇<有监督学习选择深度学习 ...
- [ML学习笔记] 决策树与随机森林(Decision Tree&Random Forest)
[ML学习笔记] 决策树与随机森林(Decision Tree&Random Forest) 决策树 决策树算法以树状结构表示数据分类的结果.每个决策点实现一个具有离散输出的测试函数,记为分支 ...
- web安全之机器学习入门——3.2 决策树与随机森林
目录 简介 决策树简单用法 决策树检测P0P3爆破 决策树检测FTP爆破 随机森林检测FTP爆破 简介 决策树和随机森林算法是最常见的分类算法: 决策树,判断的逻辑很多时候和人的思维非常接近. 随机森 ...
- 逻辑斯蒂回归VS决策树VS随机森林
LR 与SVM 不同 1.logistic regression适合需要得到一个分类概率的场景,SVM则没有分类概率 2.LR其实同样可以使用kernel,但是LR没有support vector在计 ...
- Machine Learning笔记整理 ------ (五)决策树、随机森林
1. 决策树 一般的,一棵决策树包含一个根结点.若干内部结点和若干叶子结点,叶子节点对应决策结果,其他每个结点对应一个属性测试,每个结点包含的样本集合根据属性测试结果被划分到子结点中,而根结点包含样本 ...
- 美团店铺评价语言处理以及分类(tfidf,SVM,决策树,随机森林,Knn,ensemble)
第一篇 数据清洗与分析部分 第二篇 可视化部分, 第三篇 朴素贝叶斯文本分类 支持向量机分类 支持向量机 网格搜索 临近法 决策树 随机森林 bagging方法 import pandas as pd ...
- chapter02 三种决策树模型:单一决策树、随机森林、GBDT(梯度提升决策树) 预测泰坦尼克号乘客生还情况
单一标准的决策树:会根每维特征对预测结果的影响程度进行排序,进而决定不同特征从上至下构建分类节点的顺序.Random Forest Classifier:使用相同的训练样本同时搭建多个独立的分类模型, ...
随机推荐
- xml声明中的standalone属性
晚上,在测试tinyxml的时候,发现其中声明了<?xml version="1.0" standalone="no" ?>,经查,其含义为stan ...
- mysql服务器,大量tcp连接状态TIME_WAIT
今天早上,java应用中发现too many open files,检查了下使用的连接数发现基本上在两三百左右,mysql打开的文件数也就几百左右,再看所有tcp连接,发现3306的连接有4000多, ...
- Linux查看网卡带宽的两个命令
1.ethtool ethtool 网络接口名 #ethtool em4 Settings for em4: Supported ports: [ TP ] Supported link modes: ...
- C# string字节数组转换
string转byte[]:byte[] byteArray = System.Text.Encoding.Default.GetBytes ( str ); byte[]转string:string ...
- cogs 1962. [HAOI2015]树上染色
★★☆ 输入文件:haoi2015_t1.in 输出文件:haoi2015_t1.out 简单对比 时间限制:1 s 内存限制:256 MB [题目描述] 有一棵点数为N的树,树边有边 ...
- 网络安全、Web安全、渗透测试之笔经面经总结(二)
这篇文章涉及的知识点有如下几方面: 1.SSL Strip(SSp)攻击到底是什么? 2.中间人攻击——ARP欺骗的原理.实战及防御 3会话劫持原理 4.CC攻击 5.添加时间戳防止重放攻击 6.浅析 ...
- 客户端向服务端请求连接是出现"ssh : Connection refused"原因有哪些
注意:服务端的sshd服务已经正常开启 (可以正常进行连接) 1.在服务端负载比较高的情况下客户端请求连接时会出现连接被拒绝的情况
- mips32和x86下的大小端模式判定
一.背景 1.1 mips32搭载32bit vxworks操作系统 1.2 x86搭载64bit windows10操作系统 二.大小端模式判定前的准备 2.1 先要知道各种架构上各种整型数占据的b ...
- 分布式系统一致性协议--2PC,3PC
分布式系统中最重要的一块,一致性协议,其中就包括了大名鼎鼎的Paxos算法. 2PC与3PC 在分布式系统中,每一个机器节点虽然能够明确知道自己在进行事务操作过程中的结果是成功或是失败,但是却无法直接 ...
- ACM-ICPC 2018 沈阳赛区网络预赛 Made In Heaven(K短路)题解
思路:K短路裸题 代码: #include<queue> #include<cstring> #include<set> #include<map> # ...