使用Python将PMML

Question

我有一个简单的PMML文件，我想要PUT到一个评分服务器。下面是curl调用：

curl -X PUT --data-binary @DecisionTreeIris.pmml -H "Content-type: text/xml" http://localhost:8080/openscoring/model/DecisionTreeIris

以下是PMML文件：

<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<PMML xmlns="http://www.dmg.org/PMML-4_1" version="4.1">
    <Header copyright="Copyright (c) 2013 Vfed" description="RPart Decision Tree Model">
        <Extension extender="Rattle/PMML" name="user" value="Vfed"/>
        <Application name="Rattle/PMML" version="1.2.34r27"/>
        <Timestamp>2013-05-15 22:02:28</Timestamp>
    </Header>
    <DataDictionary numberOfFields="5">
        <DataField name="Species" optype="categorical" dataType="string">
            <Value value="setosa"/>
            <Value value="versicolor"/>
            <Value value="virginica"/>
        </DataField>
        <DataField name="Sepal.Length" optype="continuous" dataType="double"/>
        <DataField name="Sepal.Width" optype="continuous" dataType="double"/>
        <DataField name="Petal.Length" optype="continuous" dataType="double"/>
        <DataField name="Petal.Width" optype="continuous" dataType="double"/>
    </DataDictionary>
    <TreeModel modelName="RPart_Model" functionName="classification" algorithmName="rpart" missingValueStrategy="defaultChild" splitCharacteristic="binarySplit">
        <MiningSchema>
            <MiningField name="Species" usageType="predicted"/>
            <MiningField name="Sepal.Length" usageType="active"/>
            <MiningField name="Sepal.Width" usageType="active"/>
            <MiningField name="Petal.Length" usageType="active"/>
            <MiningField name="Petal.Width" usageType="active"/>
        </MiningSchema>
        <Output>
            <OutputField name="Predicted_Species" optype="categorical" dataType="string" feature="predictedValue"/>
            <OutputField name="Probability_setosa" optype="continuous" dataType="double" feature="probability" value="setosa"/>
            <OutputField name="Probability_versicolor" optype="continuous" dataType="double" feature="probability" value="versicolor"/>
            <OutputField name="Probability_virginica" optype="continuous" dataType="double" feature="probability" value="virginica"/>
            <!-- Custom output field -->
            <OutputField name="Node_Id" optype="categorical" dataType="string" feature="entityId"/>
        </Output>
        <Node id="1" score="setosa" recordCount="150.0" defaultChild="3">
            <True/>
            <ScoreDistribution value="setosa" recordCount="50.0" confidence="0.333333333333333"/>
            <ScoreDistribution value="versicolor" recordCount="50.0" confidence="0.333333333333333"/>
            <ScoreDistribution value="virginica" recordCount="50.0" confidence="0.333333333333333"/>
            <Node id="2" score="setosa" recordCount="50.0">
                <CompoundPredicate booleanOperator="surrogate">
                    <SimplePredicate field="Petal.Length" operator="lessThan" value="2.45"/>
                    <SimplePredicate field="Petal.Width" operator="lessThan" value="0.8"/>
                    <SimplePredicate field="Sepal.Length" operator="lessThan" value="5.45"/>
                    <SimplePredicate field="Sepal.Width" operator="greaterOrEqual" value="3.35"/>
                </CompoundPredicate>
                <ScoreDistribution value="setosa" recordCount="50.0" confidence="1.0"/>
                <ScoreDistribution value="versicolor" recordCount="0.0" confidence="0.0"/>
                <ScoreDistribution value="virginica" recordCount="0.0" confidence="0.0"/>
            </Node>
            <Node id="3" score="versicolor" recordCount="100.0" defaultChild="7">
                <CompoundPredicate booleanOperator="surrogate">
                    <SimplePredicate field="Petal.Length" operator="greaterOrEqual" value="2.45"/>
                    <SimplePredicate field="Petal.Width" operator="greaterOrEqual" value="0.8"/>
                    <SimplePredicate field="Sepal.Length" operator="greaterOrEqual" value="5.45"/>
                    <SimplePredicate field="Sepal.Width" operator="lessThan" value="3.35"/>
                </CompoundPredicate>
                <ScoreDistribution value="setosa" recordCount="0.0" confidence="0.0"/>
                <ScoreDistribution value="versicolor" recordCount="50.0" confidence="0.5"/>
                <ScoreDistribution value="virginica" recordCount="50.0" confidence="0.5"/>
                <Node id="6" score="versicolor" recordCount="54.0">
                    <CompoundPredicate booleanOperator="surrogate">
                        <SimplePredicate field="Petal.Width" operator="lessThan" value="1.75"/>
                        <SimplePredicate field="Petal.Length" operator="lessThan" value="4.75"/>
                        <SimplePredicate field="Sepal.Length" operator="lessThan" value="6.15"/>
                        <SimplePredicate field="Sepal.Width" operator="lessThan" value="2.95"/>
                    </CompoundPredicate>
                    <ScoreDistribution value="setosa" recordCount="0.0" confidence="0.0"/>
                    <ScoreDistribution value="versicolor" recordCount="49.0" confidence="0.907407407407407"/>
                    <ScoreDistribution value="virginica" recordCount="5.0" confidence="0.0925925925925926"/>
                </Node>
                <Node id="7" score="virginica" recordCount="46.0">
                    <CompoundPredicate booleanOperator="surrogate">
                        <SimplePredicate field="Petal.Width" operator="greaterOrEqual" value="1.75"/>
                        <SimplePredicate field="Petal.Length" operator="greaterOrEqual" value="4.75"/>
                        <SimplePredicate field="Sepal.Length" operator="greaterOrEqual" value="6.15"/>
                        <SimplePredicate field="Sepal.Width" operator="greaterOrEqual" value="2.95"/>
                    </CompoundPredicate>
                    <ScoreDistribution value="setosa" recordCount="0.0" confidence="0.0"/>
                    <ScoreDistribution value="versicolor" recordCount="1.0" confidence="0.0217391304347826"/>
                    <ScoreDistribution value="virginica" recordCount="45.0" confidence="0.978260869565217"/>
                </Node>
            </Node>
        </Node>
    </TreeModel>
</PMML>

不确定这是否重要，但我使用的是开放取心 PMML评分服务器。

Answer 1

我建议使用Kenneth (GitHub和文档)的请求库。

具体来说，有一个关于如何发布文件的示例。用它来构造你需要的东西。

我只是在这里假设，但我会尝试以下几点：

import requests

url = 'http://localhost:8080/openscoring/model/DecisionTreeIris'
files = {'file': open('/path/to/file/DecisionTreeIris.pmml', 'rb')}

response = requests.post(url, files=files)

您还可以设置标头或任何您需要的内容。请求使用起来非常简单，对Python社区来说也是一件好事。文档非常优秀，您通常可以通过Google/Bing/DuckDuckGo搜索找到示例。

我希望这能帮上忙！