决策树 - 如何获得良好的估计
我想检查一个网上商店的数据集。数据集包括访问次数和包括一些个人数据的订单数量。 我想找出一个＆＃34;高订单率＆＃34;要看。我的想法是使用决策树，因为规则易于理解，您可以根据结果轻松采取行动。 我创建了一个名为＆＃34;堕胎率＆＃34;的新专栏。它的访问和订单的关系。 50％以上的一切都很高，其他都很低。 之后，我将数据拆分为训练和测试数据，并基于决策树生成模型。 我的问题是，有一些＆＃34;少数＆＃34;堕胎率低的记录。决策树似乎工作正常，但实际上它宣称几乎所有记录都很高，只有5个低流产率的记录是正确的。 我真的不知道如何解决这个问题。有什么想法吗？
提前致谢。
＆＃13;
＆＃13;
＆＃13;
＆＃13;
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.3.015">
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" class="process" compatibility="5.3.015" expanded="true" name="Process">
<parameter key="logverbosity" value="init"/>
<parameter key="random_seed" value="2001"/>
<parameter key="send_mail" value="never"/>
<parameter key="notification_email" value=""/>
<parameter key="process_duration_for_mail" value="30"/>
<parameter key="encoding" value="SYSTEM"/>
<process expanded="true">
<operator activated="true" class="read_csv" compatibility="5.3.015" expanded="true" height="60" name="Read CSV" width="90" x="45" y="30">
<parameter key="csv_file" value="C:\temp\WebData.csv"/>
<parameter key="column_separators" value=";"/>
<parameter key="trim_lines" value="false"/>
<parameter key="use_quotes" value="true"/>
<parameter key="quotes_character" value="""/>
<parameter key="escape_character" value="\"/>
<parameter key="skip_comments" value="false"/>
<parameter key="comment_characters" value="#"/>
<parameter key="parse_numbers" value="true"/>
<parameter key="decimal_character" value=","/>
<parameter key="grouped_digits" value="false"/>
<parameter key="grouping_character" value=","/>
<parameter key="date_format" value=""/>
<parameter key="first_row_as_names" value="false"/>
<list key="annotations">
<parameter key="0" value="Name"/>
</list>
<parameter key="time_zone" value="SYSTEM"/>
<parameter key="locale" value="English (United States)"/>
<parameter key="encoding" value="windows-1252"/>
<list key="data_set_meta_data_information">
<parameter key="0" value="ID.true.integer.attribute"/>
<parameter key="1" value="Age.true.integer.attribute"/>
<parameter key="2" value="Sex.true.polynominal.attribute"/>
<parameter key="3" value="Income.true.polynominal.attribute"/>
<parameter key="4" value="PersonsHoushold.true.integer.attribute"/>
<parameter key="5" value="ShippingFlat.true.binominal.attribute"/>
<parameter key="6" value="OneKlickBuy.true.binominal.attribute"/>
<parameter key="7" value="CustomerSince.true.real.attribute"/>
<parameter key="8" value="Visits.true.integer.attribute"/>
<parameter key="9" value="Orders.true.integer.attribute"/>
<parameter key="10" value="att11.false.attribute_value.attribute"/>
</list>
<parameter key="read_not_matching_values_as_missings" value="false"/>
<parameter key="datamanagement" value="double_array"/>
</operator>
<operator activated="true" class="generate_attributes" compatibility="5.3.015" expanded="true" height="76" name="Generate Attributes" width="90" x="179" y="30">
<list key="function_descriptions">
<parameter key="AbortionRate" value="(Visits-Orders)/Visits"/>
</list>
<parameter key="use_standard_constants" value="true"/>
<parameter key="keep_all" value="true"/>
</operator>
<operator activated="true" class="generate_attributes" compatibility="5.3.015" expanded="true" height="76" name="Generate Attributes (2)" width="90" x="313" y="30">
<list key="function_descriptions">
<parameter key="AbortionRate_Bio" value="(if(AbortionRate<0.5, "low","high"))"/>
</list>
<parameter key="use_standard_constants" value="true"/>
<parameter key="keep_all" value="true"/>
</operator>
<operator activated="true" class="set_role" compatibility="5.3.015" expanded="true" height="76" name="Set Role" width="90" x="447" y="30">
<parameter key="attribute_name" value="AbortionRate_Bio"/>
<parameter key="target_role" value="label"/>
<list key="set_additional_roles"/>
</operator>
<operator activated="true" class="select_attributes" compatibility="5.3.015" expanded="true" height="76" name="Select Attributes" width="90" x="581" y="30">
<parameter key="attribute_filter_type" value="subset"/>
<parameter key="attribute" value=""/>
