📄 page_166.html
字号:
<HTML> <HEAD> <!--SCRIPT LANGUAGE="JavaScript" SRC="http://a1835.g.akamai.net/f/1835/276/3h/www.netlibrary.com/include/js/dictionary_library.js"></SCRIPT> <SCRIPT LANGUAGE="JavaScript"> if (!opener){document.onkeyup=parent.turnBookPage;} </SCRIPT!--> <META HTTP-EQUIV="Cache-Control" CONTENT="no-cache"> <META HTTP-EQUIV="Pragma" CONTENT="no-cache"> <META HTTP-EQUIV="Expires" CONTENT="-1"><META http-equiv="Content-Type" content="text/html; charset=windows-1252"><SCRIPT>var PrevPage="Page_165";var NextPage="Page_167";var CurPage="Page_166";var PageOrder="175";</SCRIPT> <TITLE>Document</TITLE> </HEAD> <BODY BGCOLOR="#FFFFFF"><CENTER><TABLE BORDER=0 WIDTH=100% CELLPADDING=0><TR><TD ALIGN=CENTER> <TABLE BORDER=0 CELLPADDING=2 CELLSPACING=0 WIDTH=100%> <TR> <TD ALIGN=LEFT><A HREF='Page_165.html'>Previous</A></TD> <TD ALIGN=RIGHT><A HREF='Page_167.html'>Next</A></TD> </TR> </TABLE></TD></TR><TR><TD ALIGN=LEFT><P><A NAME='JUMPDEST_Page_166'/><A NAME='{5CF}'/><TABLE BORDER=0 CELLSPACING=0 CELLPADDING=0 WIDTH='100%'><TR><TD ALIGN=RIGHT><FONT FACE='Times New Roman, Times, Serif' SIZE=2 COLOR=#FF0000>Page 166</FONT></TD></TR></TABLE><A NAME='{5D0}'/><TABLE BORDER=0 CELLSPACING=0 CELLPADDING=0><TR> <TD ROWSPAN=5></TD> <TD COLSPAN=3 HEIGHT=12></TD> <TD ROWSPAN=5></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR><TD></TD> <TD><FONT FACE='Times New Roman, Times, Serif' SIZE=3>Another setting is for the Split Search Criterion, which lets you change the criterion used to guide the split search for any field as well as change how to display significance values. The default method is the adjusted level of significance. This method is the most statistically sound approach since it reduces the possibility of producing chance results and puts all the fields on a common statistical footing. These are the options:</FONT></TD><TD></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR> <TD COLSPAN=3 HEIGHT=1></TD></TR></TABLE><A NAME='{5D1}'/><TABLE CELLPADDING=0 CELLSPACING=0 BORDER=0 WIDTH='100%'><TR><TD HEIGHT=12></TD></TR><TR><TD><TABLE CELLSPACING=0 WIDTH=583 CELLPADDING=5><TR><TD WIDTH=137 VALIGN=TOP><FONT FACE='Times New Roman, Times, Serif' SIZE=2><I>Adjusted</I></FONT></TD><TD WIDTH=446 VALIGN=TOP><FONT FACE='Times New Roman, Times, Serif' SIZE=2> this setting is designed to ensure the integrity of the classification tree</FONT></TD></TR><TR><TD WIDTH=137 VALIGN=TOP><FONT FACE='Times New Roman, Times, Serif' SIZE=2><I>Unadjusted</I></FONT></TD><TD WIDTH=446 VALIGN=TOP><FONT FACE='Times New Roman, Times, Serif' SIZE=2> this setting is prone to a bias towards fields with a lot of categories</FONT></TD></TR><TR><TD WIDTH=137 VALIGN=TOP><FONT FACE='Times New Roman, Times, Serif' SIZE=2><I>Entropy/Variance</I></FONT></TD><TD WIDTH=446 VALIGN=TOP><FONT FACE='Times New Roman, Times, Serif' SIZE=2>this setting simulates the ID3 machine-learning algorithm</FONT></TD></TR></TABLE></TD></TR></TABLE><BR><A NAME='{5D2}'/><TABLE BORDER=0 CELLSPACING=0 CELLPADDING=0><TR> <TD ROWSPAN=5></TD> <TD COLSPAN=3 HEIGHT=12></TD> <TD ROWSPAN=5></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR><TD></TD> <TD><FONT FACE='Times New Roman, Times, Serif' SIZE=3>KnowledgeSEEKER incorporates both CART and CHAID algorithms concurrently, which allow the user to segment a data set on either a categorical or continuous value variable. Another useful feature of KnowledgeSEEKER is the ability to <I>Reshape</I> any decision tree, which enables the user to page through various splits of their data set. For example, Figure 5-3 is a view on an ACORN consumer class "Successful Suburbanites" from our sample data set. Figure 5-4 is another decision tree of the same data set, split by another consumer class, "High Rise Renters."</FONT></TD><TD></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR> <TD COLSPAN=3 HEIGHT=1></TD></TR></TABLE><A NAME='{5D3}'/><TABLE BORDER=0 CELLSPACING=0 CELLPADDING=0><TR> <TD ROWSPAN=5></TD> <TD COLSPAN=3 HEIGHT=12></TD> <TD ROWSPAN=5></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR><TD></TD> <TD><FONT FACE='Times New Roman, Times, Serif' SIZE=3>KnowledgeSEEKER not only generates decision tree, but can also produce Crosstabs, IF/THEN rules, and SQL syntax for export use. For example, the following rules and syntax were generated from the decision tree in Figure 5-4.</FONT><FONT FACE='Times New Roman, Times, Serif' SIZE=3 COLOR=#FFFF00><!-- break --></FONT></TD><TD></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR> <TD COLSPAN=3 HEIGHT=1></TD></TR></TABLE><A NAME='{5D4}'/><TABLE BORDER=0 CELLSPACING=0 CELLPADDING=0 WIDTH='100%'><TR> <TD ROWSPAN=5></TD> <TD COLSPAN=3 HEIGHT=12></TD> <TD ROWSPAN=5></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR><TD></TD> <TD ALIGN=CENTER><FONT FACE='Times New Roman, Times, Serif' SIZE=3><IMG SRC='0166-01.JPG' BORDER=0 ALT='0166-01.jpg' WIDTH=440 HEIGHT=180></FONT></TD><TD></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR> <TD COLSPAN=3 HEIGHT=1></TD></TR></TABLE><A NAME='{5D5}'/><TABLE BORDER=0 CELLSPACING=0 CELLPADDING=0 WIDTH='100%'><TR> <TD ROWSPAN=5></TD> <TD COLSPAN=3 HEIGHT=12></TD> <TD ROWSPAN=5></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR><TD></TD> <TD ALIGN=CENTER><FONT FACE='Times New Roman, Times, Serif' SIZE=2>Figure 5-3 <BR>KnowledgeSEEKER's split of the web data of a specific<BR> consumer class: Successful Suburbanites. </FONT></TD><TD></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR> <TD COLSPAN=3 HEIGHT=1></TD></TR></TABLE><A NAME='{5D6}'/></FORM></P></TD></TR></TABLE><P><FONT SIZE=0 COLOR=WHITE></CENTER><A NAME="bottom"> </A><!-- netLibrary.com Copyright Notice --> </BODY></HTML>⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -