Rapidminer 中运算符 "Process documents from data" 的数据结果的 2 倍
2 times the data results from the operater "Process documents from data" in Rapidminer
我是 rapidminer 的新手，我尝试阅读 rss 提要并将其放入一些文件中，例如 vimeo 上的本教程 (https://vimeo.com/62963128)。几乎一切正常，但我有一个问题。该过程生成每个文件两次。文件 1 和 21 是同一个文件，文件 2 和 22 是同一个文件，依此类推。有人知道我做错了什么吗？
这是代码：
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="6.5.002">
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" class="process" compatibility="6.5.002" 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="web:read_rss" compatibility="6.5.000" expanded="true" height="60" name="Read RSS Feed" width="90" x="112" y="255">
<parameter key="url" value="http://www.autoblog.com/category/recap/rss.xml"/>
<parameter key="random_user_agent" value="true"/>
<parameter key="connection_timeout" value="10000"/>
<parameter key="read_timeout" value="10000"/>
</operator>
<operator activated="true" class="web:retrieve_webpages" compatibility="6.5.000" expanded="true" height="60" name="Get Pages" width="90" x="514" y="435">
<parameter key="link_attribute" value="Link"/>
<parameter key="page_attribute" value="myhtml"/>
<parameter key="random_user_agent" value="false"/>
<parameter key="connection_timeout" value="10000"/>
<parameter key="read_timeout" value="10000"/>
<parameter key="follow_redirects" value="true"/>
<parameter key="accept_cookies" value="none"/>
<parameter key="cookie_scope" value="global"/>
<parameter key="request_method" value="GET"/>
<parameter key="delay" value="none"/>
<parameter key="delay_amount" value="1000"/>
<parameter key="min_delay_amount" value="0"/>
<parameter key="max_delay_amount" value="1000"/>
</operator>
<operator activated="true" class="text:process_document_from_data" compatibility="6.5.000" expanded="true" height="76" name="Process Documents from Data" width="90" x="715" y="345">
<parameter key="create_word_vector" value="true"/>
<parameter key="vector_creation" value="TF-IDF"/>
<parameter key="add_meta_information" value="true"/>
<parameter key="keep_text" value="false"/>
<parameter key="prune_method" value="none"/>
<parameter key="prune_below_percent" value="3.0"/>
<parameter key="prune_above_percent" value="30.0"/>
<parameter key="prune_below_rank" value="0.05"/>
<parameter key="prune_above_rank" value="0.95"/>
<parameter key="datamanagement" value="double_sparse_array"/>
<parameter key="select_attributes_and_weights" value="false"/>
<list key="specify_weights"/>
<process expanded="true">
<operator activated="true" class="web:extract_html_text_content" compatibility="6.5.000" expanded="true" height="60" name="Extract Content" width="90" x="112" y="30">
<parameter key="extract_content" value="true"/>
<parameter key="minimum_text_block_length" value="5"/>
<parameter key="override_content_type_information" value="true"/>
<parameter key="neglegt_span_tags" value="true"/>
<parameter key="neglect_p_tags" value="true"/>
<parameter key="neglect_b_tags" value="true"/>
<parameter key="neglect_i_tags" value="true"/>
<parameter key="neglect_br_tags" value="true"/>
<parameter key="ignore_non_html_tags" value="true"/>
</operator>
<operator activated="true" class="web:unescape_html" compatibility="6.5.000" expanded="true" height="60" name="Unescape HTML Document" width="90" x="313" y="30"/>
<operator activated="true" class="text:write_document" compatibility="6.5.000" expanded="true" height="76" name="Write Document" width="90" x="514" y="30">
<parameter key="overwrite" value="true"/>
<parameter key="encoding" value="SYSTEM"/>
</operator>
<operator activated="true" class="write_file" compatibility="6.5.002" expanded="true" height="60" name="Write File" width="90" x="715" y="165">
<parameter key="resource_type" value="file"/>
<parameter key="filename" value="d:\test\%{t}-%{a}.txt"/>
<parameter key="mime_type" value="application/octet-stream"/>
</operator>
<connect from_port="document" to_op="Extract Content" to_port="document"/>
<connect from_op="Extract Content" from_port="document" to_op="Unescape HTML Document" to_port="document"/>
<connect from_op="Unescape HTML Document" from_port="document" to_op="Write Document" to_port="document"/>
<connect from_op="Write Document" from_port="document" to_port="document 1"/>
<connect from_op="Write Document" from_port="file" to_op="Write File" to_port="file"/>
<portSpacing port="source_document" spacing="0"/>
<portSpacing port="sink_document 1" spacing="0"/>
<portSpacing port="sink_document 2" spacing="0"/>
</process>
</operator>
<connect from_op="Read RSS Feed" from_port="output" to_op="Get Pages" to_port="Example Set"/>
<connect from_op="Get Pages" from_port="Example Set" to_op="Process Documents from Data" to_port="example set"/>
<connect from_op="Process Documents from Data" from_port="example set" to_port="result 1"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="sink_result 1" spacing="0"/>
<portSpacing port="sink_result 2" spacing="0"/>
</process>
</operator>
</process>
提前致谢。
此致，
戴夫