<parameter key="attributes" value="Income|Sex|OneKlickBuy|ShippingFlat|Age|PersonsHoushold|AbortionRate_Bio|CustomerSince"/>
<parameter key="use_except_expression" value="false"/>
<parameter key="value_type" value="attribute_value"/>
<parameter key="use_value_type_exception" value="false"/>
<parameter key="except_value_type" value="time"/>
<parameter key="block_type" value="attribute_block"/>
<parameter key="use_block_type_exception" value="false"/>
<parameter key="except_block_type" value="value_matrix_row_start"/>
<parameter key="invert_selection" value="false"/>
<parameter key="include_special_attributes" value="false"/>
</operator>
<operator activated="true" class="split_data" compatibility="5.3.015" expanded="true" height="94" name="Split Data" width="90" x="715" y="30">
<enumeration key="partitions">
<parameter key="ratio" value="0.7"/>
<parameter key="ratio" value="0.3"/>
</enumeration>
<parameter key="sampling_type" value="shuffled sampling"/>
<parameter key="use_local_random_seed" value="false"/>
<parameter key="local_random_seed" value="1992"/>
</operator>
<operator activated="true" class="decision_tree" compatibility="5.3.015" expanded="true" height="76" name="Decision Tree" width="90" x="447" y="210">
<parameter key="criterion" value="gain_ratio"/>
<parameter key="minimal_size_for_split" value="4"/>
<parameter key="minimal_leaf_size" value="2"/>
<parameter key="minimal_gain" value="0.02"/>
<parameter key="maximal_depth" value="20"/>
<parameter key="confidence" value="0.25"/>
<parameter key="number_of_prepruning_alternatives" value="3"/>
<parameter key="no_pre_pruning" value="false"/>
<parameter key="no_pruning" value="false"/>
</operator>
<operator activated="true" class="apply_model" compatibility="5.3.015" expanded="true" height="76" name="Apply Model" width="90" x="648" y="210">
<list key="application_parameters"/>
<parameter key="create_view" value="false"/>
</operator>
<connect from_op="Read CSV" from_port="output" to_op="Generate Attributes" to_port="example set input"/>
<connect from_op="Generate Attributes" from_port="example set output" to_op="Generate Attributes (2)" to_port="example set input"/>
<connect from_op="Generate Attributes (2)" from_port="example set output" to_op="Set Role" to_port="example set input"/>
<connect from_op="Set Role" from_port="example set output" to_op="Select Attributes" to_port="example set input"/>
<connect from_op="Select Attributes" from_port="example set output" to_op="Split Data" to_port="example set"/>
<connect from_op="Split Data" from_port="partition 1" to_op="Decision Tree" to_port="training set"/>
<connect from_op="Split Data" from_port="partition 2" to_op="Apply Model" to_port="unlabelled data"/>
<connect from_op="Decision Tree" from_port="model" to_op="Apply Model" to_port="model"/>
<connect from_op="Apply Model" from_port="labelled data" to_port="result 1"/>
<connect from_op="Apply Model" from_port="model" to_port="result 2"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="sink_result 1" spacing="0"/>
<portSpacing port="sink_result 2" spacing="0"/>
<portSpacing port="sink_result 3" spacing="0"/>
</process>
</operator>
</process>
更新：
我将Rapidminer流程更改为：
＆＃13;
＆＃13;
＆＃13;
＆＃13;
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.3.015">
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" class="process" compatibility="5.3.015" expanded="true" name="Process">
<process expanded="true">
<operator activated="true" class="read_csv" compatibility="5.3.015" expanded="true" height="60" name="Read CSV" width="90" x="45" y="30">
<parameter key="csv_file" value="C:\temp\WebData.csv"/>
<parameter key="decimal_character" value=","/>
<parameter key="first_row_as_names" value="false"/>
<list key="annotations">
<parameter key="0" value="Name"/>
</list>
<parameter key="encoding" value="windows-1252"/>
<list key="data_set_meta_data_information">
<parameter key="0" value="ID.true.integer.attribute"/>
<parameter key="1" value="Age.true.integer.attribute"/>
<parameter key="2" value="Sex.true.polynominal.attribute"/>
<parameter key="3" value="Income.true.polynominal.attribute"/>
<parameter key="4" value="PersonsHoushold.true.integer.attribute"/>
<parameter key="5" value="ShippingFlat.true.binominal.attribute"/>
<parameter key="6" value="OneKlickBuy.true.binominal.attribute"/>
<parameter key="7" value="CustomerSince.true.real.attribute"/>
<parameter key="8" value="Visits.true.integer.attribute"/>
<parameter key="9" value="Orders.true.integer.attribute"/>
<parameter key="10" value="att11.false.attribute_value.attribute"/>
</list>
<parameter key="read_not_matching_values_as_missings" value="false"/>
</operator>
<operator activated="true" class="generate_attributes" compatibility="5.3.015" expanded="true" height="76" name="Generate Attributes" width="90" x="179" y="30">
<list key="function_descriptions">
<parameter key="A_AbortionRate" value="(Visits-Orders)/Visits"/>
</list>
</operator>
<operator activated="true" class="generate_attributes" compatibility="5.3.015" expanded="true" height="76" name="Generate Attributes (2)" width="90" x="313" y="30">
<list key="function_descriptions">
<parameter key="A_AbortionRate_Bio" value="(if(AbortionRate<0.5, "low","high"))"/>
<parameter key="A_Age" value="(if(Age<18,"Teen",if(Age<30,"young Adult",if(Age<60,"Adult","Pensioner"))))"/>
<parameter key="A_CustomerSince" value="(if(CustomerSince<=1,"up to 1 Year",if(CustomerSince<=2,"1-2 Years",if(CustomerSince<=3,"2-3 Years","over 3 Years"))))"/>
<parameter key="A_PersonsHoushold" value="(if(PersonsHoushold<=1,"Single",if(PersonsHoushold<=2,"Pair",if(PersonsHoushold<=5,"Family","extended family"))))"/>
</list>
</operator>
<operator activated="true" class="set_role" compatibility="5.3.015" expanded="true" height="76" name="Set Role" width="90" x="447" y="30">
<parameter key="attribute_name" value="A_AbortionRate_Bio"/>
<parameter key="target_role" value="label"/>
<list key="set_additional_roles">
<parameter key="K_ID" value="id"/>
</list>
</operator>
<operator activated="true" class="select_attributes" compatibility="5.3.015" expanded="true" height="76" name="Select Attributes" width="90" x="581" y="30">
<parameter key="attribute_filter_type" value="subset"/>
<parameter key="attributes" value="A_AbortionRate_Bio|A_Aage|A_CustomerSince|Income|Sex|OneKlickBuy|ShippingFlat|A_PersonsHoushold"/>
</operator>
<operator activated="true" class="split_validation" compatibility="5.3.015" expanded="true" height="130" name="Validation" width="90" x="715" y="30">
<parameter key="sampling_type" value="stratified sampling"/>
<process expanded="true">
<operator activated="true" class="multiply" compatibility="5.3.015" expanded="true" height="94" name="Multiply (2)" width="90" x="45" y="30"/>
<operator activated="true" class="filter_examples" compatibility="5.3.015" expanded="true" height="76" name="Filter Examples (3)" width="90" x="179" y="120">
<parameter key="condition_class" value="attribute_value_filter"/>
<parameter key="parameter_string" value="A_AbortionRate_Bio = high"/>
</operator>
<operator activated="true" class="sample" compatibility="5.3.015" expanded="true" height="76" name="Sample (4)" width="90" x="313" y="120">
<parameter key="sample_size" value="1675"/>
<list key="sample_size_per_class"/>
<list key="sample_ratio_per_class"/>
<list key="sample_probability_per_class"/>
</operator>
<operator activated="true" class="filter_examples" compatibility="5.3.015" expanded="true" height="76" name="Filter Examples (4)" width="90" x="179" y="30">
<parameter key="condition_class" value="attribute_value_filter"/>
<parameter key="parameter_string" value="A_AbortionRate_Bio = low"/>
</operator>
<operator activated="true" class="sample" compatibility="5.3.015" expanded="true" height="76" name="Sample" width="90" x="313" y="30">
<parameter key="sample_size" value="1675"/>
<list key="sample_size_per_class"/>
<list key="sample_ratio_per_class"/>
<list key="sample_probability_per_class"/>
</operator>
<operator activated="true" class="append" compatibility="5.3.015" expanded="true" height="94" name="Append (2)" width="90" x="447" y="75"/>