如果您为 Process Documents 运算符关闭 create word vector，您应该会发现您得到 20 个文件。我无法解释。
我是 rapidminer 的新手，我尝试阅读 rss 提要并将其放入一些文件中，例如 vimeo 上的本教程 (https://vimeo.com/62963128)。几乎一切正常，但我有一个问题。该过程生成每个文件两次。文件 1 和 21 是同一个文件，文件 2 和 22 是同一个文件，依此类推。有人知道我做错了什么吗？
这是代码：
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="6.5.002">
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" class="process" compatibility="6.5.002" 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="web:read_rss" compatibility="6.5.000" expanded="true" height="60" name="Read RSS Feed" width="90" x="112" y="255">
<parameter key="url" value="http://www.autoblog.com/category/recap/rss.xml"/>
<parameter key="random_user_agent" value="true"/>
<parameter key="connection_timeout" value="10000"/>
<parameter key="read_timeout" value="10000"/>
</operator>
<operator activated="true" class="web:retrieve_webpages" compatibility="6.5.000" expanded="true" height="60" name="Get Pages" width="90" x="514" y="435">
<parameter key="link_attribute" value="Link"/>
<parameter key="page_attribute" value="myhtml"/>
<parameter key="random_user_agent" value="false"/>
<parameter key="connection_timeout" value="10000"/>
<parameter key="read_timeout" value="10000"/>
<parameter key="follow_redirects" value="true"/>
<parameter key="accept_cookies" value="none"/>
<parameter key="cookie_scope" value="global"/>
<parameter key="request_method" value="GET"/>
<parameter key="delay" value="none"/>
<parameter key="delay_amount" value="1000"/>
<parameter key="min_delay_amount" value="0"/>
<parameter key="max_delay_amount" value="1000"/>
</operator>
<operator activated="true" class="text:process_document_from_data" compatibility="6.5.000" expanded="true" height="76" name="Process Documents from Data" width="90" x="715" y="345">
<parameter key="create_word_vector" value="true"/>
<parameter key="vector_creation" value="TF-IDF"/>
<parameter key="add_meta_information" value="true"/>
<parameter key="keep_text" value="false"/>
<parameter key="prune_method" value="none"/>
<parameter key="prune_below_percent" value="3.0"/>
<parameter key="prune_above_percent" value="30.0"/>
<parameter key="prune_below_rank" value="0.05"/>
<parameter key="prune_above_rank" value="0.95"/>
<parameter key="datamanagement" value="double_sparse_array"/>
<parameter key="select_attributes_and_weights" value="false"/>
<list key="specify_weights"/>
<process expanded="true">
<operator activated="true" class="web:extract_html_text_content" compatibility="6.5.000" expanded="true" height="60" name="Extract Content" width="90" x="112" y="30">
<parameter key="extract_content" value="true"/>
<parameter key="minimum_text_block_length" value="5"/>
<parameter key="override_content_type_information" value="true"/>
<parameter key="neglegt_span_tags" value="true"/>
<parameter key="neglect_p_tags" value="true"/>
<parameter key="neglect_b_tags" value="true"/>
<parameter key="neglect_i_tags" value="true"/>
<parameter key="neglect_br_tags" value="true"/>
<parameter key="ignore_non_html_tags" value="true"/>
</operator>
<operator activated="true" class="web:unescape_html" compatibility="6.5.000" expanded="true" height="60" name="Unescape HTML Document" width="90" x="313" y="30"/>
<operator activated="true" class="text:write_document" compatibility="6.5.000" expanded="true" height="76" name="Write Document" width="90" x="514" y="30">
<parameter key="overwrite" value="true"/>
<parameter key="encoding" value="SYSTEM"/>
</operator>
<operator activated="true" class="write_file" compatibility="6.5.002" expanded="true" height="60" name="Write File" width="90" x="715" y="165">
<parameter key="resource_type" value="file"/>
<parameter key="filename" value="d:\test\%{t}-%{a}.txt"/>
<parameter key="mime_type" value="application/octet-stream"/>
</operator>
<connect from_port="document" to_op="Extract Content" to_port="document"/>
<connect from_op="Extract Content" from_port="document" to_op="Unescape HTML Document" to_port="document"/>
<connect from_op="Unescape HTML Document" from_port="document" to_op="Write Document" to_port="document"/>
<connect from_op="Write Document" from_port="document" to_port="document 1"/>
<connect from_op="Write Document" from_port="file" to_op="Write File" to_port="file"/>
<portSpacing port="source_document" spacing="0"/>
<portSpacing port="sink_document 1" spacing="0"/>
<portSpacing port="sink_document 2" spacing="0"/>
</process>
</operator>
<connect from_op="Read RSS Feed" from_port="output" to_op="Get Pages" to_port="Example Set"/>
<connect from_op="Get Pages" from_port="Example Set" to_op="Process Documents from Data" to_port="example set"/>
<connect from_op="Process Documents from Data" from_port="example set" to_port="result 1"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="sink_result 1" spacing="0"/>
<portSpacing port="sink_result 2" spacing="0"/>
</process>
</operator>
</process>
提前致谢。
此致，
戴夫
如果您为 Process Documents 运算符关闭 create word vector，您应该会发现您得到 20 个文件。我无法解释。