<operator activated="true" class="decision_tree" compatibility="5.3.015" expanded="true" height="76" name="Decision Tree (2)" width="90" x="581" y="75">
<parameter key="criterion" value="information_gain"/>
<parameter key="minimal_gain" value="0.025"/>
<parameter key="maximal_depth" value="6"/>
</operator>
<connect from_port="training" to_op="Multiply (2)" to_port="input"/>
<connect from_op="Multiply (2)" from_port="output 1" to_op="Filter Examples (4)" to_port="example set input"/>
<connect from_op="Multiply (2)" from_port="output 2" to_op="Filter Examples (3)" to_port="example set input"/>
<connect from_op="Filter Examples (3)" from_port="example set output" to_op="Sample (4)" to_port="example set input"/>
<connect from_op="Sample (4)" from_port="example set output" to_op="Append (2)" to_port="example set 2"/>
<connect from_op="Filter Examples (4)" from_port="example set output" to_op="Sample" to_port="example set input"/>
<connect from_op="Sample" from_port="example set output" to_op="Append (2)" to_port="example set 1"/>
<connect from_op="Append (2)" from_port="merged set" to_op="Decision Tree (2)" to_port="training set"/>
<connect from_op="Decision Tree (2)" from_port="model" to_port="model"/>
<portSpacing port="source_training" spacing="0"/>
<portSpacing port="sink_model" spacing="0"/>
<portSpacing port="sink_through 1" spacing="0"/>
</process>
<process expanded="true">
<operator activated="true" class="apply_model" compatibility="5.3.015" expanded="true" height="76" name="Apply Model (2)" width="90" x="45" y="30">
<list key="application_parameters"/>
</operator>
<operator activated="true" class="performance" compatibility="5.3.015" expanded="true" height="76" name="Performance" width="90" x="179" y="30"/>
<connect from_port="model" to_op="Apply Model (2)" to_port="model"/>
<connect from_port="test set" to_op="Apply Model (2)" to_port="unlabelled data"/>
<connect from_op="Apply Model (2)" from_port="labelled data" to_op="Performance" to_port="labelled data"/>
<connect from_op="Performance" from_port="performance" to_port="averagable 1"/>
<portSpacing port="source_model" spacing="0"/>
<portSpacing port="source_test set" spacing="0"/>
<portSpacing port="source_through 1" spacing="0"/>
<portSpacing port="sink_averagable 1" spacing="0"/>
<portSpacing port="sink_averagable 2" spacing="0"/>
<portSpacing port="sink_averagable 3" spacing="0"/>
</process>
</operator>
<connect from_op="Read CSV" from_port="output" to_op="Generate Attributes" to_port="example set input"/>
<connect from_op="Generate Attributes" from_port="example set output" to_op="Generate Attributes (2)" to_port="example set input"/>
<connect from_op="Generate Attributes (2)" from_port="example set output" to_op="Set Role" to_port="example set input"/>
<connect from_op="Set Role" from_port="example set output" to_op="Select Attributes" to_port="example set input"/>
<connect from_op="Select Attributes" from_port="example set output" to_op="Validation" to_port="training"/>
<connect from_op="Validation" from_port="model" to_port="result 1"/>
<connect from_op="Validation" from_port="training" to_port="result 2"/>
<connect from_op="Validation" from_port="averagable 1" to_port="result 3"/>
<connect from_op="Validation" from_port="averagable 2" to_port="result 4"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="sink_result 1" spacing="0"/>
<portSpacing port="sink_result 2" spacing="0"/>
<portSpacing port="sink_result 3" spacing="0"/>
<portSpacing port="sink_result 4" spacing="0"/>
<portSpacing port="sink_result 5" spacing="0"/>
</process>
</operator>
</process>
结果更好，但仍然不好。
类预测为91.53％（高）和33.47％（低）。而低是有趣的部分...... :) 有什么想法吗？
0 个答案:
没有答案
相关问题
最新问题
- 我写了这段代码，但我无法理解我的错误
- 我无法从一个代码实例的列表中删除 None 值，但我可以在另一个实例中。为什么它适用于一个细分市场而不适用于另一个细分市场？
- 是否有可能使 loadstring 不可能等于打印？卢阿
- java中的random.expovariate()
- Appscript 通过会议在 Google 日历中发送电子邮件和创建活动
- 为什么我的 Onclick 箭头功能在 React 中不起作用？
- 在此代码中是否有使用“this”的替代方法？
- 在 SQL Server 和 PostgreSQL 上查询，我如何从第一个表获得第二个表的可视化
- 每千个数字得到
- 更新了城市边界 KML 文件的来源？